Publications
2024
Stephan Johann Lehmler; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis
In: pp. 128473, 2024, ISSN: 0925-2312.
Abstract | Links | BibTeX | Tags: Artificial neural networks, Generalization, Memorization, Poisson process, Stochastic modeling
@article{lehmlerUnderstandingActivationPatterns2024,
title = {Understanding Activation Patterns in Artificial Neural Networks by Exploring Stochastic Processes: Discriminating Generalization from Memorization},
author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},
url = {https://www.sciencedirect.com/science/article/pii/S092523122401244X},
doi = {10.1016/j.neucom.2024.128473},
issn = {0925-2312},
year = {2024},
date = {2024-09-19},
urldate = {2024-09-23},
pages = {128473},
abstract = {To gain a deeper understanding of the behavior and learning dynamics of artificial neural networks, mathematical abstractions and models are valuable. They provide a simplified perspective and facilitate systematic investigations. In this paper, we propose to analyze dynamics of artificial neural activation using stochastic processes, which have not been utilized for this purpose thus far. Our approach involves modeling the activation patterns of nodes in artificial neural networks as stochastic processes. By focusing on the activation frequency, we can leverage techniques used in neuroscience to study neural spike trains. Specifically, we extract the activity of individual artificial neurons during a classification task and model their activation frequency. The underlying process model is an arrival process following a Poisson distribution.We examine the theoretical fit of the observed data generated by various artificial neural networks in image recognition tasks to the proposed model’s key assumptions. Through the stochastic process model, we derive measures describing activation patterns of each network. We analyze randomly initialized, generalizing, and memorizing networks, allowing us to identify consistent differences in learning methods across multiple architectures and training sets. We calculate features describing the distribution of Activation Rate and Fano Factor, which prove to be stable indicators of memorization during learning. These calculated features offer valuable insights into network behavior. The proposed model demonstrates promising results in describing activation patterns and could serve as a general framework for future investigations. It has potential applications in theoretical simulation studies as well as practical areas such as pruning or transfer learning.},
keywords = {Artificial neural networks, Generalization, Memorization, Poisson process, Stochastic modeling},
pubstate = {published},
tppubtype = {article}
}
To gain a deeper understanding of the behavior and learning dynamics of artificial neural networks, mathematical abstractions and models are valuable. They provide a simplified perspective and facilitate systematic investigations. In this paper, we propose to analyze dynamics of artificial neural activation using stochastic processes, which have not been utilized for this purpose thus far. Our approach involves modeling the activation patterns of nodes in artificial neural networks as stochastic processes. By focusing on the activation frequency, we can leverage techniques used in neuroscience to study neural spike trains. Specifically, we extract the activity of individual artificial neurons during a classification task and model their activation frequency. The underlying process model is an arrival process following a Poisson distribution.We examine the theoretical fit of the observed data generated by various artificial neural networks in image recognition tasks to the proposed model’s key assumptions. Through the stochastic process model, we derive measures describing activation patterns of each network. We analyze randomly initialized, generalizing, and memorizing networks, allowing us to identify consistent differences in learning methods across multiple architectures and training sets. We calculate features describing the distribution of Activation Rate and Fano Factor, which prove to be stable indicators of memorization during learning. These calculated features offer valuable insights into network behavior. The proposed model demonstrates promising results in describing activation patterns and could serve as a general framework for future investigations. It has potential applications in theoretical simulation studies as well as practical areas such as pruning or transfer learning.
Artur Pilacinski; Lukas Christ; Marius Boshoff; Ioannis Iossifidis; Patrick Adler; Michael Miro; Bernd Kuhlenkötter; Christian Klaes
In: vol. 18, 2024, ISSN: 1662-5218.
Links | BibTeX | Tags: brain-machine interfaces, EEG, Human action recognition, Human-robot collaboration, Sensor Fusion
@article{pilacinskiHumanCollaborativeLoop2024,
title = {Human in the Collaborative Loop: A Strategy for Integrating Human Activity Recognition and Non-Invasive Brain-Machine Interfaces to Control Collaborative Robots},
author = {Artur Pilacinski and Lukas Christ and Marius Boshoff and Ioannis Iossifidis and Patrick Adler and Michael Miro and Bernd Kuhlenkötter and Christian Klaes},
url = {https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1383089/full},
doi = {10.3389/fnbot.2024.1383089},
issn = {1662-5218},
year = {2024},
date = {2024-09-18},
urldate = {2024-09-24},
volume = {18},
publisher = {Frontiers},
keywords = {brain-machine interfaces, EEG, Human action recognition, Human-robot collaboration, Sensor Fusion},
pubstate = {published},
tppubtype = {article}
}
Aline Xavier Fidêncio; Christian Klaes; Ioannis Iossifidis
A Generic Error-Related Potential Classifier Based on Simulated Subjects Journal Article
In: vol. 18, 2024, ISSN: 1662-5161.
Abstract | Links | BibTeX | Tags: adaptive brain-machine (computer) interface, BCI, EEG, Error-related potential (ErrP), ErrP classifier, Generic decoder, Machine Learning, SEREEGA, Simulation
@article{xavierfidencioGenericErrorrelatedPotential2024,
title = {A Generic Error-Related Potential Classifier Based on Simulated Subjects},
author = {Aline Xavier Fidêncio and Christian Klaes and Ioannis Iossifidis},
url = {https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2024.1390714/full},
doi = {10.3389/fnhum.2024.1390714},
issn = {1662-5161},
year = {2024},
date = {2024-07-17},
urldate = {2024-07-17},
volume = {18},
publisher = {Frontiers},
abstract = {$<$p$>$Error-related potentials (ErrPs) are brain signals known to be generated as a reaction to erroneous events. Several works have shown that not only self-made errors but also mistakes generated by external agents can elicit such event-related potentials. The possibility of reliably measuring ErrPs through non-invasive techniques has increased the interest in the brain-computer interface (BCI) community in using such signals to improve performance, for example, by performing error correction. Extensive calibration sessions are typically necessary to gather sufficient trials for training subject-specific ErrP classifiers. This procedure is not only time-consuming but also boresome for participants. In this paper, we explore the effectiveness of ErrPs in closed-loop systems, emphasizing their dependency on precise single-trial classification. To guarantee the presence of an ErrPs signal in the data we employ and to ensure that the parameters defining ErrPs are systematically varied, we utilize the open-source toolbox SEREEGA for data simulation. We generated training instances and evaluated the performance of the generic classifier on both simulated and real-world datasets, proposing a promising alternative to conventional calibration techniques. Results show that a generic support vector machine classifier reaches balanced accuracies of 72.9%, 62.7%, 71.0%, and 70.8% on each validation dataset. While performing similarly to a leave-one-subject-out approach for error class detection, the proposed classifier shows promising generalization across different datasets and subjects without further adaptation. Moreover, by utilizing SEREEGA, we can systematically adjust parameters to accommodate the variability in the ErrP, facilitating the systematic validation of closed-loop setups. Furthermore, our objective is to develop a universal ErrP classifier that captures the signal's variability, enabling it to determine the presence or absence of an ErrP in real EEG data.$<$/p$>$},
keywords = {adaptive brain-machine (computer) interface, BCI, EEG, Error-related potential (ErrP), ErrP classifier, Generic decoder, Machine Learning, SEREEGA, Simulation},
pubstate = {published},
tppubtype = {article}
}
$<$p$>$Error-related potentials (ErrPs) are brain signals known to be generated as a reaction to erroneous events. Several works have shown that not only self-made errors but also mistakes generated by external agents can elicit such event-related potentials. The possibility of reliably measuring ErrPs through non-invasive techniques has increased the interest in the brain-computer interface (BCI) community in using such signals to improve performance, for example, by performing error correction. Extensive calibration sessions are typically necessary to gather sufficient trials for training subject-specific ErrP classifiers. This procedure is not only time-consuming but also boresome for participants. In this paper, we explore the effectiveness of ErrPs in closed-loop systems, emphasizing their dependency on precise single-trial classification. To guarantee the presence of an ErrPs signal in the data we employ and to ensure that the parameters defining ErrPs are systematically varied, we utilize the open-source toolbox SEREEGA for data simulation. We generated training instances and evaluated the performance of the generic classifier on both simulated and real-world datasets, proposing a promising alternative to conventional calibration techniques. Results show that a generic support vector machine classifier reaches balanced accuracies of 72.9%, 62.7%, 71.0%, and 70.8% on each validation dataset. While performing similarly to a leave-one-subject-out approach for error class detection, the proposed classifier shows promising generalization across different datasets and subjects without further adaptation. Moreover, by utilizing SEREEGA, we can systematically adjust parameters to accommodate the variability in the ErrP, facilitating the systematic validation of closed-loop setups. Furthermore, our objective is to develop a universal ErrP classifier that captures the signal's variability, enabling it to determine the presence or absence of an ErrP in real EEG data.$<$/p$>$
Omair Ali; Muhammad Saif-ur-Rehman; Marita Metzler; Tobias Glasmachers; Ioannis Iossifidis; Christian Klaes
GET: A Generative EEG Transformer for Continuous Context-Based Neural Signals Journal Article
In: arXiv:2406.03115 [q-bio], 2024.
Abstract | Links | BibTeX | Tags: BCI, EEG, Machine Learning, Quantitative Biology - Neurons and Cognition
@article{aliGETGenerativeEEG2024,
title = {GET: A Generative EEG Transformer for Continuous Context-Based Neural Signals},
author = {Omair Ali and Muhammad Saif-ur-Rehman and Marita Metzler and Tobias Glasmachers and Ioannis Iossifidis and Christian Klaes},
url = {http://arxiv.org/abs/2406.03115},
doi = {10.48550/arXiv.2406.03115},
year = {2024},
date = {2024-06-09},
urldate = {2024-06-09},
journal = {arXiv:2406.03115 [q-bio]},
abstract = {Generating continuous electroencephalography (EEG) signals through advanced artificial neural networks presents a novel opportunity to enhance brain-computer interface (BCI) technology. This capability has the potential to significantly enhance applications ranging from simulating dynamic brain activity and data augmentation to improving real-time epilepsy detection and BCI inference. By harnessing generative transformer neural networks, specifically designed for EEG signal generation, we can revolutionize the interpretation and interaction with neural data. Generative AI has demonstrated significant success across various domains, from natural language processing (NLP) and computer vision to content creation in visual arts and music. It distinguishes itself by using large-scale datasets to construct context windows during pre-training, a technique that has proven particularly effective in NLP, where models are fine-tuned for specific downstream tasks after extensive foundational training. However, the application of generative AI in the field of BCIs, particularly through the development of continuous, context-rich neural signal generators, has been limited. To address this, we introduce the Generative EEG Transformer (GET), a model leveraging transformer architecture tailored for EEG data. The GET model is pre-trained on diverse EEG datasets, including motor imagery and alpha wave datasets, enabling it to produce high-fidelity neural signals that maintain contextual integrity. Our empirical findings indicate that GET not only faithfully reproduces the frequency spectrum of the training data and input prompts but also robustly generates continuous neural signals. By adopting the successful training strategies of the NLP domain for BCIs, the GET sets a new standard for the development and application of neural signal generation technologies.},
keywords = {BCI, EEG, Machine Learning, Quantitative Biology - Neurons and Cognition},
pubstate = {published},
tppubtype = {article}
}
Generating continuous electroencephalography (EEG) signals through advanced artificial neural networks presents a novel opportunity to enhance brain-computer interface (BCI) technology. This capability has the potential to significantly enhance applications ranging from simulating dynamic brain activity and data augmentation to improving real-time epilepsy detection and BCI inference. By harnessing generative transformer neural networks, specifically designed for EEG signal generation, we can revolutionize the interpretation and interaction with neural data. Generative AI has demonstrated significant success across various domains, from natural language processing (NLP) and computer vision to content creation in visual arts and music. It distinguishes itself by using large-scale datasets to construct context windows during pre-training, a technique that has proven particularly effective in NLP, where models are fine-tuned for specific downstream tasks after extensive foundational training. However, the application of generative AI in the field of BCIs, particularly through the development of continuous, context-rich neural signal generators, has been limited. To address this, we introduce the Generative EEG Transformer (GET), a model leveraging transformer architecture tailored for EEG data. The GET model is pre-trained on diverse EEG datasets, including motor imagery and alpha wave datasets, enabling it to produce high-fidelity neural signals that maintain contextual integrity. Our empirical findings indicate that GET not only faithfully reproduces the frequency spectrum of the training data and input prompts but also robustly generates continuous neural signals. By adopting the successful training strategies of the NLP domain for BCIs, the GET sets a new standard for the development and application of neural signal generation technologies.
