Temporal Convolution-based Hybrid Model Approach with Representation Learning for Real-Time Acoustic Anomaly Detection

被引:0
|
作者
Dissanayaka, Sahan [1 ]
Wickramasinghe, Manjusri [1 ]
Marasinghe, Pasindu [1 ]
机构
[1] Univ Colombo, Sch Comp, Colombo, Sri Lanka
关键词
Anomaly Detection; Time Series; Deep Learning; Hybrid Modelling; Signal Processing;
D O I
10.1145/3651671.3651693
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The early detection of potential failures in industrial machinery components is paramount for ensuring the reliability and safety of operations, thereby preserving Machine Condition Monitoring (MCM). This research addresses this imperative by introducing an innovative approach to Real-Time Acoustic Anomaly Detection. Our method combines semi-supervised temporal convolution with representation learning and a hybrid model strategy with Temporal Convolutional Networks (TCN) to handle various intricate anomaly patterns found in acoustic data effectively. The proposed model demonstrates superior performance compared to established research in the field, underscoring the effectiveness of this approach. Not only do we present quantitative evidence of its superiority, but we also employ visual representations, such as t-SNE plots, to further substantiate the model's efficacy.
引用
收藏
页码:218 / 227
页数:10
相关论文
共 50 条
  • [31] Spatio-temporal texture modelling for real-time crowd anomaly detection
    Wang, Jing
    Xu, Zhijie
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 144 : 177 - 187
  • [32] Real-Time Network Anomaly Detection System Using Machine Learning
    Zhao, Shuai
    Chandrashekar, Mayanka
    Lee, Yugyung
    Medhi, Deep
    2015 11TH INTERNATIONAL CONFERENCE ON THE DESIGN OF RELIABLE COMMUNICATION NETWORKS (DRCN), 2015, : 267 - 270
  • [33] Real-Time Anomaly Detection of Network Traffic Based on CNN
    Liu, Haitao
    Wang, Haifeng
    SYMMETRY-BASEL, 2023, 15 (06):
  • [34] Online Learning of Spatial-Temporal Convolution Response for Robust Real-Time Tracking
    Zhou, Jinglin
    Wang, Rong
    Ding, Jianwei
    2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 1821 - 1826
  • [35] A Deep Learning Approach for Real-Time Application-Level Anomaly Detection in IoT Data Streaming
    Raeiszadeh, Mahsa
    Saleem, Ahsan
    Ebrahimzadeh, Amin
    Glitho, Roch H.
    Eker, Johan
    Mini, Raquel A. F.
    2023 IEEE 20TH CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE, CCNC, 2023,
  • [36] A hybrid dynamic graph neural network framework for real-time anomaly detection
    Moraitis, Georgios
    Makropoulos, Christos
    JOURNAL OF HYDROINFORMATICS, 2024,
  • [37] REAL-TIME HYPERSPECTRAL ANOMALY DETECTION USING COLLABORATIVE SUPERPIXEL REPRESENTATION WITH BOUNDARY REFINEMENT
    Lin, Jhao-Ting
    Lin, Chia-Hsiang
    2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 1752 - 1755
  • [38] Learning motion representation for real-time spatio-temporal action localization
    Zhang, Dejun
    He, Linchao
    Tu, Zhigang
    Zhang, Shifu
    Han, Fei
    Yang, Boxiong
    PATTERN RECOGNITION, 2020, 103
  • [39] Hybrid Statistical-Machine Learning for Real-Time Anomaly Detection in Industrial Cyber-Physical Systems
    Hao, Weijie
    Yang, Tao
    Yang, Qiang
    IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2023, 20 (01) : 32 - 46
  • [40] On Real-time and Self-taught Anomaly Detection in Optical Networks Using Hybrid Unsupervised/Supervised Learning
    Chen, X.
    Li, B.
    Shamsabardeh, M.
    Proietti, R.
    Zhu, Z.
    Yoo, S. J. B.
    2018 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC), 2018,