Pub Date : 2015-04-22DOI: 10.1109/NER.2015.7146704
John A. Spanias, A. M. Simon, Kimberly A. Ingraham, L. Hargrove
Powered lower limb prostheses can improve amputees' ability to traverse stairs and ramps by providing positive mechanical work at the knee and ankle joint. EMG signals have been proposed as one way of providing seamless mode transitions by using them in combination with embedded mechanical sensors as inputs to a pattern recognition system that predicts the user's desired locomotion mode. In this study, we have expanded the amount of mechanical sensor information to include data from an additional five degrees of freedom in the load cell, as well as calculated thigh and shank angles. The purpose of this study was to determine the impact of this additional information on the performance of an EMG-based pattern recognition system designed to predict the desired locomotion mode. Our results indicate that including the additional mechanical sensor signals decreased the error rates of the system for both steady-state and transitional steps when compared to the reduced sensor set. We also found that EMG still decreased the error rate of the system, but to a lesser extent when using the additional mechanical sensors.
{"title":"Effect of additional mechanical sensor data on an EMG-based pattern recognition system for a powered leg prosthesis","authors":"John A. Spanias, A. M. Simon, Kimberly A. Ingraham, L. Hargrove","doi":"10.1109/NER.2015.7146704","DOIUrl":"https://doi.org/10.1109/NER.2015.7146704","url":null,"abstract":"Powered lower limb prostheses can improve amputees' ability to traverse stairs and ramps by providing positive mechanical work at the knee and ankle joint. EMG signals have been proposed as one way of providing seamless mode transitions by using them in combination with embedded mechanical sensors as inputs to a pattern recognition system that predicts the user's desired locomotion mode. In this study, we have expanded the amount of mechanical sensor information to include data from an additional five degrees of freedom in the load cell, as well as calculated thigh and shank angles. The purpose of this study was to determine the impact of this additional information on the performance of an EMG-based pattern recognition system designed to predict the desired locomotion mode. Our results indicate that including the additional mechanical sensor signals decreased the error rates of the system for both steady-state and transitional steps when compared to the reduced sensor set. We also found that EMG still decreased the error rate of the system, but to a lesser extent when using the additional mechanical sensors.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129915643","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 : 2015-04-22DOI: 10.1109/NER.2015.7146607
Tianruo Guo, N. Lovell, D. Tsai, Perry Twyford, S. Fried, J. Morley, G. Suaning, S. Dokos
A retinal ganglion cell (RGC) model based on accurate biophysics and detailed representations of cell morphologies was used to understand how these cells respond to electrical stimulation over a wide range of frequencies, spanning 50-2000 pulses per second (PPS). Our modeling results and associated in vitro data both suggest the usefulness of high stimulation frequency in effectively modulating the activity of RGCs. This model can be used for optimizing varied extracellular stimulus profiles, and to assist in the design of sophisticated stimulation strategies for clinical visual neuroprostheses.
{"title":"Optimizing retinal ganglion cell responses to high-frequency electrical stimulation strategies for preferential neuronal excitation","authors":"Tianruo Guo, N. Lovell, D. Tsai, Perry Twyford, S. Fried, J. Morley, G. Suaning, S. Dokos","doi":"10.1109/NER.2015.7146607","DOIUrl":"https://doi.org/10.1109/NER.2015.7146607","url":null,"abstract":"A retinal ganglion cell (RGC) model based on accurate biophysics and detailed representations of cell morphologies was used to understand how these cells respond to electrical stimulation over a wide range of frequencies, spanning 50-2000 pulses per second (PPS). Our modeling results and associated in vitro data both suggest the usefulness of high stimulation frequency in effectively modulating the activity of RGCs. This model can be used for optimizing varied extracellular stimulus profiles, and to assist in the design of sophisticated stimulation strategies for clinical visual neuroprostheses.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130170164","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 : 2015-04-22DOI: 10.1109/NER.2015.7146670
U. K. Zhu, P. Li, G. Chai, X. Sui
Incorporation of tactile sensory feedback by non-invasive transcutaneous electrical nerve stimulation (TENS) is potentially helpful for a prosthetic hand to accomplish dexterous manipulation. As for TENS through surface electrode, the stimulating current flows directly through the conductive gel and the stratum corneum (SC) layers to activate the tactile afferent nerve fibers. In our study the specific modulation effect of recruiting afferent nerve fibers in the two layers was investigated by establishing a 3D finite element model of the forearm. The results showed that both decreasing the gel thickness and increasing the gel resistivity improved the electrical stimulation sensitivity for electrotactile feedback, which would be beneficial to lower the threshold current of TENS. Meanwhile, decreasing the SC resistivity was also beneficial to improve the electrical stimulation sensitivity, but the variations of the normal SC thickness had negligible influence on the sensitivity. On one hand, these results gave us a specific guidance for choosing appropriate property parameters for conductive gel. On the other hand, both the thickness and resistivity of SC were susceptible to age, gender, and physical conditions etc., so it was significant for us to comprehend specific modulation effect under variation of SC properties.