2023
Omair Ali; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis; Christian Klaes
ConTraNet: A Hybrid Network for Improving the Classification of EEG and EMG Signals with Limited Training Data Journal Article
In: Computers in Biology and Medicine, pp. 107649, 2023, ISSN: 0010-4825.
Abstract | Links | BibTeX | Tags: Brain computer interface, Deep learning, EEG decoding, EMG decoding, Machine Learning
@article{aliConTraNetHybridNetwork2023,
title = {ConTraNet: A Hybrid Network for Improving the Classification of EEG and EMG Signals with Limited Training Data},
author = {Omair Ali and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis and Christian Klaes},
url = {https://www.sciencedirect.com/science/article/pii/S0010482523011149},
doi = {10.1016/j.compbiomed.2023.107649},
issn = {0010-4825},
year = {2023},
date = {2023-11-02},
urldate = {2023-11-02},
journal = {Computers in Biology and Medicine},
pages = {107649},
abstract = {Objective Bio-Signals such as electroencephalography (EEG) and electromyography (EMG) are widely used for the rehabilitation of physically disabled people and for the characterization of cognitive impairments. Successful decoding of these bio-signals is however non-trivial because of the time-varying and non-stationary characteristics. Furthermore, existence of short- and long-range dependencies in these time-series signal makes the decoding even more challenging. State-of-the-art studies proposed Convolutional Neural Networks (CNNs) based architectures for the classification of these bio-signals, which are proven useful to learn spatial representations. However, CNNs because of the fixed size convolutional kernels and shared weights pay only uniform attention and are also suboptimal in learning short-long term dependencies, simultaneously, which could be pivotal in decoding EEG and EMG signals. Therefore, it is important to address these limitations of CNNs. To learn short- and long-range dependencies simultaneously and to pay more attention to more relevant part of the input signal, Transformer neural network-based architectures can play a significant role. Nonetheless, it requires a large corpus of training data. However, EEG and EMG decoding studies produce limited amount of the data. Therefore, using standalone transformers neural networks produce ordinary results. In this study, we ask a question whether we can fix the limitations of CNN and transformer neural networks and provide a robust and generalized model that can simultaneously learn spatial patterns, long-short term dependencies, pay variable amount of attention to time-varying non-stationary input signal with limited training data. Approach In this work, we introduce a novel single hybrid model called ConTraNet, which is based on CNN and Transformer architectures that contains the strengths of both CNN and Transformer neural networks. ConTraNet uses a CNN block to introduce inductive bias in the model and learn local dependencies, whereas the Transformer block uses the self-attention mechanism to learn the short- and long-range or global dependencies in the signal and learn to pay different attention to different parts of the signals. Main results We evaluated and compared the ConTraNet with state-of-the-art methods on four publicly available datasets (BCI Competition IV dataset 2b, Physionet MI-EEG dataset, Mendeley sEMG dataset, Mendeley sEMG V1 dataset) which belong to EEG-HMI and EMG-HMI paradigms. ConTraNet outperformed its counterparts in all the different category tasks (2-class, 3-class, 4-class, 7-class, and 10-class decoding tasks). Significance With limited training data ConTraNet significantly improves classification performance on four publicly available datasets for 2, 3, 4, 7, and 10-classes compared to its counterparts.},
keywords = {Brain computer interface, Deep learning, EEG decoding, EMG decoding, Machine Learning},
pubstate = {published},
tppubtype = {article}
}
Objective Bio-Signals such as electroencephalography (EEG) and electromyography (EMG) are widely used for the rehabilitation of physically disabled people and for the characterization of cognitive impairments. Successful decoding of these bio-signals is however non-trivial because of the time-varying and non-stationary characteristics. Furthermore, existence of short- and long-range dependencies in these time-series signal makes the decoding even more challenging. State-of-the-art studies proposed Convolutional Neural Networks (CNNs) based architectures for the classification of these bio-signals, which are proven useful to learn spatial representations. However, CNNs because of the fixed size convolutional kernels and shared weights pay only uniform attention and are also suboptimal in learning short-long term dependencies, simultaneously, which could be pivotal in decoding EEG and EMG signals. Therefore, it is important to address these limitations of CNNs. To learn short- and long-range dependencies simultaneously and to pay more attention to more relevant part of the input signal, Transformer neural network-based architectures can play a significant role. Nonetheless, it requires a large corpus of training data. However, EEG and EMG decoding studies produce limited amount of the data. Therefore, using standalone transformers neural networks produce ordinary results. In this study, we ask a question whether we can fix the limitations of CNN and transformer neural networks and provide a robust and generalized model that can simultaneously learn spatial patterns, long-short term dependencies, pay variable amount of attention to time-varying non-stationary input signal with limited training data. Approach In this work, we introduce a novel single hybrid model called ConTraNet, which is based on CNN and Transformer architectures that contains the strengths of both CNN and Transformer neural networks. ConTraNet uses a CNN block to introduce inductive bias in the model and learn local dependencies, whereas the Transformer block uses the self-attention mechanism to learn the short- and long-range or global dependencies in the signal and learn to pay different attention to different parts of the signals. Main results We evaluated and compared the ConTraNet with state-of-the-art methods on four publicly available datasets (BCI Competition IV dataset 2b, Physionet MI-EEG dataset, Mendeley sEMG dataset, Mendeley sEMG V1 dataset) which belong to EEG-HMI and EMG-HMI paradigms. ConTraNet outperformed its counterparts in all the different category tasks (2-class, 3-class, 4-class, 7-class, and 10-class decoding tasks). Significance With limited training data ConTraNet significantly improves classification performance on four publicly available datasets for 2, 3, 4, 7, and 10-classes compared to its counterparts.
Felix Grün; Ioannis Iossifidis
Investigation of the Interplay of Model-Based and Model-Free Learning Using Reinforcement Learning Inproceedings
In: BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2023.
@inproceedings{grunInvestigationInterplayModelBased2023,
title = {Investigation of the Interplay of Model-Based and Model-Free Learning Using Reinforcement Learning},
author = {Felix Grün and Ioannis Iossifidis},
year = {2023},
date = {2023-09-15},
booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
abstract = {The reward prediction error hypothesis of dopamine in the brain states that activity of dopaminergic neurons in certain brain regions correlates with the reward prediction error that corresponds to the temporal difference error, often used as a learning signal in model free reinforcement learning (RL). This suggests that some form of reinforcement learning is used in animal and human brains when learning a task. On the other hand, it is clear that humans are capable of building an internal model of a task, or environment, and using it for planning, especially in sequential tasks. In RL, these two learning approaches, model-driven and reward-driven, are known as model based and model-free RL approaches. Both systems were previously thought to exist in parallel, with some higher process choosing which to use. A decade ago, research suggested both could be used concurrently, with some subject-specific weight assigned to each [1]. Still, the prevalent belief appeared to be that model-free learning is the default mechanism used, replaced or assisted by model-based planning only when the task demands it, i.e. higher rewards justify the additional cognitive effort. Recently, Feher da Silva et al. [2] questioned this belief, presenting data and analyses that indicate model-based learning may be used on its own and can even be computationally more efficient. We take a RL perspective, consider different ways to combine model-based and model-free approaches for modeling and for performance, and discuss how to further study this interplay in human behavioral experiments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The reward prediction error hypothesis of dopamine in the brain states that activity of dopaminergic neurons in certain brain regions correlates with the reward prediction error that corresponds to the temporal difference error, often used as a learning signal in model free reinforcement learning (RL). This suggests that some form of reinforcement learning is used in animal and human brains when learning a task. On the other hand, it is clear that humans are capable of building an internal model of a task, or environment, and using it for planning, especially in sequential tasks. In RL, these two learning approaches, model-driven and reward-driven, are known as model based and model-free RL approaches. Both systems were previously thought to exist in parallel, with some higher process choosing which to use. A decade ago, research suggested both could be used concurrently, with some subject-specific weight assigned to each [1]. Still, the prevalent belief appeared to be that model-free learning is the default mechanism used, replaced or assisted by model-based planning only when the task demands it, i.e. higher rewards justify the additional cognitive effort. Recently, Feher da Silva et al. [2] questioned this belief, presenting data and analyses that indicate model-based learning may be used on its own and can even be computationally more efficient. We take a RL perspective, consider different ways to combine model-based and model-free approaches for modeling and for performance, and discuss how to further study this interplay in human behavioral experiments.
Marie Dominique Schmidt; Ioannis Iossifidis
The Link between Muscle Activity and Upper Limb Kinematics Inproceedings
In: BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2023.
@inproceedings{schmidtLinkMuscleActivity2023,
title = {The Link between Muscle Activity and Upper Limb Kinematics},
author = {Marie Dominique Schmidt and Ioannis Iossifidis},
year = {2023},
date = {2023-09-15},
booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
abstract = {The upper limbs are crucial in performing daily tasks that require strength, a wide range of motion, and precision. To achieve coordinated motion, planning and timing are critical. Sensory information about the target and the current body state is essential, as well as integrating past experiences, represented by pre-learned inverse dynamics that generate associated muscle activity. We propose a generative model that predicts upper limb muscle activity from a variety of simple and complex everyday motions by means of a recurrent neural network. The model shows promising results, with a good fit for different subjects and abstracts well for new motions. We handle the high inter-subject variation in muscle activity using a transfer learning approach, resulting in a good fit for new subjects. Our approach has implications for fundamental movement control understanding and the rehabilitation of neuromuscular diseases using myoelectric prostheses and functional electrical stimulation. Our model can efficiently predict both muscle activity and motion trajectory, which can assist in developing more effective rehabilitation techniques.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The upper limbs are crucial in performing daily tasks that require strength, a wide range of motion, and precision. To achieve coordinated motion, planning and timing are critical. Sensory information about the target and the current body state is essential, as well as integrating past experiences, represented by pre-learned inverse dynamics that generate associated muscle activity. We propose a generative model that predicts upper limb muscle activity from a variety of simple and complex everyday motions by means of a recurrent neural network. The model shows promising results, with a good fit for different subjects and abstracts well for new motions. We handle the high inter-subject variation in muscle activity using a transfer learning approach, resulting in a good fit for new subjects. Our approach has implications for fundamental movement control understanding and the rehabilitation of neuromuscular diseases using myoelectric prostheses and functional electrical stimulation. Our model can efficiently predict both muscle activity and motion trajectory, which can assist in developing more effective rehabilitation techniques.
Tim Sziburis; Susanne Blex; Ioannis Iossifidis
Variability Study of Human Hand Motion during 3D Center-out Tasks Captured for the Diagnosis of Movement Disorders Inproceedings
In: BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2023.
