Deep Learning Approaches for Real-Time Anomaly Detection in Industrial IoT Networks

Abstract

This paper presents a novel deep learning framework for detecting anomalies in real-time industrial IoT sensor streams. We propose a hybrid LSTM-autoencoder architecture that achieves 96.4% detection accuracy while maintaining sub-100ms inference latency, making it suitable for deployment on edge devices in manufacturing environments.

Keywords: deep learning, IoT, anomaly detection, edge computing, LSTM

Authors & Affiliations

• Ananya Rao (Corresponding Author) — Vellore Institute of Technology, India
• Karthik Subramaniam — Vellore Institute of Technology, India

How to Cite

APA: Ananya Rao, Karthik Subramaniam (2025). Deep Learning Approaches for Real-Time Anomaly Detection in Industrial IoT Networks. Journal of Innovative Technologies, 1(1), 1-12. https://doi.org/10.5555/jit.2025.00001

MLA: Ananya Rao, et al. "Deep Learning Approaches for Real-Time Anomaly Detection in Industrial IoT Networks." Journal of Innovative Technologies, vol. 1, no. 1, 2025, pp. 1-12.

IEEE: Ananya Rao, Karthik Subramaniam, "Deep Learning Approaches for Real-Time Anomaly Detection in Industrial IoT Networks," Journal of Innovative Technologies, vol. 1, no. 1, pp. 1-12, 2025.

Chicago: Ananya Rao, Karthik Subramaniam. "Deep Learning Approaches for Real-Time Anomaly Detection in Industrial IoT Networks." Journal of Innovative Technologies 1, no. 1 (2025): 1-12.

References

1. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
3. Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1-58.