Pub Date : 2017-09-18DOI: 10.3217/978-3-85125-533-1-76
Léa Pillette, C. Jeunet, Boris Mansencal, R. Nkambou, B. N'Kaoua, F. Lotte
Mental-Imagery based Brain-Computer Interfaces (MI-BCI) are neurotechnologies enabling users to control applications using their brain activity alone. Although promising, they are barely used outside laboratories because they are poorly reliable, partly due to inappropriate training protocols. Indeed, it has been shown that tense and non-autonomous users, that is to say those who require the greatest social presence and emotional support, struggle to use MI-BCI. Yet, the importance of such support during MI-BCI training is neglected. Therefore we designed and tested PEANUT, the first Learning Companion providing social presence and emotional support dedicated to the improvement of MI-BCI user-training. PEANUT was designed based on the literature , data analyses and user-studies. Promising results revealed that participants accompanied by PEANUT found the MI-BCI system significantly more usable.
{"title":"Peanut: Personalised Emotional Agent for Neurotechnology User-Training","authors":"Léa Pillette, C. Jeunet, Boris Mansencal, R. Nkambou, B. N'Kaoua, F. Lotte","doi":"10.3217/978-3-85125-533-1-76","DOIUrl":"https://doi.org/10.3217/978-3-85125-533-1-76","url":null,"abstract":"Mental-Imagery based Brain-Computer Interfaces (MI-BCI) are neurotechnologies enabling users to control applications using their brain activity alone. Although promising, they are barely used outside laboratories because they are poorly reliable, partly due to inappropriate training protocols. Indeed, it has been shown that tense and non-autonomous users, that is to say those who require the greatest social presence and emotional support, struggle to use MI-BCI. Yet, the importance of such support during MI-BCI training is neglected. Therefore we designed and tested PEANUT, the first Learning Companion providing social presence and emotional support dedicated to the improvement of MI-BCI user-training. PEANUT was designed based on the literature , data analyses and user-studies. Promising results revealed that participants accompanied by PEANUT found the MI-BCI system significantly more usable.","PeriodicalId":433248,"journal":{"name":"Graz Brain-Computer Interface Conference","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133542188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.3217/978-3-85125-533-1-51
C. Liti, L. Bianchi, V. Piccialli, M. Cosmi
The detection of brain state changes can dramatically improve the comprehension of cerebral functioning. To reach this aim, machine learning based automatic tools may be extremely useful to correctly classify different brain responses. The performance of these instruments depends on the features and the classification algorithm employed, but also from a good data preprocessing able to improve the poor signal-to-noise ratio [4] of the EEG signal. In this work, we combine data preprocessing with a feature selection based on the filter ReliefF and the linear SVM classifier LibLinear in order to analyse the data deriving from a P300 speller paradigm on patients with Amyotrophic lateral sclerosis (ALS). The purpose of this study is twofold: on the one hand we want to maximize the predictor’s performance, but most importantly, we aim at showing how the features ranking can be used to support scientific hypotheses or diagnoses.
{"title":"Can Feature Selection be used to Detect Physiological Components in P300 based BCI for amyotrophic lateral Sclerosis patients?","authors":"C. Liti, L. Bianchi, V. Piccialli, M. Cosmi","doi":"10.3217/978-3-85125-533-1-51","DOIUrl":"https://doi.org/10.3217/978-3-85125-533-1-51","url":null,"abstract":"The detection of brain state changes can dramatically improve the comprehension of cerebral functioning. To reach this aim, machine learning based automatic tools may be extremely useful to correctly classify different brain responses. The performance of these instruments depends on the features and the classification algorithm employed, but also from a good data preprocessing able to improve the poor signal-to-noise ratio [4] of the EEG signal. In this work, we combine data preprocessing with a feature selection based on the filter ReliefF and the linear SVM classifier LibLinear in order to analyse the data deriving from a P300 speller paradigm on patients with Amyotrophic lateral sclerosis (ALS). The purpose of this study is twofold: on the one hand we want to maximize the predictor’s performance, but most importantly, we aim at showing how the features ranking can be used to support scientific hypotheses or diagnoses.","PeriodicalId":433248,"journal":{"name":"Graz Brain-Computer Interface Conference","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131632089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.3217/978-3-85125-682-6-24
M. Borhanazad, J. Thielen, J. Farquhar, P. Desain
Broadband code modulated visual evoked potential (BBVEP, c-VEP) is the basis of one of the fastest braincomputer interface (BCI) paradigms. Unlike other systems, like those based on steady-state visual evoked potential (SSVEP, f-VEP), the stimulus specificity of c-VEP has not been thoroughly studied yet. One of the important stimulus characteristics that can influence both performance and user comfort is the frequency (the bit clock or frame rate). In this study, we evaluated the effect of stimuli presented at various frame rates (40, 60, 90 and 120 Hz) on c-VEP using LED lights. Accuracy and ITR were used to assess the performance and a questionnaire was used to evaluate the visual comfort. No significant differences in the performance of different frequencies were found, so comfort can be the main factor in the design decision. However, there is a trend for the frame rates of 40 and 90 Hz to yield a higher accuracy as compared to 60 and 120 Hz.
