基于約束獨立分量分析的腦電特征提取
發(fā)布時間：2018-10-14 12:30
【摘要】：針對腦機接口(brain-computer interface,BCI)系統(tǒng)特征提取較慢的現(xiàn)狀,提出基于約束獨立分量分析(constrained independent component analysis,cICA)的P300特征提取方法.首先,針對各位P300實驗被試,通過EEG圖像研究其特有P300時域特性;然后,根據(jù)P300特性構建參考信號,并將參考信號與獨立分量分析(independent component analysis,ICA)方法結合,基于64導聯(lián)EEG,提取出與P300相關度最大的獨立分量;最后,依據(jù)提取出的獨立分量構造3維特征向量進行分類.實驗采用線性分類器,針對BCI Competition II dataset IIb和BCI Competition III dataset II兩組公共數(shù)據(jù)集進行了驗證.結果表明,提出方法在3次疊加平均下識別正確率達67.1%,15次達95.2%,在相同實驗條件下,分類時間也較其他方法縮短.
[Abstract]:A P300 feature extraction method based on constrained Independent component Analysis (constrained independent component analysis,cICA) is proposed to solve the problem of slow feature extraction in brain-computer interface (brain-computer interface,BCI) systems. First of all, the special P300 time-domain characteristics of P300 are studied by EEG images, and then the reference signal is constructed according to the P300 characteristics, and the reference signal is combined with the independent component analysis (independent component analysis,ICA) method. Based on 64-lead EEG, the independent components with the greatest correlation with P300 are extracted. Finally, 3D feature vectors are constructed according to the extracted independent components. The experiment uses linear classifier to verify two groups of common data sets: BCI Competition II dataset IIb and BCI Competition III dataset II. The results show that the accuracy rate of the proposed method is 67.1 times and 95.2 times on the average of three superpositions, and the classification time is shorter than that of other methods under the same experimental conditions.
【作者單位】： 東北大學中荷生物醫(yī)學與信息工程學院;東北大學機械工程與自動化學院;
【基金】：國家自然科學基金資助項目(61071057)
【分類號】：R318
[Abstract]:A P300 feature extraction method based on constrained Independent component Analysis (constrained independent component analysis,cICA) is proposed to solve the problem of slow feature extraction in brain-computer interface (brain-computer interface,BCI) systems. First of all, the special P300 time-domain characteristics of P300 are studied by EEG images, and then the reference signal is constructed according to the P300 characteristics, and the reference signal is combined with the independent component analysis (independent component analysis,ICA) method. Based on 64-lead EEG, the independent components with the greatest correlation with P300 are extracted. Finally, 3D feature vectors are constructed according to the extracted independent components. The experiment uses linear classifier to verify two groups of common data sets: BCI Competition II dataset IIb and BCI Competition III dataset II. The results show that the accuracy rate of the proposed method is 67.1 times and 95.2 times on the average of three superpositions, and the classification time is shorter than that of other methods under the same experimental conditions.
【作者單位】： 東北大學中荷生物醫(yī)學與信息工程學院;東北大學機械工程與自動化學院;
【基金】：國家自然科學基金資助項目(61071057)
【分類號】：R318
【參考文獻】
相關期刊論文 前2條
1 劉沖;趙海濱;李春勝;王宏;;基于CSP與SVM算法的運動想象腦電信號分類[J];東北大學學報(自然科學版);2010年08期
2 劉曉志;馮大偉;楊英華;秦樹凱;;基于核獨立分量分析的盲多用戶檢測算法[J];東北大學學報(自然科學版);2012年06期
【共引文獻】
相關期刊論文 前10條
1 劉沖;李春勝;趙海濱;王宏;;特征選擇算法在ECoG分類中的應用[J];東北大學學報(自然科學版);2011年05期
2 顏世玉;王宏;劉沖;趙海濱;;基于小波方差的運動想象腦電信號特征提取[J];東北大學學報(自然科學版);2012年07期
3 顏世玉;王宏;趙海濱;劉沖;;腦-機接口中小波和小波包方差的特征比較[J];東北大學學報(自然科學版);2012年10期
4 蔣夕平;吳鳳凰;蔣昱;修連存;;基于FastICA算法的高光譜礦物豐度反演[J];吉林大學學報(地球科學版);2013年05期
5 張云嬌;雷斌;朱婷婷;;針對電磁干擾的濾波技術[J];電聲技術;2013年12期
6 孫通;許文麗;胡田;劉木華;;基于UVE-ICA和支持向量機的南豐蜜桔可溶性固形物可見-近紅外檢測[J];光譜學與光譜分析;2013年12期
7 李春蔚;;一種改進的獨立成分分析算法的計算機仿真研究[J];電腦知識與技術;2013年32期
8 納躍躍;謝，
本文編號：2270461
本文鏈接：http://sikaile.net/yixuelunwen/swyx/2270461.html
