Action detection of Objects Devices Using Deep Learning in IoT Applications

Abstract

Abstract Internet of Things (IoT) technology is the communication and communication of smart technological devices with each other. However, with the development of the Internet of Things, the number of smart applications and connected devices is increasing day by day. Deep Learning (DL) method has become necessary to process the large amount of raw data collected, to further develop intelligence and application capabilities. It is seen that the majority of researchers focus on action perception. Direct action detection on IoT devices using deep learning is not a common method. Standard Deep Learning techniques are difficult to use in IoT devices as Deep Learning applications require high CPU, RAM and storage. In the study, unlike the use of deep learning techniques in IoT devices, the action detection process was carried out directly on the edge device. For this, mini-size Deep Learning (DL-Lite) techniques have been applied on the real IoT device. Comparison of IoT devices and mini Deep Learning techniques was carried out according to parameters such as detection accuracy, delay and device temperature resulting from the application of these techniques in IoT devices.