IoT-Based Fall Detection System with Energy Efficient Sensor Nodes

Fall needs to be attentively considered due to its highly frequent occurrence especially with old people - up to one third of 65 and above year-old people around the world are risk of being injured due to falling. Furthermore, fall is a direct or indirect factor causing severe traumas such as brain injuries or bone fractures. However, timely medical attention might help to avoid serious consequences from a fall. A viable solution to solve this is an IoT-based system which takes advantage of wireless sensor networks, wearable devices, Fog and Cloud computing. To deliver sufficient degree of reliability, wearable devices working at the core of a fall detection system, are required to work for prolonged period of time. In this paper we investigate energy consumption of sensor nodes in an IoT-based fall detection system and present a design of a customized sensor node. In addition, we compare the customized sensor node with other sensor nodes, built on general purpose development boards. The results show that sensor nodes based on delicate customized devices are more energy efficient than the others based on general purpose devices while considering identical specification of micro-controller and memory capacity. Furthermore, our customized sensor node with energy efficiency selections can operate continuously up to 35 hours.