Roman Mouček - Academia.edu (original) (raw)

Papers by Roman Mouček

2013 IEEE International Conference on Bioinformatics and Biomedicine

Despite standardization efforts there is still no widely used standard format for storing electro... more Despite standardization efforts there is still no widely used standard format for storing electrophysiological data. This standard is necessary for effective collaboration between scientists. This work deals with adjustments of existing general data/metadata model for electrophysiological experiments and proposal/implementation of HDF data format for their storage.

Abnormal functional connectivity (FC) has been commonly observed during alcohol use disorder (AUD... more Abnormal functional connectivity (FC) has been commonly observed during alcohol use disorder (AUD). In this work, FC analysis has been performed by incorporating EEG-based graph-theoretic analysis and a machine learning (ML) framework. Brain FC was quantified with synchronization likelihood (SL). Undirected graphs for each channel pair were constructed involving the SL measures. Furthermore, the graph-based features such as minimum spanning tree, distances between nodes, and maximum flow between the graph nodes were computed, termed as EEG data matrix. The matrix was used as input data to the ML framework to classify the study participants. The ML framework was validated with data acquired from 30 AUD patients and an age-matched group of 30 healthy controls. In this study, the classifiers such as SVM (accuracy = 98.7%), Naive Bayes (accuracy = 88.6%), and logistic regression (accuracy = 89%) have shown promising discrimination results. The method was compared with two existing metho...

With increasing amounts of experimental data, openness, fairness, and reproducibility of scientif... more With increasing amounts of experimental data, openness, fairness, and reproducibility of scientific experimental work have become important factors for researchers, journals and funding bodies. However, these kinds of challenges are not easily and directly achievable. The goal of this paper is to contribute to these efforts by introducing advances in building more mature lifecycle of electroencephalography/event-related potential data. The progressive data standardization initiatives, data formats, and trends in using machine and deep learning methods for processing of domain data are described and discussed. An open processing workflow based on the analysis of current software tools for preprocessing, processing and classification of electroencephalography/event-related potential data is proposed, implemented and verified on a publicly

The P3 (or P300) event-related brain potential is thought to reflect brain electric activity rela... more The P3 (or P300) event-related brain potential is thought to reflect brain electric activity related to cognitive processes. It is widely used not only in psychological research and clinical diagnosis but also in the brain computer interface (BCI) systems. To elicit the P3 component the oddball stimulation protocol is often used. In this paper, design of simple visual odd-ball protocol stimulator, which generates stimuli with predefined parameters, is described. The stimulator also generates additional signals for synchronization with EEG recording computer. Application of the stimulator in experimental work is also presented here.

Deep learning has emerged as a new branch of machine learning in recent years. Some of the relate... more Deep learning has emerged as a new branch of machine learning in recent years. Some of the related algorithms have been reported to beat state-of-the-art approaches in many applications. The main aim of this paper is to verify one of the deep learning algorithms, specifically a stacked autoencoder, to detect the P300 component. This component, as a specific brain response, is widely used in the systems based on brain-computer interface. A simple brain-computer interface experiment more than 200 school-age participants was performed to obtain large datasets containing the P300 component. After feature extraction the collected data were split into the training and testing sets. State-of-the art BCI classifiers (such as LDA, SVM, or Bayesian LDA) were applied to the data and then compared with the results of stacked autoencoders.

Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies

The growing electrophysiology research leads to the collection of large amounts of experimental d... more The growing electrophysiology research leads to the collection of large amounts of experimental data and consequently to the broader application, eventually development of analytic methods, algorithms, and workflows. Then appropriate metadata definition and related data description is critical for long term storage and later identification of experimental data. Although a detailed description of electrophysiology data has not become a commonly used procedure so far, publicly available and well described data have started to appear in professional journals. The next reasonable step is to shift attention to the analysis of electrophysiology data. Since the analysis of this kind of data is rather complex, identification and appropriate description of used methods, algorithms and workflows would help reproducibility of the research in the field. This description would also allow developing automatic or semi-automatic systems for data analysis or constructing complex workflows in a more user friendly way. Based on these assumptions authors present a custom ontology for description of analytic methods and workflows in electrophysiology that is proposed to be discussed within the scientific community.

