Pub Date : 2005-05-26DOI: 10.1109/ICNIC.2005.1499832
Wang Yongjil, Wang Wan, He Jiping, Huang Jian
In this paper, cortical control of virtual cursor was investigated by means of support vector machine (SVM). In SVM, the training inputs of the regression estimation are firing rates of neuronal ensembles in motor and premotor cortex, and the outputs are trajectories of virtual cursors. The regression results prove that the SVM is effective and available for simulation.
{"title":"Support vector regression for cortical control of virtual cursor","authors":"Wang Yongjil, Wang Wan, He Jiping, Huang Jian","doi":"10.1109/ICNIC.2005.1499832","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499832","url":null,"abstract":"In this paper, cortical control of virtual cursor was investigated by means of support vector machine (SVM). In SVM, the training inputs of the regression estimation are firing rates of neuronal ensembles in motor and premotor cortex, and the outputs are trajectories of virtual cursors. The regression results prove that the SVM is effective and available for simulation.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123962240","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499868
Xiao Deyun, Zongjun Wang, Rongda Chen
The paper discussed design of general measures system of investment decision-making. Measure system filtration method of benchmarking combined with principal component analysis was built in the paper. Integration model of performance evaluation of investment decision-making based on fuzzy set and neural network was devised and experimental research has been done.
{"title":"Strategic performance measurement of investment decision-making based on fuzzy set and neural network","authors":"Xiao Deyun, Zongjun Wang, Rongda Chen","doi":"10.1109/ICNIC.2005.1499868","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499868","url":null,"abstract":"The paper discussed design of general measures system of investment decision-making. Measure system filtration method of benchmarking combined with principal component analysis was built in the paper. Integration model of performance evaluation of investment decision-making based on fuzzy set and neural network was devised and experimental research has been done.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129560092","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499846
W. Ruiping, Zhang Yajing, G. Xiaorong, G. Shangkai
In binocular rivalry, a subject views two incongruent stimuli through each eye but consciously perceives only one stimulus at a time, with a switch in perceptual dominance every few seconds. To investigate the continuous alternations in perceptual dominance across eyes objectively, thirteen subjects were recorded with 64-channel electroencephalograph while experiencing binocular rivalry. A blue vertical grating flickering at one frequency was presented to one eye and a blue horizontal grating flickering at a different frequency was presented to the other eye. Steady state evoked potential (SSVEP) at the two frequencies were used as tags for the two stimuli. SSVEP-based binocular rivalry has potential advantage of registering the alternation in physiological dominance of the two eyes. This paper presents a method of lead selection to improve the applicability of SSVEP-based binocular rivalry. Optimal lead is selected by comparing signal strength at two stimulus frequencies during rivalry dominance and rivalry suppression. The method with one optimal lead correlates better with the subjects' report of perceptual dominance.
{"title":"Lead selection for SSVEP-based binocular rivalry","authors":"W. Ruiping, Zhang Yajing, G. Xiaorong, G. Shangkai","doi":"10.1109/ICNIC.2005.1499846","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499846","url":null,"abstract":"In binocular rivalry, a subject views two incongruent stimuli through each eye but consciously perceives only one stimulus at a time, with a switch in perceptual dominance every few seconds. To investigate the continuous alternations in perceptual dominance across eyes objectively, thirteen subjects were recorded with 64-channel electroencephalograph while experiencing binocular rivalry. A blue vertical grating flickering at one frequency was presented to one eye and a blue horizontal grating flickering at a different frequency was presented to the other eye. Steady state evoked potential (SSVEP) at the two frequencies were used as tags for the two stimuli. SSVEP-based binocular rivalry has potential advantage of registering the alternation in physiological dominance of the two eyes. This paper presents a method of lead selection to improve the applicability of SSVEP-based binocular rivalry. Optimal lead is selected by comparing signal strength at two stimulus frequencies during rivalry dominance and rivalry suppression. The method with one optimal lead correlates better with the subjects' report of perceptual dominance.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127015977","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499860
Y. Dezhong, Wang Ling
In the research of direct collision course, the computation of TTC, time to collision, is thought subjectively an important critical criteria. Formula /spl tau/ /spl ap/ /spl theta///spl theta/' was usually utilized to calculate TTC where /spl theta/ is the visual angle subtended by the looming object and /spl theta/' is the derivative of /spl theta/ over time. In this paper, we found that 1//spl tau/ can also be approximated by using a weighted combination of 1/(/spl theta/+B) and /spl theta/, where B is a constant. We then built a simple computational model by including an improved back propagation algorithm as a way of simulating the brain response patterns. The accurate estimation of TTC, relative definite physiological meaning of the hidden neurons, and the good plasticity and robustness of the model imply that it is a potential and realizable model and is very likely to imitate the physiological brain mechanism of the visual information processing in the direct collision course.