@inproceedings{sziburisVariabilityStudyHuman2023,
title = {Variability Study of Human Hand Motion during 3D Center-out Tasks Captured for the Diagnosis of Movement Disorders},
author = {Tim Sziburis and Susanne Blex and Ioannis Iossifidis},
year = {2023},
date = {2023-09-15},
booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
abstract = {Variability analysis bears the potential to differentiate between healthy and pathological human movements [1]. Our study is conducted in the context of developing a portable glove for the diagnosis of movement disorders. This proposal has methodical as well as technical requirements. Generally, the identification of movement disorders via an analysis of motion data needs to be confirmed within the given setup. Typically, rhythmic movements like gait or posture control are examined for their variability, but here, the characteristic pathological traits of arm movement like tremors are under observation. In addition, the usability of a portable sensor instead of a stationary tracking system has to be validated. In this part of the project, human motion data are recorded redundantly by both an optical tracking system and an IMU. In our setup, a small cylinder is transported in three-dimensional space from a unified start position to one of nine target positions, which are equidistantly aligned on a semicircle. 10 trials are performed per target and hand, resulting in 180 trials per participant in total. 31 participants (11 female and 20 male) without known movement disorders, aged between 21 and 78 years, took part in the study. In addition, the 10-item EHI is used. The purpose of the analysis is to compare different variability measures to uncover differences between trials (intra-subject variability) and participants (inter-subject variability), especially in terms of age and handedness effects. Particularly, a novel variability measure is introduced which makes use of the characteristic planarity of the examined hand paths [2]. For this, the angle of the plane which best fits the travel phase of the trajectory is determined. In addition to neurological motivation, the advantage of this measure is that it allows the comparison of trials of different time spans and to different target directions without depending on trajectory warping. In the future, measurements of the same experimental setup with patients experiencing movement disorders are planned. For the subsequent pathological analysis, this study provides a basis in terms of methodological considerations and ground truth data of healthy participants. In parallel, the captured motion data are modelled utilizing dynamical systems (extended attractor dynamics approach). For this approach, the recorded and modelled data can be compared by the variability measures examined in this study.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Variability analysis bears the potential to differentiate between healthy and pathological human movements [1]. Our study is conducted in the context of developing a portable glove for the diagnosis of movement disorders. This proposal has methodical as well as technical requirements. Generally, the identification of movement disorders via an analysis of motion data needs to be confirmed within the given setup. Typically, rhythmic movements like gait or posture control are examined for their variability, but here, the characteristic pathological traits of arm movement like tremors are under observation. In addition, the usability of a portable sensor instead of a stationary tracking system has to be validated. In this part of the project, human motion data are recorded redundantly by both an optical tracking system and an IMU. In our setup, a small cylinder is transported in three-dimensional space from a unified start position to one of nine target positions, which are equidistantly aligned on a semicircle. 10 trials are performed per target and hand, resulting in 180 trials per participant in total. 31 participants (11 female and 20 male) without known movement disorders, aged between 21 and 78 years, took part in the study. In addition, the 10-item EHI is used. The purpose of the analysis is to compare different variability measures to uncover differences between trials (intra-subject variability) and participants (inter-subject variability), especially in terms of age and handedness effects. Particularly, a novel variability measure is introduced which makes use of the characteristic planarity of the examined hand paths [2]. For this, the angle of the plane which best fits the travel phase of the trajectory is determined. In addition to neurological motivation, the advantage of this measure is that it allows the comparison of trials of different time spans and to different target directions without depending on trajectory warping. In the future, measurements of the same experimental setup with patients experiencing movement disorders are planned. For the subsequent pathological analysis, this study provides a basis in terms of methodological considerations and ground truth data of healthy participants. In parallel, the captured motion data are modelled utilizing dynamical systems (extended attractor dynamics approach). For this approach, the recorded and modelled data can be compared by the variability measures examined in this study.
Aline Xavier Fidencio; Christian Klaes; Ioannis Iossifidis
Exploring Error-related Potentials in Adaptive Brain-Machine Interfaces: Challenges and Investigation of Occurrence and Detection Ratios Inproceedings
In: BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2023.
@inproceedings{xavierfidencioExploringErrorrelatedPotentials2023,
title = {Exploring Error-related Potentials in Adaptive Brain-Machine Interfaces: Challenges and Investigation of Occurrence and Detection Ratios},
author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},
year = {2023},
date = {2023-09-15},
booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
abstract = {Non-invasive techniques like EEG can record error-related potentials (ErrPs), neural signals associated with error processing and awareness. ErrPs are generated in response to self-made and external errors, including those produced by the BMI. Since ErrPs are implicitly elicited and don’t add extra workload for the subject, they serve as a natural and intrinsic feedback source for developing adaptive BMIs. In our study, we assess the occurrence of interaction ErrPs in an adaptive BMI that combines ErrPs and reinforcement learning. We intentionally provoke ErrPs when the BMI misinterprets the user’s intention and performs an incorrect action. Subjects participated in a game controlled by a keyboard and/or motor imagery (imagining hand movements), and EEG data were recorded using an eight-electrode gel-based EEG system. Results reveal that obtaining a distinct ErrPs signal for each subject is more challenging than anticipated. Current practices report the ErrP in terms of over all subjects and trials difference grand average (error minus correct). This approach has, however, the limitation of masking the inter-trial and subject variability, which are relevant for the online single-trial detection of such signals. Moreover, the reported ErrPs waveshape exhibit differences in terms of components observed, as well as their respective latencies, even when very similar tasks are used. Consequently, we conducted additional individualized data analysis to gain deeper insights into the single-trial nature of the ErrPs. As a result, we determined the need for a better understanding and further investigation of how effectively the ErrPs waveforms generalize across subjects, tasks, experimental protocols, and feedback modalities. Given the challenges in obtaining a clear signal for all subjects and the limitations found in existing literature (Xavier Fidêncio et al., 2022), we hypothesize whether an error signal measurable at the scalp level is consistently generated when subjects encounter erroneous conditions. To address this question, we will assess the occurrence-to-detection ratio of ErrPs using invasive and non-invasive recording techniques, examining how uncertainties regarding error generation in the brain impact the learning pipeline.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Non-invasive techniques like EEG can record error-related potentials (ErrPs), neural signals associated with error processing and awareness. ErrPs are generated in response to self-made and external errors, including those produced by the BMI. Since ErrPs are implicitly elicited and don’t add extra workload for the subject, they serve as a natural and intrinsic feedback source for developing adaptive BMIs. In our study, we assess the occurrence of interaction ErrPs in an adaptive BMI that combines ErrPs and reinforcement learning. We intentionally provoke ErrPs when the BMI misinterprets the user’s intention and performs an incorrect action. Subjects participated in a game controlled by a keyboard and/or motor imagery (imagining hand movements), and EEG data were recorded using an eight-electrode gel-based EEG system. Results reveal that obtaining a distinct ErrPs signal for each subject is more challenging than anticipated. Current practices report the ErrP in terms of over all subjects and trials difference grand average (error minus correct). This approach has, however, the limitation of masking the inter-trial and subject variability, which are relevant for the online single-trial detection of such signals. Moreover, the reported ErrPs waveshape exhibit differences in terms of components observed, as well as their respective latencies, even when very similar tasks are used. Consequently, we conducted additional individualized data analysis to gain deeper insights into the single-trial nature of the ErrPs. As a result, we determined the need for a better understanding and further investigation of how effectively the ErrPs waveforms generalize across subjects, tasks, experimental protocols, and feedback modalities. Given the challenges in obtaining a clear signal for all subjects and the limitations found in existing literature (Xavier Fidêncio et al., 2022), we hypothesize whether an error signal measurable at the scalp level is consistently generated when subjects encounter erroneous conditions. To address this question, we will assess the occurrence-to-detection ratio of ErrPs using invasive and non-invasive recording techniques, examining how uncertainties regarding error generation in the brain impact the learning pipeline.
Muhammad Ayaz Hussain; Ioannis Iossifidis
Advancements in Upper Body Exoskeleton: Implementing Active Gravity Compensation with a Feedforward Controller Journal Article
In: arXiv:2309.04698 [cs.RO], 2023.
Abstract | Links | BibTeX | Tags: Computer Science - Artificial Intelligence, Computer Science - Information Theory, Computer Science - Machine Learning, I.2.6, I.2.8, Quantitative Biology - Neurons and Cognition
@article{ayazhussainAdvancementsUpperBody2023,
title = {Advancements in Upper Body Exoskeleton: Implementing Active Gravity Compensation with a Feedforward Controller},
author = {Muhammad Ayaz Hussain and Ioannis Iossifidis},
url = {https://doi.org/10.48550/arXiv.2309.04698},
doi = {10.48550/arXiv.2309.04698},
year = {2023},
date = {2023-09-09},
urldate = {2023-09-09},
journal = {arXiv:2309.04698 [cs.RO]},
abstract = {In this study, we present a feedforward control system designed for active gravity compensation on an upper body exoskeleton. The system utilizes only positional data from internal motor sensors to calculate torque, employing analytical control equations based on Newton-Euler Inverse Dynamics. Compared to feedback control systems, the feedforward approach offers several advantages. It eliminates the need for external torque sensors, resulting in reduced hardware complexity and weight. Moreover, the feedforward control exhibits a more proactive response, leading to enhanced performance. The exoskeleton used in the experiments is lightweight and comprises 4 Degrees of Freedom, closely mimicking human upper body kinematics and three-dimensional range of motion. We conducted tests on both hardware and simulations of the exoskeleton, demonstrating stable performance. The system maintained its position over an extended period, exhibiting minimal friction and avoiding undesired slewing.},
keywords = {Computer Science - Artificial Intelligence, Computer Science - Information Theory, Computer Science - Machine Learning, I.2.6, I.2.8, Quantitative Biology - Neurons and Cognition},
pubstate = {published},
tppubtype = {article}
}
In this study, we present a feedforward control system designed for active gravity compensation on an upper body exoskeleton. The system utilizes only positional data from internal motor sensors to calculate torque, employing analytical control equations based on Newton-Euler Inverse Dynamics. Compared to feedback control systems, the feedforward approach offers several advantages. It eliminates the need for external torque sensors, resulting in reduced hardware complexity and weight. Moreover, the feedforward control exhibits a more proactive response, leading to enhanced performance. The exoskeleton used in the experiments is lightweight and comprises 4 Degrees of Freedom, closely mimicking human upper body kinematics and three-dimensional range of motion. We conducted tests on both hardware and simulations of the exoskeleton, demonstrating stable performance. The system maintained its position over an extended period, exhibiting minimal friction and avoiding undesired slewing.
Marie D. Schmidt; Tobias Glasmachers; Ioannis Iossifidis
The Concepts of Muscle Activity Generation Driven by Upper Limb Kinematics Journal Article
In: BioMedical Engineering OnLine, vol. 22, no. 1, pp. 63, 2023, ISSN: 1475-925X.
Abstract | Links | BibTeX | Tags: Artificial generated signal, BCI, Electromyography (EMG), Generative model, Inertial measurement unit (IMU), Machine Learning, Motion parameters, Muscle activity, Neural networks, transfer learning, Voluntary movement
@article{schmidtConceptsMuscleActivity2023,
title = {The Concepts of Muscle Activity Generation Driven by Upper Limb Kinematics},
author = {Marie D. Schmidt and Tobias Glasmachers and Ioannis Iossifidis},
url = {https://doi.org/10.1186/s12938-023-01116-9},
doi = {10.1186/s12938-023-01116-9},
issn = {1475-925X},
year = {2023},
date = {2023-06-24},
urldate = {2023-06-24},
journal = {BioMedical Engineering OnLine},
volume = {22},
number = {1},
pages = {63},
abstract = {The underlying motivation of this work is to demonstrate that artificial muscle activity of known and unknown motion can be generated based on motion parameters, such as angular position, acceleration, and velocity of each joint (or the end-effector instead), which are similarly represented in our brains. This model is motivated by the known motion planning process in the central nervous system. That process incorporates the current body state from sensory systems and previous experiences, which might be represented as pre-learned inverse dynamics that generate associated muscle activity.},
keywords = {Artificial generated signal, BCI, Electromyography (EMG), Generative model, Inertial measurement unit (IMU), Machine Learning, Motion parameters, Muscle activity, Neural networks, transfer learning, Voluntary movement},
pubstate = {published},
tppubtype = {article}
}
The underlying motivation of this work is to demonstrate that artificial muscle activity of known and unknown motion can be generated based on motion parameters, such as angular position, acceleration, and velocity of each joint (or the end-effector instead), which are similarly represented in our brains. This model is motivated by the known motion planning process in the central nervous system. That process incorporates the current body state from sensory systems and previous experiences, which might be represented as pre-learned inverse dynamics that generate associated muscle activity.
Muhammad Saif-ur-Rehman; Omair Ali; Christian Klaes; Ioannis Iossifidis
Adaptive SpikeDeep-Classifier: Self-organizing and self-supervised machine learning algorithm for online spike sorting Journal Article
In: arXiv:2304.01355 [cs, math, q-bio], 2023.
Links | BibTeX | Tags: BCI, Machine Learning, Spike Sorting
@article{saifurrehman2023adaptive,
title = {Adaptive SpikeDeep-Classifier: Self-organizing and self-supervised machine learning algorithm for online spike sorting},
author = {Muhammad Saif-ur-Rehman and Omair Ali and Christian Klaes and Ioannis Iossifidis},
doi = {10.48550/arXiv.2304.01355},
year = {2023},
date = {2023-05-02},
urldate = {2023-05-02},
journal = {arXiv:2304.01355 [cs, math, q-bio]},
keywords = {BCI, Machine Learning, Spike Sorting},
pubstate = {published},
tppubtype = {article}
}
2022
Felix Grün; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis
Invariance to Quantile Selection in Distributional Continuous Control Journal Article
In: arXiv:2212.14262 [cs.LG], 2022.
