基于sEMG与足底压力信号融合的跌倒检测研究

跌倒已经成为一种普遍危害老年人身心健康的事故,需要得到及时救治。设计了一种基于表面肌电(s EMG)和足底压力信号融合的跌倒检测系统。提取s EMG的近似熵及基本尺度熵特征,并根据足底压力的变化规律,提取动作信号段的压力特征,通过D-S证据推理将肌电信号与足底压力信号的SVM决策融合获得综合判别结果。实验结果表明,该方法对跌倒与ADL的平均识别率达到了91.7%,优于单一信源识别结果。

Study on fall detection based on surface EMG and plantar pressure signal fusion

Fall accidents have become a common physical and mental health hazard for the elderly, and need to receive timely medical treatment. This paper presents a fall detection system based on sEMG and plantar pressure signal fusion. The sEMG approximate entropy and basic scale entropy are extracted. The pressure feature of action signal segment is extracted according to the rules of the plantar pressure change. The SVM decision fusion of the sEMG and plantar pressure signal is conducted through DS evidential reasoning to obtain the comprehensive recognition results. The experiment results show that the average recognition rates of fall and ADL reach 91.7%, which is higher than the recognition results of single source recognition.