{"title":"Visual information processing in direct collision course - a simple computational model","authors":"Y. Dezhong, Wang Ling","doi":"10.1109/ICNIC.2005.1499860","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499860","url":null,"abstract":"In the research of direct collision course, the computation of TTC, time to collision, is thought subjectively an important critical criteria. Formula /spl tau/ /spl ap/ /spl theta///spl theta/' was usually utilized to calculate TTC where /spl theta/ is the visual angle subtended by the looming object and /spl theta/' is the derivative of /spl theta/ over time. In this paper, we found that 1//spl tau/ can also be approximated by using a weighted combination of 1/(/spl theta/+B) and /spl theta/, where B is a constant. We then built a simple computational model by including an improved back propagation algorithm as a way of simulating the brain response patterns. The accurate estimation of TTC, relative definite physiological meaning of the hidden neurons, and the good plasticity and robustness of the model imply that it is a potential and realizable model and is very likely to imitate the physiological brain mechanism of the visual information processing in the direct collision course.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129186709","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499836
S. Xie, C. Gao, Z.L. Yang, R.Y. Wang
As software running on computer, mental activities of human brain may entry a dead loop too. Computer-brain interfaces give computers special channels to detect and interfere to interrupt unwanted thoughts which induce unpleasant intrusive thoughts and uncontrollable worry. In the present study, we intend to develop a noninterference and non-wake-up solution to detect and interrupt those unwanted thoughts which extend the transition from waking to sleeping. When an appropriate stimulus serial is given by this embedded computer according to subject brain state, it is possible that inhibition of the fluctuation-thought sources would be sustained until the sources are inactivated finally. The most important part of our solution is a small, wrist-watch like embedded computer which is based on VxWorks real time operation system and ARM processor. The operations of computer-brain interface are all completed by this computer which is noninterference and non-wake-up. By using this novel solution to interrupt unpleasant intrusive thoughts and excessive and uncontrollable worry during the pre-sleep period, in small sample trials, we have improved the measurement precision of sleep onset from more than ten minutes to about 6 seconds, and controlled unwanted thoughts efficiently.
{"title":"Computer-brain interface","authors":"S. Xie, C. Gao, Z.L. Yang, R.Y. Wang","doi":"10.1109/ICNIC.2005.1499836","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499836","url":null,"abstract":"As software running on computer, mental activities of human brain may entry a dead loop too. Computer-brain interfaces give computers special channels to detect and interfere to interrupt unwanted thoughts which induce unpleasant intrusive thoughts and uncontrollable worry. In the present study, we intend to develop a noninterference and non-wake-up solution to detect and interrupt those unwanted thoughts which extend the transition from waking to sleeping. When an appropriate stimulus serial is given by this embedded computer according to subject brain state, it is possible that inhibition of the fluctuation-thought sources would be sustained until the sources are inactivated finally. The most important part of our solution is a small, wrist-watch like embedded computer which is based on VxWorks real time operation system and ARM processor. The operations of computer-brain interface are all completed by this computer which is noninterference and non-wake-up. By using this novel solution to interrupt unpleasant intrusive thoughts and excessive and uncontrollable worry during the pre-sleep period, in small sample trials, we have improved the measurement precision of sleep onset from more than ten minutes to about 6 seconds, and controlled unwanted thoughts efficiently.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129394670","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499839
Jin-an Guan, Yaguang Chen, Jiarui Lin, YunYuan, Ming Huang
A mental speller using brain computer interface (BCI) may allow a user to communicate by gazing at a virtual keyboard on the screen to select a desired character to compose a word, and thus sentences. Different from other paradigms, a so called imitating-natural-reading (INR) modality was exploited to construct a novel mental speller-INR SPELLER. In order to boost the bit rate, a 300ms window was used to estimate the accurate time of target stimuli onset from EEG signals. To meet this task, N2 components of visual evoked potentials (VEP) were investigated. Experimental results indicated that the object-specified component can be estimated in single trial at an accuracy of 90.5% with support vector machine (SVM) classifier.
