Pub Date : 2018-09-05DOI: 10.1109/iww-bci.2018.8311486
P. König, Andrew Melnik, Caspar Goeke, Anna L. Gert, Sabine U. König, Tim C Kietzmann
In this presentation, we discuss embodied cognition in the human brain from perspectives of spatial cognition, sensorimotor processing, face processing, and mobile EEG recordings. The argument is based upon experimental evidence gathered from five separate studies. First, we focus on spatial representations and demonstrate that, given time pressure, information on the spatial orientation of houses, independent of a participant's own location, is best retrieved when it directly relates to potential actions. Thus providing evidence that even spatial representations code information in a manner directly related to the action. Next, we discuss the concept of representations as such. Using the example of face processing in the human visual system, we argue that the concept of representations should be confined to cases where neuronal activity contains explicit information on the variable of interest and, in turn, that this variable explains the complete part of the explainable variance, i.e. reaches the noise limit. Next, to push towards an investigation of cognition under natural conditions we present a benchmark test of mobile and research-grade EEG systems. Specifically, we demonstrate that the variance over systems contributes a significant part to the total variance of recorded event related potentials. As a next step, using Independent Component Analysis of EEG data we demonstrate that in cognitive tasks some independent components systematically relate to sensory processing as well as to action execution. This supports theories of the common coding theory and, thus, a mechanistic part of the embodied cognition framework. Finally, we demonstrate a real world application investigating face processing in the form of the N170 event related potential during natural visual exploration in a fully mobile setup. This technique allows investigating the physiological basis of cognitive processes under real world conditions. In this presentation we argue that understanding cognitive processes will need to consider the (inter)actions in the natural environment.
{"title":"Embodied cognition","authors":"P. König, Andrew Melnik, Caspar Goeke, Anna L. Gert, Sabine U. König, Tim C Kietzmann","doi":"10.1109/iww-bci.2018.8311486","DOIUrl":"https://doi.org/10.1109/iww-bci.2018.8311486","url":null,"abstract":"In this presentation, we discuss embodied cognition in the human brain from perspectives of spatial cognition, sensorimotor processing, face processing, and mobile EEG recordings. The argument is based upon experimental evidence gathered from five separate studies. First, we focus on spatial representations and demonstrate that, given time pressure, information on the spatial orientation of houses, independent of a participant's own location, is best retrieved when it directly relates to potential actions. Thus providing evidence that even spatial representations code information in a manner directly related to the action. Next, we discuss the concept of representations as such. Using the example of face processing in the human visual system, we argue that the concept of representations should be confined to cases where neuronal activity contains explicit information on the variable of interest and, in turn, that this variable explains the complete part of the explainable variance, i.e. reaches the noise limit. Next, to push towards an investigation of cognition under natural conditions we present a benchmark test of mobile and research-grade EEG systems. Specifically, we demonstrate that the variance over systems contributes a significant part to the total variance of recorded event related potentials. As a next step, using Independent Component Analysis of EEG data we demonstrate that in cognitive tasks some independent components systematically relate to sensory processing as well as to action execution. This supports theories of the common coding theory and, thus, a mechanistic part of the embodied cognition framework. Finally, we demonstrate a real world application investigating face processing in the form of the N170 event related potential during natural visual exploration in a fully mobile setup. This technique allows investigating the physiological basis of cognitive processes under real world conditions. In this presentation we argue that understanding cognitive processes will need to consider the (inter)actions in the natural environment.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"15 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87768042","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311534
Hoseok Choi, Jeyeon Lee, Jinsick Park, B. Cho, K. Lee, D. Jang
During bimanual movement, brain state is known to be different from the unimanual movement. Thus the conventional arm movement classifier for unimanual arm movement decoding method seems to be insufficient to decode bimanual movement. In this research, we suggested the convolutional neural network (CNN) for movement state classification to improve the decoding accuracy for bimanual movement estimation. We recorded the monkey's cortical signal while the bimanual task, and convert to spectrogram dataset for decoding. To evaluate the CNN, we stacked several layers for deep structure and figured out the best configuration. As a result, this method showed improved the arm movement state classification performance for bimanual tasks. This technique could be applied to arm movement brain computer interfaces (BCIs) in real world and the various neuro-prosthetics fields.
