一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號碼
標(biāo)題
留言內(nèi)容
驗證碼

Chernof f加權(quán)分類器框架在運動想象腦-機(jī)接口中的應(yīng)用

譚平,  劉利枚,  郭璠,  周開軍

譚平, 劉利枚, 郭璠, 周開軍. Chernof f加權(quán)分類器框架在運動想象腦-機(jī)接口中的應(yīng)用[J]. 電子與信息學(xué)報, 2020, 42(2): 488-494. doi: 10.11999/JEIT181132
引用本文: 譚平, 劉利枚, 郭璠, 周開軍. Chernof f加權(quán)分類器框架在運動想象腦-機(jī)接口中的應(yīng)用[J]. 電子與信息學(xué)報, 2020, 42(2): 488-494. doi: 10.11999/JEIT181132
Ping TAN, Limei LIU, Fan GUO, Kaijun ZHOU. Applying Chernoff Weighted Classification Frame Method to MotorImagery Brain Computer Interface[J]. Journal of Electronics & Information Technology, 2020, 42(2): 488-494. doi: 10.11999/JEIT181132
Citation: Ping TAN, Limei LIU, Fan GUO, Kaijun ZHOU. Applying Chernoff Weighted Classification Frame Method to MotorImagery Brain Computer Interface[J]. Journal of Electronics & Information Technology, 2020, 42(2): 488-494. doi: 10.11999/JEIT181132

Chernof f加權(quán)分類器框架在運動想象腦-機(jī)接口中的應(yīng)用

doi: 10.11999/JEIT181132
  • 1.

    湖南工商大學(xué)新零售虛擬現(xiàn)實技術(shù)湖南省重點實驗室 長沙 410205

  • 2.

    中南大學(xué)自動化學(xué)院 長沙 410083

基金項目: 國家自然科學(xué)基金(61502537)，國家社科基金(19BGL111)，湖南省教育廳科學(xué)研究優(yōu)秀青年項目(18B338)，湖南省重點實驗室開放研究基金項目(2017TP1026)，教育部人文社科基金(14YJCZH099)
詳細(xì)信息
    作者簡介:

    譚平：男，1981年生，講師，主要研究方向為腦電信號處理、計算智能、模式識別

    劉利枚：女，1975年生，教授，主要研究方向為人工智能、機(jī)器人

    郭璠：女，1982年生，副教授，主要研究方向為圖像增強(qiáng)、機(jī)器視覺、模式識別

    周開軍：男，1978年生，副教授，主要研究方向為機(jī)器視覺、模式識別

    通訊作者:

    郭璠　guofancsu@163.com

  • 中圖分類號: R741.044;?TP391

Applying Chernoff Weighted Classification Frame Method to MotorImagery Brain Computer Interface

  • 1.

    Key Laboratory of Hunan Province for New Retail Virtual Reality Technology, Hunan University ofTechnology and Business, Changsha 410205, China

  • 2.

    School of Automation, Central South University, Changsha 410083, China

Funds: The National Natural Science Foundation of China (61502537), The National Social Science Foundation of China (19BGL111), The Scientific Research Project of the Education Department of Hunan Province (18B338), The Open Fund of Key Laboratory of Hunan Province (2017TP1026), The Foundation of Ministry of Education Humanities and Social Sciences (14YJCZH099)
  • 摘要:

    針對現(xiàn)有腦機(jī)接口(BCI)分類器與大腦認(rèn)知過程結(jié)合不夠緊密的問題，該文提出一種基于Chernoff加權(quán)的分類器集成框架方法，并用于同步運動想象腦機(jī)接口中。通過對訓(xùn)練數(shù)據(jù)進(jìn)行統(tǒng)計分析，獲得各時刻腦電信號(EEG)的統(tǒng)計特性，并建立基于大腦認(rèn)知過程的高斯概率模型。然后利用Chernoff邊界特性得到該概率模型的最小誤差，并以此確定該時刻分類器的權(quán)重，通過對各時刻分類器的加權(quán)，實現(xiàn)同步腦機(jī)接口的信號分類。以腦機(jī)接口競賽數(shù)據(jù)作為測試，并與線性判決分析、支持向量機(jī)和極限學(xué)習(xí)方法分別結(jié)合構(gòu)成新的集成方法。由實驗結(jié)果可知，加權(quán)集成框架方法的分類性能比原獨立分類方法有顯著提高。

    Abstract:

    For the problem that the classifier is less considered to be combined with the brain's cognitive process in the Brain-Computer Interface (BCI) system, a Chernoff-weighted based classifier integrated frame method is proposed and used in synchronous motor imagery BCI. In the method, the statistic characteristics of ElectroEncephaloGraphy (EEG) are obtained by analyzing in each time point of synchronous BCI, and then the probability model is established to compute the Chernoff error bound, which is adopted as the weight of common classifier to take the discriminant process. The test experiments are based on the datasets from BCI competitions, and the proposed frame method is employed to compose with LDA, SVM, ELM respectively. The experimental results demonstrate that the proposed frame method shows competitive performance compared with other methods.

