Human Activity Diagnosis System Based on the Internet of Things

Abstract

Abstract The Cognitive Internet of Things (CIoT) is the next step in enhancing the accuracy and reliability of the Internet of Things (IoT) technology used for Cognitive Computing, which plays a main role in health and disease diagnosis. The study was suggested a diagnosis method to sound sensitivity by developing a framework with IoT and cloud based on a facial expression recognition system. It was achieved through the creation of a cognitive IoT hardware-based environment and the elements of the programs that are implemented to test the behaviour of people suffering from sound sensitivity, this operation is done by using a camera and image processing and it used Convolutional Neural Network (CNN) as a facial recognition software to track human facial emotions through live video. The sentiment values were analysed that they were collected and stored in a cloud using Transmission Control Protocol (TCP) protocol. These emotions were categorized as abnormal or normal. Normal states represented by happy or natural feelings that give the impression that the environment is suitable for people’s senses and that they do not suffer from discomfort towards this environment, therefore; the system operates on a mechanism to increase the volume in this environment by using an Arduino microcontroller. Although the device operates automatically in the event of hypersensitivity detection, it reduces this severity. The obtained results showed the efficiency of the proposed system in recognizing facial emotions with 80% accuracy.