{"title":"Movement state classification for bimanual BCI from non-human primate's epidural ECoG using three-dimensional convolutional neural network","authors":"Hoseok Choi, Jeyeon Lee, Jinsick Park, B. Cho, K. Lee, D. Jang","doi":"10.1109/IWW-BCI.2018.8311534","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311534","url":null,"abstract":"During bimanual movement, brain state is known to be different from the unimanual movement. Thus the conventional arm movement classifier for unimanual arm movement decoding method seems to be insufficient to decode bimanual movement. In this research, we suggested the convolutional neural network (CNN) for movement state classification to improve the decoding accuracy for bimanual movement estimation. We recorded the monkey's cortical signal while the bimanual task, and convert to spectrogram dataset for decoding. To evaluate the CNN, we stacked several layers for deep structure and figured out the best configuration. As a result, this method showed improved the arm movement state classification performance for bimanual tasks. This technique could be applied to arm movement brain computer interfaces (BCIs) in real world and the various neuro-prosthetics fields.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"29 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82291874","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311518
Seung-Bo Lee, Eun-Suk Song, Hakseung Kim, Dong-Joo Kim
Arterial blood pressure (ABP) is used in various areas such as brain computer interface and clinical field. The morphological analysis of the ABP signal allows researchers to identify important information such as cardiovascular system and psychopathology. Detection of onset, which is the most important landmark in the ABP waveform, is essential for morphology analysis of ABP. Since the physiological signal is vulnerable to the risk of contamination, the robust onset detection method is needed. This study proposed a pulse onset detection method based on Monte Carlo approach that is robust from artifacts. The 10 cases of ABP signals were analyzed to detect signal onset. When we assessed the time difference from the actual onset, there was an average error of 2.4μs. The results suggested that the proposed method could achieve robustness in pulse detection and facilitated pulse wave analysis using clinical recordings with various artifacts.
{"title":"Robust arterial blood pressure onset detection method from signal artifacts","authors":"Seung-Bo Lee, Eun-Suk Song, Hakseung Kim, Dong-Joo Kim","doi":"10.1109/IWW-BCI.2018.8311518","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311518","url":null,"abstract":"Arterial blood pressure (ABP) is used in various areas such as brain computer interface and clinical field. The morphological analysis of the ABP signal allows researchers to identify important information such as cardiovascular system and psychopathology. Detection of onset, which is the most important landmark in the ABP waveform, is essential for morphology analysis of ABP. Since the physiological signal is vulnerable to the risk of contamination, the robust onset detection method is needed. This study proposed a pulse onset detection method based on Monte Carlo approach that is robust from artifacts. The 10 cases of ABP signals were analyzed to detect signal onset. When we assessed the time difference from the actual onset, there was an average error of 2.4μs. The results suggested that the proposed method could achieve robustness in pulse detection and facilitated pulse wave analysis using clinical recordings with various artifacts.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"2 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81955605","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311505
Seokyun Ryun, J. Kim, Donghyuk Lee, C. Chung
One of the most challenging issues in recent BCI research is not only achieving high performance, but also creating a sense of ownership of artificial devices. To investigate this issue, sensory-motor integrated BMI system should be considered. In this study, we attempted to predict the somatosensory property of tactile stimulus as well as the movement trajectory and type using elctrocorticography (ECoG) signals. We showed that 1) single-trial 3-D movement trajectory can be estimated from low-frequency ECoG signals with relatively high performance, 2) high-gamma activity can be a robust feature for movement type classification, and 3) the location of pressure stimulation can be classified by macro ECoG signals from sensory-related cortical areas. These results might be applied to the closed-loop BMBI systems which simultaneously encode sensory information during movement decoding.