2012 5th International Conference on BioMedical Engineering and Informatics

ABSTRACT EEG/ERP (electroencephalography, event related potential) laboratories produce experimen... more ABSTRACT EEG/ERP (electroencephalography, event related potential) laboratories produce experimental data and metadata. Large amounts of data and various data formats lead to incompatible results and difficult communication among laboratories. Authors' research group has contributed to the building of a neuroinformatics infrastructure by developing and integrating data management and analytic tools for EEG/ERP research. In addition, a module integrated within the EEG/ERP Portal allowing to process experimental data using analytic tools is developed. An integration of the EEG/ERP Portal with other systems is ensured using web services.

Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies, 2018

Deep learning techniques have proved to be beneficial in many scientific disciplines and have bea... more Deep learning techniques have proved to be beneficial in many scientific disciplines and have beaten stateof-the-art approaches in many applications. The main aim of this article is to improve the success rate of deep learning algorithms, especially stacked autoencoders, when they are used for detection and classification of P300 event-related potential component that reflects brain processes related to stimulus evaluation or categorization. Moreover, the classification results provided by stacked autoencoders are compared with the classification results given by other classification models and classification results provided by combinations of various types of neural network layers.

Clinical Neurophysiology

Introduction Navigated transcranial magnetic stimulation (nTMS) is non invasive method to map the... more Introduction Navigated transcranial magnetic stimulation (nTMS) is non invasive method to map the motor cortex including primary motor cortex (PrG - precentral gyrus) and premotor areas (PMa). This study aimed to investigate whether tumorous brain lesion induce a change in motor cortex localization or organisation investigated by nTMS. Methods We enrolled 10 patients with intraaxial motor tumor (gliomas). All patients underwent preoperative navigational MRI folowed by nTMS. Both lesional and non lesional hemispheres were stimulated. MEPs were recorded by EMG. The measured muscle was APB. MEPs latency for each positive stimulation point was measured. The surface of positive stimulation areas on the cortex were calculated for both hemispheres and results were compared. Results The positive MEPs responses were registered from PrG as well as from PMa with different latencies. There were mosaic distribution of short and long latencies of MEPs responses without dependence on the location in the PrG or PMa in both hemispheres. The positive motor area distributions were significantly larger from lesional than for non lesional hemisphere for both PrG and PMa areas (PrG lesional vs. non lesional surface = 947 mm2 vs. 393 mm2, PMa lesional vs. non lesional surface = 620 mm2 vs. 545 mm2). Conclusion The intraaxial motor eloquent tumors induce changes in motor cortex. The motor areas spread widely in the anterior-posterior direction in lesional hemisphere. The localisation short latencies found in PMa suggesting for detection of primary motor areas outside the PrG. This study was supported by the Charles University Research Fund Progress Q 39.

Activitas Nervosa Superior, 2014

The present study aims to investigate and compare the auditory attention performance of children ... more The present study aims to investigate and compare the auditory attention performance of children with developmental coordination disorder (DCD) and normally developing children (NDC) using cognitive evoked potentials (ERPs) in passive conditions. ERPs data showed that children with DCD have less ability to detect small physical differences between acoustic stimuli (no MMN response in DCD children) and have a reduced attentional engagement and stimulus evaluation of salient stimuli (a reduction of P3 amplitude in DCD children). The results of our study suggest that children with DCD do not only suffer from a visuospatial attention deficit as previous studies reported but also have auditory attention deficit.

Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies, 2017

Unwillingness of many people to assume responsibilities for a personal health, fitness and wellne... more Unwillingness of many people to assume responsibilities for a personal health, fitness and wellness seems to be widespread. This can be partially remedied by individualized exercise and wellness program that integrates the basic knowledge domains: lifestyle, sports and fitness, and nutrition and personal/environmental health. However, collection, management and analysis of data and metadata related to these domains is demanding and time consuming task. Moreover, the appropriate annotation of raw data is crucial for their next processing. To promote such a program a software infrastructure for collection, storage, management, analysis and interpretation of health related data and metadata has been proposed and part of this infrastructure has been developed and tested outside laboratory conditions. This software prototype allows experimenters to collect various heterogeneous health related data in a highly organized and efficient way. Data are then evaluated and users can view relevant information related to their health and fitness.

Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies, 2017

Attention of drivers is very important for road safety and it is worth observing even in laborato... more Attention of drivers is very important for road safety and it is worth observing even in laboratory conditions during a simulated drive. This paper deals with design of an experiment investigating driver's attention, validation of collected data, and first preprocessing and processing steps used within data analysis. Brain activity is considered as a primary biosignal and is measured and analyzed using the techniques and methods of electroencephalography and event related potentials. Respiration is considered as a secondary biosignal that is captured together with brain activity. Validation of collected data using a stacked autoencoder is emphasized as an important step preceding data analysis.

Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies, 2016

Although research into brain-computer interfaces is more common in recent years, studies concerni... more Although research into brain-computer interfaces is more common in recent years, studies concerning large groups of specific subjects are still lacking. This paper describes a simple brain-computer interface (BCI) experiment that was performed on a group of over 200 school-age children using the technique and methods of event related potentials. In the first phase, experimental data were recorded in various elementary and secondary schools, mainly in the Pilsen region of the Czech Republic. The task was to guess the number between 1 and 9 that the measured subject thinks on. Concurrently, a human expert made a decision about the target number based on averaged P300 waveforms observed on-line. In the second phase, an application for automatic classification was developed for off-line data. A small subset of the data was used for training; the rest of the data was used to evaluate the accuracy of classification. Two feature extraction methods were compared; subsampling and discrete wavelet transform for feature extraction. Multi-layer perceptron was used for classification. The human expert achieved the accuracy of 67.6%, while some of the automatic algorithms were able to significantly outperform the expert; the maximum classification accuracy reached 77.2%.

Lecture Notes in Computer Science, 2001

ABSTRACT The paper deals with the help system as a part of dialogue grammar based development env... more ABSTRACT The paper deals with the help system as a part of dialogue grammar based development environment. This programming environment is intended especially for visually impaired programmers. The generation of help dialogues according to language grammar is described. Different levels of the help system are widely discussed and specific examples for C/C++ language are presented. The final part of the paper is devoted to possible improvements in the current help system.

Lecture Notes in Computer Science, 2001

ABSTRACT This paper deals with adaptation of typical dialogue manager structure to dialogue syste... more ABSTRACT This paper deals with adaptation of typical dialogue manager structure to dialogue system for blind and purblind programmers within the framework of the project: “Dialog System for Support of Visually Impaired Programmers”. The main goal of this project is to develop a dialogue system allowing generating, editing and debugging of source code. The dialogue is based on the natural speech communication, supported by the speech recognition system and speech synthesis considering the large extent prosodic aspects of the Czech language.

The Kohonen Self-organizing Feature Map (SOM) has been developed for the clustering of input vect... more The Kohonen Self-organizing Feature Map (SOM) has been developed for the clustering of input vectors and for projection of continuous high-dimensional signal to discrete low-dimensional space. The application area, where the map can be also used, is the processing of collections of text documents. The basic principles of the WEBSOM method, a transformation of text information into a real components feature vector and results of documents classification are described in the article. The Carpenter-Grossberg ART-2 neural network, usually used for adaptive vector clustering, was also tested as a document categorization tool. The results achieved by using this network are also presented here.

2013 International Conference on Applied Electronics, 2013

For neurophysiological data sharing, it is vital for researchers to validate their data from diff... more For neurophysiological data sharing, it is vital for researchers to validate their data from different perspectives. Detection of eye artifacts is especially important since the artifacts may distort the data to an unacceptable extent. Most methods for their correction either require EOG channels or they are very time consuming. This paper proposes a fast method that does not require EOG channels. It outperforms amplitudebased methods in accuracy and Independent Component Analysis in computational complexity.