{"title":"The effect of high and low frequencies in c-VEP BCI","authors":"M. Borhanazad, J. Thielen, J. Farquhar, P. Desain","doi":"10.3217/978-3-85125-682-6-24","DOIUrl":"https://doi.org/10.3217/978-3-85125-682-6-24","url":null,"abstract":"Broadband code modulated visual evoked potential (BBVEP, c-VEP) is the basis of one of the fastest braincomputer interface (BCI) paradigms. Unlike other systems, like those based on steady-state visual evoked potential (SSVEP, f-VEP), the stimulus specificity of c-VEP has not been thoroughly studied yet. One of the important stimulus characteristics that can influence both performance and user comfort is the frequency (the bit clock or frame rate). In this study, we evaluated the effect of stimuli presented at various frame rates (40, 60, 90 and 120 Hz) on c-VEP using LED lights. Accuracy and ITR were used to assess the performance and a questionnaire was used to evaluate the visual comfort. No significant differences in the performance of different frequencies were found, so comfort can be the main factor in the design decision. However, there is a trend for the frame rates of 40 and 90 Hz to yield a higher accuracy as compared to 60 and 120 Hz.","PeriodicalId":433248,"journal":{"name":"Graz Brain-Computer Interface Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133294089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.3217/978-3-85125-682-6-53
Darisy G. Zhao, A. Vasilyev, B. Kozyrskiy, Andrey V. Isachenko, Eugeny V. Melnichuk, B. Velichkovsky, S. Shishkin
The use of an EEG expectation-related component, the expectancy wave (E-wave), in brainmachine interaction was proposed more than 50 years ago, but active exploration of this possibility has started only recently, in the context of developing passive brain-computer interfaces for the enhancement of gaze interaction. We report, for the first time, the results of a systematic experimental study that revealed an EEG marker for selecting intentionally an object among other moving objects using smooth pursuit eye movements. This marker appeared to have the same nature as the Ewave previously observed in the EEG accompanying the selection of static objects with gaze fixations. A convolutional neural network classified the intentional and spontaneous smooth pursuit eye movements with average ROC AUC 0.69±0.13 (M±SD). These results suggest that the E-wave might be robust enough to serve, after further improvement of the methodology, as the basis of hybrid eye-brain-computer interfaces applied for selection in dynamically changing visual environments.
{"title":"An expectation-based EEG marker for the selection of moving objects with gaze","authors":"Darisy G. Zhao, A. Vasilyev, B. Kozyrskiy, Andrey V. Isachenko, Eugeny V. Melnichuk, B. Velichkovsky, S. Shishkin","doi":"10.3217/978-3-85125-682-6-53","DOIUrl":"https://doi.org/10.3217/978-3-85125-682-6-53","url":null,"abstract":"The use of an EEG expectation-related component, the expectancy wave (E-wave), in brainmachine interaction was proposed more than 50 years ago, but active exploration of this possibility has started only recently, in the context of developing passive brain-computer interfaces for the enhancement of gaze interaction. We report, for the first time, the results of a systematic experimental study that revealed an EEG marker for selecting intentionally an object among other moving objects using smooth pursuit eye movements. This marker appeared to have the same nature as the Ewave previously observed in the EEG accompanying the selection of static objects with gaze fixations. A convolutional neural network classified the intentional and spontaneous smooth pursuit eye movements with average ROC AUC 0.69±0.13 (M±SD). These results suggest that the E-wave might be robust enough to serve, after further improvement of the methodology, as the basis of hybrid eye-brain-computer interfaces applied for selection in dynamically changing visual environments.","PeriodicalId":433248,"journal":{"name":"Graz Brain-Computer Interface Conference","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133358309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.3217/978-3-85125-682-6-29
B. V. D. Vijgh, M. V. D. Boom, M. Branco, S. Leinders, Z. Freudenburg, Elmar G. M. Pels, M. V. Steensel, N. Ramsey, E. Aarnoutse
Individuals with locked-in syndrome can benefit from Brain-Computer Interfaces (BCIs) as an alternative assistive technology for communication. The Utrecht NeuroProsthesis (UNP) is a fully implanted ECoG based BCI that provides the user with independent control of a computer using intentional brain signals. In order to avoid technology abandonment and to stimulate home use, a user-centered approach to design and development of the system is essential. Here we show accommodation of several of the needs expressed by users of the UNP system, including new features that provide the user with control over the system during the night and which increase training efficacy.
{"title":"Utrecht neuroprosthesis System: New Features to Accommodate User Needs","authors":"B. V. D. Vijgh, M. V. D. Boom, M. Branco, S. Leinders, Z. Freudenburg, Elmar G. M. Pels, M. V. Steensel, N. Ramsey, E. Aarnoutse","doi":"10.3217/978-3-85125-682-6-29","DOIUrl":"https://doi.org/10.3217/978-3-85125-682-6-29","url":null,"abstract":"Individuals with locked-in syndrome can benefit from Brain-Computer Interfaces (BCIs) as an alternative assistive technology for communication. The Utrecht NeuroProsthesis (UNP) is a fully implanted ECoG based BCI that provides the user with independent control of a computer using intentional brain signals. In order to avoid technology abandonment and to stimulate home use, a user-centered approach to design and development of the system is essential. Here we show accommodation of several of the needs expressed by users of the UNP system, including new features that provide the user with control over the system during the night and which increase training efficacy.","PeriodicalId":433248,"journal":{"name":"Graz Brain-Computer Interface Conference","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134468058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：