{"title":"Prediction of motor and somatosensory function from human ECoG","authors":"Seokyun Ryun, J. Kim, Donghyuk Lee, C. Chung","doi":"10.1109/IWW-BCI.2018.8311505","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311505","url":null,"abstract":"One of the most challenging issues in recent BCI research is not only achieving high performance, but also creating a sense of ownership of artificial devices. To investigate this issue, sensory-motor integrated BMI system should be considered. In this study, we attempted to predict the somatosensory property of tactile stimulus as well as the movement trajectory and type using elctrocorticography (ECoG) signals. We showed that 1) single-trial 3-D movement trajectory can be estimated from low-frequency ECoG signals with relatively high performance, 2) high-gamma activity can be a robust feature for movement type classification, and 3) the location of pressure stimulation can be classified by macro ECoG signals from sensory-related cortical areas. These results might be applied to the closed-loop BMBI systems which simultaneously encode sensory information during movement decoding.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"160 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87547872","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311526
Min-Hee Ahn, Byoung-Kyong Min
Brain-machine interfaces (BMIs) enable humans to control devices by modulating their brain signals. As the current BMI technology has several obstacles to overcome, additional sources of brain activity need to be explored. It seems plausible that the brain activity associated with top-down cognitive functions could open a new prospect in the field of BMIs. As top-down cognitive BMIs could exploit neural signals from more diverse networks, a deep-learning approach with complex hidden layers may provide a more optimal decoding performance. In this study, using our top-down steady-state visual evoked potential (SSVEP) paradigm (N = 20), we observed that the decoding accuracy (48.42%) of a deep-learning algorithm with a sigmoid activation function was significantly higher than that of regularized linear discriminant analysis (rLDA) with shrinkage (42.52%; t(19) = −3.183, p < 0.01), used in our previous study. Therefore, a deep-learning approach seems to be more optimized for classification in the top-down cognitive BMI paradigm.
脑机接口(bmi)使人类能够通过调节大脑信号来控制设备。由于目前的BMI技术有几个障碍需要克服，需要探索大脑活动的其他来源。与自上而下的认知功能相关的大脑活动似乎可以在bmi领域开辟新的前景。由于自上而下的认知bmi可以利用来自更多样化网络的神经信号，具有复杂隐藏层的深度学习方法可能提供更优化的解码性能。本研究采用自顶向下稳态视觉诱发电位(SSVEP)范式(N = 20)，发现具有s型激活函数的深度学习算法的解码准确率(48.42%)显著高于具有收缩(42.52%)的正则化线性判别分析(rLDA);T (19) = - 3.183, p < 0.01)，在我们之前的研究中使用。因此，在自上而下的认知BMI范式中，深度学习方法似乎更适合分类。
{"title":"Applying deep-learning to a top-down SSVEP BMI","authors":"Min-Hee Ahn, Byoung-Kyong Min","doi":"10.1109/IWW-BCI.2018.8311526","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311526","url":null,"abstract":"Brain-machine interfaces (BMIs) enable humans to control devices by modulating their brain signals. As the current BMI technology has several obstacles to overcome, additional sources of brain activity need to be explored. It seems plausible that the brain activity associated with top-down cognitive functions could open a new prospect in the field of BMIs. As top-down cognitive BMIs could exploit neural signals from more diverse networks, a deep-learning approach with complex hidden layers may provide a more optimal decoding performance. In this study, using our top-down steady-state visual evoked potential (SSVEP) paradigm (N = 20), we observed that the decoding accuracy (48.42%) of a deep-learning algorithm with a sigmoid activation function was significantly higher than that of regularized linear discriminant analysis (rLDA) with shrinkage (42.52%; t(19) = −3.183, p < 0.01), used in our previous study. Therefore, a deep-learning approach seems to be more optimized for classification in the top-down cognitive BMI paradigm.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"75 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77071033","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311501
Sunghee Dong, Jichai Jeong
It is challenging to remove the physiological noise that is not evoked by the brain activity in fNIRS signals. We propose a novel method to effectively remove the superficial noise in the hemodynamic signals by combining an extended Kalman filter (EKF) with a short separation measurement based on a nonlinear balloon model. To demonstrate the improved performances of the proposed method over the existing linear Kalman filter (LKF), we use a synthetic hemodynamic signal to compare. As a result, the proposed EKF recovers the modeled hemodynamic responses with lower errors and higher correlation than the LKF.
