A Distributed Fall Detection Architecture Using Ensemble Learning
Che-Cheng Chang, Yo-Chun Chen, Bing-Herng Sieh, Yee-Ming Ooi · 2021
Falling accidents are serious and costly for people, especially for elders. Each year, millions of older people fall. Particularly, more than one out of four older people falls each year, and falling doubles the chance of falling again. Moreover, without immediate treatment, it would cause higher medical costs. Hence, we intend to design a novel distributed fall detection architecture, where the distributed nature and ensemble learning enhance the classical concept of fall detection based on computer vision. Lastly, in the experiments, we show that the prototype is accurate and stable enough to alert the emergency contact person.