Links | BibTeX | Tags: Artificial Intelligence (cs.AI), FOS: Computer and information sciences, I.2.6, I.2.8, Machine Learning, Machine Learning (cs.LG)
@article{grunInvarianceQuantileSelection2022,
title = {Invariance to Quantile Selection in Distributional Continuous Control},
author = {Felix Grün and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},
url = {https://arxiv.org/abs/2212.14262},
doi = {10.48550/ARXIV.2212.14262},
year = {2022},
date = {2022-12-29},
urldate = {2022-12-29},
journal = {arXiv:2212.14262 [cs.LG]},
keywords = {Artificial Intelligence (cs.AI), FOS: Computer and information sciences, I.2.6, I.2.8, Machine Learning, Machine Learning (cs.LG)},
pubstate = {published},
tppubtype = {article}
}
Stephan Johann Lehmler; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis
Deep transfer learning compared to subject-specific models for sEMG decoders Journal Article
In: Journal of Neural Engineering, 2022.
Links | BibTeX | Tags: BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning, transfer learning
@article{lehmlerTransferLearningPatientSpecific2021bb,
title = {Deep transfer learning compared to subject-specific models for sEMG decoders},
author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},
url = {http://iopscience.iop.org/article/10.1088/1741-2552/ac9860},
doi = {10.1088/1741-2552/ac9860},
year = {2022},
date = {2022-10-28},
urldate = {2022-10-28},
journal = {Journal of Neural Engineering},
keywords = {BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning, transfer learning},
pubstate = {published},
tppubtype = {article}
}
Felix Grün; Ioannis Iossifidis
Exploring Distribution Parameterizations for Distributional Continuous Control Inproceedings
In: BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2022.
Links | BibTeX | Tags: Machine Learning, Reinforcement learning
@inproceedings{grunExploringDistributionParameterizations2022,
title = {Exploring Distribution Parameterizations for Distributional Continuous Control},
author = {Felix Grün and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2022.112},
year = {2022},
date = {2022-09-15},
urldate = {2022-09-15},
booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {Machine Learning, Reinforcement learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Stephan Johann Lehmler; Muhammad Saif-ur-Rehman; Ioannis Iossifidis
Modeling Subject Specfic Surface EMG Features by Means of Deep Learning Inproceedings
In: BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2022.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{lehmlerModelingSubjectSpecfic2022,
title = {Modeling Subject Specfic Surface EMG Features by Means of Deep Learning},
author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2022.309},
year = {2022},
date = {2022-09-15},
urldate = {2022-09-15},
booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Marie Dominique Schmidt; Ioannis Iossifidis
Linking Muscle Activity and Motion Trajectory Inproceedings
In: BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2022.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{schmidtLinkingMuscleActivity2022,
title = {Linking Muscle Activity and Motion Trajectory},
author = {Marie Dominique Schmidt and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2022.191},
year = {2022},
date = {2022-09-15},
urldate = {2022-09-15},
booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Tim Sziburis; Susanne Blex; Ioannis Iossifidis
A Dataset of 3D Hand Transport Trajectories Determined by Inertial Measurements from a Single Sensor Inproceedings
In: BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2022.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{sziburisDataset3DHand2022,
title = {A Dataset of 3D Hand Transport Trajectories Determined by Inertial Measurements from a Single Sensor},
author = {Tim Sziburis and Susanne Blex and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2022.186},
year = {2022},
date = {2022-09-15},
urldate = {2022-09-15},
booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Aline Xavier Fidencio; Christian Klaes; Ioannis Iossifidis
Closed-Loop Adaptation of Brain-Machine Interfaces Using Error-Related Potentials and Reinforcement Learning Inproceedings
In: BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022, BCCN Bernstein Network Computational Network, 2022.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{xavierfidencioClosedloopAdaptationBrainmachine2022,
title = {Closed-Loop Adaptation of Brain-Machine Interfaces Using Error-Related Potentials and Reinforcement Learning},
author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2022.136},
year = {2022},
date = {2022-09-15},
urldate = {2022-09-15},
booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Sebastian Doliwa; Muhammad Ayaz Hussain; Tim Sziburis; Ioannis Iossifidis
Biologically Inspired Model for Timed Motion in Robotic Systems Inproceedings
In: 9th IEEE RAS/EMBS International Conference on Biomedical Robotics & Biomechatronics, IEEE, Seoul, South Korea, 2022.
BibTeX | Tags: Autonomous robotics, dynamical systems
@inproceedings{doliwaBiologicallyInspiredModel2022,
title = {Biologically Inspired Model for Timed Motion in Robotic Systems},
author = {Sebastian Doliwa and Muhammad Ayaz Hussain and Tim Sziburis and Ioannis Iossifidis},
year = {2022},
date = {2022-08-12},
urldate = {2022-08-12},
booktitle = {9th IEEE RAS/EMBS International Conference on Biomedical Robotics & Biomechatronics},
publisher = {IEEE},
address = {Seoul, South Korea},
keywords = {Autonomous robotics, dynamical systems},
pubstate = {published},
tppubtype = {inproceedings}
}
Aline Xavier Fidencio; Christian Klaes; Ioannis Iossifidis
Error-Related Potentials in Reinforcement Learning-Based Brain-Machine Interfaces Journal Article
In: Frontiers in Human Neuroscience, vol. 16, 2022.
Abstract | Links | BibTeX | Tags: BCI, EEG, error-related potentials, Machine Learning, Reinforcement learning
@article{xavierfidencioErrorrelated,
title = {Error-Related Potentials in Reinforcement Learning-Based Brain-Machine Interfaces},
author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},
url = {https://www.frontiersin.org/article/10.3389/fnhum.2022.806517},
doi = {https://doi.org/10.3389/fnhum.2022.806517},
year = {2022},
date = {2022-06-24},
urldate = {2022-06-24},
journal = {Frontiers in Human Neuroscience},
volume = {16},
abstract = {The human brain has been an object of extensive investigation in different fields. While several studies have focused on understanding the neural correlates of error processing, advances in brain-machine interface systems using non-invasive techniques further enabled the use of the measured signals in different applications. The possibility of detecting these error-related potentials (ErrPs) under different experimental setups on a single-trial basis has further increased interest in their integration in closed-loop settings to improve system performance, for example, by performing error correction. Fewer works have, however, aimed at reducing future mistakes or learning. We present a review focused on the current literature using non-invasive systems that have combined the ErrPs information specifically in a reinforcement learning framework to go beyond error correction and have used these signals for learning.},
keywords = {BCI, EEG, error-related potentials, Machine Learning, Reinforcement learning},
pubstate = {published},
tppubtype = {article}
}
The human brain has been an object of extensive investigation in different fields. While several studies have focused on understanding the neural correlates of error processing, advances in brain-machine interface systems using non-invasive techniques further enabled the use of the measured signals in different applications. The possibility of detecting these error-related potentials (ErrPs) under different experimental setups on a single-trial basis has further increased interest in their integration in closed-loop settings to improve system performance, for example, by performing error correction. Fewer works have, however, aimed at reducing future mistakes or learning. We present a review focused on the current literature using non-invasive systems that have combined the ErrPs information specifically in a reinforcement learning framework to go beyond error correction and have used these signals for learning.
Omair Ali; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis; Christian Klaes
ConTraNet: A Single End-to-End Hybrid Network for EEG-based and EMG-based Human Machine Interfaces Journal Article
In: arXiv:2206.10677 [q-bio.NC], 2022.
Abstract | Links | BibTeX | Tags: BCI, Machine Learning, neural processing, signal processing
@article{aliConTraNetSingleEndtoend2022,
title = {ConTraNet: A Single End-to-End Hybrid Network for EEG-based and EMG-based Human Machine Interfaces},
author = {Omair Ali and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis and Christian Klaes},
url = {http://arxiv.org/abs/2206.10677},
doi = {10.48550/arXiv.2206.10677},
year = {2022},
date = {2022-06-21},
urldate = {2022-06-21},
journal = {arXiv:2206.10677 [q-bio.NC]},
abstract = {Objective: Electroencephalography (EEG) and electromyography (EMG) are two non-invasive bio-signals, which are widely used in human machine interface (HMI) technologies (EEG-HMI and EMG-HMI paradigm) for the rehabilitation of physically disabled people. Successful decoding of EEG and EMG signals into respective control command is a pivotal step in the rehabilitation process. Recently, several Convolutional neural networks (CNNs) based architectures are proposed that directly map the raw time-series signal into decision space and the process of meaningful features extraction and classification are performed simultaneously. However, these networks are tailored to the learn the expected characteristics of the given bio-signal and are limited to single paradigm. In this work, we addressed the question that can we build a single architecture which is able to learn distinct features from different HMI paradigms and still successfully classify them. Approach: In this work, we introduce a single hybrid model called ConTraNet, which is based on CNN and Transformer architectures that is equally useful for EEG-HMI and EMG-HMI paradigms. ConTraNet uses CNN block to introduce inductive bias in the model and learn local dependencies, whereas the Transformer block uses the self-attention mechanism to learn the long-range dependencies in the signal, which are crucial for the classification of EEG and EMG signals. Main results: We evaluated and compared the ConTraNet with state-of-the-art methods on three publicly available datasets which belong to EEG-HMI and EMG-HMI paradigms. ConTraNet outperformed its counterparts in all the different category tasks (2-class, 3-class, 4-class, and 10-class decoding tasks). Significance: The results suggest that ConTraNet is robust to learn distinct features from different HMI paradigms and generalizes well as compared to the current state of the art algorithms.},
keywords = {BCI, Machine Learning, neural processing, signal processing},
pubstate = {published},
tppubtype = {article}
}
Objective: Electroencephalography (EEG) and electromyography (EMG) are two non-invasive bio-signals, which are widely used in human machine interface (HMI) technologies (EEG-HMI and EMG-HMI paradigm) for the rehabilitation of physically disabled people. Successful decoding of EEG and EMG signals into respective control command is a pivotal step in the rehabilitation process. Recently, several Convolutional neural networks (CNNs) based architectures are proposed that directly map the raw time-series signal into decision space and the process of meaningful features extraction and classification are performed simultaneously. However, these networks are tailored to the learn the expected characteristics of the given bio-signal and are limited to single paradigm. In this work, we addressed the question that can we build a single architecture which is able to learn distinct features from different HMI paradigms and still successfully classify them. Approach: In this work, we introduce a single hybrid model called ConTraNet, which is based on CNN and Transformer architectures that is equally useful for EEG-HMI and EMG-HMI paradigms. ConTraNet uses CNN block to introduce inductive bias in the model and learn local dependencies, whereas the Transformer block uses the self-attention mechanism to learn the long-range dependencies in the signal, which are crucial for the classification of EEG and EMG signals. Main results: We evaluated and compared the ConTraNet with state-of-the-art methods on three publicly available datasets which belong to EEG-HMI and EMG-HMI paradigms. ConTraNet outperformed its counterparts in all the different category tasks (2-class, 3-class, 4-class, and 10-class decoding tasks). Significance: The results suggest that ConTraNet is robust to learn distinct features from different HMI paradigms and generalizes well as compared to the current state of the art algorithms.
Sebastian Doliwa; Andreas Erbeslöh; Karsten Seidl; Ioannis Iossifidis
Development of a Scalable Analog Front-End for Brain-Computer Interfaces Inproceedings
In: 17th International Conference on PhD Research in Microelectronics and Electronics, IEEE Prime 2022, Sardinia, Italy, 2022.
