CNN Based Fall Detection and Health Monitoring System Using IoT

Abstract

Falls are the common problem faced by elderly population. Fall may happen due to fainting. The reason for faint involves sudden changes in the heart rate. Falls are the common cause of traumatic brain injuries in elderly people and also cause severe injuries such as fracture of the hip. This kind of injuries can create a negative impact on their quality of life. In most of the cases the elder people who are unnoticed for more than an hour after a fall undergoes a serious trauma, also leading to death of the individuals. There are some existing systems for detecting the falls of the elderly people. These ambient sensors involve recording of videos for fall detection with various machine learning methods. The wearable sensor for motion detection mainly involves sensors such as infrared sensor, accelerometer sensor and kinetic RGBD camera. The existing systems are based upon the ambient sensors faces some risks such as storage and processing of video is a complex task and it also affects the privacy of the people. It is necessary to propose a system that can overcome the above drawbacks. The system proposed involves capturing the motion of the elderly people using accelerometer sensors. Those captured data via sensors are processed using CNN, which involve steps such as convolution, it results in feature map then it has to be down sampled using the max pooling methods and based on the resultant layers, the captured motion can be determined whether it is a day to day activities or a fall. Once the fall is identified the message about the fall of the person is sent to the family members and neighbours. Additionally, it is provided with a sensor to monitor the heart rate of the elder people, whenever the rate deteriorates, a message about abnormal heart rate is sent to neighbours and family, so that they can provide medical assistance.