A Machine Learning Approach for Fall Detection and Daily Living Activity Recognition
Abstract: The number of older people in western countries is constantly increasing. Most of them prefer to live independently and are susceptible to fall incidents. Falls often lead to serious or even fatal injuries which are the leading cause of death for elderlies. To address this problem, it is essential to develop robust fall detection systems. In this context, we develop a machine improve the performance of the classifier are extracted from the power spectral density of the acceleration. In a first step, only the acceleration data are used for activity recognition. Our results reveal that the KNN, ANN, QSVM, and EBT algorithms could achieve an overall accuracy of 81.2%, 87.8%, 93.2%, and 94.1%, respectively. The accuracy of fall detection reaches 97.2% and 99.1% without any false alarms for the QSVM and EBT algorithms, respectively. In a second step, we extract features from the autocorrelation function and the power spectral density of both the acceleration and the angular velocity data, which improves the classification accuracy. By using the proposed features, we could achieve an overall accuracy of 85.8%, 91.8%, 96.1%, and 97.7% for the KNN, ANN, QSVM, and EBT algorithms, respectively. The