{"title":"N2 components as features for brain computer interface","authors":"Jin-an Guan, Yaguang Chen, Jiarui Lin, YunYuan, Ming Huang","doi":"10.1109/ICNIC.2005.1499839","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499839","url":null,"abstract":"A mental speller using brain computer interface (BCI) may allow a user to communicate by gazing at a virtual keyboard on the screen to select a desired character to compose a word, and thus sentences. Different from other paradigms, a so called imitating-natural-reading (INR) modality was exploited to construct a novel mental speller-INR SPELLER. In order to boost the bit rate, a 300ms window was used to estimate the accurate time of target stimuli onset from EEG signals. To meet this task, N2 components of visual evoked potentials (VEP) were investigated. Experimental results indicated that the object-specified component can be estimated in single trial at an accuracy of 90.5% with support vector machine (SVM) classifier.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126685788","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499854
Su Xiaohong, Pei Weihua, Gu Ming, Liu Jin-bin, Chen Hongda
A novel CMOS-based preamplifier for amplifying brain neural signal obtained by scalp electrodes in brain-computer interface (BCI) is presented in this paper. By means of constructing effective equivalent input circuit structure of the preamplifier, two capacitors of 5 pF are included to realize the DC suppression compared to conventional preamplifiers. Then this preamplifier is designed and simulated using the standard 0.6 /spl mu/m CMOS process technology model parameters with a supply voltage of 5 volts. With differential input structures adopted, simulation results of the preamplifier show that the input impedance amounts to more than 2 Gohm with brain neural signal frequency of 0.5 Hz-100 Hz. The equivalent input noise voltage is 18 nV/Hz/sup 1/2 /. The common mode rejection ratio (CMRR) of 112 dB and the open-loop differential gain of 90 dB are achieved.
{"title":"Circuit design and simulation of a CMOS-based preamplifier for brain neural signals","authors":"Su Xiaohong, Pei Weihua, Gu Ming, Liu Jin-bin, Chen Hongda","doi":"10.1109/ICNIC.2005.1499854","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499854","url":null,"abstract":"A novel CMOS-based preamplifier for amplifying brain neural signal obtained by scalp electrodes in brain-computer interface (BCI) is presented in this paper. By means of constructing effective equivalent input circuit structure of the preamplifier, two capacitors of 5 pF are included to realize the DC suppression compared to conventional preamplifiers. Then this preamplifier is designed and simulated using the standard 0.6 /spl mu/m CMOS process technology model parameters with a supply voltage of 5 volts. With differential input structures adopted, simulation results of the preamplifier show that the input impedance amounts to more than 2 Gohm with brain neural signal frequency of 0.5 Hz-100 Hz. The equivalent input noise voltage is 18 nV/Hz/sup 1/2 /. The common mode rejection ratio (CMRR) of 112 dB and the open-loop differential gain of 90 dB are achieved.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127044364","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499849
Xiong Xinbing, Chen Yaguang
This paper proposed a new approach in order to reduce the number of trials required for the extraction of the brain event related potentials (ERPs). The approach is developed by combining both the subspace methods and wavelet transform. The first step is to estimate the signal subspace by applying the singular value decomposition (SVD) and orthonormally projecting the raw data onto the estimated signal subspace to obtain an enhanced version. At the same time it whitened the colored noise. Next, the ERPs are extracted by wavelet denoising from the enhanced version. Simulation results show that combination of both two methods provides much better capability than each of them separately. The results of experiments showed that the practical processed results were effective.
