Enhancing Fall Detection for Elderly with Smart Helmet in a Cloud-Network-Edge Architecture

Falls commonly occur for elder citizens which may lead to severe injuries. In this paper, we propose a cloud-network-edge architecture to enhance fall detection, prevention and protection which consists of the medical cloud, edge networks and end-devices, such smart helmet. The smart helmet is integrated with wearable cameras, accelerometers, gyroscope sensors; hence, it is able to sense daily activities of the elderly based on data fusion from multi sensors collaboratively. The processing of the sensor data can be offloaded at the edge for reducing delay and preserving privacy. The medical data can be delivered over a secure medical network to the medical cloud for services, such as fall alarm. In particular, we evaluate the performance of multimode processing algorithms for video and accelerometer data to enhance fall detection. Our experimental results show that the proposed algorithms are able to increase the accuracy and reduce the false alarm effectively.