【摘要】：為提高腦電信號(hào)情感識(shí)別分類(lèi)準(zhǔn)確率,結(jié)合經(jīng)驗(yàn)?zāi)B(tài)(EMD)分解和能量熵提出一種新的腦電特征提取方法。本研究主要介紹了EMD分解的基本原理,分析了傳統(tǒng)EMD算法中的"端點(diǎn)效應(yīng)",采用分段冪函數(shù)插值算法改善了EMD分解的精度和性能,然后將改進(jìn)后的算法應(yīng)用到腦電信號(hào)特征提取,獲取腦電信號(hào)的IMF分量后計(jì)算出IMF能量熵作為情感識(shí)別的特征,最后通過(guò)分類(lèi)實(shí)驗(yàn)對(duì)比改進(jìn)后的EMD算法和傳統(tǒng)EMD算法對(duì)腦電情感特征的分類(lèi)準(zhǔn)確率。實(shí)驗(yàn)結(jié)果顯示改進(jìn)的EMD算法能使識(shí)別率提高15%左右,并且以IMF能量熵為特征的平均識(shí)別率在80%以上,實(shí)驗(yàn)結(jié)果表明將IMF能量熵用于腦電信號(hào)情感識(shí)別是可行的。
[Abstract]:In order to improve the classification accuracy of EEG emotion recognition, a new EEG feature extraction method combining empirical mode (EMD) decomposition and energy entropy is proposed. This paper mainly introduces the basic principle of EMD decomposition, analyzes the "endpoint effect" in traditional EMD algorithm, and improves the precision and performance of EMD decomposition by using piecewise power function interpolation algorithm. Then the improved algorithm is applied to the feature extraction of EEG signal, and then the IMF energy entropy is calculated as the feature of emotion recognition by obtaining the IMF component of EEG signal. Finally, the classification accuracy of the improved EMD algorithm and the traditional EMD algorithm is compared with the classification experiment. The experimental results show that the improved EMD algorithm can increase the recognition rate by about 15%, and the average recognition rate based on the IMF energy entropy is over 80%. The experimental results show that it is feasible to apply the IMF energy entropy to EEG emotion recognition.
【作者單位】： 華東理工大學(xué);
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61071085) 上海市科委科技創(chuàng)新行動(dòng)計(jì)劃生物醫(yī)藥領(lǐng)域產(chǎn)學(xué)研合作項(xiàng)目(12DZ1940903)
【分類(lèi)號(hào)】：TN911.7;R338
，

本文編號(hào)：2420332