{"title":"Effects of stratum corneum and conductive gel properties on sensory afferents recruitment by 3D TENS computational modeling","authors":"U. K. Zhu, P. Li, G. Chai, X. Sui","doi":"10.1109/NER.2015.7146670","DOIUrl":"https://doi.org/10.1109/NER.2015.7146670","url":null,"abstract":"Incorporation of tactile sensory feedback by non-invasive transcutaneous electrical nerve stimulation (TENS) is potentially helpful for a prosthetic hand to accomplish dexterous manipulation. As for TENS through surface electrode, the stimulating current flows directly through the conductive gel and the stratum corneum (SC) layers to activate the tactile afferent nerve fibers. In our study the specific modulation effect of recruiting afferent nerve fibers in the two layers was investigated by establishing a 3D finite element model of the forearm. The results showed that both decreasing the gel thickness and increasing the gel resistivity improved the electrical stimulation sensitivity for electrotactile feedback, which would be beneficial to lower the threshold current of TENS. Meanwhile, decreasing the SC resistivity was also beneficial to improve the electrical stimulation sensitivity, but the variations of the normal SC thickness had negligible influence on the sensitivity. On one hand, these results gave us a specific guidance for choosing appropriate property parameters for conductive gel. On the other hand, both the thickness and resistivity of SC were susceptible to age, gender, and physical conditions etc., so it was significant for us to comprehend specific modulation effect under variation of SC properties.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122532481","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 : 2015-04-22DOI: 10.1109/NER.2015.7146688
Rishabh Gupta, T. Falk
Affective states are typically characterized using spectral power information obtained from electroencephalography (EEG) data collected over specific brain regions. However, while experiencing a complex emotional audio-video stimuli, brain networks transfer information in a highly interactive manner. To characterize this information, we propose using graph theoretical features. Towards this end, first, we established graph theoretical features as meaningful correlates of affective states through Pearson correlation. Then we compared the classification performance of these features with that of conventional spectral power features where percentage increases in classification performance of 7% and 11% were found in arousal and valence, respectively. Moreover, feature level fusion was explored and resulted in better performance as compared to the feature sets alone thus, highlighting the complementarity of EEG graph based features and spectral powers. Overall it is hoped that this study will enhance affective state evaluation via passive brain computer interfaces, thus leading to a plethora of applications such as user experience perception modelling and affective indexing/tagging of videos, to name a few.
{"title":"Affective state characterization based on electroencephalography graph-theoretic features","authors":"Rishabh Gupta, T. Falk","doi":"10.1109/NER.2015.7146688","DOIUrl":"https://doi.org/10.1109/NER.2015.7146688","url":null,"abstract":"Affective states are typically characterized using spectral power information obtained from electroencephalography (EEG) data collected over specific brain regions. However, while experiencing a complex emotional audio-video stimuli, brain networks transfer information in a highly interactive manner. To characterize this information, we propose using graph theoretical features. Towards this end, first, we established graph theoretical features as meaningful correlates of affective states through Pearson correlation. Then we compared the classification performance of these features with that of conventional spectral power features where percentage increases in classification performance of 7% and 11% were found in arousal and valence, respectively. Moreover, feature level fusion was explored and resulted in better performance as compared to the feature sets alone thus, highlighting the complementarity of EEG graph based features and spectral powers. Overall it is hoped that this study will enhance affective state evaluation via passive brain computer interfaces, thus leading to a plethora of applications such as user experience perception modelling and affective indexing/tagging of videos, to name a few.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"83 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121315250","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 : 2015-04-22DOI: 10.1109/NER.2015.7146656
Aaron D. Gilmour, J. Goding, L. Poole-Warren, C. Thomson, R. Green
The development of the next generation electrode interfaces for neural prosthetic devices requires high-through-put multifaceted testing strategies to assess material interactions with both peripheral and central nervous system (CNS) immune cells. The utility of a primary astrocyte enriched glial cell culture was assessed as a potential in vitro tool for understanding the immune response to electrode materials. Conductive polymer consisting of electropolymerized poly(3,4-ethylenedioxythiophene) (PEDOT) doped with paratoluene sulfonate (pTS) was used as a novel electrode material and compared to the conventional electrode material, platinum (Pt). Morphology of astrocytes and microglia in contact with the materials was analyzed and compared to an immunoassay of TNFα release from human blood plasma. While all electrode materials failed to stimulate TNFα release from human leukocytes, the materials in contact with glial cells resulted in progressive reactive gliosis. This primary astrocyte in vitro assay provides insight into the degeneration of electrode performance in vivo as a result of scar tissue reactions in chronic implant devices. It also highlights the relevance of testing for immune reactions with an appropriate cell system.
