Human Fall Detection with Wearable Sensors Using ML Algorithms

In the healthcare systems, wearable technology is enhanced by continuously monitoring people's physical activities and behaviors in daily life. A wearable system has two technologies, one based on sensors and the other based on cameras. The use of machine learning (ML) in health care applications, such as human fall detection, has become an active area of research. This research work has proposed a sensor based human fall detection system, which detect a fall by using sensor-based technology other than the vision-based technology because most people are concerned about their privacy very seriously. The overall performance of the proposed scheme was examined by using four machine learning algorithms namely, Support Vector Machine (SVM), k-nearest neighbour’s (KNNs), Decision Tree (DT), and Random Forest (RF). The proposed methodology achieves the best accuracy for human fall detection, i.e., 98% , by using ensemble technique as RF classifier.