Frontiers in Human Neuroscience, 2008

2013 IEEE International Conference on Bioinformatics and Biomedicine

Despite standardization efforts there is still no widely used standard format for storing electro... more Despite standardization efforts there is still no widely used standard format for storing electrophysiological data. This standard is necessary for effective collaboration between scientists. This work deals with adjustments of existing general data/metadata model for electrophysiological experiments and proposal/implementation of HDF data format for their storage.

Abnormal functional connectivity (FC) has been commonly observed during alcohol use disorder (AUD... more Abnormal functional connectivity (FC) has been commonly observed during alcohol use disorder (AUD). In this work, FC analysis has been performed by incorporating EEG-based graph-theoretic analysis and a machine learning (ML) framework. Brain FC was quantified with synchronization likelihood (SL). Undirected graphs for each channel pair were constructed involving the SL measures. Furthermore, the graph-based features such as minimum spanning tree, distances between nodes, and maximum flow between the graph nodes were computed, termed as EEG data matrix. The matrix was used as input data to the ML framework to classify the study participants. The ML framework was validated with data acquired from 30 AUD patients and an age-matched group of 30 healthy controls. In this study, the classifiers such as SVM (accuracy = 98.7%), Naive Bayes (accuracy = 88.6%), and logistic regression (accuracy = 89%) have shown promising discrimination results. The method was compared with two existing metho...

With increasing amounts of experimental data, openness, fairness, and reproducibility of scientif... more With increasing amounts of experimental data, openness, fairness, and reproducibility of scientific experimental work have become important factors for researchers, journals and funding bodies. However, these kinds of challenges are not easily and directly achievable. The goal of this paper is to contribute to these efforts by introducing advances in building more mature lifecycle of electroencephalography/event-related potential data. The progressive data standardization initiatives, data formats, and trends in using machine and deep learning methods for processing of domain data are described and discussed. An open processing workflow based on the analysis of current software tools for preprocessing, processing and classification of electroencephalography/event-related potential data is proposed, implemented and verified on a publicly

The P3 (or P300) event-related brain potential is thought to reflect brain electric activity rela... more The P3 (or P300) event-related brain potential is thought to reflect brain electric activity related to cognitive processes. It is widely used not only in psychological research and clinical diagnosis but also in the brain computer interface (BCI) systems. To elicit the P3 component the oddball stimulation protocol is often used. In this paper, design of simple visual odd-ball protocol stimulator, which generates stimuli with predefined parameters, is described. The stimulator also generates additional signals for synchronization with EEG recording computer. Application of the stimulator in experimental work is also presented here.

Deep learning has emerged as a new branch of machine learning in recent years. Some of the relate... more Deep learning has emerged as a new branch of machine learning in recent years. Some of the related algorithms have been reported to beat state-of-the-art approaches in many applications. The main aim of this paper is to verify one of the deep learning algorithms, specifically a stacked autoencoder, to detect the P300 component. This component, as a specific brain response, is widely used in the systems based on brain-computer interface. A simple brain-computer interface experiment more than 200 school-age participants was performed to obtain large datasets containing the P300 component. After feature extraction the collected data were split into the training and testing sets. State-of-the art BCI classifiers (such as LDA, SVM, or Bayesian LDA) were applied to the data and then compared with the results of stacked autoencoders.

Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies

The growing electrophysiology research leads to the collection of large amounts of experimental d... more The growing electrophysiology research leads to the collection of large amounts of experimental data and consequently to the broader application, eventually development of analytic methods, algorithms, and workflows. Then appropriate metadata definition and related data description is critical for long term storage and later identification of experimental data. Although a detailed description of electrophysiology data has not become a commonly used procedure so far, publicly available and well described data have started to appear in professional journals. The next reasonable step is to shift attention to the analysis of electrophysiology data. Since the analysis of this kind of data is rather complex, identification and appropriate description of used methods, algorithms and workflows would help reproducibility of the research in the field. This description would also allow developing automatic or semi-automatic systems for data analysis or constructing complex workflows in a more user friendly way. Based on these assumptions authors present a custom ontology for description of analytic methods and workflows in electrophysiology that is proposed to be discussed within the scientific community.