{"title":"In vitro biological assessment of electrode materials for neural interfaces","authors":"Aaron D. Gilmour, J. Goding, L. Poole-Warren, C. Thomson, R. Green","doi":"10.1109/NER.2015.7146656","DOIUrl":"https://doi.org/10.1109/NER.2015.7146656","url":null,"abstract":"The development of the next generation electrode interfaces for neural prosthetic devices requires high-through-put multifaceted testing strategies to assess material interactions with both peripheral and central nervous system (CNS) immune cells. The utility of a primary astrocyte enriched glial cell culture was assessed as a potential in vitro tool for understanding the immune response to electrode materials. Conductive polymer consisting of electropolymerized poly(3,4-ethylenedioxythiophene) (PEDOT) doped with paratoluene sulfonate (pTS) was used as a novel electrode material and compared to the conventional electrode material, platinum (Pt). Morphology of astrocytes and microglia in contact with the materials was analyzed and compared to an immunoassay of TNFα release from human blood plasma. While all electrode materials failed to stimulate TNFα release from human leukocytes, the materials in contact with glial cells resulted in progressive reactive gliosis. This primary astrocyte in vitro assay provides insight into the degeneration of electrode performance in vivo as a result of scar tissue reactions in chronic implant devices. It also highlights the relevance of testing for immune reactions with an appropriate cell system.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121350280","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 : 2015-04-22DOI: 10.1109/NER.2015.7146621
Michael J. Crosse, H. ElShafei, John J. Foxe, E. Lalor
Neuroimaging research has demonstrated that observing visual speech in the absence of auditory speech activates primary auditory cortex. However, it remains unclear what this activation precisely reflects. It is well established that, during continuous auditory speech, neural activity in auditory cortex tracks the temporal envelope of the speech signal. Recently, it has been suggested that this process may in fact reflect an internal synthesis of the speech stream rather than the encoding of the envelope per se. Could silent lipreading therefore elicit a similar “entrainment” to the envelope in the absence of auditory speech? Here, we test this hypothesis by examining the impact of lipreading accuracy on envelope tracking using electroencephalography (EEG). We provide evidence to suggest that the EEG response over left temporal scalp tracks the unheard speech more faithfully during accurate lipreading. We also demonstrate that the envelope can be reconstructed from EEG data recorded during silent lipreading with accuracy above chance level. This could have implications for brain-computer interface technology.
{"title":"Investigating the temporal dynamics of auditory cortical activation to silent lipreading","authors":"Michael J. Crosse, H. ElShafei, John J. Foxe, E. Lalor","doi":"10.1109/NER.2015.7146621","DOIUrl":"https://doi.org/10.1109/NER.2015.7146621","url":null,"abstract":"Neuroimaging research has demonstrated that observing visual speech in the absence of auditory speech activates primary auditory cortex. However, it remains unclear what this activation precisely reflects. It is well established that, during continuous auditory speech, neural activity in auditory cortex tracks the temporal envelope of the speech signal. Recently, it has been suggested that this process may in fact reflect an internal synthesis of the speech stream rather than the encoding of the envelope per se. Could silent lipreading therefore elicit a similar “entrainment” to the envelope in the absence of auditory speech? Here, we test this hypothesis by examining the impact of lipreading accuracy on envelope tracking using electroencephalography (EEG). We provide evidence to suggest that the EEG response over left temporal scalp tracks the unheard speech more faithfully during accurate lipreading. We also demonstrate that the envelope can be reconstructed from EEG data recorded during silent lipreading with accuracy above chance level. This could have implications for brain-computer interface technology.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122293042","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 : 2015-04-22DOI: 10.1109/NER.2015.7146624
B. Jarrahi, D. Mantini, S. Kollias
Most stimuli in the viscera do not reach conscious perception, although they may activate some cortical structures. However, recent evidences suggest that various forms of subliminal interoceptive inputs may influence brain function. In this study, we used spatial independent component analysis (ICA) as a multivariate method to investigate the effect of interoception on the intra- and inter-network connectivity of the human brain. 15 healthy participants were scanned during the resting-state and a visceral stimulation task. Following a recently suggested ICA framework, we applied a high model order ICA of 75 to the fMRI data, and identified 34 components as non-artifactual intrinsic connectivity networks (ICNs). Results demonstrate significant intra-network connectivity difference within the salience network (SN) and the default mode network (p <; 0.05, family-wise error corrected). Significant inter-network connectivity differences were also found for several ICN pairs, most notably between the SN and the frontoparietal central executive network, and between the SN and the limbic association network (p<;0.05, false discovery rate corrected for multiple comparisons). Taken together, these observations suggest significant effect of interoception on the network connectivity architecture of the human brain especially involving the SN when compared to the resting-state baseline.