Links | BibTeX | Tags: BCI, Implantable BCI
@inproceedings{doliwaDevelopmentScalableAnalogaccepted,
title = {Development of a Scalable Analog Front-End for Brain-Computer Interfaces},
author = {Sebastian Doliwa and Andreas Erbeslöh and Karsten Seidl and Ioannis Iossifidis},
doi = {10.1109/PRIME55000.2022.9816757},
year = {2022},
date = {2022-06-15},
urldate = {2022-06-15},
booktitle = {17th International Conference on PhD Research in Microelectronics and Electronics},
publisher = {IEEE Prime 2022},
address = {Sardinia, Italy},
keywords = {BCI, Implantable BCI},
pubstate = {published},
tppubtype = {inproceedings}
}
Omair Ali; Muhammad Saif-ur-Rehman; Susanne Dyck; Tobias Glasmachers; Ioannis Iossifidis; Christian Klaes
Enhancing the decoding accuracy of EEG signals by the introduction of anchored-STFT and adversarial data augmentation method Journal Article
In: Nature Scientific Reports, vol. 12, iss. 1, pp. 4245, 2022, ISSN: 2045-2322.
Abstract | Links | BibTeX | Tags: Adversarial NN, BCI, computer science, EEG, Machine Learning, Quantitative Biology, Quantitative Methods
@article{aliAnchoredSTFTGNAAExtension2021a,
title = {Enhancing the decoding accuracy of EEG signals by the introduction of anchored-STFT and adversarial data augmentation method},
author = {Omair Ali and Muhammad Saif-ur-Rehman and Susanne Dyck and Tobias Glasmachers and Ioannis Iossifidis and Christian Klaes},
url = {https://www.nature.com/articles/s41598-022-07992-w},
doi = {https://doi.org/10.1038/s41598-022-07992-w},
issn = {2045-2322},
year = {2022},
date = {2022-03-10},
urldate = {2022-03-10},
journal = {Nature Scientific Reports},
volume = {12},
issue = {1},
pages = {4245},
abstract = {Brain-computer interfaces (BCIs) enable communication between humans and machines by translating brain activity into control commands. Electroencephalography (EEG) signals are one of the most used brain signals in non-invasive BCI applications but are often contaminated with noise. Therefore, it is possible that meaningful patterns for classifying EEG signals are deeply hidden. State-of-the-art deep-learning algorithms are successful in learning hidden, meaningful patterns. However, the quality and the quantity of the presented inputs is pivotal. Here, we propose a novel feature extraction method called anchored Short Time Fourier Transform (anchored-STFT), which is an advanced version of STFT, as it minimizes the trade-off between temporal and spectral resolution presented by STFT. In addition, we propose a novel augmentation method, called gradient norm adversarial augmentation (GNAA). GNAA is not only an augmentation method but is also used to harness adversarial inputs in EEG data, which not only improves the classification accuracy but also enhances the robustness of the classifier. In addition, we also propose a new CNN architecture, namely Skip-Net, for the classification of EEG signals. The proposed pipeline outperforms all state-of-the-art methods and yields an average classification accuracy of 90.7 % and 89.54 % on BCI competition II dataset III and BCI competition IV dataset 2b, respectively.},
keywords = {Adversarial NN, BCI, computer science, EEG, Machine Learning, Quantitative Biology, Quantitative Methods},
pubstate = {published},
tppubtype = {article}
}
Brain-computer interfaces (BCIs) enable communication between humans and machines by translating brain activity into control commands. Electroencephalography (EEG) signals are one of the most used brain signals in non-invasive BCI applications but are often contaminated with noise. Therefore, it is possible that meaningful patterns for classifying EEG signals are deeply hidden. State-of-the-art deep-learning algorithms are successful in learning hidden, meaningful patterns. However, the quality and the quantity of the presented inputs is pivotal. Here, we propose a novel feature extraction method called anchored Short Time Fourier Transform (anchored-STFT), which is an advanced version of STFT, as it minimizes the trade-off between temporal and spectral resolution presented by STFT. In addition, we propose a novel augmentation method, called gradient norm adversarial augmentation (GNAA). GNAA is not only an augmentation method but is also used to harness adversarial inputs in EEG data, which not only improves the classification accuracy but also enhances the robustness of the classifier. In addition, we also propose a new CNN architecture, namely Skip-Net, for the classification of EEG signals. The proposed pipeline outperforms all state-of-the-art methods and yields an average classification accuracy of 90.7 % and 89.54 % on BCI competition II dataset III and BCI competition IV dataset 2b, respectively.
Marie Dominique Schmidt; Tobias Glasmachers; Ioannis Iossifidis
From Motion to Muscle Journal Article
In: arXiv: 2201.11501 [cs.LG], 2022.
Links | BibTeX | Tags: BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network
@article{schmidt2022motion,
title = {From Motion to Muscle},
author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},
doi = {https://doi.org/10.48550/arXiv.2201.11501},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {arXiv: 2201.11501 [cs.LG]},
keywords = {BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network},
pubstate = {published},
tppubtype = {article}
}
Aline Xavier Fidencio; Tobias Glasmachers; Ioannis Iossifidis
Error-Related Potentials Detection with Dry- and Wet-Electrode EEG Inproceedings
In: FENS, Forum 2022, FENS, Federation of European Neuroscience Societies, 2022.
Abstract | BibTeX | Tags: BCI, EEG, error-related potentials, Machine Learning
@inproceedings{fidencioErrorrelatedPotentialsDetection2022,
title = {Error-Related Potentials Detection with Dry- and Wet-Electrode EEG},
author = {Aline Xavier Fidencio and Tobias Glasmachers and Ioannis Iossifidis},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {FENS, Forum 2022},
publisher = {FENS, Federation of European Neuroscience Societies},
abstract = {Electroencephalography (EEG) is a non-invasive technique for measuring brain electrical activity from electrodes placed on the scalp surface. Improvements in this technology are particularly relevant because they also boost brain-machine interfaces (BMI) development. Commonly, gel-based electrodes are used since they guarantee a high-quality signal. Alternatively, dry electrodes have been introduced, more suitable for daily use. In this work, we compare conventional dry and wet electrode systems specifically for the detection of error-related potentials (ErrPs). ErrPs are elicited as a reaction to both self-made and external errors. There has been increased interest in the integration of these signals into BMIs to improve their performance since they provide a convenient source of feedback to the system with no extra workload for the subject. These signals can be used, e.g., to correct errors or even for system adaptation. ErrP-based BMIs in the literature have consistently used wet electrodes. Therefore, even though both electrodes types have been compared for other event-related potentials (e.g., P300), it is relevant to know whether the signal quality for the detection of ErrPs is comparable among them. In this work, we implement a simple game to elicit ErrPs and compare the quality of the measured signals. We tested the feasibility of the experimental protocol to elicit ErrP and the measured ErrP displayed a similar waveshape in terms of observed peaks. However, differences exist in both latencies as well as in their amplitude. These variations and other relevant characteristics have to be further verified with more subjects},
keywords = {BCI, EEG, error-related potentials, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Electroencephalography (EEG) is a non-invasive technique for measuring brain electrical activity from electrodes placed on the scalp surface. Improvements in this technology are particularly relevant because they also boost brain-machine interfaces (BMI) development. Commonly, gel-based electrodes are used since they guarantee a high-quality signal. Alternatively, dry electrodes have been introduced, more suitable for daily use. In this work, we compare conventional dry and wet electrode systems specifically for the detection of error-related potentials (ErrPs). ErrPs are elicited as a reaction to both self-made and external errors. There has been increased interest in the integration of these signals into BMIs to improve their performance since they provide a convenient source of feedback to the system with no extra workload for the subject. These signals can be used, e.g., to correct errors or even for system adaptation. ErrP-based BMIs in the literature have consistently used wet electrodes. Therefore, even though both electrodes types have been compared for other event-related potentials (e.g., P300), it is relevant to know whether the signal quality for the detection of ErrPs is comparable among them. In this work, we implement a simple game to elicit ErrPs and compare the quality of the measured signals. We tested the feasibility of the experimental protocol to elicit ErrP and the measured ErrP displayed a similar waveshape in terms of observed peaks. However, differences exist in both latencies as well as in their amplitude. These variations and other relevant characteristics have to be further verified with more subjects
Marie Dominique Schmidt; Tobias Glasmachers; Ioannis Iossifidis
Motion Intention Prediction Inproceedings
In: FENS, Forum 2022, FENS, Federation of European Neuroscience Societies, 2022.
Abstract | BibTeX | Tags: BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network
@inproceedings{schmidtMotionIntentionPrediction2022a,
title = {Motion Intention Prediction},
author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {FENS, Forum 2022},
publisher = {FENS, Federation of European Neuroscience Societies},
abstract = {Motion intention prediction is the key to robot-assisted rehabilitation systems. These can rely on various biological signals. One commonly used signal is the muscle activity measured by an electromyogram that occurs between 50-100 milliseconds before the actual movement, allowing a real-world application to assist in time. We show that upper limb motion can be estimated from the corresponding muscle activity. To this end, eight-arm muscles are mapped to the joint angle, velocity, and acceleration of the shoulder, elbow, and wrist. For this purpose, we specifically develop an artificial neural network that estimates complex motions involving multiple upper limb joints. The network model is evaluated concerning its ability to generalize across subjects as well as for new motions. This is achieved through training on multiple subjects and additional transfer learning methods so that the prediction for new subjects is significantly improved. In particular, this is beneficial for a robust real-world application. Furthermore, we investigate the importance of the different parameters such as angle, velocity, and acceleration for simple and complex motions. Predictions for simple motions along with the main components of complex motions achieve excellent accuracy while joints that do not play a dominant role during the motion have comparatively lower accuracy.},
keywords = {BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network},
pubstate = {published},
tppubtype = {inproceedings}
}
Motion intention prediction is the key to robot-assisted rehabilitation systems. These can rely on various biological signals. One commonly used signal is the muscle activity measured by an electromyogram that occurs between 50-100 milliseconds before the actual movement, allowing a real-world application to assist in time. We show that upper limb motion can be estimated from the corresponding muscle activity. To this end, eight-arm muscles are mapped to the joint angle, velocity, and acceleration of the shoulder, elbow, and wrist. For this purpose, we specifically develop an artificial neural network that estimates complex motions involving multiple upper limb joints. The network model is evaluated concerning its ability to generalize across subjects as well as for new motions. This is achieved through training on multiple subjects and additional transfer learning methods so that the prediction for new subjects is significantly improved. In particular, this is beneficial for a robust real-world application. Furthermore, we investigate the importance of the different parameters such as angle, velocity, and acceleration for simple and complex motions. Predictions for simple motions along with the main components of complex motions achieve excellent accuracy while joints that do not play a dominant role during the motion have comparatively lower accuracy.
2021
Felix Grün; Tobias Glasmachers; Ioannis Iossifidis
Off-Policy Continuous Control Using Distributional Reinforcement Learning Inproceedings
In: Bernstein Conference, 2021.
Links | BibTeX | Tags: Machine Learning, Reinforcement learning
@inproceedings{grunOffPolicyContinuousControl2021b,
title = {Off-Policy Continuous Control Using Distributional Reinforcement Learning},
author = {Felix Grün and Tobias Glasmachers and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p001},
year = {2021},
date = {2021-10-01},
urldate = {2021-10-01},
publisher = {Bernstein Conference},
keywords = {Machine Learning, Reinforcement learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Stephan Johann Lehmler; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis
Transfer-Learning for Patient Specific Model Re-Calibration: Application to sEMG-Classification Inproceedings
In: Bernstein Conferen, 2021.
Links | BibTeX | Tags: BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning, transfer learning
@inproceedings{lehmlerTransferLearningPatientSpecific2021b,
title = {Transfer-Learning for Patient Specific Model Re-Calibration: Application to sEMG-Classification},
author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p005},
year = {2021},
date = {2021-10-01},
urldate = {2021-10-01},
publisher = {Bernstein Conferen},
keywords = {BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning, transfer learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Marie Dominique Schmidt; Tobias Glasmachers; Ioannis Iossifidis
Artificially Generated Muscle Signals Inproceedings
In: Bernstein Conference, 2021.
Links | BibTeX | Tags: BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network
@inproceedings{schmidtArtificiallyGeneratedMuscle2021b,
title = {Artificially Generated Muscle Signals},
author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p111},
year = {2021},
date = {2021-10-01},
urldate = {2021-10-01},
publisher = {Bernstein Conference},
keywords = {BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network},
pubstate = {published},
tppubtype = {inproceedings}
}
Tim Sziburis; Susanne Blex; Tobias Glasmachers; Inaki Rano; Ioannis Iossifidis
Modelling the Generation of Human Upper-Limb Reaching Trajectories: An Extended Behavioural Attractor Dynamics Approach Inproceedings
In: Bernstein Conference, 2021.
