Time-Series Analysis of Sensor Data for Smart Devices
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P129Keywords:
Time-Series Analysis, Sensor Data, Smart Devices, User Activity Modeling, Anomaly Detection, Predictive Maintenance, Health Monitoring, Real-Time Processing, Resource-Constrained Environments, LSTM NetworksAbstract
The rapid influx of intelligent devices has generated enormous amounts of sensor data, with new possibilities for modeling device user behavior and device optimization through predictive maintenance and health monitoring. The thrust of this paper is in the application of time-series analysis methods to comprehend and model sensor data from intelligent devices with a focus on lean methods for low-resource settings. We discuss techniques for identifying patterns of user behavior and device usage, such as statistical models, machine learning models, and deep networks like LSTMs. We also discuss anomaly detection that can predict device failure and track health metrics to facilitate early intervention and maintenance. Examples of real-world applications like predictive maintenance of home automation systems and health monitoring with wearable sensors are presented. All major challenges like computational expense, data quality, and privacy are discussed, and future directions toward extending time-series analysis by using edge computing and future models. The paper concludes by showing the potential of time-series analysis to make devices efficient, enhance user experience, and real-time health monitoring
References
[1] Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2017, April). Deepsense: A unified deep learning framework for time-series mobile sensing data processing. In Proceedings of the 26th international conference on world wide web (pp. 351-360).
[2] Malki, A., Atlam, E. S., & Gad, I. (2022). Machine learning approach of detecting anomalies and forecasting time-series of IoT devices. Alexandria Engineering Journal, 61(11), 8973-8986.
[3] Jirkovský, V., Obitko, M., Novák, P., & Kadera, P. (2014, September). Big Data analysis for sensor time-series in automation. In Proceedings of the 2014 IEEE emerging technology and factory automation (ETFA) (pp. 1-8). IEEE.
[4] Bandyopadhyay, S., Ukil, A., Puri, C., Singh, R., Bose, T., & Pal, A. (2016, June). SensIPro: Smart sensor analytics for Internet of things. In 2016 IEEE Symposium on Computers and Communication (ISCC) (pp. 415-421). IEEE.
[5] Nizam, H., Zafar, S., Lv, Z., Wang, F., & Hu, X. (2022). Real-time deep anomaly detection framework for multivariate time-series data in industrial IoT. IEEE Sensors Journal, 22(23), 22836-22849.
[6] Zainab, A., S. Refaat, S., & Bouhali, O. (2020). Ensemble-based spam detection in smart home IoT devices time series data using machine learning techniques. Information, 11(7), 344.
[7] Cook, A. A., Mısırlı, G., & Fan, Z. (2019). Anomaly detection for IoT time-series data: A survey. IEEE Internet of Things Journal, 7(7), 6481-6494.
[8] Liu, Y., Garg, S., Nie, J., Zhang, Y., Xiong, Z., Kang, J., & Hossain, M. S. (2020). Deep anomaly detection for time-series data in industrial IoT: A communication-efficient on-device federated learning approach. IEEE Internet of Things Journal, 8(8), 6348-6358.
[9] Andrysiak, T., Saganowski, Ł., & Kiedrowski, P. (2017). Anomaly detection in smart metering infrastructure with the use of time series analysis. Journal of Sensors, 2017(1), 8782131.
[10] Kolozali, Ş., Puschmann, D., Bermudez-Edo, M., & Barnaghi, P. (2016). On the effect of adaptive and nonadaptive analysis of time-series sensory data. IEEE Internet of Things Journal, 3(6), 1084-1098.
