Fall Detection System Using Machine Learning Approach
Nirbhay Jain, Anish Mittal, Prashant ., Shikha Rastogi, Ankit Jha, Sarita Yadav · 2024
Fall is one of the worst possible things that can happen to older individuals. The creation of fall detection systems is urgently needed due to the ageing population that is constantly expanding. Fall detection system (FDS) based on machine learning (ML) approach has emerged as a significant investigated area because of its ability to automatically aid the elderly people. The capability of a fall detection system to differentiate between the occurrence of fall & non-fall events precisely will determine how effective the system is. In this paper, we have done the literature survey on fall detection systems using the machine learning algorithms and suggested the most effective method which has the best accuracy and low false alarm rate. While comparing the results of different classification methods like Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Random Forest. We have analysed that SVM has the greatest accuracy of 97% which is much higher than 90% of KNN and 93% of Random Forest. SVM also has the lowest false alarm rate, demonstrating that it can efficiently distinguish between the various classes with the fewest possible faults.