IoT-Based Intelligent Monitoring System Applying RNN

Abstract

In this paper, we propose an intelligent monitoring framework based on the Internet of Things (IoT) by applying a Recurrent Neural Network (RNN) for the predictive maintenance of a biobanking system. RNN, which is one of the deep learning models, is used for time series data. It is called a sequence model because it processes inputs and outputs in sequence units. The proposed framework measures the internal temperature of the cryogenic freezer and the temperature of each component simultaneously, monitors the internal temperatures of internal and middle layers in real time, sends the sensing temperature data to the server, and performs predictive learning. Thus, it is possible to support the intelligent predictive maintenance of the biobank by performing a time series data analysis of the temperature sensor using RNN. Among RNN methods, a simple RNN has a longer-term dependency problem; therefore, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), which have higher learning performance, are selected. To support the intelligent predictive maintenance of the biobank, both the LSTM and GRU models were constructed, and comparative experiments were performed. The proposed system can ensure the safety of bio-resources by performing predictive maintenance using RNN and provide an accurate status of the biobank in real-time. In addition, before an abnormal situation occurs, it is possible to respond immediately to emergencies that may damage biological resources.

Current Research in Future Information and Communication Engineering 2022

“…Four papers focused on deep-learning-based IOT systems. The first paper, authored by Shin et al [12], proposed and evaluated an intelligent monitoring framework based on the IoT by applying a recurrent neural network (RNN) for the predictive maintenance of a biobanking system in real time. The second paper, authored by Kwon et al [13], analyzed the effect of compressed sensing (CS) rates (from 100% to 10%) and video resolutions (1280 × 720, 640 × 480, 480 × 360) in the IoT sensing device on the pose score of the PoseNet model in the artificial intelligence of things (AIoT) edge server.…”