Pub Date : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737349
Satyam Kumar, F. Yger, F. Lotte
The omnipresence of non-stationarity and noise in Electroencephalogram signals restricts the ubiquitous use of Brain-Computer interface. One of the possible ways to tackle this problem is to adapt the computational model used to detect and classify different mental states. Adapting the model will possibly help us to track the changes and thus reducing the effect of non-stationarities. In this paper, we present different adaptation strategies for state of the art Riemannian geometry based classifiers. The offline evaluation of our proposed methods on two different datasets showed a statistically significant improvement over baseline non-adaptive classifiers. Moreover, we also demonstrate that combining different (hybrid) adaptation strategies generally increased the performance over individual adaptation schemes. Also, the improvement in average classification accuracy for a 3-class mental imagery BCI with hybrid adaption is as high as around 17% above the baseline non-adaptive classifier.
{"title":"Towards Adaptive Classification using Riemannian Geometry approaches in Brain-Computer Interfaces","authors":"Satyam Kumar, F. Yger, F. Lotte","doi":"10.1109/IWW-BCI.2019.8737349","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737349","url":null,"abstract":"The omnipresence of non-stationarity and noise in Electroencephalogram signals restricts the ubiquitous use of Brain-Computer interface. One of the possible ways to tackle this problem is to adapt the computational model used to detect and classify different mental states. Adapting the model will possibly help us to track the changes and thus reducing the effect of non-stationarities. In this paper, we present different adaptation strategies for state of the art Riemannian geometry based classifiers. The offline evaluation of our proposed methods on two different datasets showed a statistically significant improvement over baseline non-adaptive classifiers. Moreover, we also demonstrate that combining different (hybrid) adaptation strategies generally increased the performance over individual adaptation schemes. Also, the improvement in average classification accuracy for a 3-class mental imagery BCI with hybrid adaption is as high as around 17% above the baseline non-adaptive classifier.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131395237","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737345
Wonjun Ko, Eunjin Jeon, Jiyeon Lee, Heung-Il Suk
Recent advances in deep learning have made a progressive impact on BCI researches. In particular, convolutional neural networks (CNNs) with different architectural forms have been studied for spatio-temporal or spatio-spectral feature representation learning. However, there still remain many challenges and limitations due to the necessity of a large annotated training samples for robustness. In this paper, we propose a semi-supervised deep adversarial learning framework that effectively utilizes generated artificial samples along with labeled and unlabelled real samples in discovering class-discriminative features to boost robustness of a classifier, thus to enhance BCI performance. It is also noteworthy that the proposed framework allows to exploit unlabelled real samples to better uncover the underlying patterns inherent in a user’s EEG signals. In order to justify the validity of the proposed framework, we conducted exhaustive experiments with ‘Recurrent Spatio-Temporal Neural Network’ CNN architectures over the public BCI Competition IV-IIa dataset. From our experiments, we could observe statistically significant improvements on performance, compared to the competing methods with the conventional framework. We have also visualized learned convolutional weights in terms of activation pattern maps, separability of extracted features, and validity of generated artificial samples.
{"title":"Semi-Supervised Deep Adversarial Learning for Brain-Computer Interface","authors":"Wonjun Ko, Eunjin Jeon, Jiyeon Lee, Heung-Il Suk","doi":"10.1109/IWW-BCI.2019.8737345","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737345","url":null,"abstract":"Recent advances in deep learning have made a progressive impact on BCI researches. In particular, convolutional neural networks (CNNs) with different architectural forms have been studied for spatio-temporal or spatio-spectral feature representation learning. However, there still remain many challenges and limitations due to the necessity of a large annotated training samples for robustness. In this paper, we propose a semi-supervised deep adversarial learning framework that effectively utilizes generated artificial samples along with labeled and unlabelled real samples in discovering class-discriminative features to boost robustness of a classifier, thus to enhance BCI performance. It is also noteworthy that the proposed framework allows to exploit unlabelled real samples to better uncover the underlying patterns inherent in a user’s EEG signals. In order to justify the validity of the proposed framework, we conducted exhaustive experiments with ‘Recurrent Spatio-Temporal Neural Network’ CNN architectures over the public BCI Competition IV-IIa dataset. From our experiments, we could observe statistically significant improvements on performance, compared to the competing methods with the conventional framework. We have also visualized learned convolutional weights in terms of activation pattern maps, separability of extracted features, and validity of generated artificial samples.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130770335","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737259
SangWook Park, F. Park, Junhyuk Choi, Hyungmin Kim
EEG-based BCI was recently applied to lower limb exoskeleton robots. Various machine learning decoders have shown high accuracy performance on classifying the gait state whether the subject is walking or standing. However, there is a trade-off between the accuracy and the responsiveness due to the delay time. The delay time is critical when controlling the exoskeleton robots with EEG decoders online (real-time). In this research, we propose spatio-spectral convolutional neural networks with relatively short segment of EEG data (0.2s) having 83.4% accuracy on gait state recognition. The gait intention recognition that detects the subject’s gait intention prior to the actual gait had 77.3% accuracy. We were able to classify EEG data of both healthy subjects and stroke patients at subacute and chronic phases.
