본문 바로가기
KERD
논문KCI 등재

Application of Conditional Tabular Generative Adversarial Networks (GAN) for Addressing Class Imbalance in Nationwide Employment Big Data

변해원
한국기계기술학회 (Korean Society of Mechanical Technology)|2024.10|한국기계기술학회지 (Journal of the Korean Society of Mechanical Technology)|제26권 제5호|pp. 911-926|DOI 10.17958/ksmt.26.5.202410.911

2

조회

0

다운로드

0

인용

0

참고문헌

키워드

Predictive ModelingIndustrial Accident산업 재해예측 모델링Return-to-Work PredictionRUSBoost직장 복귀 예측무작위 언더샘플링 부스팅
주제분류기계공학

초록

This study investigates using Conditional Tabular Generative Adversarial Networks (CT-GAN) to generate synthetic data for turnover prediction in large employment datasets. The effectiveness of CT-GAN is compared with Adaptive Synthetic Sampling (ADASYN), Synthetic Minority Over-sampling Technique (SMOTE), and Random Oversampling (ROS) using Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forest (RF), and Extreme Learning Machines (ELM), evaluated with AUC and F1-scores. Results show that GAN-based techniques, especially CT-GAN, outperform traditional methods in addressing data imbalance, highlighting the need for advanced oversampling methods to improve classification accuracy in imbalanced datasets.

Abstract

This study investigates using Conditional Tabular Generative Adversarial Networks (CT-GAN) to generate synthetic data for turnover prediction in large employment datasets. The effectiveness of CT-GAN is compared with Adaptive Synthetic Sampling (ADASYN), Synthetic Minority Over-sampling Technique (SMOTE), and Random Oversampling (ROS) using Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forest (RF), and Extreme Learning Machines (ELM), evaluated with AUC and F1-scores. Results show that GAN-based techniques, especially CT-GAN, outperform traditional methods in addressing data imbalance, highlighting the need for advanced oversampling methods to improve classification accuracy in imbalanced datasets.

참고문헌 (47)

