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
  • [1] Real-Time Online Tracking via a Convolution-Based Complementary Model
    Xu Qi
    Wang Huabin
    Zhou Jian
    Tao Liang
    IEEE ACCESS, 2018, 6 : 30073 - 30085
  • [2] An enhanced skin lesion detection and classification model using hybrid convolution-based ensemble learning model
    Nagadevi D.
    Suman K.
    Lakshmi P.S.
    Research on Biomedical Engineering, 2024, 40 (02) : 347 - 372
  • [3] Deep learning based anomaly detection in real-time video
    Elmetwally A.
    Eldeeb R.
    Elmougy S.
    Multimedia Tools and Applications, 2025, 84 (11) : 9555 - 9571
  • [4] Unsupervised Learning Model for Real-Time Anomaly Detection in Computer Networks
    Limthong, Kriangkrai
    Fukuda, Kensuke
    Ji, Yusheng
    Yamada, Shigeki
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2014, E97D (08) : 2084 - 2094
  • [5] 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
  • [6] 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,
  • [7] 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):
  • [8] A Mixed Clustering Approach for Real-Time Anomaly Detection
    Mazarbhuiya, Fokrul Alom
    Shenify, Mohamed
    APPLIED SCIENCES-BASEL, 2023, 13 (07):
  • [9] An Adaptive Approach to Granular Real-Time Anomaly Detection
    Huang, Chin-Tser
    Janies, Jeff
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2009,
  • [10] Fates: A granular approach to real-time anomaly detection
    Janies, Jeff
    Huang, Chin-Tser
    PROCEEDINGS - 16TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATIONS AND NETWORKS, VOLS 1-3, 2007, : 605 - 610