{"title":"EEG-based Gait State and Gait Intention Recognition Using Spatio-Spectral Convolutional Neural Network","authors":"SangWook Park, F. Park, Junhyuk Choi, Hyungmin Kim","doi":"10.1109/IWW-BCI.2019.8737259","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737259","url":null,"abstract":"EEG-based BCI was recently applied to lower limb exoskeleton robots. Various machine learning decoders have shown high accuracy performance on classifying the gait state whether the subject is walking or standing. However, there is a trade-off between the accuracy and the responsiveness due to the delay time. The delay time is critical when controlling the exoskeleton robots with EEG decoders online (real-time). In this research, we propose spatio-spectral convolutional neural networks with relatively short segment of EEG data (0.2s) having 83.4% accuracy on gait state recognition. The gait intention recognition that detects the subject’s gait intention prior to the actual gait had 77.3% accuracy. We were able to classify EEG data of both healthy subjects and stroke patients at subacute and chronic phases.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133979287","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737317
Soo-Yeon Han, Jeong-Woo Kim, Seong-Whan Lee
Pilot’s cognitive states induced by mental fatigue, distraction, and workload could be a cause of catastrophic accidents. Therefore, many methods for the detection of pilot cognitive states have been proposed in previous studies. Especially, neuro- and peripheral physiological measures (PPMs) such as electroencephalogram (EEG), electrocardiogram (ECG), respiration, and electrodermal activity (EDA) were employed to develop the novel flight assistant technologies for assurance of pilot’s safety. However, each study investigated only one kind of state. Also, they did not consider the feature optimization for each subject. In this paper, we propose a method for the recognition of pilot’s diversified mental states during simulated flight. The method selects the most fitted features for each subject based on the statistical analysis. The results show that the proposed method is superior to previous methods. Consequently, it shows that the pilot assistant system based on human-computer interaction (HCI) technologies could be facilitated in real-world.
{"title":"Recognition of Pilot’s Cognitive States based on Combination of Physiological Signals","authors":"Soo-Yeon Han, Jeong-Woo Kim, Seong-Whan Lee","doi":"10.1109/IWW-BCI.2019.8737317","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737317","url":null,"abstract":"Pilot’s cognitive states induced by mental fatigue, distraction, and workload could be a cause of catastrophic accidents. Therefore, many methods for the detection of pilot cognitive states have been proposed in previous studies. Especially, neuro- and peripheral physiological measures (PPMs) such as electroencephalogram (EEG), electrocardiogram (ECG), respiration, and electrodermal activity (EDA) were employed to develop the novel flight assistant technologies for assurance of pilot’s safety. However, each study investigated only one kind of state. Also, they did not consider the feature optimization for each subject. In this paper, we propose a method for the recognition of pilot’s diversified mental states during simulated flight. The method selects the most fitted features for each subject based on the statistical analysis. The results show that the proposed method is superior to previous methods. Consequently, it shows that the pilot assistant system based on human-computer interaction (HCI) technologies could be facilitated in real-world.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123459797","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737336
Jin Woo Choi, Taehyean Choi, Shinjeong Kim, Sungho Jo
Brain-computer interfaces (BCIs) rely on accurate classification of a user’s intent in order to perform the correct actions. However, when used in reality, devices controlled by BCIs may often react differently from what the user intended due to noise and other factors resulting in misclassification. In such cases, error-related potentials (ErrPs) may be evoked and can be captured from the user’s neural signals. Detection of these ErrPs can then be used to recognize and correct erroneous responses. In this research, we have created a graphical application in which the user drives a virtual car from a first-person perspective. Results of our experiments show that ErrPs can be captured from the user when the car moves differently from how the user intended to drive.