2012 5th International Conference on BioMedical Engineering and Informatics

ABSTRACT EEG/ERP (electroencephalography, event related potential) laboratories produce experimen... more ABSTRACT EEG/ERP (electroencephalography, event related potential) laboratories produce experimental data and metadata. Large amounts of data and various data formats lead to incompatible results and difficult communication among laboratories. Authors' research group has contributed to the building of a neuroinformatics infrastructure by developing and integrating data management and analytic tools for EEG/ERP research. In addition, a module integrated within the EEG/ERP Portal allowing to process experimental data using analytic tools is developed. An integration of the EEG/ERP Portal with other systems is ensured using web services.

Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies, 2018

Deep learning techniques have proved to be beneficial in many scientific disciplines and have bea... more Deep learning techniques have proved to be beneficial in many scientific disciplines and have beaten stateof-the-art approaches in many applications. The main aim of this article is to improve the success rate of deep learning algorithms, especially stacked autoencoders, when they are used for detection and classification of P300 event-related potential component that reflects brain processes related to stimulus evaluation or categorization. Moreover, the classification results provided by stacked autoencoders are compared with the classification results given by other classification models and classification results provided by combinations of various types of neural network layers.

Clinical Neurophysiology

Introduction Navigated transcranial magnetic stimulation (nTMS) is non invasive method to map the... more Introduction Navigated transcranial magnetic stimulation (nTMS) is non invasive method to map the motor cortex including primary motor cortex (PrG - precentral gyrus) and premotor areas (PMa). This study aimed to investigate whether tumorous brain lesion induce a change in motor cortex localization or organisation investigated by nTMS. Methods We enrolled 10 patients with intraaxial motor tumor (gliomas). All patients underwent preoperative navigational MRI folowed by nTMS. Both lesional and non lesional hemispheres were stimulated. MEPs were recorded by EMG. The measured muscle was APB. MEPs latency for each positive stimulation point was measured. The surface of positive stimulation areas on the cortex were calculated for both hemispheres and results were compared. Results The positive MEPs responses were registered from PrG as well as from PMa with different latencies. There were mosaic distribution of short and long latencies of MEPs responses without dependence on the location in the PrG or PMa in both hemispheres. The positive motor area distributions were significantly larger from lesional than for non lesional hemisphere for both PrG and PMa areas (PrG lesional vs. non lesional surface = 947 mm2 vs. 393 mm2, PMa lesional vs. non lesional surface = 620 mm2 vs. 545 mm2). Conclusion The intraaxial motor eloquent tumors induce changes in motor cortex. The motor areas spread widely in the anterior-posterior direction in lesional hemisphere. The localisation short latencies found in PMa suggesting for detection of primary motor areas outside the PrG. This study was supported by the Charles University Research Fund Progress Q 39.

Activitas Nervosa Superior, 2014

The present study aims to investigate and compare the auditory attention performance of children ... more The present study aims to investigate and compare the auditory attention performance of children with developmental coordination disorder (DCD) and normally developing children (NDC) using cognitive evoked potentials (ERPs) in passive conditions. ERPs data showed that children with DCD have less ability to detect small physical differences between acoustic stimuli (no MMN response in DCD children) and have a reduced attentional engagement and stimulus evaluation of salient stimuli (a reduction of P3 amplitude in DCD children). The results of our study suggest that children with DCD do not only suffer from a visuospatial attention deficit as previous studies reported but also have auditory attention deficit.

Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies, 2017

Unwillingness of many people to assume responsibilities for a personal health, fitness and wellne... more Unwillingness of many people to assume responsibilities for a personal health, fitness and wellness seems to be widespread. This can be partially remedied by individualized exercise and wellness program that integrates the basic knowledge domains: lifestyle, sports and fitness, and nutrition and personal/environmental health. However, collection, management and analysis of data and metadata related to these domains is demanding and time consuming task. Moreover, the appropriate annotation of raw data is crucial for their next processing. To promote such a program a software infrastructure for collection, storage, management, analysis and interpretation of health related data and metadata has been proposed and part of this infrastructure has been developed and tested outside laboratory conditions. This software prototype allows experimenters to collect various heterogeneous health related data in a highly organized and efficient way. Data are then evaluated and users can view relevant information related to their health and fitness.

Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies, 2017

Attention of drivers is very important for road safety and it is worth observing even in laborato... more Attention of drivers is very important for road safety and it is worth observing even in laboratory conditions during a simulated drive. This paper deals with design of an experiment investigating driver's attention, validation of collected data, and first preprocessing and processing steps used within data analysis. Brain activity is considered as a primary biosignal and is measured and analyzed using the techniques and methods of electroencephalography and event related potentials. Respiration is considered as a secondary biosignal that is captured together with brain activity. Validation of collected data using a stacked autoencoder is emphasized as an important step preceding data analysis.

Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies, 2016

Although research into brain-computer interfaces is more common in recent years, studies concerni... more Although research into brain-computer interfaces is more common in recent years, studies concerning large groups of specific subjects are still lacking. This paper describes a simple brain-computer interface (BCI) experiment that was performed on a group of over 200 school-age children using the technique and methods of event related potentials. In the first phase, experimental data were recorded in various elementary and secondary schools, mainly in the Pilsen region of the Czech Republic. The task was to guess the number between 1 and 9 that the measured subject thinks on. Concurrently, a human expert made a decision about the target number based on averaged P300 waveforms observed on-line. In the second phase, an application for automatic classification was developed for off-line data. A small subset of the data was used for training; the rest of the data was used to evaluate the accuracy of classification. Two feature extraction methods were compared; subsampling and discrete wavelet transform for feature extraction. Multi-layer perceptron was used for classification. The human expert achieved the accuracy of 67.6%, while some of the automatic algorithms were able to significantly outperform the expert; the maximum classification accuracy reached 77.2%.

Lecture Notes in Computer Science, 2001

ABSTRACT The paper deals with the help system as a part of dialogue grammar based development env... more ABSTRACT The paper deals with the help system as a part of dialogue grammar based development environment. This programming environment is intended especially for visually impaired programmers. The generation of help dialogues according to language grammar is described. Different levels of the help system are widely discussed and specific examples for C/C++ language are presented. The final part of the paper is devoted to possible improvements in the current help system.

Lecture Notes in Computer Science, 2001

ABSTRACT This paper deals with adaptation of typical dialogue manager structure to dialogue syste... more ABSTRACT This paper deals with adaptation of typical dialogue manager structure to dialogue system for blind and purblind programmers within the framework of the project: “Dialog System for Support of Visually Impaired Programmers”. The main goal of this project is to develop a dialogue system allowing generating, editing and debugging of source code. The dialogue is based on the natural speech communication, supported by the speech recognition system and speech synthesis considering the large extent prosodic aspects of the Czech language.

The Kohonen Self-organizing Feature Map (SOM) has been developed for the clustering of input vect... more The Kohonen Self-organizing Feature Map (SOM) has been developed for the clustering of input vectors and for projection of continuous high-dimensional signal to discrete low-dimensional space. The application area, where the map can be also used, is the processing of collections of text documents. The basic principles of the WEBSOM method, a transformation of text information into a real components feature vector and results of documents classification are described in the article. The Carpenter-Grossberg ART-2 neural network, usually used for adaptive vector clustering, was also tested as a document categorization tool. The results achieved by using this network are also presented here.

2013 International Conference on Applied Electronics, 2013

For neurophysiological data sharing, it is vital for researchers to validate their data from diff... more For neurophysiological data sharing, it is vital for researchers to validate their data from different perspectives. Detection of eye artifacts is especially important since the artifacts may distort the data to an unacceptable extent. Most methods for their correction either require EOG channels or they are very time consuming. This paper proposes a fast method that does not require EOG channels. It outperforms amplitudebased methods in accuracy and Independent Component Analysis in computational complexity.

Frontiers in Human Neuroscience, 2008