A Smart Sensing Period Control on Back propagation Neural Network in IoT
사물인터넷에서 역전파 신경망 기반 스마트 센싱 주기 제어

Woojae Kim, Manbae Kim, Inbum Jung
2019 KIISE Transactions on Computing Practices  
The "things" in IoT have sensors and actuators for monitoring their surroundings. They are powered through battery energy according to the characteristics of their deployed environment. In order to enhance the longevity of an IoT network, the devices working on battery power have to restrict unnecessary sensing operations. However, existing sensing methods are affected by the collected sensing data and have fixed sensing periods, leading to the inevitable waste of battery power. In this paper,
more » ... smart sensing period control is proposed for the IoT middleware MinT. The proposed method uses a learning model based on a back propagation neural network. Until the target time, it can make the best use of battery energy without surplus or waste in the range of the preserved bateery energy. The experimental results indicate that the proposed method shows enhanced results in terms of battery energy consumption compared to the existing static sensing period method.
doi:10.5626/ktcp.2019.25.8.377 fatcat:27hxjqjttvhqzeeqbghens3g2e