Links | BibTeX | Tags: attractor dynamics approach, human arm motion
@inproceedings{sziburisModellingGenerationHuman2021b,
title = {Modelling the Generation of Human Upper-Limb Reaching Trajectories: An Extended Behavioural Attractor Dynamics Approach},
author = {Tim Sziburis and Susanne Blex and Tobias Glasmachers and Inaki Rano and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p078},
year = {2021},
date = {2021-10-01},
urldate = {2021-10-01},
publisher = {Bernstein Conference},
keywords = {attractor dynamics approach, human arm motion},
pubstate = {published},
tppubtype = {inproceedings}
}
Aline Xavier Fidencio; Tobias Glasmachers; Christian Klaes; Ioannis Iossifidis
Beyond Error Correction: Integration of Error-Related Potentials into Brain-Computer Interfaces for Improved Performance Inproceedings
In: Bernstein Conference, 2021.
Links | BibTeX | Tags: BCI, error-related potentials, Machine Learning, Reinforcement learning
@inproceedings{xavierfidencioErrorCorrectionIntegration2021b,
title = {Beyond Error Correction: Integration of Error-Related Potentials into Brain-Computer Interfaces for Improved Performance},
author = {Aline Xavier Fidencio and Tobias Glasmachers and Christian Klaes and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p163},
year = {2021},
date = {2021-10-01},
urldate = {2021-10-01},
publisher = {Bernstein Conference},
keywords = {BCI, error-related potentials, Machine Learning, Reinforcement learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Felix Grün; Tobias Glasmachers; Ioannis Iossifidis
Off-Policy Continuous Control Using Distributional Reinforcement Learning Inproceedings
In: BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021, BCCN Bernstein Network Computational Network, 2021.
Links | BibTeX | Tags: Machine Learning, Reinforcement learning
@inproceedings{grunOffPolicyContinuousControl2021,
title = {Off-Policy Continuous Control Using Distributional Reinforcement Learning},
author = {Felix Grün and Tobias Glasmachers and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p001},
year = {2021},
date = {2021-09-15},
urldate = {2021-09-15},
booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {Machine Learning, Reinforcement learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Aline Xavier Fidencio; Tobias Glasmachers; Christian Klaes; Ioannis Iossifidis
Beyond error correction: Integration of error-related potentials into brain-computer interfaces for improved performance Inproceedings
In: BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021, BCCN Bernstein Network Computational Network, 2021.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{xavierfidencioErrorCorrectionIntegration2021,
title = {Beyond error correction: Integration of error-related potentials into brain-computer interfaces for improved performance},
author = {Aline Xavier Fidencio and Tobias Glasmachers and Christian Klaes and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p163},
year = {2021},
date = {2021-09-15},
urldate = {2021-09-15},
booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Stephan Johann Lehmler; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis
Transfer-Learning for Patient Specific Model Re-Calibration: Application to sEMG-Classification Inproceedings
In: BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021, BCCN Bernstein Network Computational Network, 2021.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{lehmlerTransferLearningPatientSpecific2021,
title = {Transfer-Learning for Patient Specific Model Re-Calibration: Application to sEMG-Classification},
author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p005},
year = {2021},
date = {2021-09-15},
urldate = {2021-09-15},
booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Marie Dominique Schmidt; Tobias Glasmachers; Ioannis Iossifidis
Artificially Generated Muscle Signals Inproceedings
In: BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021, BCCN Bernstein Network Computational Network, 2021.
Links | BibTeX | Tags: BCI, Machine Learning
@inproceedings{schmidtArtificiallyGeneratedMuscle2021,
title = {Artificially Generated Muscle Signals},
author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p111},
year = {2021},
date = {2021-09-15},
urldate = {2021-09-15},
booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Tim Sziburis; Susanne Blex; Tobias Glasmachers; Inaki Rano; Ioannis Iossifidis
Modelling the Generation of Human Upper-Limb Reaching Trajectories: An Extended Behavioural Attractor Dynamics Approach Inproceedings
In: BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021, BCCN Bernstein Network Computational Network, 2021.
Links | BibTeX | Tags: BCI, Machine Learning, movement model
@inproceedings{sziburisModellingGenerationHuman2021,
title = {Modelling the Generation of Human Upper-Limb Reaching Trajectories: An Extended Behavioural Attractor Dynamics Approach},
author = {Tim Sziburis and Susanne Blex and Tobias Glasmachers and Inaki Rano and Ioannis Iossifidis},
doi = {10.12751/nncn.bc2021.p078},
year = {2021},
date = {2021-09-15},
urldate = {2021-09-15},
booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},
publisher = {BCCN Bernstein Network Computational Network},
keywords = {BCI, Machine Learning, movement model},
pubstate = {published},
tppubtype = {inproceedings}
}
Omair Ali; Muhammad Saif-ur-Rehman; Susanne Dyck; Tobias Glasmachers; Ioannis Iossifidis; Christian Klaes
Anchored-STFT and GNAA: An Extension of STFT in Conjunction with an Adversarial Data Augmentation Technique for the Decoding of Neural Signals Journal Article
In: arXiv:2011.14694 [cs, q-bio], 2021.
Abstract | BibTeX | Tags: BCI, Machine Learning, Quantitative Biology, Quantitative Methods
@article{aliAnchoredSTFTGNAAExtension2021,
title = {Anchored-STFT and GNAA: An Extension of STFT in Conjunction with an Adversarial Data Augmentation Technique for the Decoding of Neural Signals},
author = {Omair Ali and Muhammad Saif-ur-Rehman and Susanne Dyck and Tobias Glasmachers and Ioannis Iossifidis and Christian Klaes},
year = {2021},
date = {2021-08-01},
urldate = {2021-08-01},
journal = {arXiv:2011.14694 [cs, q-bio]},
abstract = {Brain-computer interfaces (BCIs) enable communication between humans and machines by translating brain activity into control commands. Electroencephalography (EEG) signals are one of the most used brain signals in non-invasive BCI applications but are often contaminated with noise. Therefore, it is possible that meaningful patterns for classifying EEG signals are deeply hidden. State-of-the-art deep-learning algorithms are successful in learning hidden, meaningful patterns. However, the quality and the quantity of the presented inputs is pivotal. Here, we propose a novel feature extraction method called anchored Short Time Fourier Transform (anchored-STFT), which is an advanced version of STFT, as it minimizes the trade-off between temporal and spectral resolution presented by STFT. In addition, we propose a novel augmentation method, called gradient norm adversarial augmentation (GNAA). GNAA is not only an augmentation method but is also used to harness adversarial inputs in EEG data, which not only improves the classification accuracy but also enhances the robustness of the classifier. In addition, we also propose a new CNN architecture, namely Skip-Net, for the classification of EEG signals. The proposed pipeline outperforms all state-of-the-art methods and yields an average classification accuracy of 90.7 % and 89.54 % on BCI competition II dataset III and BCI competition IV dataset 2b, respectively.},
keywords = {BCI, Machine Learning, Quantitative Biology, Quantitative Methods},
pubstate = {published},
tppubtype = {article}
}
Brain-computer interfaces (BCIs) enable communication between humans and machines by translating brain activity into control commands. Electroencephalography (EEG) signals are one of the most used brain signals in non-invasive BCI applications but are often contaminated with noise. Therefore, it is possible that meaningful patterns for classifying EEG signals are deeply hidden. State-of-the-art deep-learning algorithms are successful in learning hidden, meaningful patterns. However, the quality and the quantity of the presented inputs is pivotal. Here, we propose a novel feature extraction method called anchored Short Time Fourier Transform (anchored-STFT), which is an advanced version of STFT, as it minimizes the trade-off between temporal and spectral resolution presented by STFT. In addition, we propose a novel augmentation method, called gradient norm adversarial augmentation (GNAA). GNAA is not only an augmentation method but is also used to harness adversarial inputs in EEG data, which not only improves the classification accuracy but also enhances the robustness of the classifier. In addition, we also propose a new CNN architecture, namely Skip-Net, for the classification of EEG signals. The proposed pipeline outperforms all state-of-the-art methods and yields an average classification accuracy of 90.7 % and 89.54 % on BCI competition II dataset III and BCI competition IV dataset 2b, respectively.
Sebastian Doliwa; Muhammad Ayaz Hussain; Tim Sziburis; Ioannis Iossifidis
Biologically Inspired Model for Timed Motion in Robotic Systems Journal Article
In: arXiv:2106.15864 [cs, math], 2021.
Abstract | BibTeX | Tags: attractor dynamics approach, Autonomous robotics, dynamical systems
@article{doliwaBiologicallyInspiredModel2021,
title = {Biologically Inspired Model for Timed Motion in Robotic Systems},
author = {Sebastian Doliwa and Muhammad Ayaz Hussain and Tim Sziburis and Ioannis Iossifidis},
year = {2021},
date = {2021-07-01},
urldate = {2021-07-01},
journal = {arXiv:2106.15864 [cs, math]},
abstract = {The goal of this work is the development of a motion model for sequentially timed movement actions in robotic systems under specific consideration of temporal stabilization, that is maintaining an approximately constant overall movement time (isochronous behavior). This is demonstrated both in simulation and on a physical robotic system for the task of intercepting a moving target in three-dimensional space. Motivated from humanoid motion, timing plays a vital role to generate a naturalistic behavior in interaction with the dynamic environment as well as adaptively planning and executing action sequences on-line. In biological systems, many of the physiological and anatomical functions follow a particular level of periodicity and stabilization, which exhibit a certain extent of resilience against external disturbances. A main aspect thereof is stabilizing movement timing against limited perturbations. Especially human arm movement, namely when it is tasked to reach a certain goal point, pose or configuration, shows a stabilizing behavior. This work incorporates the utilization of an extended Kalman filter (EKF) which was implemented to predict the target position while coping with non-linear system dynamics. The periodicity and temporal stabilization in biological systems was artificially generated by a Hopf oscillator, yielding a sinusoidal velocity profile for smooth and repeatable motion.},
keywords = {attractor dynamics approach, Autonomous robotics, dynamical systems},
pubstate = {published},
tppubtype = {article}
}
The goal of this work is the development of a motion model for sequentially timed movement actions in robotic systems under specific consideration of temporal stabilization, that is maintaining an approximately constant overall movement time (isochronous behavior). This is demonstrated both in simulation and on a physical robotic system for the task of intercepting a moving target in three-dimensional space. Motivated from humanoid motion, timing plays a vital role to generate a naturalistic behavior in interaction with the dynamic environment as well as adaptively planning and executing action sequences on-line. In biological systems, many of the physiological and anatomical functions follow a particular level of periodicity and stabilization, which exhibit a certain extent of resilience against external disturbances. A main aspect thereof is stabilizing movement timing against limited perturbations. Especially human arm movement, namely when it is tasked to reach a certain goal point, pose or configuration, shows a stabilizing behavior. This work incorporates the utilization of an extended Kalman filter (EKF) which was implemented to predict the target position while coping with non-linear system dynamics. The periodicity and temporal stabilization in biological systems was artificially generated by a Hopf oscillator, yielding a sinusoidal velocity profile for smooth and repeatable motion.
Tim Sziburis; Markus Nowak; Davide Brunelli
Prototype Reduction on sEMG Data for Instance-Based Gesture Learning towards Real-Time Prosthetic Control: Inproceedings
In: Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies, pp. 299–305, SCITEPRESS - Science and Technology Publications, Online Streaming, --- Select a Country ---, 2021, ISBN: 978-989-758-490-9.
@inproceedings{sziburisPrototypeReductionSEMG2021,
title = {Prototype Reduction on sEMG Data for Instance-Based Gesture Learning towards Real-Time Prosthetic Control:},
author = {Tim Sziburis and Markus Nowak and Davide Brunelli},
url = {https://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0010327502990305},
doi = {10.5220/0010327502990305},
isbn = {978-989-758-490-9},
year = {2021},
date = {2021-03-26},
urldate = {2021-03-26},
booktitle = {Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies},
pages = {299--305},
publisher = {SCITEPRESS - Science and Technology Publications},
address = {Online Streaming, --- Select a Country ---},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A X Fidêncio; T Glasmachers; D Naro
Application of Reinforcement Learning to a Mining System Inproceedings
In: 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI), pp. 000111–000118, 2021.
