1. NCCU Academic Hub
  2. Publications
  3. College of Commerce
  4. Periodical Articles
  5. Item

Publications-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 Enhancing Anomaly Detection in Structured Data Using Siamese Neural Networks as a Feature Extractor
作者 周珮婷
Chou, Elizabeth P.;Hsieh, Bo-Cheng
貢獻者 統計系
關鍵詞 siamese neural network; anomaly detection; structured data; supervised learning
日期 2025-03
上傳時間 30-Apr-2025 15:03:20 (UTC+8)
摘要 Anomaly detection in structured data presents significant challenges, particularly in scenarios with extreme class imbalance. The Siamese Neural Network (SNN) is traditionally recognized for its ability to measure pairwise similarities, rather than being utilized as a feature extractor. However, in this study, we introduce a novel approach by leveraging the feature extraction capabilities of SNN, inspired by the powerful representation learning ability of neural networks. We integrate SNN with four different classifiers and the Synthetic Minority Over-sampling Technique (SMOTE) for supervised anomaly detection and evaluate its performance across five structured datasets under varying anomaly ratios. Our findings reveal that, when used as a feature extractor, SNN significantly enhances classification performance and demonstrates superior robustness compared to traditional anomaly detection methods, particularly under extreme class imbalance. These results highlight the potential of repurposing SNN beyond similarity learning, offering a scalable and effective feature extraction framework for anomaly detection in structured data applications.
關聯 Mathematics, Vol.13, No.7, 1090
資料類型 article
DOI https://doi.org/10.3390/math13071090
dc.contributor 統計系
dc.creator (作者) 周珮婷
dc.creator (作者) Chou, Elizabeth P.;Hsieh, Bo-Cheng
dc.date (日期) 2025-03
dc.date.accessioned 30-Apr-2025 15:03:20 (UTC+8)-
dc.date.available 30-Apr-2025 15:03:20 (UTC+8)-
dc.date.issued (上傳時間) 30-Apr-2025 15:03:20 (UTC+8)-
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/156774-
dc.description.abstract (摘要) Anomaly detection in structured data presents significant challenges, particularly in scenarios with extreme class imbalance. The Siamese Neural Network (SNN) is traditionally recognized for its ability to measure pairwise similarities, rather than being utilized as a feature extractor. However, in this study, we introduce a novel approach by leveraging the feature extraction capabilities of SNN, inspired by the powerful representation learning ability of neural networks. We integrate SNN with four different classifiers and the Synthetic Minority Over-sampling Technique (SMOTE) for supervised anomaly detection and evaluate its performance across five structured datasets under varying anomaly ratios. Our findings reveal that, when used as a feature extractor, SNN significantly enhances classification performance and demonstrates superior robustness compared to traditional anomaly detection methods, particularly under extreme class imbalance. These results highlight the potential of repurposing SNN beyond similarity learning, offering a scalable and effective feature extraction framework for anomaly detection in structured data applications.
dc.format.extent 100 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) Mathematics, Vol.13, No.7, 1090
dc.subject (關鍵詞) siamese neural network; anomaly detection; structured data; supervised learning
dc.title (題名) Enhancing Anomaly Detection in Structured Data Using Siamese Neural Networks as a Feature Extractor
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.3390/math13071090
dc.doi.uri (DOI) https://doi.org/10.3390/math13071090