Smartphone Based Fall Detection Using Thresholding and Machine Learning Approach

Abstract

Fall detection is an approach, which is used to detect fall event when some person falls unconsciously and sends this information to the caretaker of that person. Fall detection methods can be broadly classified in machine learning based methods and threshold based methods. Our method is based on the combined approach of both threshold based method and machine learning based method. In this proposed method, first we calculate the variance of every five continuous accelerometer values because there is a sudden change in acceleration values during fall which increases variance very suddenly. Then we have used support vector machine (SVM) and K-nearest neighbor (KNN) classifiers to classify ADL and fall activities. In this proposed method SVM classifier using Gaussian kernel function performs better than other classifiers.