Anomaly Detection in IoT Sensor Data Using Auto Encoder-Based Unsupervised Learning

International Journal of Electronics and Communication Engineering

© 2024 by SSRG - IJECE Journal

Volume 11 Issue 8

Year of Publication : 2024

Authors : Kusuma Shalini, Anvesh Thatikonda

10.14445/23488549/IJECE-V11I8P116

How to Cite?

Kusuma Shalini, Anvesh Thatikonda, "Anomaly Detection in IoT Sensor Data Using Auto Encoder-Based Unsupervised Learning," SSRG International Journal of Electronics and Communication Engineering, vol. 11,  no. 8, pp. 151-159, 2024. Crossref, https://doi.org/10.14445/23488549/IJECE-V11I8P116

Abstract:

In recent years, automated systems have emerged, and these automated systems should take the data through their sensors and identify abnormal patterns called anomalies. Anomaly is an abnormal pattern in sequence data, like malfunctions, hazards, etc., in sequence data. By reading this data continuously from time to time, the model learned the different patterns, such as regular and abnormal, and separated the abnormal patterns. Many researchers have worked on this, using data like environment, industry, etc., and standard pattern identification methods to deep learning models like LSTM. This paper presents a novel approach to detecting anomalies in IoT sensor data, including time, temperature, etc., and trains an unsupervised autoencoder model to predict anomalies at various threshold levels. Moreover, we got the 0.0004720 mean square error, at this level, the data is reconstructed.

Keywords:

IoT sensor data, Anomaly detection, Unsupervised learning, Autoencoder, Deep learning.

References:

[1] Cheng Fan et al., “Analytical Investigation of Autoencoder-Based Methods for Unsupervised Anomaly Detection in Building Energy Data,” Applied Energy, vol. 211, pp. 1123-1135, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Oleksandr I. Provotar, Yaroslav M. Linder, and Maksym M. Veres, “Unsupervised Anomaly Detection in Time Series Using LSTMBased Autoencoders,” IEEE International Conference on Advanced Trends in Information Theory, Kyiv, Ukraine, pp. 513-517, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Sabtain Ahmad et al., “Autoencoder-Based Condition Monitoring and Anomaly Detection Method for Rotating Machines,” 2020 IEEE International Conference on Big Data, Atlanta, GA, USA, pp. 4093-4102, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mary Adkisson et al., “Autoencoder-based Anomaly Detection in Smart Farming Ecosystem,” IEEE International Conference on Big Data, Orlando, FL, USA, pp. 3390-3399, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Zhaomin Chen et al., “Autoencoder-Based Network Anomaly Detection,” Wireless Telecommunications Symposium, Phoenix, AZ, USA, pp. 1-5, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Tie Luo, and Sai G. Nagarajan, “Distributed Anomaly Detection Using Autoencoder Neural Networks in WSN for IoT,” IEEE International Conference on Communications, Kansas City, MO, USA, pp. 1-6, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Geunbae Lee et al., “Unsupervised Anomaly Detection of the Gas Turbine Operation via Convolutional Auto-Encoder,” IEEE International Conference on Prognostics and Health Management, Detroit, MI, USA, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Zhiyuan Li et al., “Unsupervised Machine Anomaly Detection Using Autoencoder and Temporal Convolutional Network,” IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Sajid Nazir, Shushma Patel, and Dilip Patel, “Autoencoder Based Anomaly Detection for SCADA Networks,” International Journal of Artificial Intelligence and Machine Learning, vol. 11, no. 2, pp. 83-99, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Gimin Bae et al., “Autoencoder-Based on Anomaly Detection with Intrusion Scoring for Smart Factory Environments,” Parallel and Distributed Computing, Applications and Technologies, Jeju Island, South Korea, pp. 414-423, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Amgad Muneer et al., “A Hybrid Deep Learning-Based Unsupervised Anomaly Detection in High Dimensional Data,” Computers, Materials & Continua, vol. 70, no. 3, pp. 5363-5381, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sepehr Maleki, Sasan Maleki, and Nicholas R. Jennings, “Unsupervised Anomaly Detection with LSTM Autoencoders Using Statistical Data-Filtering,” Applied Soft Computing, vol. 108, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Yuxin Zhang et al., “Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 2, pp. 2118-2132, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Tingting Chen et al., “Unsupervised Anomaly Detection of Industrial Robots Using Sliding-Window Convolutional Variational Autoencoder,” IEEE Access, vol. 8, pp. 47072-47081, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Di Hu et al., “Anomaly Detection of Power Plant Equipment using Long Short-Term Memory Based Autoencoder Neural Network,” Sensors, vol. 20, no. 21, pp. 1-18, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] David J. Hill, and Barbara S. Minsker, “Anomaly Detection in Streaming Environmental Sensor Data: A Data-Driven Modeling Approach,” Environmental Modelling & Software, vol. 25, no. 9, pp. 1014-1022, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Luis Martí et al., “Anomaly Detection Based on Sensor Data in Petroleum Industry Applications,” Sensors, vol. 15, no. 2, pp. 2774-2797, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Michael A. Hayes, and Miriam A.M. Capretz, “Contextual Anomaly Detection in Big Sensor Data,” IEEE International Congress on Big Data, Anchorage, AK, USA, pp. 64-71, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Julien Rabatel, Sandra Bringay, and Pascal Poncelet, “Anomaly Detection in Monitoring Sensor Data for Preventive Maintenance,” Expert Systems with Applications, vol. 38, no. 6, pp. 7003-7015, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[20] David J. Hill, Barbara S. Minsker, and Eyal Amir, “Real-Time Bayesian Anomaly Detection for Environmental Sensor Data,” Proceedings of the Congress-International Association for Hydraulic Research, vol. 32, no. 2, 2007.
[Google Scholar]
[21] Colin O'Reilly et al., “Anomaly Detection in Wireless Sensor Networks in a Non-Stationary Environment,” IEEE Communications Surveys & Tutorials, vol. 16, no. 3, pp. 1413-1432, 2014.
[CrossRef] [Google Scholar] [Publisher Link]