{"title":"Design of a radial basis function neural network for attention tasks event related potentials extraction","authors":"L. Mingyu, Wang Jue, Yan Nan","doi":"10.1109/ICNIC.2005.1499852","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499852","url":null,"abstract":"Electroencephalogram (EEG) based biofeedback is widely employed to treat certain kinds of diseases especially Attention Deficit Hyperactivity Disorder (ADD/ADHD). Thus to design a system capable of learning a particular mapping between EEG features and different attention-level mental tasks is of great significance. Event Related Potentials (ERP) is such a powerful feature which is traditionally extracted by averaging. The paper proposed a new ERP extraction algorithm using radial basis function (RBF) neural network. It discussed the configuration, learning and running of the designed network. In order to reduce computational complexity and the influence of noise in estimating ERP, the partial least square regression was introduced to train the RBF network. Series experiments showed that the method is effective and is suitable for single-trail ERP estimation.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"26 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":"131054960","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}
{"title":"Research on non-invasive measurement for the early diagnosis of diabetic peripheral neuropathy","authors":"Chen Haifeng, Dengqinkai","doi":"10.1109/ICNIC.2005.1499847","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499847","url":null,"abstract":"Various complications cause the main damage of diabetic mellitus (DM). Diabetic peripheral neuropathy (DPN) is one of the most common syndromes of the DM. Based on the clinic requirement, we develop a new instrument and do research on non-invasive measurement for the early diagnosis of the DPN by nerve conduction studies. Our work is consisted of two parts: (1) combining the virtual instrument technology with single chip microcomputer (SCM) module to make an instrument for non-invasive measurement; (2) doing clinic tests to find the quantitative indices of nerve electrophysiological characters for the early diagnosis of DPN by statistics. The prototype instrument is composed of two parts: SCM module and PC. The weak nerve conduction signals in company with strong noise are processed and recognized by signal averaging and cross correlation. The operating software is designed by the virtual instrument workbench-LabVIEW. 60 DM patients were examined by the prototype instrument to collect the electrophysiological parameters. We concluded that the SCV of the sural nerve and the minimal F-wave latency of the fibular nerve have a higher degree of sensitivity in the early diagnosis of DPN by statistic. By the discriminative analysis, we find the consistency of some electrophysiological data with clinic criteria.","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":"131077306","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}
{"title":"Improved cable function to represent the excitation of peripheral nerves","authors":"Yu Hui, Z. Chong-xun, Wang Yi","doi":"10.1109/ICNIC.2005.1499861","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499861","url":null,"abstract":"The classical cable function has been used to represent the response of peripheral nerves stimulated by an external parallel electric field. This function cannot describe the excitation of peripheral nerves stimulated by a perpendicular electric field. In the present paper, responses of the Ranvier nodes to a transverse-field are thoroughly investigated by mathematic simulation. This simulation demonstrates that the excitation results from the net inward current driven by an external field. Based on a two-stage process, a novel model is introduced to describe peripheral nerves stimulated by a transverse-field, and the classical cable function is modified. Using this modified cable equation, the excitation threshold of peripheral nerves in a transverse field during MS is obtained. The modified cable equation can be used to represent the response of peripheral nerves by an arbitrary electric field.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"44 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":"132308762","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}
{"title":"Controlling epileptic seizures EEG with a dynamic neural population model","authors":"X. Tian, Zhenguo Xiao, X. Geng","doi":"10.1109/ICNIC.2005.1499882","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499882","url":null,"abstract":"In this study a dynamic neural population model between brain stem, cortex and thalamus circuits is established on mesoscopic level using Matlab/Simulink. The electric activities in brain circuits are simulated with the model output. The output signals are the derivatives of postsynaptic potentials from thalamus, which are reflected in EEG for both normal and epileptic seizures cases. The epileptic seizures EEG are simulated and then controlled to normal level in the model via an added perturbation to the cortex or sensory. Because the brain activity is naturally chaotic, the correlation dimension of the output signal is used to test the brainstem dysfunction.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"45 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":"115236676","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}
{"title":"New evolutionary neural networks","authors":"Wei Gao","doi":"10.1109/ICNIC.2005.1499869","DOIUrl":"https://doi.org/10.1109/ICNIC.2005.1499869","url":null,"abstract":"The evolutionary neural network can be generated combining the evolutionary computation and neural network. Based on analysis of merits and demerits of previously proposed evolutionary neural network models, combining the immunized evolutionary programming proposed by author and BP neural network, a new evolutionary neural network model whose architecture and connection weights evolve simultaneously is proposed. At last, through the typical XOR problem, the new model is compared and analyzed with BP neural network and traditional evolutionary neural network. The computing results show that the precision and efficiency of the new model are all good.","PeriodicalId":169717,"journal":{"name":"Proceedings. 2005 First International Conference on Neural Interface and Control, 2005.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115705351","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}