Wireless ambulatory EEG (AEEG) monitoring over long periods of time is currently infeasible due to battery limitations and the EEG analysis time required. A detailed comparison of methods for reducing the amount of AEEG data is presented. It is concluded that a discontinuous recording scheme can alleviate both of the above problems. Discontinuous monitoring introduces data interpretation and practical issues which are discussed. With suitable low power algorithm implementations and realistic system expectations such systems are deemed to be feasible.
{"title":"Data reduction techniques to facilitate wireless and long term AEEG epilepsy monitoring","authors":"A. Casson, E. Rodríguez-Villegas","doi":"10.1109/CNE.2007.369670","DOIUrl":"https://doi.org/10.1109/CNE.2007.369670","url":null,"abstract":"Wireless ambulatory EEG (AEEG) monitoring over long periods of time is currently infeasible due to battery limitations and the EEG analysis time required. A detailed comparison of methods for reducing the amount of AEEG data is presented. It is concluded that a discontinuous recording scheme can alleviate both of the above problems. Discontinuous monitoring introduces data interpretation and practical issues which are discussed. With suitable low power algorithm implementations and realistic system expectations such systems are deemed to be feasible.","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133153744","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}
Brain-computer interface (BCI) systems allow the user to interact with a computer by merely thinking. Successful BCI operation depends on the continuous adaptation of the system to the user. This paper presents an implementation of this adaptation using incremental support vector machines (SVM). This approach is tested on three subjects and three types of mental activities across ten sessions. The results show that the continuous adaptation of the BCI to the user's brain activity brings clear advantages over a non-adapting approach.
{"title":"BCI adaptation using incremental-SVM learning","authors":"Gary Garcia Molina","doi":"10.1109/CNE.2007.369679","DOIUrl":"https://doi.org/10.1109/CNE.2007.369679","url":null,"abstract":"Brain-computer interface (BCI) systems allow the user to interact with a computer by merely thinking. Successful BCI operation depends on the continuous adaptation of the system to the user. This paper presents an implementation of this adaptation using incremental support vector machines (SVM). This approach is tested on three subjects and three types of mental activities across ten sessions. The results show that the continuous adaptation of the BCI to the user's brain activity brings clear advantages over a non-adapting approach.","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129328676","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}
A novel penetrating microelectrode array was designed and fabricated for the purpose of recording activity in the hippocampus of mice. The array allows two dimensional recording of 64 simultaneous sites of the hippocampus, in vitro. Traditional surface electrode arrays, although easy to fabricate, do not penetrate to the active tissue of hippocampus slices and thus theoretically have a lower signal/noise ratio and lower selectivity than a penetrating array. Furthermore, the structure of the hippocampus slice preparation results in dead tissue in closest proximity to these traditional electrodes and the cell bodies of the CA1 region are obscured by them, degrading activity-based optical imaging techniques as well. An array of 64 electrode posts was fabricated in silicon and bonded to a clear glass substrate. The impedance of the electrodes was measured to be approximately 1.5M Ohms + -500Ohms. The signal to noise ratio was measured and found to be 19.4 +/-3 dB compared to 3.9 +/-0.8 dB S/N for signals obtained with voltage sensitive dye RH414. These data suggest that the penetrating electrode array is superior to that of the voltage sensitive dye technique for two-dimensional recording.
{"title":"A Transparent Penetrating Microelectrode Array for in-vitro Hippocampus Recording","authors":"A. Kibler, B. Jamieson, D. Durand","doi":"10.1109/CNE.2007.369664","DOIUrl":"https://doi.org/10.1109/CNE.2007.369664","url":null,"abstract":"A novel penetrating microelectrode array was designed and fabricated for the purpose of recording activity in the hippocampus of mice. The array allows two dimensional recording of 64 simultaneous sites of the hippocampus, in vitro. Traditional surface electrode arrays, although easy to fabricate, do not penetrate to the active tissue of hippocampus slices and thus theoretically have a lower signal/noise ratio and lower selectivity than a penetrating array. Furthermore, the structure of the hippocampus slice preparation results in dead tissue in closest proximity to these traditional electrodes and the cell bodies of the CA1 region are obscured by them, degrading activity-based optical imaging techniques as well. An array of 64 electrode posts was fabricated in silicon and bonded to a clear glass substrate. The impedance of the electrodes was measured to be approximately 1.5M Ohms + -500Ohms. The signal to noise ratio was measured and found to be 19.4 +/-3 dB compared to 3.9 +/-0.8 dB S/N for signals obtained with voltage sensitive dye RH414. These data suggest that the penetrating electrode array is superior to that of the voltage sensitive dye technique for two-dimensional recording.","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121703963","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}
T. Solis-Escalante, G. Gentiletti, O. Yáñez-Suárez
In this work we evaluated a method for detection of steady-state visual evoked potentials in one-second EEG recordings, based on the multisignal classification (MUSIC) algorithm and support vector machine classification. Three experiments were carried out to test the performance of the method and its applicability for BCI related tasks. The first experiment showed the advantages of using pseudo-spectral features derived from MUSIC over DFT-based detection, using synthetic data within a range of SNR values. A second experiment tested classification of pseudo-spectral features in a dual checkerboard stimuli condition. Finally, a third experiment with ten subjects included an additional no-stimulus condition to be detected. Results showed a faster and more accurate performance for the two- and three-class problems than previously reported DFT-based approaches.
