A Fall Detection Device Based on Single Sensor Combined with Joint Features

Accidental falls pose a significant threat to the well-being of the elderly, thus facilitating a quantum leap in the field of fall detection technology. For fall detection, accurate identification of fall behavior is a key priority. Our study proposes an innovative methodology to detect falls during activities of daily living (ADL), with the objective of preventing further harm. Our design aims to achieve precise identification of falls by extracting a variety of features obtained from the simultaneous acquisition of acceleration and angular velocity data using a single sensor. To enhance detection accuracy and reduce false alarms, we establish a classifier based on the joint acceleration and Euler angle feature (JAEF) analysis. With the aid of a support vector machine (SVM) classifier, human activities are classified into eight categories: going upstairs, going downstairs, running, walking, falling forward, falling backward, falling left, and falling right. In particular, we introduce a novel approach to enhance the accuracy of fall detection algorithms by introducing the Equal Signal Amplitude Difference method. Through experimental demonstration, the proposed method exhibits a remarkable sensitivity of 99.25%, precision of 98.75%, and excels in classification accuracy. It is noteworthy that the utilization of multiple features proves more effective than relying solely on a single aspect. The preliminary findings highlight the promising applications of our study in the field of fall injury systems.