    • HTML全文

  • 圖  1  Chernoff加權(quán)框架方法的結(jié)構(gòu)框圖

    圖  2  每次試驗的時序示意圖

    圖  3  各個時刻的特征統(tǒng)計概率分布圖

    圖  4  數(shù)據(jù)集1的互信息圖

    圖  5  數(shù)據(jù)集2的互信息圖

    圖  6  數(shù)據(jù)集3的互信息圖

    圖  7  數(shù)據(jù)集4的互信息圖

    圖  8  各算法分類精度結(jié)果圖

    圖  9  dout的統(tǒng)計均值和方差變化圖

    表  1  算法1 Chernoff框架方法的訓(xùn)練過程

    　輸入：EEG訓(xùn)練數(shù)據(jù)
    　輸出：獨立分類器模型參數(shù)和概率權(quán)重w
    　步驟 1　對EEG數(shù)據(jù)進(jìn)行預(yù)處理，提取特征向量；
    　步驟 2　利用獨立分類器訓(xùn)練得到模型參數(shù)；
    　步驟 3　利用式(1)得到特征向量的均值和方差；
    　步驟 4：利用式(8)得到權(quán)重w。
    下載: 導(dǎo)出CSV

    表  2  算法2 Chernoff框架方法的測試過程

    　輸入：t 時刻的測試 EEG 數(shù)據(jù),獨立分類器參數(shù)和權(quán)重w
    　輸出：分類結(jié)果和判定值dout(t)
    　步驟 1　對EEG數(shù)據(jù)進(jìn)行預(yù)處理，提取特征向量；
    　步驟 2　通過獨立分類器的訓(xùn)練模型得到yc(t)；
    　步驟 3　利用式(11)和式(12)將yc轉(zhuǎn)化到p(t)∈[0, 1]；
    　步驟 4　利用式(9)計算pout(t)；
    　步驟 5　利用式(10)將pout(t) 變換到dout(t)∈[–1, 1]；
    　步驟 6　通過dout(t)的符號獲得分類結(jié)果。
    下載: 導(dǎo)出CSV

    表  3  實驗中的數(shù)據(jù)集

    序號數(shù)據(jù)集來源訓(xùn)練集個數(shù)(試驗次數(shù))測試集個數(shù)(試驗次數(shù))類別
    1BCI II (III)1 (140)1 (140)2
    2BCI III (IIIb)1 (320)1 (320)2
    3BCI IV (IIb)3 (400)2 (320)2
    4BCI IV (IIb)3 (400)2 (320)2
    下載: 導(dǎo)出CSV

    表  4  數(shù)據(jù)集1的最大互信息(bit)

    分類方法最大互信息
    ELM0.524/0.051
    LDA0.414
    SVM0.471
    LSTM0.511
    ELM-CF0.680/0.020
    LDA-CF0.631
    SVM-CF0.662
    第II屆BCI競賽的第1名0.61
    下載: 導(dǎo)出CSV
  • TIWARI N, EDLA D R, DODIA S, et al. Brain computer interface: A comprehensive survey[J]. Biologically Inspired Cognitive Architectures, 2018, 26: 118–129. doi: 10.1016/j.bica.2018.10.005
    楊幫華, 李博. 基于腦機(jī)接口的康復(fù)訓(xùn)練系統(tǒng)[J]. 系統(tǒng)仿真學(xué)報, 2019, 31(2): 174–180. doi: 10.16182/j.issn1004731x.joss.18-0791

