Development of Falling Notification System for Elderly Using MPU6050 Sensor and Short Message Service

Abstract

Falls in the elderly are quite common because their motor skills have begun to decline. The elderly who live alone are often late in getting first aid after a fall, as a result of which intensive care is needed. This paper describes the design of falling detection and notification system for the elderly in the form of short messages sent to mobile phones and stored in the system database. The proposed prototype is designed using the MPU6050 sensor to detect falling movements and a continuous notification system in the form of three different messages immediately sent after falling. The tools used to test the research results are the confusion matrix method. The experimental results of this study show that the recall value is 90%, the precision is approximately 82%, the specificity is about 94%, and the accuracy equals 93% respectively.