{"title":"Towards Utilization of Error-Related Potentials for Brain-to-Vehicle Communication","authors":"Jin Woo Choi, Taehyean Choi, Shinjeong Kim, Sungho Jo","doi":"10.1109/IWW-BCI.2019.8737336","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737336","url":null,"abstract":"Brain-computer interfaces (BCIs) rely on accurate classification of a user’s intent in order to perform the correct actions. However, when used in reality, devices controlled by BCIs may often react differently from what the user intended due to noise and other factors resulting in misclassification. In such cases, error-related potentials (ErrPs) may be evoked and can be captured from the user’s neural signals. Detection of these ErrPs can then be used to recognize and correct erroneous responses. In this research, we have created a graphical application in which the user drives a virtual car from a first-person perspective. Results of our experiments show that ErrPs can be captured from the user when the car moves differently from how the user intended to drive.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121157002","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737341
Seul-Kee Kim, Da-hye Kim, Laehyun Kim
This paper proposes an optimization method of error-related potentials (ErrPs). The method is used to improve motor imagery (MI)-BCI performance by rapidly correcting MIBCI errors. We used the linear discriminant analysis and spatial-temporal domain analysis (STDA) algorithms to detect ErrP, which is the brain response measured immediately after MIBCI error. We found the optimal conditions for detecting ErrPs by comparing the performances of the algorithms in terms of the resampling rate, spatial domain, and temporal domain. The best sample size was obtained at a resampling rate of 21 Hz. In the spatial domain, using the data from 8 or 16 channels provided better performance compared to using a higher number of channels. For epoch selection in the temporal domain, the highest accuracy was obtained for the data at 1000 ms. Finally, the best performers among all subjects exhibited 86% accuracy in the optimal condition (21 Hz, 1000 ms, 16 ch), while the worst performers exhibited 58.67% accuracy in the first trial in the STDA algorithm.
{"title":"Optimization method of error-related potentials to improve MI-BCI performance","authors":"Seul-Kee Kim, Da-hye Kim, Laehyun Kim","doi":"10.1109/IWW-BCI.2019.8737341","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737341","url":null,"abstract":"This paper proposes an optimization method of error-related potentials (ErrPs). The method is used to improve motor imagery (MI)-BCI performance by rapidly correcting MIBCI errors. We used the linear discriminant analysis and spatial-temporal domain analysis (STDA) algorithms to detect ErrP, which is the brain response measured immediately after MIBCI error. We found the optimal conditions for detecting ErrPs by comparing the performances of the algorithms in terms of the resampling rate, spatial domain, and temporal domain. The best sample size was obtained at a resampling rate of 21 Hz. In the spatial domain, using the data from 8 or 16 channels provided better performance compared to using a higher number of channels. For epoch selection in the temporal domain, the highest accuracy was obtained for the data at 1000 ms. Finally, the best performers among all subjects exhibited 86% accuracy in the optimal condition (21 Hz, 1000 ms, 16 ch), while the worst performers exhibited 58.67% accuracy in the first trial in the STDA algorithm.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124479221","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737258
Siju G. Chacko, P. Tayade, Simran Kaur, Ratna Sharma
Application of Brain Computer Interface (BCI) is revolutionizing control of prosthetic or exoskeleton devices directly through human thought. A BCI is expected to classify day-to-day life activities like grabbing and lifting a glass of water. Currently, motor imagery based BCI for two closely separated muscle groups like grabbing and lifting an object has not been studied. Challenge of classifying motor imagery of these activities accurately could be solved by using individual BCI. We proposed to achieve the same by using a neural network (machine learning) classifier on high resolution (129 channel) EEG data evaluated continuously every 80ms after spatial filtering using spherical Laplacian. This study employed a motor imagery based BCI optimized for individual subjects (n=28) using EEG data of actual movement for classifying motor imagery of grab, lift and grab+lift of right forearm. A three layered neural network with two output nodes was created for classifying the motor imagery using power of 8–14 Hz band of 500 ms EEG data. This BCI was able to classify motor imagery with 95.65% accuracy. In continuous evaluation, BCI showed a True Positive Rate of 24.89% and False Positive Rate of 12.93%. The percentage of correctly classified motor imagery in each trial was 84.99%, 72.23%, 17.07% for grab, lift and combined respectively. In conclusion, the current BCI was able to classify the motor imagery of grab, lift and grab+lift successfully based on EEG of movement data without any prior training of motor imagery based on last 500ms of data.
