Earticle

초록

영어

This study aims to enhance the efficacy of anomaly detection techniques through the application of autoencoders. Autoencoders, neural network models that compress and reconstruct input data by learning patterns from normal instances, typically struggle with reconstructing anomalous data. To address this limitation, we propose integrating Mahalanobis Distance, a method for measuring the distance between a data point and the distribution center, into the autoencoder's latent space. Our approach diverges from conventional methods by treating reconstruction error as a vector rather than a scalar value, allowing for more granular outlier information. We evaluate the model's performance across multiple metrics, including accuracy, precision, recall, F1 score, and ROC-AUC, utilizing five different scaling techniques. Experimental results indicate that RobustScaler offers superior performance due to its resilience to outliers, ensuring consistent results across varied data distributions. This research contributes to the advancement of anomaly detection methodologies, potentially enhancing their applicability in realworld scenarios.

목차

Abstract
I. INTRODUCTION
II. RELATED WORKS
A. Autoencoder
B. Mahalanobis Distance
C. Vector Reconstruction
D. Scaling methods: Data preprocesing for performance analytics
III. MAHALANOBIS-AUGMENTED VECTOR RECONSTRUCTION OF AUTOENCODER FOR IMPROVED ANOMALY DETECTION
A. Data Handling
B. Model implementation
C. Anomaly detection
D. Performance Comparison
IV. EXPERIMENTAL RESULTS AND ANALYSIS
A. Authors and Affiliations
B. Comparing anomal detection by scalers
C. Performance Metrics Comparison Across Different Scalers
V. CONCLUSON
ACKNOWLEDGMENT
REFERENCES

키워드

저자

• Seung Bum Ha [ Dept. of Computer Engineering Chonnam National University Yeosu, S. Korea ]
• Joon-Goo Shin [ Dept. of Information Security Convergence Chonnam National University GwangJu, S. Korea ]
• Yong-Min Kim [ Dept. of Electronic Commerce Chonnam National University Yeosu, S. Korea ]
• Chang Gyoon Lim [ Dept. of Computer Engineering Chonnam National University Yeosu, S. Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국차세대컴퓨팅학회 학술대회

• 간기

  반년간

• 수록기간

  2021~2025

• 십진분류

  KDC 566 DDC 004