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
来源
2024 16TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND COMPUTING, ICMLC 2024 | 2024年
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
  • [1] Deep learning based anomaly detection in real-time video
    Elmetwally A.
    Eldeeb R.
    Elmougy S.
    Multimedia Tools and Applications, 2025, 84 (11) : 9555 - 9571
  • [2] A Real-Time Deep Learning Approach for Real-World Video Anomaly Detection
    Petrocchi, Stefano
    Giorgi, Giacomo
    Cimino, Mario G. C. A.
    ARES 2021: 16TH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY AND SECURITY, 2021,
  • [3] Real-time traffic incident detection based on a hybrid deep learning model
    Li, Linchao
    Lin, Yi
    Du, Bowen
    Yang, Fan
    Ran, Bin
    TRANSPORTMETRICA A-TRANSPORT SCIENCE, 2022, 18 (01) : 78 - 98
  • [4] Real-Time Pipeline Leak Detection: A Hybrid Deep Learning Approach Using Acoustic Emission Signals
    Saleem, Faisal
    Ahmad, Zahoor
    Kim, Jong-Myon
    APPLIED SCIENCES-BASEL, 2025, 15 (01):
  • [5] An Adaptive Approach to Granular Real-Time Anomaly Detection
    Chin-Tser Huang
    Jeff Janies
    EURASIP Journal on Advances in Signal Processing, 2009
  • [6] Real-time kernel collaborative representation-based anomaly detection for hyperspectral imagery
    Zhao, Chunhui
    Li, Chuang
    Yao, Xifeng
    Li, Wei
    INFRARED PHYSICS & TECHNOLOGY, 2020, 107
  • [7] An Adaptive Approach to Granular Real-Time Anomaly Detection
    Huang, Chin-Tser
    Janies, Jeff
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2009,
  • [8] Comparison of Deep Autoencoder Architectures for Real-time Acoustic Based Anomaly Detection in Assets
    Meire, Maarten
    Karsmakers, Peter
    PROCEEDINGS OF THE 2019 10TH IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS - TECHNOLOGY AND APPLICATIONS (IDAACS), VOL. 2, 2019, : 786 - 790
  • [9] 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,
  • [10] Real-time anomaly detection on surveillance video with two-stream spatio-temporal generative model
    Weijia Liu
    Jiuxin Cao
    Yilin Zhu
    Bo Liu
    Xuelin Zhu
    Multimedia Systems, 2023, 29 : 59 - 71