{"title":"Efficient extraction of event related potentials by the combination of subspace method and wavelet transform","authors":"Xiong Xinbing, Chen Yaguang","doi":"10.1109/ICNIC.2005.1499849","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499849","url":null,"abstract":"This paper proposed a new approach in order to reduce the number of trials required for the extraction of the brain event related potentials (ERPs). The approach is developed by combining both the subspace methods and wavelet transform. The first step is to estimate the signal subspace by applying the singular value decomposition (SVD) and orthonormally projecting the raw data onto the estimated signal subspace to obtain an enhanced version. At the same time it whitened the colored noise. Next, the ERPs are extracted by wavelet denoising from the enhanced version. Simulation results show that combination of both two methods provides much better capability than each of them separately. The results of experiments showed that the practical processed results were effective.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128291701","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499866
Yiran Zhai, D. Yao
A moderate scale approach of the realistic geometry spline Laplacian (MSL) for high-resolution EEG mapping was proposed. In this approach, firstly find the neighboring electrodes of one electrode on the scalp surface within a chosen radius, use their spatial coordinates and potentials to generate a regional spline interpolated potential distribution function, and then estimate the surface Laplacian of this electrode position using Laplacian differentiation operation. The effects of MSL and the global realistic geometry spline Laplacian (GSL) were compared by computer simulation studies using a realistic head model and by human visual evoked potential data. All the results show MSL can provide better results than that do by GSL.
{"title":"Realistic geometry Laplacian: a moderate spline estimation approach","authors":"Yiran Zhai, D. Yao","doi":"10.1109/ICNIC.2005.1499866","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499866","url":null,"abstract":"A moderate scale approach of the realistic geometry spline Laplacian (MSL) for high-resolution EEG mapping was proposed. In this approach, firstly find the neighboring electrodes of one electrode on the scalp surface within a chosen radius, use their spatial coordinates and potentials to generate a regional spline interpolated potential distribution function, and then estimate the surface Laplacian of this electrode position using Laplacian differentiation operation. The effects of MSL and the global realistic geometry spline Laplacian (GSL) were compared by computer simulation studies using a realistic head model and by human visual evoked potential data. All the results show MSL can provide better results than that do by GSL.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117189528","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 : 2005-05-26DOI: 10.1109/ICNIC.2005.1499829
Mingui Sun, D. Li, Jun Zhao, P. Roche, B. Wessel, R. Sclabassi
Implantable neural devices have many therapeutic, diagnostic, and prosthetic applications. Although there have been exciting developments in constructing these devices, two critical problems, data communication between the implanted device and external computers as well as electrical power to the device, have not yet been solved. We investigate these problems using the volume conduction properties of the human body. A prototype implantable device is constructed equipped with a volume conduction data communication channel. A new power delivery antenna is conceptualized, inspired by a study of the power delivery mechanisms of electric fish. Our investigation indicates that the volume conduction resources within the human body may provide a powerful solution to both problems.
{"title":"Biological resources within the human body can be used to operate neural implants","authors":"Mingui Sun, D. Li, Jun Zhao, P. Roche, B. Wessel, R. Sclabassi","doi":"10.1109/ICNIC.2005.1499829","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499829","url":null,"abstract":"Implantable neural devices have many therapeutic, diagnostic, and prosthetic applications. Although there have been exciting developments in constructing these devices, two critical problems, data communication between the implanted device and external computers as well as electrical power to the device, have not yet been solved. We investigate these problems using the volume conduction properties of the human body. A prototype implantable device is constructed equipped with a volume conduction data communication channel. A new power delivery antenna is conceptualized, inspired by a study of the power delivery mechanisms of electric fish. Our investigation indicates that the volume conduction resources within the human body may provide a powerful solution to both problems.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121157112","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：