Proceedings of the International Conference on Innovation & Entrepreneurship in Computing, Engineering & Science Education (InvENT 2024)

<Previous Article In Volume
Next Article In Volume>

Anomaly Detection Model Combined with Attention Mechanisms for Chest X-ray Images

Authors
Tan Yanli1, 2, Azliza Mohd Ali2, *, Sharifalillah Nordin2, Wang Jin1, 2
1Department of Electronic Engineering, Taiyuan Institute of Technology, 030008, Taiyuan, Shanxi, China
2College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, 40450, Selangor, Malaysia
*Corresponding author. Email: azliza@tmsk.uitm.edu.my
Corresponding Author
Azliza Mohd Ali
Available Online 1 December 2024.
DOI
10.2991/978-94-6463-589-8_8How to use a DOI?
Keywords
Anomaly detection; Attention mechanism; ResNet; DenseNet
Abstract

This study introduces CB-ResNet and CB-DenseNet anomaly detection models that utilise attention mechanisms. The objective is to overcome the limitations of classic anomaly detection algorithms, including low detection accuracy and unstable model performance. The backbone network utilises the convolutional block attention mechanism (CBAM) to improve the extraction of target feature information in both spatial and channel dimensions during shallow feature extraction. By assigning importance to the extracted features of the CNN network, the attention mechanism can eliminate irrelevant information and enhance the model’s ability to learn anomalous data features. The experimental findings demonstrate that both CB-ResNet and CB-DenseNet models, which utilise attention mechanisms, may reach detection accuracy over 99%. Furthermore, these models exhibit strong stability and possess a high level of generalisation capability. We gain superior efficiency compared to conventional models such as ResNet and DenseNet.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Innovation & Entrepreneurship in Computing, Engineering & Science Education (InvENT 2024)
Series
Advances in Computer Science Research
Publication Date
1 December 2024
ISBN
978-94-6463-589-8
ISSN
2352-538X
DOI
10.2991/978-94-6463-589-8_8How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Tan Yanli
AU  - Azliza Mohd Ali
AU  - Sharifalillah Nordin
AU  - Wang Jin
PY  - 2024
DA  - 2024/12/01
TI  - Anomaly Detection Model Combined with Attention Mechanisms for Chest X-ray Images
BT  - Proceedings of the International Conference on Innovation & Entrepreneurship in Computing, Engineering & Science Education (InvENT 2024)
PB  - Atlantis Press
SP  - 64
EP  - 74
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-589-8_8
DO  - 10.2991/978-94-6463-589-8_8
ID  - Yanli2024
ER  -