Human Wearable IoT-Cloud Based Touch
IoT based human activity and health care tracking have been emerging rapidly, most of these IoTs work through smartphones. However, they provide data on human health parameters or the human context information only. Leveraging on the IoT-edge, Fog(smartphone), cloud computing, and Deep Learning techniques, we build a new model which have the features of capturing and analyzing the human touch-points during his/her daily activities and generates a report of safe and unsafe touch-points, which helps in reducing the unsafe touch-points to keep themselves away from infections such as, chickenpox, common cold, Hepatitis A and B, influenza, measles, COVID-19, etc.
Human touch-point activity data which is collected by the human wearable IoT will be shared with the Smartphone and the Smartphone analyzes the type of touch-point with the help of a Deep Learning based Mobile-App running in the Smartphone and sends commands back to the IoT as needed and also shares the data with the Cloud for the further processing and report generation.
In this proposed model, we discuss the idea with the help of building blocks of the IoT, Mobile-App, filtering algorithm, and Cloud application. This model relies on the communication between the IoT and the Fog hence, the amount of the data shared by the IoT needs to be fine-tuned and filtered for reducing the latency by applying different filtering mechanishms.