{"title":"Creation of a high resolution EEG based Brain Computer Interface for classifying motor imagery of daily life activities","authors":"Siju G. Chacko, P. Tayade, Simran Kaur, Ratna Sharma","doi":"10.1109/IWW-BCI.2019.8737258","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737258","url":null,"abstract":"Application of Brain Computer Interface (BCI) is revolutionizing control of prosthetic or exoskeleton devices directly through human thought. A BCI is expected to classify day-to-day life activities like grabbing and lifting a glass of water. Currently, motor imagery based BCI for two closely separated muscle groups like grabbing and lifting an object has not been studied. Challenge of classifying motor imagery of these activities accurately could be solved by using individual BCI. We proposed to achieve the same by using a neural network (machine learning) classifier on high resolution (129 channel) EEG data evaluated continuously every 80ms after spatial filtering using spherical Laplacian. This study employed a motor imagery based BCI optimized for individual subjects (n=28) using EEG data of actual movement for classifying motor imagery of grab, lift and grab+lift of right forearm. A three layered neural network with two output nodes was created for classifying the motor imagery using power of 8–14 Hz band of 500 ms EEG data. This BCI was able to classify motor imagery with 95.65% accuracy. In continuous evaluation, BCI showed a True Positive Rate of 24.89% and False Positive Rate of 12.93%. The percentage of correctly classified motor imagery in each trial was 84.99%, 72.23%, 17.07% for grab, lift and combined respectively. In conclusion, the current BCI was able to classify the motor imagery of grab, lift and grab+lift successfully based on EEG of movement data without any prior training of motor imagery based on last 500ms of data.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123341073","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737315
Boin Suh, Injun Song, Woojin Jeon, Younggil Cha, Kyerim Che, Seung Hyun Lee, Kijoon Lee, J. An
This paper is to explore the specific cortical regions associated with a visual-auditory integration. Cortical activities were acquired by fNIRS during rhythm game which offered visual-auditory stimulation with synchronous and asynchronous situations. Nine subjects have participated in the experiment. The results from group analysis showed that time difference between auditory and visual stimuli affected the change of cortical activation in terms of the concentration change of oxygenated hemoglobin. Especially, the cortical activation went higher in right hemisphere than left hemisphere except Broca’s area. Superior Temporal Gyrus (STG) and Middle Temporal Gyrus (MTG) were observed as the cortical regions directly engaged in human visual-auditory integration processing.
{"title":"Cortical Regions Associated with Visual-Auditory Integration: an fNIRS study","authors":"Boin Suh, Injun Song, Woojin Jeon, Younggil Cha, Kyerim Che, Seung Hyun Lee, Kijoon Lee, J. An","doi":"10.1109/IWW-BCI.2019.8737315","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737315","url":null,"abstract":"This paper is to explore the specific cortical regions associated with a visual-auditory integration. Cortical activities were acquired by fNIRS during rhythm game which offered visual-auditory stimulation with synchronous and asynchronous situations. Nine subjects have participated in the experiment. The results from group analysis showed that time difference between auditory and visual stimuli affected the change of cortical activation in terms of the concentration change of oxygenated hemoglobin. Especially, the cortical activation went higher in right hemisphere than left hemisphere except Broca’s area. Superior Temporal Gyrus (STG) and Middle Temporal Gyrus (MTG) were observed as the cortical regions directly engaged in human visual-auditory integration processing.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123126907","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 : 2019-02-01DOI: 10.1109/IWW-BCI.2019.8737333
Ciarán McGeady, A. Vučković, S. Puthusserypady
This pilot study implements a hybrid BCI system in an effort to deduce the effects of measuring more than one brain signal in a motor imagery (MI) task. In addition to sensorimotor rhythms (SMRs), a steady state visual evoked potential (SSVEP) was introduced to acquire additional information relating to user intention. A common spatial pattern (CSP) filter followed by a support vector machine (SVM) classifier were used to distinguish between MI and the resting state. The power spectral density (PSD) was used to classify the SSVEP. Results from online simulations of EEG data collected from 10 able-bodied participants showed that the hybrid BCI’s performance achieved a classification accuracy of 77.3±8.2%, with an SSVEP classification accuracy of 94.4±3.5%, and MI classification accuracy of 80.9±8.1%, an improvement upon purely MI-based multi-class BCI paradigms.
{"title":"A Hybrid MI-SSVEP based Brain Computer Interface for Potential Upper Limb Neurorehabilitation: A Pilot Study","authors":"Ciarán McGeady, A. Vučković, S. Puthusserypady","doi":"10.1109/IWW-BCI.2019.8737333","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2019.8737333","url":null,"abstract":"This pilot study implements a hybrid BCI system in an effort to deduce the effects of measuring more than one brain signal in a motor imagery (MI) task. In addition to sensorimotor rhythms (SMRs), a steady state visual evoked potential (SSVEP) was introduced to acquire additional information relating to user intention. A common spatial pattern (CSP) filter followed by a support vector machine (SVM) classifier were used to distinguish between MI and the resting state. The power spectral density (PSD) was used to classify the SSVEP. Results from online simulations of EEG data collected from 10 able-bodied participants showed that the hybrid BCI’s performance achieved a classification accuracy of 77.3±8.2%, with an SSVEP classification accuracy of 94.4±3.5%, and MI classification accuracy of 80.9±8.1%, an improvement upon purely MI-based multi-class BCI paradigms.","PeriodicalId":345970,"journal":{"name":"2019 7th International Winter Conference on Brain-Computer Interface (BCI)","volume":"463 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115922766","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：