Performance enhancement of human activity recognition and fall related system using multi-modal broad learning system (mBLS)

Elder citizens face sudden fall which can cause injuries of both fatal and non-fatal type. These sudden falls are sometime more dangerous than diseases heart attract, blood sugar, blood pressure because these can be untreated for a long period of time which can lead to death. An elder citizen who faces an sudden fall, make his or her social life limited. This is why a smart and effective anti-fallen system needed to be developed to support elderly health care, especially to those who lives independently, which can detect and predict a sudden fall through proper human activity recognition. In this paper, we have introduced an end-edge-cloud based wearable smarachFALL (smart activity recognition architecture for fall detection and prediction) architecture for elderly care. We have designed simulation setups to answer the question of why we need such system and the effectiveness. These experimental results also shows the advantage of using tightly couple multiple information for recognizing human activity. We are able to achieve a low false alarm rate (FAR) with an improved accuracy. These work serves as the starting point for future related research activities.