Abstract
Fall detection is a major problem in the healthcare department. Elderly people are more prone to fall than others. There are more than 50% of injury-related hospitalizations in people aged over 65. Commercial fall detection devices are expensive and charge a monthly fee for their services. A more affordable and adaptable system is necessary for retirement homes and clinics to build a smart city powered by IoT and artificial intelligence. An effective fall detection system would detect a fall and send an alarm to the appropriate authorities. We propose a framework that uses edge computing where instead of sending data to the cloud, wearable devices send data to a nearby edge device like a laptop or mobile device for real-time analysis. We use cheap wearable sensor devices from MbientLab, an open source streaming engine called Apache Flink for streaming data analytics, and a long short-term memory (LSTM) network model for fall classification. The model is trained using a published dataset called “MobiAct.” Using the trained model, we analyse optimal sampling rates, sensor placement, and multistream data correction. Our edge computing framework can perform real-time streaming data analytics to detect falls with an accuracy of 95.8%.
Highlights
According to the World Health Organization, a fall is de ned as an event in which a person comes to rest onto the ground or any lower level [2]
We propose an edge computing framework which is deployed in close proximity, i.e., within a maximum range of 100 ft from the wireless sensor devices, and collects and performs preprocessing of the data to only transfer the important data to the cloud
We developed a Universal Windows Platform application (UWP app) in C-sharp using the template provided by MbientLab to stream raw X, Y, and Z-axis accelerometer data to a streaming data-processing engine running on the edge device
Summary
Fall monitoring has been an emerging field with new systems being introduced constantly. Cheap sensors called MetaMotionR from MbientLab. e data from the wearable devices were collected at an edge device like a laptop which preprocessed the data using Apache Flink and sent it to the level of analytics when the magnitude exceeded a predefined threshold. At this level, the data were analysed using TensorFlow where a pretrained LSTM model was used to classify the data as fall or nonfall.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