{"title":"Detection of Steady-State Visual Evoked Potentials based on the Multisignal Classification Algorithm","authors":"T. Solis-Escalante, G. Gentiletti, O. Yáñez-Suárez","doi":"10.1109/CNE.2007.369642","DOIUrl":"https://doi.org/10.1109/CNE.2007.369642","url":null,"abstract":"In this work we evaluated a method for detection of steady-state visual evoked potentials in one-second EEG recordings, based on the multisignal classification (MUSIC) algorithm and support vector machine classification. Three experiments were carried out to test the performance of the method and its applicability for BCI related tasks. The first experiment showed the advantages of using pseudo-spectral features derived from MUSIC over DFT-based detection, using synthetic data within a range of SNR values. A second experiment tested classification of pseudo-spectral features in a dual checkerboard stimuli condition. Finally, a third experiment with ten subjects included an additional no-stimulus condition to be detected. Results showed a faster and more accurate performance for the two- and three-class problems than previously reported DFT-based approaches.","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125432935","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}
J. Löfhede, N. Löfgren, M. Thordstein, A. Flisberg, I. Kjellmer, K. Lindecrantz
A support vector machine (SVM) was trained to distinguish bursts from suppression in burst-suppression EEG, using five features inherent in the electro-encephalogram (EEG) as input. The study was based on data from six full term infants who had suffered from perinatal asphyxia, and the machine was trained with reference classifications made by an experienced electroencephalographer. The results show that the method may be useful, but that differences between patients in the data set makes optimization of the system difficult
{"title":"Classifying Burst and Suppression in the EEG of Post Asphyctic Newborns using a Support Vector Machine","authors":"J. Löfhede, N. Löfgren, M. Thordstein, A. Flisberg, I. Kjellmer, K. Lindecrantz","doi":"10.1109/CNE.2007.369752","DOIUrl":"https://doi.org/10.1109/CNE.2007.369752","url":null,"abstract":"A support vector machine (SVM) was trained to distinguish bursts from suppression in burst-suppression EEG, using five features inherent in the electro-encephalogram (EEG) as input. The study was based on data from six full term infants who had suffered from perinatal asphyxia, and the machine was trained with reference classifications made by an experienced electroencephalographer. The results show that the method may be useful, but that differences between patients in the data set makes optimization of the system difficult","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130176405","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}
N. R. Srivastava, P. Troyk, G. Dagnelie, D. Bradley
Earlier experiments in the field of cortical visual prosthesis have shown the possibility of generation of phosphenes. Experiments have been performed with different types of electrodes, researchers have found the stimulation parameters required to elicit a phosphene and they have shown the possibility of targeting different areas of visual cortex to elicit phosphenes. Experiments have not been conducted in which an image was captured and processed in real time, and an array of electrodes stimulated, corresponding to the image, to generate a sense of vision. Development of a prosthetic device faces the crucial question whether a practical number of cortical stimulating electrodes can provide a useful sense of vision. We aim to answer this question by designing a wearable cortical prosthesis device and testing it on blind human volunteers. Before we implant this device in human volunteers, we want to estimate the performance we might expect from a human implantation. We are planning to conduct psychophysical tests on normally-sighted humans and stimulation tests on non-human primates. Results from these experiments will help us understand what we should expect from implantation in a human volunteer.
