Fuzzy Spiking Neural Network for Abnormality Detection in Cognitive Robot Life Supporting System

In aging nation such as Japan, elderly people belong to the vulnerable group that constantly need health care and monitoring for their well-being. Therefore, an early warning system for detecting abnormality in their daily activities could save their life (e.g. Heart attack, stroke and etc.). However, such early warning system must not trigger any false warning signals in order to robustly operate in real world applications. Robot interactions with human are useful to prevent false warning signals from sending out to healthcare worker. Next, the system should be able to detect short-term abnormal and also long-term abnormal behaviors of the elderly people within their normal daily life routine. Therefore, it is important to integrate information ally structured space with cognitive robot to confirm the elderly´s abnormal situation with human-robot interactions before sending out warning signals to healthcare workers. In this work, we proposed an evolutionary computation based approach to optimize fuzzy spiking neural network for detecting abnormal activities in the elderly people´s daily activities.