{"title":"Effect of interoception on intra- and inter-network connectivity of human brain — An independent component analysis of fMRI data","authors":"B. Jarrahi, D. Mantini, S. Kollias","doi":"10.1109/NER.2015.7146624","DOIUrl":"https://doi.org/10.1109/NER.2015.7146624","url":null,"abstract":"Most stimuli in the viscera do not reach conscious perception, although they may activate some cortical structures. However, recent evidences suggest that various forms of subliminal interoceptive inputs may influence brain function. In this study, we used spatial independent component analysis (ICA) as a multivariate method to investigate the effect of interoception on the intra- and inter-network connectivity of the human brain. 15 healthy participants were scanned during the resting-state and a visceral stimulation task. Following a recently suggested ICA framework, we applied a high model order ICA of 75 to the fMRI data, and identified 34 components as non-artifactual intrinsic connectivity networks (ICNs). Results demonstrate significant intra-network connectivity difference within the salience network (SN) and the default mode network (p <; 0.05, family-wise error corrected). Significant inter-network connectivity differences were also found for several ICN pairs, most notably between the SN and the frontoparietal central executive network, and between the SN and the limbic association network (p<;0.05, false discovery rate corrected for multiple comparisons). Taken together, these observations suggest significant effect of interoception on the network connectivity architecture of the human brain especially involving the SN when compared to the resting-state baseline.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126923121","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 : 2015-04-22DOI: 10.1109/NER.2015.7146557
A. Fiorillo, S. Pullano, M. Menniti, R. Citraro, G. Sarro, E. Russo
Hearing loss is one of the most common neural impairments and is usually due to damage to peripheral structures. The insertion of a specific electronic interface along the auditory pathway, bypassing the area of peripheral damage, can at least partially reactivate the auditory faculty. Herein, a rat brain stimulation technique based on an ultrasound system is presented. The complete system consists of two polyvinylidene-fluoride transducers and an electronic interface, which processes ultrasounds in the air mimicking what happens in the cochlea, simulating action potentials spontaneously generated by the hair cells and then sending them to the brain. The cortical response is closely connected to environmental characteristics carried out by the external stimuli presented to the inferior colliculus, bypassing the sense organ.
{"title":"A brain-to-sonar electronic interface to bypass peripheral auditory system in rats","authors":"A. Fiorillo, S. Pullano, M. Menniti, R. Citraro, G. Sarro, E. Russo","doi":"10.1109/NER.2015.7146557","DOIUrl":"https://doi.org/10.1109/NER.2015.7146557","url":null,"abstract":"Hearing loss is one of the most common neural impairments and is usually due to damage to peripheral structures. The insertion of a specific electronic interface along the auditory pathway, bypassing the area of peripheral damage, can at least partially reactivate the auditory faculty. Herein, a rat brain stimulation technique based on an ultrasound system is presented. The complete system consists of two polyvinylidene-fluoride transducers and an electronic interface, which processes ultrasounds in the air mimicking what happens in the cochlea, simulating action potentials spontaneously generated by the hair cells and then sending them to the brain. The cortical response is closely connected to environmental characteristics carried out by the external stimuli presented to the inferior colliculus, bypassing the sense organ.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127090062","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 : 2015-04-22DOI: 10.1109/NER.2015.7146732
A. A. Fedorova, S. Shishkin, Yuri O. Nuzhdin, B. Velichkovsky
We propose a novel way of robotic device control with communicative eye movements that could possibly help to solve the problem of false activations during the gaze control, known as the Midas touch problem. The proposed approach can be considered as explicitly based on communication between a human operator and a robot. Specifically, we employed gaze patterns that are characteristic for “joint attention” type of communication between two persons. “Joint attention” gaze patterns are automatized and able to convey information about object location even under a high cognitive load. Therefore, we assumed that they may make robot control with gaze more stable. In a study with 28 healthy participants who were naive to this approach most of them easily acquired robot control with “joint attention” gaze patterns. The study did not reveal higher preference for communicative type of control, possibly because the participants did not practice before the tests. We discuss potential benefits of the new approach that can be tested in future studies.
