Bayes methods; biological tissues; decision trees; feature extraction; fluctuations; medical disorders; medical signal processing; oscillations; patient diagnosis; signal classification; statistical analysis; vibrations; Bayesian decision rule; CV of envelope energy value; Kolmogorov-Smirnov test; VAG signal characterization; abnormal knee joint vibroarthrographic signal identification; classification experiment; coefficient of variation; fixed threshold; fluctuation feature; intrinsic oscillation characterization; knee joint VAG signal processing; overall classification accuracy; pathological VAG signal; pattern classification; sensitivity value; signal turn count threshold; specificity value; variation feature extraction; Bayes methods; Feature extraction; Joints; Knee; Pathology; Support vector machines; Vibrations;
机译:核密度建模方法在病理性膝关节脉搏动心动图信号中表现波动特征
机译:整体经验模态分解和去趋势波动分析法去除膝关节颤动信号中的伪影
机译:使用时间和光谱域特征筛选膝关节蛛网图中的信号
机译:基于起伏特征的膝关节异常关节电图异常信号识别
机译:自适应信号处理技术,用于分析膝关节颤动心电图信号。
机译:vibroarthrographic信号光谱特征在5级膝关节分类中
机译:整体经验模态分解和去趋势波动分析法去除膝关节颤动信号中的伪影