Abstract | Links | BibTeX | Tags: Control Applications, Industrial Application, Machine Learning, Machine learning algorithms, Mining Industry, Reinforcement learning
@inproceedings{fidencioApplicationReinforcementLearning2021,
title = {Application of Reinforcement Learning to a Mining System},
author = {A X Fidêncio and T Glasmachers and D Naro},
doi = {10.1109/SAMI50585.2021.9378663},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)},
pages = {000111--000118},
abstract = {Automation techniques have been widely applied in different industry segments, among others, to increase both productivity and safety. In the mining industry, with the usage of such systems, the operator can be removed from hazardous environments without compromising task execution and it is possible to achieve more efficient and standardized operation. In this work a study case on the application of machine learning algorithms to a mining system example is presented, in which reinforcement learning algorithms were used to solve a control problem. As an example, a machine chain consisting of a Bucket Wheel Excavator, a Belt Wagon and a Hopper Car was used. This system has two material transfer points that need to remain aligned during operation in order to allow continuous material flow. To keep the alignment, the controller makes use of seven degrees of freedom given by slewing, luffing and crawler drives. Experimental tests were done in a simulated environment with two state-of-the-art algorithms, namely Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC). The trained agents were evaluated in terms of episode return and length, as well as alignment quality and action values used. Results show that, for the given task, the PPO agent performs quantitatively and qualitatively better than the SAC agent. However, none of the agents were able to completely solve the proposed testing task.},
keywords = {Control Applications, Industrial Application, Machine Learning, Machine learning algorithms, Mining Industry, Reinforcement learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Automation techniques have been widely applied in different industry segments, among others, to increase both productivity and safety. In the mining industry, with the usage of such systems, the operator can be removed from hazardous environments without compromising task execution and it is possible to achieve more efficient and standardized operation. In this work a study case on the application of machine learning algorithms to a mining system example is presented, in which reinforcement learning algorithms were used to solve a control problem. As an example, a machine chain consisting of a Bucket Wheel Excavator, a Belt Wagon and a Hopper Car was used. This system has two material transfer points that need to remain aligned during operation in order to allow continuous material flow. To keep the alignment, the controller makes use of seven degrees of freedom given by slewing, luffing and crawler drives. Experimental tests were done in a simulated environment with two state-of-the-art algorithms, namely Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC). The trained agents were evaluated in terms of episode return and length, as well as alignment quality and action values used. Results show that, for the given task, the PPO agent performs quantitatively and qualitatively better than the SAC agent. However, none of the agents were able to completely solve the proposed testing task.
Stephan Johann Lehmler; Muhammad Saif-ur-Rehman; Tobias Glasmachers; Ioannis Iossifidis
Deep Transfer-Learning for patient specific model re-calibration: Application to sEMG-Classification Journal Article
In: 2021.
Links | BibTeX | Tags: BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning
@article{lehmler2021deep,
title = {Deep Transfer-Learning for patient specific model re-calibration: Application to sEMG-Classification},
author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},
url = {https://api.semanticscholar.org/CorpusID:245634948},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
keywords = {BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning},
pubstate = {published},
tppubtype = {article}
}
2020
Muhammad Ayaz Hussain; Muhammad Saif-ur-Rehman; Christian Klaes; Ioannis Iossifidis
Comparison of Anomaly Detection between Statistical Method and Undercomplete Inproceedings
In: IEEE IInternational Congress on Big Data, pp. 32–38, Los Angeles, USA, 2020.
Links | BibTeX | Tags: Anomaly Detection, Autoencoder, Machine Learning
@inproceedings{Hussain2020,
title = {Comparison of Anomaly Detection between Statistical Method and Undercomplete},
author = {Muhammad Ayaz Hussain and Muhammad Saif-ur-Rehman and Christian Klaes and Ioannis Iossifidis},
doi = {https://doi.org/10.1145/3404687.3404689},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
booktitle = {IEEE IInternational Congress on Big Data},
pages = {32--38},
address = {Los Angeles, USA},
keywords = {Anomaly Detection, Autoencoder, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Muhammad Saif-ur-Rehman; Omair Ali; Susanne Dyck; Robin Lienkämper; Marita Metzler; Yaroslav Parpaley; Jörg Wellmer; Charles Liu; Brian Lee; Spencer Kellis; Richard A Andersen; Ioannis Iossifidis; Tobias Glasmachers; Christian Klaes
SpikeDeep-Classifier: A deep-learning based fully automatic offline spike sorting algorithm Journal Article
In: Journal of Neural Engineering, 2020.
Abstract | Links | BibTeX | Tags: BCI, CNN, Machine Learning, Spike Sorting
@article{10.1088/1741-2552/abc8d4,
title = {SpikeDeep-Classifier: A deep-learning based fully automatic offline spike sorting algorithm},
author = {Muhammad Saif-ur-Rehman and Omair Ali and Susanne Dyck and Robin Lienkämper and Marita Metzler and Yaroslav Parpaley and Jörg Wellmer and Charles Liu and Brian Lee and Spencer Kellis and Richard A Andersen and Ioannis Iossifidis and Tobias Glasmachers and Christian Klaes},
url = {http://iopscience.iop.org/article/10.1088/1741-2552/abc8d4},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {Journal of Neural Engineering},
abstract = {Objective. Advancements in electrode design have resulted in micro-electrode arrays with hundreds of channels for single cell recordings. In the resulting electrophysiological recordings, each implanted electrode can record spike activity (SA) of one or more neurons along with background activity (BA). The aim of this study is to isolate SA of each neural source. This process is called spike sorting or spike classification. Advanced spike sorting algorithms are time consuming because of the human intervention at various stages of the pipeline. Current approaches lack generalization because the values of hyperparameters are not fixed, even for multiple recording sessions of the same subject. In this study, a fully automatic spike sorting algorithm called “SpikeDeep-Classifier” is proposed. The values of hyperparameters remain fixed for all the evaluation data. Approach. The proposed approach is based on our previous study (SpikeDeeptector) and a novel background activity rejector (BAR), which are both supervised learning algorithms and an unsupervised learning algorithm (K-means). SpikeDeeptector and BAR are used to extract meaningful channels and remove BA from the extracted meaningful channels, respectively. The process of clustering becomes straight-forward once the BA is completely removed from the data. Then, K-means with a predefined maximum number of clusters is applied on the remaining data originating from neural sources only. Lastly, a similarity-based criterion and a threshold are used to keep distinct clusters and merge similar looking clusters. The proposed approach is called cluster accept or merge (CAOM) and it has only two hyperparameters (maximum number of clusters and similarity threshold) which are kept fixed for all the evaluation data after tuning. Main Results. We compared the results of our algorithm with ground-truth labels. The algorithm is evaluated on data of human patients and publicly available labeled non-human primates (NHPs) datasets. The average accuracy of BAR on datasets of human patients is 92.3% which is further reduced to 88.03% after (K-means + CAOM). In addition, the average accuracy of BAR on a publicly available labeled dataset of NHPs is 95.40% which reduces to 86.95% after (K-mean + CAOM). Lastly, we compared the performance of the SpikeDeep-Classifier with two human experts, where SpikeDeep-Classifier has produced comparable results. Significance. The results demonstrate that “SpikeDeep-Classifier” possesses the ability to generalize well on a versatile dataset and henceforth provides a generalized well on a versatile dataset and henceforth provides a generalized and fully automated solution to offline spike sorting.},
keywords = {BCI, CNN, Machine Learning, Spike Sorting},
pubstate = {published},
tppubtype = {article}
}
Objective. Advancements in electrode design have resulted in micro-electrode arrays with hundreds of channels for single cell recordings. In the resulting electrophysiological recordings, each implanted electrode can record spike activity (SA) of one or more neurons along with background activity (BA). The aim of this study is to isolate SA of each neural source. This process is called spike sorting or spike classification. Advanced spike sorting algorithms are time consuming because of the human intervention at various stages of the pipeline. Current approaches lack generalization because the values of hyperparameters are not fixed, even for multiple recording sessions of the same subject. In this study, a fully automatic spike sorting algorithm called “SpikeDeep-Classifier” is proposed. The values of hyperparameters remain fixed for all the evaluation data. Approach. The proposed approach is based on our previous study (SpikeDeeptector) and a novel background activity rejector (BAR), which are both supervised learning algorithms and an unsupervised learning algorithm (K-means). SpikeDeeptector and BAR are used to extract meaningful channels and remove BA from the extracted meaningful channels, respectively. The process of clustering becomes straight-forward once the BA is completely removed from the data. Then, K-means with a predefined maximum number of clusters is applied on the remaining data originating from neural sources only. Lastly, a similarity-based criterion and a threshold are used to keep distinct clusters and merge similar looking clusters. The proposed approach is called cluster accept or merge (CAOM) and it has only two hyperparameters (maximum number of clusters and similarity threshold) which are kept fixed for all the evaluation data after tuning. Main Results. We compared the results of our algorithm with ground-truth labels. The algorithm is evaluated on data of human patients and publicly available labeled non-human primates (NHPs) datasets. The average accuracy of BAR on datasets of human patients is 92.3% which is further reduced to 88.03% after (K-means + CAOM). In addition, the average accuracy of BAR on a publicly available labeled dataset of NHPs is 95.40% which reduces to 86.95% after (K-mean + CAOM). Lastly, we compared the performance of the SpikeDeep-Classifier with two human experts, where SpikeDeep-Classifier has produced comparable results. Significance. The results demonstrate that “SpikeDeep-Classifier” possesses the ability to generalize well on a versatile dataset and henceforth provides a generalized well on a versatile dataset and henceforth provides a generalized and fully automated solution to offline spike sorting.
Omair Ali; Muhammad Saif-ur-Rehman; Susanne Dyck; Tobias Glasmachers; Ioannis Iossifidis; Christian Klaes
Improving the performance of EEG decoding using anchored-STFT in conjunction with gradient norm adversarial augmentation Journal Article
In: arXiv preprint arXiv:2011.14694, 2020.
BibTeX | Tags: Adversarial NN, BCI, EEG, Machine Learning
@article{ali2020improving,
title = {Improving the performance of EEG decoding using anchored-STFT in conjunction with gradient norm adversarial augmentation},
author = {Omair Ali and Muhammad Saif-ur-Rehman and Susanne Dyck and Tobias Glasmachers and Ioannis Iossifidis and Christian Klaes},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {arXiv preprint arXiv:2011.14694},
keywords = {Adversarial NN, BCI, EEG, Machine Learning},
pubstate = {published},
tppubtype = {article}
}
2019
Muhammad Saif-ur-Rehman; Robin Lienkämper; S Dyck; A Rayana; Y Parpaley; J Wllner; C Liu; B Lee; S Kellis; D Manahan-Vaughn; O Güntürkün; R A Andersen; Ioannis Iossifidis; T Galmachers; C Klaes
Universal SpikeDeeptector Miscellaneous
2019.