{"title":"Noise reduction in fNIRS data using extended Kalman filter combined with short separation measurement","authors":"Sunghee Dong, Jichai Jeong","doi":"10.1109/IWW-BCI.2018.8311501","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311501","url":null,"abstract":"It is challenging to remove the physiological noise that is not evoked by the brain activity in fNIRS signals. We propose a novel method to effectively remove the superficial noise in the hemodynamic signals by combining an extended Kalman filter (EKF) with a short separation measurement based on a nonlinear balloon model. To demonstrate the improved performances of the proposed method over the existing linear Kalman filter (LKF), we use a synthetic hemodynamic signal to compare. As a result, the proposed EKF recovers the modeled hemodynamic responses with lower errors and higher correlation than the LKF.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"1 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81655136","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311514
Ji-Hoon Jeong, Keun-Tae Kim, Yong-Deok Yun, Seong-Whan Lee
This paper presents a prototype for a brain-controlled robot arm system using a variety of upper-limb movement imagery. To do that, we have designed the experimental environment based on brain signals. The experimental system architecture was modularized into three main components: BMI, network, and control parts. Six subjects participated in our experiments. The subject performed various upper-limb actual movement and imagery task. Each task consisted of three different movement/imagery: Arm reaching tasks, hand grasping tasks, and wrist twisting tasks. We confirmed the classification accuracies are 22.65%, 50.79%, and 54.44%, respectively. Moreover, we will demonstrate that brain-controlled robot arm system can achieve a high-level task in multi-dimensional space.
{"title":"Design of a brain-controlled robot arm system based on upper-limb movement imagery","authors":"Ji-Hoon Jeong, Keun-Tae Kim, Yong-Deok Yun, Seong-Whan Lee","doi":"10.1109/IWW-BCI.2018.8311514","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311514","url":null,"abstract":"This paper presents a prototype for a brain-controlled robot arm system using a variety of upper-limb movement imagery. To do that, we have designed the experimental environment based on brain signals. The experimental system architecture was modularized into three main components: BMI, network, and control parts. Six subjects participated in our experiments. The subject performed various upper-limb actual movement and imagery task. Each task consisted of three different movement/imagery: Arm reaching tasks, hand grasping tasks, and wrist twisting tasks. We confirmed the classification accuracies are 22.65%, 50.79%, and 54.44%, respectively. Moreover, we will demonstrate that brain-controlled robot arm system can achieve a high-level task in multi-dimensional space.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"3 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73088140","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311523
Jaeyoung Shin, A. Lühmann, B. Blankertz, Do-Won Kim, J. Mehnert, Jichai Jeong, Han-Jeong Hwang, K. Müller
Recently, in order to overcome the disadvantages of unimodal brain-imaging modalities such as low signal-to-noise ratio and vulnerability to motion artifact and to improve system performance, a multimodal imaging system (so-called hybrid system) has been emerging as an attractive alternative. In the present study, to meet the increasing demand on a hybrid brain-imaging data, we introduce open access datasets of electroencephalography (EEG) and near-infrared spectroscopy (NIRS) simultaneously measured during various cognitive tasks. The datasets contain BCI data such as motor imagery (MI)-, and mental arithmetic (MA), and word generation (WG)-related brain signals, and cognitive task data such as n-back (NB)-, and discrimination/selection response (DSR)-related brain signals. We provide the reference results of these datasets, which were validated using analysis pipelines widely used in related research fields. In particular, it was confirmed from classification analysis that a hybrid EEG-NIRS system can yield better classification accuracy than each of unimodal brain-imaging systems.
{"title":"Open access repository for hybrid EEG-NIRS data","authors":"Jaeyoung Shin, A. Lühmann, B. Blankertz, Do-Won Kim, J. Mehnert, Jichai Jeong, Han-Jeong Hwang, K. Müller","doi":"10.1109/IWW-BCI.2018.8311523","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311523","url":null,"abstract":"Recently, in order to overcome the disadvantages of unimodal brain-imaging modalities such as low signal-to-noise ratio and vulnerability to motion artifact and to improve system performance, a multimodal imaging system (so-called hybrid system) has been emerging as an attractive alternative. In the present study, to meet the increasing demand on a hybrid brain-imaging data, we introduce open access datasets of electroencephalography (EEG) and near-infrared spectroscopy (NIRS) simultaneously measured during various cognitive tasks. The datasets contain BCI data such as motor imagery (MI)-, and mental arithmetic (MA), and word generation (WG)-related brain signals, and cognitive task data such as n-back (NB)-, and discrimination/selection response (DSR)-related brain signals. We provide the reference results of these datasets, which were validated using analysis pipelines widely used in related research fields. In particular, it was confirmed from classification analysis that a hybrid EEG-NIRS system can yield better classification accuracy than each of unimodal brain-imaging systems.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"50 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80976121","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311529
In-Nea Wang, Hyun-Ji Kim, Eun-Ji Kim, Young-Tak Kim, Dong-Joo Kim
The purpose of this study is to investigate the association between the morphology of the brain computed tomography (CT) density distribution and pathological change of the brain. We retrospectively analyzed CT images of 221 patients with acquired brain injury (normal subject=102 vs. abnormal subject=119), obtained during emergency department admission. The kurtosis and the length of the whisker of the quartile statistics in the density distribution were derived to assess the degree of outliers of the density distribution. Although both parameters showed significance with CT abnormality (p <0.001), the area under the curve (AUC) of length of the whisker was higher than the AUC of kurtosis (0.70, 0.65, respectively). In conclusion, the length of whisker in quartile statistics more reliably reflects the extent of hemorrhagic and edematous lesions than the kurtosis.
