Deep Learning-driven Proactive Maintenance Management of IoT-empowered Smart Toilet

• Published in: IEEE internet of things journal 2023-02, Vol.10 (3), p.1-1
• Main Authors: See-To, Eric W. K., Wang, Xiao-Xi, Lee, Kwan-Yeung, Wong, Man-Leung, Dai, Hong-Ning
• Format: Article
• Language: English
• Subjects: Algorithms; Cloud Computing; Convolutional neural network (CNN); Data collection; Deep Learning; Internet of Things; Internet of Things (IoT); Long short-term memory (LSTM); Machine Learning; Maintenance management; Optimization; Proactive maintenance management; Sensors; Task scheduling; Time series
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2022.3211889

The recent proliferation of Internet of Things (IoT) sensors has driven a myriad of industrial and urban applications. Through analyzing massive data collected by these sensors, the proactive maintenance management can be achieved such that the maintenance schedule of the installed equipment can be optimized. Despite recent progress in proactive maintenance management in industrial scenarios, there are few studies on proactive maintenance management in urban informatics. In this paper, we present an integrated framework of IoT and cloud computing platform for proactive maintenance management in smart city. Our framework consists of (1) an IoT monitoring system for collecting time-series data of operating and ambient conditions of the equipment and (2) a hybrid deep learning model, namely convolutional bidirectional long short-term memory model (CBLM) for forecasting the operating and ambient conditions based on the collected time-series data. In addition, we also develop a naïve Bayes classifier to detect abnormal operating and ambient conditions and assist management personnel in scheduling maintenance tasks. To evaluate our framework, we deployed the IoT system in a Hong Kong public toilet, which is the first application of proactive maintenance management for a public hygiene and sanitary facility to the best of our knowledge. We collected the sensed data more than 33 days (808 hours) in this real system. Extensive experiments on the collected data demonstrated that our proposed CBLM outperformed six traditional machine learning algorithms.