Abstract | BibTeX | Tags: BCI, CNN, Machine Learning, Spike Detection, Spike Sorting
@misc{ur-reimann2019a,
title = {Universal SpikeDeeptector},
author = {Muhammad Saif-ur-Rehman and Robin Lienkämper and S Dyck and A Rayana and Y Parpaley and J Wllner and C Liu and B Lee and S Kellis and D Manahan-Vaughn and O Güntürkün and R A Andersen and Ioannis Iossifidis and T Galmachers and C Klaes},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
publisher = {SfN 2019},
abstract = {State-of-the-art microelectrode array technology enables simultaneous, large-scale single unit recordings from hundreds of channels. Identification of channels recording neural data as compared to noise is the first step for all further analyses. Automatizing this process aims at minimizing the human involvement and time for manual curation. In our previous study, we introduced the “SpikeDeeptector” (SD), which enables us to automatically detect and track channels containing neural data from different human patients implanted with different types of microelectrodes across different brain areas. SD works on human data and to some extent on the data of non-human primates (NHPs). However, to make SD more versatile we proposed a more generalized method called “Universal SpikeDeeptector (USD)”, which is an extended version of SD. USD intends to detect and track the channels containing neural data recorded from four different species (rats, ravens, NHPs and humans) using different kinds of microelectrodes and different recording sites. To our knowledge, there is no method that can simultaneously detect and track neural data of multiple species. To enable contextual learning, USD constructs a feature vector from a batch of waveforms. The constructed feature vectors are then fed into a deep-learning algorithm, which learns contextualized, temporal and spatial patterns. USD is a supervised learning method. Therefore, it requires labeled data for training. It is mainly trained on data from a single human tetraplegic patient, and a small but equal portion of data from the remaining three species. The trained model is then evaluated on a test dataset collected from several humans, NHPs, rats, and birds. The results show that the USD performed consistently well across data collected from each species.},
keywords = {BCI, CNN, Machine Learning, Spike Detection, Spike Sorting},
pubstate = {published},
tppubtype = {misc}
}
State-of-the-art microelectrode array technology enables simultaneous, large-scale single unit recordings from hundreds of channels. Identification of channels recording neural data as compared to noise is the first step for all further analyses. Automatizing this process aims at minimizing the human involvement and time for manual curation. In our previous study, we introduced the “SpikeDeeptector” (SD), which enables us to automatically detect and track channels containing neural data from different human patients implanted with different types of microelectrodes across different brain areas. SD works on human data and to some extent on the data of non-human primates (NHPs). However, to make SD more versatile we proposed a more generalized method called “Universal SpikeDeeptector (USD)”, which is an extended version of SD. USD intends to detect and track the channels containing neural data recorded from four different species (rats, ravens, NHPs and humans) using different kinds of microelectrodes and different recording sites. To our knowledge, there is no method that can simultaneously detect and track neural data of multiple species. To enable contextual learning, USD constructs a feature vector from a batch of waveforms. The constructed feature vectors are then fed into a deep-learning algorithm, which learns contextualized, temporal and spatial patterns. USD is a supervised learning method. Therefore, it requires labeled data for training. It is mainly trained on data from a single human tetraplegic patient, and a small but equal portion of data from the remaining three species. The trained model is then evaluated on a test dataset collected from several humans, NHPs, rats, and birds. The results show that the USD performed consistently well across data collected from each species.
Muhammad Ayaz Hussain; Muhammad Saif-ur-Rehman; Christian Klaes; Ioannis Iossifidis
Comparison of Anomaly Detection between Statistical Method and Undercomplete Inproceedings
In: IEEE IInternational Congress on Big Data, Los Angeles, USA, 2019.
BibTeX | Tags: Anomaly Detection, Autoencoder, Machine Learning
@inproceedings{Hussain2019,
title = {Comparison of Anomaly Detection between Statistical Method and Undercomplete},
author = {Muhammad Ayaz Hussain and Muhammad Saif-ur-Rehman and Christian Klaes and Ioannis Iossifidis},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
booktitle = {IEEE IInternational Congress on Big Data},
address = {Los Angeles, USA},
keywords = {Anomaly Detection, Autoencoder, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Muhammad Saif-ur-Rehman; Robin Lienkämper; Yaroslav Parpaley; Jörg Wellmer; Charles Liu; Brian Lee; Spencer Kellis; Richard Andersen; Ioannis Iossifidis; Tobias Glasmachers; Christian Klaes
SpikeDeeptector: a deep-learning based method for detection of neural spiking activity Journal Article
In: Journal of Neural Engineering, vol. 16, no. 5, pp. 056003, 2019.
Abstract | Links | BibTeX | Tags: BCI, CNN, Data Reduction, Machine Learning, Spike Sorting
@article{Saif-ur-Rehman2019,
title = {SpikeDeeptector: a deep-learning based method for detection of neural spiking activity},
author = {Muhammad Saif-ur-Rehman and Robin Lienkämper and Yaroslav Parpaley and Jörg Wellmer and Charles Liu and Brian Lee and Spencer Kellis and Richard Andersen and Ioannis Iossifidis and Tobias Glasmachers and Christian Klaes},
url = {https://iopscience.iop.org/article/10.1088/1741-2552/ab1e63/meta},
doi = {10.1088/1741-2552/ab1e63},
year = {2019},
date = {2019-01-01},
urldate = {2019-01-01},
journal = {Journal of Neural Engineering},
volume = {16},
number = {5},
pages = {056003},
abstract = {Objective . In electrophysiology, microelectrodes are the primary source for recording neural data (single unit activity). These microelectrodes can be implanted individually or in the form of arrays containing dozens to hundreds of channels. Recordings of some channels contain neural activity, which are often contaminated with noise. Another fraction of channels does not record any neural data, but only noise. By noise, we mean physiological activities unrelated to spiking, including technical artifacts and neural activities of neurons that are too far away from the electrode to be usefully processed. For further analysis, an automatic identification and continuous tracking of channels containing neural data is of great significance for many applications, e.g. automated selection of neural channels during online and offline spike sorting. Automated spike detection and sorting is also critical for online decoding in brain–computer interface (BCI) applications, in which on...},
keywords = {BCI, CNN, Data Reduction, Machine Learning, Spike Sorting},
pubstate = {published},
tppubtype = {article}
}
Objective . In electrophysiology, microelectrodes are the primary source for recording neural data (single unit activity). These microelectrodes can be implanted individually or in the form of arrays containing dozens to hundreds of channels. Recordings of some channels contain neural activity, which are often contaminated with noise. Another fraction of channels does not record any neural data, but only noise. By noise, we mean physiological activities unrelated to spiking, including technical artifacts and neural activities of neurons that are too far away from the electrode to be usefully processed. For further analysis, an automatic identification and continuous tracking of channels containing neural data is of great significance for many applications, e.g. automated selection of neural channels during online and offline spike sorting. Automated spike detection and sorting is also critical for online decoding in brain–computer interface (BCI) applications, in which on...
2018
Muhammad Ayaz Hussain; Christian Klaes; Ioannis Iossifidis:
Toward a Model of Timed Arm Movement Based on Temporal Tuning of Neurons in Primary Motor (MI) and Posterior Parietal Cortex (PPC) Title Inproceedings
In: BC18 : Computational Neuroscience & Neurotechnology Bernstein Conference 2018, BCCN, 2018.
Abstract | BibTeX | Tags: BCI, dynamical systems, Machine Learning, movement model
@inproceedings{bccn18,
title = {Toward a Model of Timed Arm Movement Based on Temporal Tuning of Neurons in Primary Motor (MI) and Posterior Parietal Cortex (PPC) Title},
author = {Muhammad Ayaz Hussain and Christian Klaes and Ioannis Iossifidis:},
year = {2018},
date = {2018-01-01},
urldate = {2018-01-01},
booktitle = {BC18 : Computational Neuroscience & Neurotechnology Bernstein Conference 2018},
publisher = {BCCN},
abstract = {To study driver behavior we set up a lab with fixed base driving simulators. In order to compensate for the lack of physical feedback in this scenario, we aimed for another means of increasing the realism of our system. In the following, we propose an efficient method of head tracking and its integration in our driving simulation. Furthermore, we illuminate why this is a promising boost of the subjects immersion in the virtual world. Our idea for increasing the feeling of immersion is to give the subject feedback on head movements relative to the screen. A real driver sometimes moves his head in order to see something better or to look behind an occluding object. In addition to these intentional movements, a study conducted by Zirkovitz and Harris has revealed that drivers involuntarily tilt their heads when they go around corners in order to maximize the use of visual information available in the scene. Our system reflects the visual changes of any head movement and hence gives feedback on both involuntary and intentional motion. If, for example, subjects move to the left, they will see more from the right-hand side of the scene. If, on the other hand, they move upwards, a larger fraction of the engine hood will be visible. The same holds for the rear view mirror},
keywords = {BCI, dynamical systems, Machine Learning, movement model},
pubstate = {published},
tppubtype = {inproceedings}
}
To study driver behavior we set up a lab with fixed base driving simulators. In order to compensate for the lack of physical feedback in this scenario, we aimed for another means of increasing the realism of our system. In the following, we propose an efficient method of head tracking and its integration in our driving simulation. Furthermore, we illuminate why this is a promising boost of the subjects immersion in the virtual world. Our idea for increasing the feeling of immersion is to give the subject feedback on head movements relative to the screen. A real driver sometimes moves his head in order to see something better or to look behind an occluding object. In addition to these intentional movements, a study conducted by Zirkovitz and Harris has revealed that drivers involuntarily tilt their heads when they go around corners in order to maximize the use of visual information available in the scene. Our system reflects the visual changes of any head movement and hence gives feedback on both involuntary and intentional motion. If, for example, subjects move to the left, they will see more from the right-hand side of the scene. If, on the other hand, they move upwards, a larger fraction of the engine hood will be visible. The same holds for the rear view mirror
2017
Ioannis Iossifidis:; Muhammad Ayaz Hussain; Christian Klaes
Temporal stabilized arm movement for efficient neuroprosthetic control by individuals with tetraplegia Miscellaneous
2017.
Abstract | BibTeX | Tags: Autonomous robotics, dynamical systems, movement model, neuroprosthetic
@misc{Iossifidis2017a,
title = {Temporal stabilized arm movement for efficient neuroprosthetic control by individuals with tetraplegia},
author = {Ioannis Iossifidis: and Muhammad Ayaz Hussain and Christian Klaes},
year = {2017},
date = {2017-01-01},
publisher = {SfN 2017},
abstract = {The generation of discrete movement with distinct and stable time courses characterizes each human movement and reflect the need to perform catching and interception tasks and for timed action sequences, incorporating dynamically changing environmental constraints. Several lines of evidence suggest neuronal mechanism for the initiation of movements i.e. in the supplementary motor area (SMA) and the premotor cortex and for movement planning mechanism generating velocity profiles satisfying time constraints. In order to meet the requirements of on-line evolving trajectories we propose a model, based on dynamical systems which describes goal directed trajectories in humans and generates trajectories for redundant anthropomorphic robotic arms The current study aim to evaluate the temporal characteristics of primary motor and posterior parietal cortex in patients with tetraplegia by using inception task implemented in virtual reality. The participants will be implanted with two 96-channel intracortical microelectrode arrays in the Primary Motor and Post Parietal Cortex. In the training phase the participants will be confronted with the observation of a robotic arm intercepting the bob of a pendulum at the lowest point of it's trajectory (maximum velocity) - the end effector reaches at the same time as the bob of the pendulum the lowest point of the trajectory performing a perfectly timed movement. The arm is positioned perpendicular to the oscillation plane exactly at the hight of the interception point to generate a one dimensional trajectory to the target. The time to contact between the robot's end effector and the bob of the pendulum is maintained constant and during the different sessions the distance between end effector and the point of interception is gradually increased. In order to catch up and to reach in time, either velocity formation or initiation time of the movement have to be changed. Both effects will be investigated independently. For the decoding of movement-related information we introduce a framework exploiting a deep learning approach with a convolutional neural networks.},
keywords = {Autonomous robotics, dynamical systems, movement model, neuroprosthetic},
pubstate = {published},
tppubtype = {misc}
}
The generation of discrete movement with distinct and stable time courses characterizes each human movement and reflect the need to perform catching and interception tasks and for timed action sequences, incorporating dynamically changing environmental constraints. Several lines of evidence suggest neuronal mechanism for the initiation of movements i.e. in the supplementary motor area (SMA) and the premotor cortex and for movement planning mechanism generating velocity profiles satisfying time constraints. In order to meet the requirements of on-line evolving trajectories we propose a model, based on dynamical systems which describes goal directed trajectories in humans and generates trajectories for redundant anthropomorphic robotic arms The current study aim to evaluate the temporal characteristics of primary motor and posterior parietal cortex in patients with tetraplegia by using inception task implemented in virtual reality. The participants will be implanted with two 96-channel intracortical microelectrode arrays in the Primary Motor and Post Parietal Cortex. In the training phase the participants will be confronted with the observation of a robotic arm intercepting the bob of a pendulum at the lowest point of it's trajectory (maximum velocity) - the end effector reaches at the same time as the bob of the pendulum the lowest point of the trajectory performing a perfectly timed movement. The arm is positioned perpendicular to the oscillation plane exactly at the hight of the interception point to generate a one dimensional trajectory to the target. The time to contact between the robot's end effector and the bob of the pendulum is maintained constant and during the different sessions the distance between end effector and the point of interception is gradually increased. In order to catch up and to reach in time, either velocity formation or initiation time of the movement have to be changed. Both effects will be investigated independently. For the decoding of movement-related information we introduce a framework exploiting a deep learning approach with a convolutional neural networks.