Deep learning-based method for detecting anomalies in electromagnetic environment situation

• Published in: Defence technology Vol. 26; no. 8; pp. 231 - 241
• Main Authors: Hu, Wei-lin, Wang, Lun-wen, Peng, Chuang, Zhu, Ran-gang, Zhang, Meng-bo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2023; College of Electronic Engineering,National University of Defense Technology,Hefei,230001,China; KeAi Communications Co., Ltd
• Subjects: Anomaly detection (AD); CNN; Electromagnetic environment situation (EMES); LSTM; Regional features integration; Anomaly detection (AD); CNN; Regional features integration; LSTM; Electromagnetic environment situation (EMES); Anomaly detection(AD); Electromagnetic environment situation(EMES)
• ISSN: 2214-9147; 2096-3459; 2214-9147
• DOI: 10.1016/j.dt.2022.05.011

The anomaly detection of electromagnetic environment situation (EMES) has essential reference value for electromagnetic equipment behavior cognition and battlefield threat assessment. In this paper, we proposed a deep learning-based method for detecting anomalies in EMES to address the problem of relatively low efficiency of electromagnetic environment situation anomaly detection (EMES-AD). Firstly, the convolutional kernel extracts the static features of different regions of the EMES. Secondly, the dynamic features of the region are obtained by using a recurrent neural network (LSTM). Thirdly, the Spatio-temporal features of the region are recovered by using a de-convolutional network and then fused to predict the EMES. The structural similarity algorithm (SSIM) is used to determine whether it is anomalous. We developed the detection framework, de-signed the network parameters, simulated the data sets containing different anomalous types of EMES, and carried out the detection experiments. The experimental results show that the proposed method is effective.