{"title":"Test Setup for Supporting Human Implantation of Intracortical Visual Prosthesis Device","authors":"N. R. Srivastava, P. Troyk, G. Dagnelie, D. Bradley","doi":"10.1109/CNE.2007.369704","DOIUrl":"https://doi.org/10.1109/CNE.2007.369704","url":null,"abstract":"Earlier experiments in the field of cortical visual prosthesis have shown the possibility of generation of phosphenes. Experiments have been performed with different types of electrodes, researchers have found the stimulation parameters required to elicit a phosphene and they have shown the possibility of targeting different areas of visual cortex to elicit phosphenes. Experiments have not been conducted in which an image was captured and processed in real time, and an array of electrodes stimulated, corresponding to the image, to generate a sense of vision. Development of a prosthetic device faces the crucial question whether a practical number of cortical stimulating electrodes can provide a useful sense of vision. We aim to answer this question by designing a wearable cortical prosthesis device and testing it on blind human volunteers. Before we implant this device in human volunteers, we want to estimate the performance we might expect from a human implantation. We are planning to conduct psychophysical tests on normally-sighted humans and stimulation tests on non-human primates. Results from these experiments will help us understand what we should expect from implantation in a human volunteer.","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"03 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127341000","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}
Based on Gibbs sampling, a novel method to identify mathematical models of neural activity in response to temporal changes of behavioral or cognitive state is presented. This work is motivated by the developing field of neural prosthetics, where a supervisory controller is required to classify activity of a brain region into suitable discrete modes. Here, neural activity in each discrete mode is modeled with nonstationary point processes, and transitions between modes are modeled as hidden Markov models. The effectiveness of this framework is first demonstrated on a simulated example. The identification algorithm is then applied to extracellular neural activity recorded from multi-electrode arrays in the parietal reach region of a rhesus monkey, and the results demonstrate the ability to decode discrete changes even from small data sets
{"title":"Learning Hybrid System Models for Supervisory Decoding of Discrete State, with applications to the Parietal Reach Region","authors":"N. Hudson, J. Burdick","doi":"10.1109/CNE.2007.369741","DOIUrl":"https://doi.org/10.1109/CNE.2007.369741","url":null,"abstract":"Based on Gibbs sampling, a novel method to identify mathematical models of neural activity in response to temporal changes of behavioral or cognitive state is presented. This work is motivated by the developing field of neural prosthetics, where a supervisory controller is required to classify activity of a brain region into suitable discrete modes. Here, neural activity in each discrete mode is modeled with nonstationary point processes, and transitions between modes are modeled as hidden Markov models. The effectiveness of this framework is first demonstrated on a simulated example. The identification algorithm is then applied to extracellular neural activity recorded from multi-electrode arrays in the parietal reach region of a rhesus monkey, and the results demonstrate the ability to decode discrete changes even from small data sets","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127366591","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}
UT Dallas, Erik Jonsson, Hussnain Ali, Philip C Loizou
Currently researchers interested in developing new signal processing algorithms for commercially available cochlear implants must rely on coding these algorithms in low-level assembly language. We propose a personal digital assistant (PDA) based research platform for developing and testing in real-time new signal processing strategies for cochlear implants. Software development can be done either in C or in LabVIEW. The C implementation can be further optimized using Intel's primitive routines. In this paper, we report on the real-time implementation of a 16-channel noise-band vocoder algorithm, which is a similar algorithm used in commercially available implant processors. We further report on EEG recordings on the PDA acquired through a compact-flash data acquisition card.