{"title":"Gaze based robot control: The communicative approach","authors":"A. A. Fedorova, S. Shishkin, Yuri O. Nuzhdin, B. Velichkovsky","doi":"10.1109/NER.2015.7146732","DOIUrl":"https://doi.org/10.1109/NER.2015.7146732","url":null,"abstract":"We propose a novel way of robotic device control with communicative eye movements that could possibly help to solve the problem of false activations during the gaze control, known as the Midas touch problem. The proposed approach can be considered as explicitly based on communication between a human operator and a robot. Specifically, we employed gaze patterns that are characteristic for “joint attention” type of communication between two persons. “Joint attention” gaze patterns are automatized and able to convey information about object location even under a high cognitive load. Therefore, we assumed that they may make robot control with gaze more stable. In a study with 28 healthy participants who were naive to this approach most of them easily acquired robot control with “joint attention” gaze patterns. The study did not reveal higher preference for communicative type of control, possibly because the participants did not practice before the tests. We discuss potential benefits of the new approach that can be tested in future studies.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126756164","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 : 2015-04-22DOI: 10.1109/NER.2015.7146782
A. Ferrante, Constantinos Gavriel, A. Faisal
EEG-based Brain Computer Interfaces (BCIs) are quite noisy brain signals recorded from the scalp (electroencephalography, EEG) to translate the user's intent into action. This is usually achieved by looking at the pattern of brain activity across many trials while the subject is imagining the performance of an instructed action - the process known as motor imagery. Nevertheless, existing motor imagery classification algorithms do not always achieve good performances because of the noisy and non-stationary nature of the EEG signal and inter-subject variability. Thus, current EEG BCI takes a considerable upfront toll on patients, who have to submit to lengthy training sessions before even being able to use the BCI. In this study, we developed a data-efficient classifier for left/right hand motor imagery by combining in our pattern recognition both the oscillation frequency range and the scalp location. We achieve this by using a combination of Morlet wavelet and Common Spatial Pattern theory to deal with nonstationarity and noise. The system achieves an average accuracy of 88% across subjects and was trained by about a dozen training (10-15) examples per class reducing the size of the training pool by up to a 100-fold, making it very data-efficient way for EEG BCI.
{"title":"Data-efficient hand motor imagery decoding in EEG-BCI by using Morlet wavelets & Common Spatial Pattern algorithms","authors":"A. Ferrante, Constantinos Gavriel, A. Faisal","doi":"10.1109/NER.2015.7146782","DOIUrl":"https://doi.org/10.1109/NER.2015.7146782","url":null,"abstract":"EEG-based Brain Computer Interfaces (BCIs) are quite noisy brain signals recorded from the scalp (electroencephalography, EEG) to translate the user's intent into action. This is usually achieved by looking at the pattern of brain activity across many trials while the subject is imagining the performance of an instructed action - the process known as motor imagery. Nevertheless, existing motor imagery classification algorithms do not always achieve good performances because of the noisy and non-stationary nature of the EEG signal and inter-subject variability. Thus, current EEG BCI takes a considerable upfront toll on patients, who have to submit to lengthy training sessions before even being able to use the BCI. In this study, we developed a data-efficient classifier for left/right hand motor imagery by combining in our pattern recognition both the oscillation frequency range and the scalp location. We achieve this by using a combination of Morlet wavelet and Common Spatial Pattern theory to deal with nonstationarity and noise. The system achieves an average accuracy of 88% across subjects and was trained by about a dozen training (10-15) examples per class reducing the size of the training pool by up to a 100-fold, making it very data-efficient way for EEG BCI.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"740 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126497273","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：