Prof. Dr. rer. nat. Ioannis Iossifidis

@article{xavierfidencioHybridBraincomputerInterface2025,

title = {Hybrid Brain-Computer Interface Using Error-Related Potential and Reinforcement Learning},

author = {Aline Xavier Fidêncio and Felix Grün and Christian Klaes and Ioannis Iossifidis},

editor = {Frontiers},

url = {https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2025.1569411/full},

doi = {10.3389/fnhum.2025.1569411},

issn = {1662-5161},

year  = {2025},

date = {2025-06-04},

urldate = {2025-06-04},

journal = {Frontiers in Human Neuroscience},

volume = {19},

publisher = {Frontiers},

abstract = {Brain-computer interfaces (BCIs) offer alternative communication methods for individuals with motor disabilities, aiming to improve their quality of life through external device control. However, non-invasive BCIs using electroencephalography (EEG) often suffer from performance limitations due to non-stationarities arising from changes in mental state or device characteristics. Addressing these challenges motivates the development of adaptive systems capable of real-time adjustment. This study investigates a novel approach for creating an adaptive, error-related potential (ErrP)-based BCI using reinforcement learning (RL) to dynamically adapt to EEG signal variations. The framework was validated through experiments on a publicly available motor imagery dataset and a novel fast-paced protocol designed to enhance user engagement. Results showed that RL agents effectively learned control policies from user interactions, maintaining robust performance across datasets. However, findings from the game-based protocol revealed that fast-paced motor imagery tasks were ineffective for most participants, highlighting critical challenges in real-time BCI task design. Overall, the results demonstrate the potential of RL for enhancing BCI adaptability while identifying practical constraints in task complexity and user responsiveness.},

keywords = {adaptive brain-computer interface, BCI, EEG, error-related potentials (ErrPs), Machine Learning, motor imagery (MI), reinforcement learning (RL)},

pubstate = {published},

tppubtype = {article}

}

@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},

editor = {Elsevier},

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 = {2024-09-19},

journal = {Neurocomputing},

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, Machine Learning, Memorization, Poisson process, Stochastic modeling},

pubstate = {published},

tppubtype = {article}

}

@article{xavierfidencioGenericErrorrelatedPotential2024,

title = {A Generic Error-Related Potential Classifier Based on Simulated Subjects},

author = {Aline Xavier Fidêncio and Christian Klaes and Ioannis Iossifidis},

editor = {Frontiers Media SA},

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 = {2024-07-19},

urldate = {2024-07-19},

journal = {Frontiers in Human Neuroscience},

volume = {18},

pages = {1390714},

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}

}

@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}

}

@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 = {BCI, Brain computer interface, Deep learning, EEG decoding, EMG decoding, Machine Learning},

pubstate = {published},

tppubtype = {article}

}

@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}

}

@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}

}

@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}

}

@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},

editor = {{IOP Publishing},

url = {https://dx.doi.org/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},

volume = {19},

number = {5},

abstract = {{Objective. Accurate decoding of surface electromyography (sEMG) is pivotal for muscle-to-machine-interfaces and their application e.g. rehabilitation therapy. sEMG signals have high inter-subject variability, due to various factors, including skin thickness, body fat percentage, and electrode placement. Deep learning algorithms require long training time and tend to overfit if only few samples are available. In this study, we aim to investigate methods to calibrate deep learning models to a new user when only a limited amount of training data is available. Approach. Two methods are commonly used in the literature, subject-specific modeling and transfer learning. In this study, we investigate the effectiveness of transfer learning using weight initialization for recalibration of two different pretrained deep learning models on new subjects data and compare their performance to subject-specific models. We evaluate two models on three publicly available databases (non invasive adaptive prosthetics database 2–4) and compare the performance of both calibration schemes in terms of accuracy, required training data, and calibration time. Main results. On average over all settings, our transfer learning approach improves 5%-points on the pretrained models without fine-tuning, and 12%-points on the subject-specific models, while being trained for 22% fewer epochs on average. Our results indicate that transfer learning enables faster learning on fewer training samples than user-specific models. Significance. To the best of our knowledge, this is the first comparison of subject-specific modeling and transfer learning. These approaches are ubiquitously used in the field of sEMG decoding. But the lack of comparative studies until now made it difficult for scientists to assess appropriate calibration schemes. Our results guide engineers evaluating similar use cases.},

keywords = {BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning, transfer learning},

pubstate = {published},

tppubtype = {article}

}

@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}

}