Fall Detection with Support Vector Machine for Elderly Care using Pressure Sensor Grid

Abstract

Generally, falling is prevalent in elderly of age 65 and above due to age-related biological changes. Falls can be life-threatening if noticed late. Hence, a fall detection and surveillance device was developed to monitor elderly living alone. The primary objective is to build a pressure sensitive mat capable of detecting fall through image processing. The subjects tested resembled the stature of elderly. The accuracy of the system in detecting fall is 93% while the accuracies for the other postures such as standing and sitting yield 93.5 and 81.5%, respectively.

Data Acquisition System and Pattern Image Generations for Hand Grip Device

“…The circuitry on the glove is connected to the microcontroller (Arduino Nano) for data acquisition and interfacing with the MATLAB program in the desktop computer. Similar approach has been used in the previous work for fall detector system [20]. The sensor circuit has 16 rows of conductor connected to 2 shift registers 74HC595, in which each of them can drive 8 channels.…”