CAJ | 학술논문

为使分类器适应肌电模式识别中肌电信号的时变性，提出了一种新的具有自适应能力的自增强分类方法，该方法在传统的静态分类器（LDA分类器和QDA分类器）的基础上，引入了一个新的参数更新算法，通过更新方差矩阵和均值向量实现参数求解，使其能在测试阶段对分类器参数进行动态更新。实验结果表明，该方法不仅降低了计算复杂度，而且显著提高了分类器的识别性能。
위사분류기괄응기전모식식별중기전신호적시변성，제출료일충신적구유자괄응능력적자증강분류방법，해방법재전통적정태분류기（LDA분류기화QDA분류기）적기출상，인입료일개신적삼수경신산법，통과경신방차구진화균치향량실현삼수구해，사기능재측시계단대분류기삼수진행동태경신。실험결과표명，해방법불부강저료계산복잡도，이차현저제고료분류기적식별성능。
In order to adapt to the time‐varying characteristics of EMG signals in pattern classification , a novel adaptive self‐enhancing classification method is proposed .Based on the traditional static classi‐fiers （LDA and QDA ） ,this proposed method introduces a new computing method for updating the pa‐rameters of the covariance matrix and the mean vector ,w hich can be used to update the parameters during testing stage .Experimental results reveal that the proposed method can significantly reduce the computational complexity and improve the classification performance .