{"title":"A PDA-based Research Platform for Cochlear Implants","authors":"UT Dallas, Erik Jonsson, Hussnain Ali, Philip C Loizou","doi":"10.1109/CNE.2007.369603","DOIUrl":"https://doi.org/10.1109/CNE.2007.369603","url":null,"abstract":"Currently researchers interested in developing new signal processing algorithms for commercially available cochlear implants must rely on coding these algorithms in low-level assembly language. We propose a personal digital assistant (PDA) based research platform for developing and testing in real-time new signal processing strategies for cochlear implants. Software development can be done either in C or in LabVIEW. The C implementation can be further optimized using Intel's primitive routines. In this paper, we report on the real-time implementation of a 16-channel noise-band vocoder algorithm, which is a similar algorithm used in commercially available implant processors. We further report on EEG recordings on the PDA acquired through a compact-flash data acquisition card.","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127929261","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}
The problem of identifying plasticity in a recorded neural population has long been the subject of intense research. With the ability to simultaneously record large ensembles of single unit activity over extended periods of time, it is becoming central to the ability to efficiently decode neuronal responses. In a previous study, we demonstrated that a graph theoretic approach can identify functional interdependency between neurons responding to a common input over multiple time scales. In this paper, we investigate the performance of the technique when both functional and structural plasticity arise post stimulus presentation. Three types of interactions between neurons are considered; auto-inhibition, cross-inhibition, and excitation. We report the clustering performance of the approach applied to three distinct probabilistic models of networks with different topologies
{"title":"Tracking Plasticity in Probabilistic Spike Trains Models of Synaptically-Coupled Neural Population","authors":"S. El Dawlatly, K. Oweiss","doi":"10.1109/CNE.2007.369718","DOIUrl":"https://doi.org/10.1109/CNE.2007.369718","url":null,"abstract":"The problem of identifying plasticity in a recorded neural population has long been the subject of intense research. With the ability to simultaneously record large ensembles of single unit activity over extended periods of time, it is becoming central to the ability to efficiently decode neuronal responses. In a previous study, we demonstrated that a graph theoretic approach can identify functional interdependency between neurons responding to a common input over multiple time scales. In this paper, we investigate the performance of the technique when both functional and structural plasticity arise post stimulus presentation. Three types of interactions between neurons are considered; auto-inhibition, cross-inhibition, and excitation. We report the clustering performance of the approach applied to three distinct probabilistic models of networks with different topologies","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128939039","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}
N. Ince, M. Stephane, A. Tewfik, G. Pellizzer, K. McClannahan
In this paper we investigate the use of event related desynchronization (ERD) and synchronization (ERS) patterns extracted from magnetoencephalogram (MEG) in a working memory task to discriminate between controls and patients with schizophrenia. In the experimental paradigm, sequential letters appearing on a screen are memorized by subjects. In one of two conditions the letters constituted a word. The ERD and ERS patterns are extracted in the theta, alpha, beta and gamma bands from 248 electrode locations covering the whole head. We noticed that most of the ERD patterns are localized on the left frontotemporal area in both word and nonword conditions in the late memorization stage. The beta band showed the most significant difference in this cortical area between controls and schizophrenia patients. By using a decision tree, 94.7% and 87.5% classification accuracy was obtained for controls and patients individually in both word and nonword conditions. Furthermore, we report that on the left frontotemporal lobe, the discrimination within the beta band between patients and controls in the word condition was higher than in the nonword condition. The higher discrimination within the word condition can be linked to the abnormalities in language processing in schizophrenia patients. Our results show that the ERD/ERS patterns extracted from MEG can be successfully used in patient-control discrimination with appropriate adjustment of spatial, spectral, temporal and functional process parameters
{"title":"Schizophrenia Classification using Working Memory MEG ERD/ERS Patterns","authors":"N. Ince, M. Stephane, A. Tewfik, G. Pellizzer, K. McClannahan","doi":"10.1109/CNE.2007.369708","DOIUrl":"https://doi.org/10.1109/CNE.2007.369708","url":null,"abstract":"In this paper we investigate the use of event related desynchronization (ERD) and synchronization (ERS) patterns extracted from magnetoencephalogram (MEG) in a working memory task to discriminate between controls and patients with schizophrenia. In the experimental paradigm, sequential letters appearing on a screen are memorized by subjects. In one of two conditions the letters constituted a word. The ERD and ERS patterns are extracted in the theta, alpha, beta and gamma bands from 248 electrode locations covering the whole head. We noticed that most of the ERD patterns are localized on the left frontotemporal area in both word and nonword conditions in the late memorization stage. The beta band showed the most significant difference in this cortical area between controls and schizophrenia patients. By using a decision tree, 94.7% and 87.5% classification accuracy was obtained for controls and patients individually in both word and nonword conditions. Furthermore, we report that on the left frontotemporal lobe, the discrimination within the beta band between patients and controls in the word condition was higher than in the nonword condition. The higher discrimination within the word condition can be linked to the abnormalities in language processing in schizophrenia patients. Our results show that the ERD/ERS patterns extracted from MEG can be successfully used in patient-control discrimination with appropriate adjustment of spatial, spectral, temporal and functional process parameters","PeriodicalId":427054,"journal":{"name":"2007 3rd International IEEE/EMBS Conference on Neural Engineering","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127835609","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：