Please use this identifier to cite or link to this item:
Title: Deep anomaly detection for time-series data in industrial IoT: a communication-efficient on-device federated learning approach
Authors: Liu, Yi
Garg, Sahil
Nie, Jiangtian
Zhang, Yang
Xiong, Zehui
Kang, Jiawen
Hossain, M. Shamim
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: 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.
Journal: IEEE Internet of Things Journal 
Abstract: Since edge device failures (i.e., anomalies) seriously affect the production of industrial products in Industrial IoT (IIoT), accurately and timely detecting anomalies is becoming increasingly important. Furthermore, data collected by the edge device may contain the user's private data, which is challenging the current detection approaches as user privacy is calling for the public concern in recent years. With this focus, this paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. Specifically, we first introduce a FL framework to enable decentralized edge devices to collaboratively train an anomaly detection model, which can improve its generalization ability. Second, we propose an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model to accurately detect anomalies. The AMCNN-LSTM model uses attention mechanism-based CNN units to capture important fine-grained features, thereby preventing memory loss and gradient dispersion problems. Furthermore, this model retains the advantages of LSTM unit in predicting time series data. Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-k selection to improve communication efficiency. Extensive experiment studies on four real-world datasets demonstrate that the proposed framework can accurately and timely detect anomalies and also reduce the communication overhead by 50% compared to the federated learning framework that does not use a gradient compression scheme.
ISSN: 2327-4662
DOI: 10.1109/JIOT.2020.3011726
Schools: School of Computer Science and Engineering 
Interdisciplinary Graduate School (IGS) 
Research Centres: Energy Research Institute @ NTU (ERI@N) 
Alibaba-NTU Joint Research Institute
Rights: © 2020 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:ERI@N Journal Articles
IGS Journal Articles
SCSE Journal Articles

Citations 5

Updated on Sep 24, 2023

Web of ScienceTM
Citations 5

Updated on Sep 29, 2023

Page view(s)

Updated on Sep 29, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.