{"title":"Evaluation of outlier prevalence of density distribution in brain computed tomography: Comparison of kurtosis and quartile statistics","authors":"In-Nea Wang, Hyun-Ji Kim, Eun-Ji Kim, Young-Tak Kim, Dong-Joo Kim","doi":"10.1109/IWW-BCI.2018.8311529","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311529","url":null,"abstract":"The purpose of this study is to investigate the association between the morphology of the brain computed tomography (CT) density distribution and pathological change of the brain. We retrospectively analyzed CT images of 221 patients with acquired brain injury (normal subject=102 vs. abnormal subject=119), obtained during emergency department admission. The kurtosis and the length of the whisker of the quartile statistics in the density distribution were derived to assess the degree of outliers of the density distribution. Although both parameters showed significance with CT abnormality (p <0.001), the area under the curve (AUC) of length of the whisker was higher than the AUC of kurtosis (0.70, 0.65, respectively). In conclusion, the length of whisker in quartile statistics more reliably reflects the extent of hemorrhagic and edematous lesions than the kurtosis.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"1 1","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79610870","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 : 2018-03-09DOI: 10.1109/IWW-BCI.2018.8311489
Minji Lee, Seul-Ki Yeom, Benjamin Baird, O. Gosseries, Jaakko O. Nieminen, G. Tononi, Seong-Whan Lee
Electroencephalogram (EEG) measurement could help to distinguish the level of consciousness in an individual without requiring a behavioral response, which could be useful as a diagnostic aid in patients with disorders of consciousness. In this study, we explored the EEG-evoked perturbation and analyzed consciousness using event-related spectral perturbation and convolutional neural network. We observed a novel EEG neurophysiological signature that can be used to monitor brain activity during unconsciousness. Also, the performance accuracy in the parietal region was higher than in the frontal region. The sensitivity for conscious experience was 90.9%, whereas sensitivity for unconscious experience was at the chance level in the parietal region. These results could be evidence for the importance of the posterior hot zone and could help shed light on the internal neural dynamics related to conscious experience.
{"title":"Spatio-temporal analysis of EEG signal during consciousness using convolutional neural network","authors":"Minji Lee, Seul-Ki Yeom, Benjamin Baird, O. Gosseries, Jaakko O. Nieminen, G. Tononi, Seong-Whan Lee","doi":"10.1109/IWW-BCI.2018.8311489","DOIUrl":"https://doi.org/10.1109/IWW-BCI.2018.8311489","url":null,"abstract":"Electroencephalogram (EEG) measurement could help to distinguish the level of consciousness in an individual without requiring a behavioral response, which could be useful as a diagnostic aid in patients with disorders of consciousness. In this study, we explored the EEG-evoked perturbation and analyzed consciousness using event-related spectral perturbation and convolutional neural network. We observed a novel EEG neurophysiological signature that can be used to monitor brain activity during unconsciousness. Also, the performance accuracy in the parietal region was higher than in the frontal region. The sensitivity for conscious experience was 90.9%, whereas sensitivity for unconscious experience was at the chance level in the parietal region. These results could be evidence for the importance of the posterior hot zone and could help shed light on the internal neural dynamics related to conscious experience.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"80 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2018-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90864521","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：