    YANG Banghua and LI Bo. Rehabilitation training system based on brain computer interface[J]. Journal of System Simulation, 2019, 31(2): 174–180. doi: 10.16182/j.issn1004731x.joss.18-0791
    ALAZRAI R, ALWANNI H, BASLAN Y, et al. EEG-based brain-computer interface for decoding motor imagery tasks within the same hand using Choi-Williams time-frequency distribution[J]. Sensors, 2017, 17(9): 1937. doi: 10.3390/s17091937
    LEEB R, LEE F, KEINRATH C, et al. Brain-computer communication: Motivation, aim, and impact of exploring a virtual apartment[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15(4): 473–482. doi: 10.1109/TNSRE.2007.906956
    GUY V, SORIANI M H, BRUNO M, et al. Brain computer interface with the P300 speller: Usability for disabled people with amyotrophic lateral sclerosis[J]. Annals of Physical and Rehabilitation Medicine, 2018, 61(1): 5–11. doi: 10.1016/j.rehab.2017.09.004
    HASAN M R, IBRAHIMY M I, MOTAKABBER S M A, et al. Classification of multichannel EEG signal by linear discriminant analysis[C]. The 23rd International Conference on Systems Engineering, 2015: 279–282. doi: 10.1007/978-3-319-08422-0_42.
    SELIM S, TANTAWI M M, SHEDEED H A, et al. A CSP\AM-BA-SVM approach for motor imagery BCI system[J]. IEEE Access, 2018, 6: 49192–49208. doi: 10.1109/access.2018.2868178
    BHADURI S, KHASNOBISH A, BOSE R, et al. Classification of lower limb motor imagery using K nearest neighbor and na?ve-bayesian classifier[C]. The 3rd IEEE International Conference on Recent Advances in Information Technology (RAIT), Dhanbad, India, 2016: 1–6. doi: 10.1109/RAIT.2016.7507952.
    ZHANG Yu, WANG Yu, JIN Jing, et al. Sparse Bayesian learning for obtaining sparsity of EEG frequency bands based feature vectors in motor imagery classification[J]. International Journal of Neural Systems, 2017, 27(2): 1650032. doi: 10.1142/S0129065716500325
    HAZRATI M K and ERFANIAN A. An online EEG-based brain-computer interface for controlling hand grasp using an adaptive probabilistic neural network[J]. Medical Engineering & Physics, 2010, 32(7): 730–739. doi: 10.1016/j.medengphy.2010.04.016
    程時偉, 周桃春, 唐智川, 等. 卷積神經(jīng)網(wǎng)絡(luò)實現(xiàn)的運動想象腦電分類及人-機(jī)器人交互應(yīng)用[J]. 軟件學(xué)報, 2019, 30(10): 1–14. doi: 10.13328/j.cnki.jos.005782

    CHENG Shiwei, ZHOU Taochun, TANG Zhichuan, et al. Motor imagery EEG classifcation based on convolutional neural network and its application in human-robot interaction[J]. Journal of Software, 2019, 30(10): 1–14. doi: 10.13328/j.cnki.jos.005782
    LEMM S, SCHAFER C, and CURIO G. BCI competition 2003-data set Ⅲ: Probabilistic modeling of sensorimotorμ-rhythms for classification of imaginary hand movements[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1077–1080. doi: 10.1109/TBME.2004.827076
    TAN Ping, TAN Guanzheng, CAI Zixing, et al. Using ELM-based weighted probabilistic model in the classification of synchronous EEG BCI[J]. Medical & Biological Engineering & Computing, 2017, 55(1): 33–43. doi: 10.1007/s11517-016-1493-x
    MATSUI H. Variable and boundary selection for functional data via multiclass logistic regression modeling[J]. Computational Statistics & Data Analysis, 2014, 78: 176–185. doi: 10.1016/j.csda.2014.04.015
    SCHLOGL A, KEINRATH C, SCHERER R, et al. Information transfer of an EEG-based brain computer interface[C]. The 1st International IEEE EMBS Conference on Neural Engineering, Capri Island, Italy, 2003: 641–644. doi: 10.1109/CNE.2003.1196910.
    FORSTMANN B U, RATCLIFF R, and WAGENMAKERS E J. Sequential sampling models in cognitive neuroscience: Advantages, applications, and extensions[J]. Annual Review of Psychology, 2016, 67: 641–666. doi: 10.1146/annurev-psych-122414-033645
  • 加載中
圖(9) / 表(4)
計量
  • 文章訪問數(shù):  2548
  • HTML全文瀏覽量:  819
  • PDF下載量:  78
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2018-12-07
  • 修回日期:  2019-07-20
  • 網(wǎng)絡(luò)出版日期:  2019-09-11
  • 刊出日期:  2020-02-19

目錄

    /

    返回文章
    返回