  1. Ge, H., "Study on the application of data visualization technology in human resource management and employee turnover prediction", Applied Mathematics and Nonlinear Sciences, 8(2), pp.123~138 (2023)
  2. Tyagi, P. K., "The Impact of Artificial Intelligence-Based Human Resource Management Systems on Organizational Efficiency", IEEE UPCON, pp.102~107 (2023)
  3. Kumar, P., "Improving Software Defect Prediction using Generative Adversarial Networks", International Journal of Software Engineering and Applications, 9(9), pp.100~115 (2020)
  4. Xue, X., "Neural network fusion with fine-grained adaptation learning for turnover prediction", Complex Systems Informatics and Modeling Quarterly, 26, pp.55~70 (2022)
  5. Rani, S., "Handling Class Imbalance Problem using Oversampling Techniques for Breast Cancer Prediction", IEEE REEDCON, pp.155~160 (2023)
  6. "harms of class imbalance corrections for machine learning-based prediction models: a simulation study" (2024)[URL]
  7. Patil, T, "Credit Card Fraud Detection Using Conditional Tabular Generative Adversarial Networks (CT-GAN) and Supervised Machine Learning Techniques", ~
  8. Alabsi, B. A, "Conditional Tabular Generative Adversarial Based Intrusion Detection System for Detecting Ddos and Dos Attacks on the Internet of Things Networks", Sensors, 23(12), pp.5644~ (2023)[DOI]
  9. Ke, Y., "Gaussian Mixture Conditional Tabular Generative Adversarial Network for Data Imbalance Problem", 2023IEEE 4th International Conference on Software and Services Engineering (ICSEE), pp.210~215 (2023)
  10. Al-Rasheed, A., "An Ensemble of Transfer Learning Models for the Prediction of Skin Lesions with Conditional Generative Adversarial Networks", Contrast Media & Molecular Imaging, 2023, pp.5869513~ (2023)[DOI]
  11. Alfakeeh, A, "Conditional Tabular Generative Adversarial Net for Enhancing Ensemble Classifiers in Sepsis Diagnosis", Advances in Computational Intelligence Systems, 2023 (2023)[DOI]
  12. Amrith, V., S, D., S, S, "An early malware threat detection model using Conditional Tabular Generative Adversarial Network", 2023 International Conference on Computing, Communication, and Networking Technologies (ICCCNT), pp.305~310 (2023)
  13. Duan, Y., "Remaining Useful Life Prediction for Complex Electro-Mechanical System Based on Conditional Generative Adversarial Networks", 2022 15th International Symposium on Systems and Multidisciplinary Research (ISSR), pp.120~125 (2022)
  14. Liu, Y., "Fault Diagnosis Method of Box-Type Substation Based on Improved Conditional Tabular Generative Adversarial Network and AlexNet", Applied Sciences, 14(7), pp.3112~ (2024)[DOI]
  15. Kang, H, "Synthetic Tabular Data Based on Generative Adversarial Networks in Health Care: Generation and Validation Using the Divide-and-Conquer Strategy", JMIR Medical Informatics, 11(5), pp.e47859~ (2023)
  16. Geng, M, "Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks", Materials, 17(5), pp.1142~ (2024)[DOI]
  17. Nigam, A, "Generating Realistic Synthetic Traffic Data using Conditional Tabular Generative Adversarial Networks for Intelligent Transportation Systems", 2023 IEEE International Transport Systems Conference, pp.455~460 (2023)
  18. Al-Rasheed, A, "An Ensemble of Transfer Learning Models for the Prediction of Skin Cancers with Conditional Generative Adversarial Networks", Diagnostics, 12(12), pp.3145~ (2022)[DOI]
  19. Salamon, P., "Handling Class Imbalance Problem using Oversampling Techniques for Breast Cancer Prediction", ~ (1990)
  20. Aljamaan, H, "Leveraging Ensemble Learning with Generative Adversarial Networks for Imbalanced Software Defects Prediction", Applied Sciences, 13(24), pp.13319~ (2023)
  21. Kumari, P., "A comprehensive study of DDoS attacks over IoT network and their countermeasures", Computers & Security, 123, pp.103096~ (2023)
  22. Xu, Y, "Enhancement of Structural Health Monitoring Data Using Conditional Generative Adversarial Networks", Sensors, 23(3), pp.569~ (2023)
  23. "Fraud Detection in E-Commerce Transactions Using Conditional Generative Adversarial Networks and Ensemble Learning Methods" (2023)[URL]
  24. Mansour, R. F, "Hybrid Deep Learning Model for Skin Disease Diagnosis Using Conditional Generative Adversarial Networks", Journal of Medical Systems, 47(1), pp.15~ (2023)
  25. Alfakeeh, A, "Conditional Tabular Generative Adversarial Net for Enhancing Ensemble Classifiers in Sepsis Diagnosis", Advances in Computational Intelligence Systems, 2023 (2023)
  26. Quan, D, "A Novel Double Ensemble Algorithm for the Classification of Multi-Class Imbalanced Hyperspectral Data", Remote Sensing, 14(15), pp.3390~ (2022)[DOI]
  27. Bounab, R., "Enhancing Medicare Fraud Detection Through Machine Learning : Addressing Class Imbalance With SMOTE-ENN", IEEE Access, 12, pp.5781~5791 (2024)
  28. Noviandy, T. R., "Credit Card Fraud Detection for Contemporary Financial Management Using XGBoost-Driven Machine Learning and Data Augmentation Techniques", International Journal of Machine Learning and Applications, 1(1), pp.78~90 (2023)
  29. "Generative Oversampling for Imbalanced Data via Majority-Guided VAE" (2023)[URL]
  30. Alamri, M., "Hybrid Undersampling and Oversampling for Handling Imbalanced Credit Card Data", IEEE Access, 12, pp.7091~7101 (2024)
  31. Untoro, M. C, "Evaluate of Random Undersampling Method and Majority Weighted Minority Oversampling Technique in Resolve Imabalanced Dataset", International Journal of Data Science, 3(4), pp.412~425 (2023)
  32. Lv, M, "Research on imbalanced data: based on SMOTE-AdaBoost algorithm", 2019 International Conference on Electronic Information Technology and Computer Engineering (EITCE), pp.4859~4868 (2019)
  33. He, H, "ADASYN: Adaptive synthetic sampling approach for imbalanced learning", IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp.1322~1328 (2008)
  34. Tyas, S. M. P, "A Robustly Optimized BERT using Random Oversampling for Analyzing Imbalanced Stock News Sentiment Data", IEEE 3rd International Conference on Computer Science and Artificial Intelligence, pp.150~155 (2023)
  35. Chawla, N. V, "SMOTE: Synthetic Minority Over-sampling Technique", Journal of Artificial Intelligence Research, 16, pp.321~357 (2002)
  36. Han, H, "Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning", 2005International Conference on Intelligent Computing (ICIC), pp.878~887 (2005)
  37. He, H, "ADASYN: Adaptive synthetic sampling approach for imbalanced learning", Proceedings of the IEEE International Joint Conference on Neural Networks, pp.1322~1328 (2008)
  38. Lee, S., "Balancing Imbalanced Datasets Using Variational Autoencoders and Synthetic Oversampling: A Comparative Study", Mathematics, 11(2), pp.352~ (2023)
  39. Patil, T., "MSc Research Project and Chakravarthi, B. R., Credit Card Fraud Detection Using Conditional Tabular Generative Adversarial Networks (CT-GAN) and Supervised Machine Learning Techniques", ~
  40. Engelmann, J., "Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learning", Expert Systems with Applications, 162, pp.114582~ (2020)
  41. Cho, H.-Y, "A genetic algorithm to optimize SMOTE and GAN ratios in class imbalanced datasets", ACM Digital Library, pp.219~224 (2020)
  42. Zhao, X., "An Improved D2GANbased oversampling algorithm for imbalanced data classification", Statistical Analysis and Data Mining: The ASA Data Science Journal, 16(1), pp.29~42 (2023)
  43. Eom, G., "Searching for Optimal Oversampling to Process Imbalanced Data:Generative Adversarial Networks and Synthetic Minority Over-Sampling Technique", Mathematics, 11(16), pp.3605~ (2023)[DOI]
  44. Sharma, A, "SMOTified-GAN for Class Imbalanced Pattern Classification Problems", IEEE Access, 9, pp.110434~110445 (2021)
  45. Chen, H.-Y, "Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-body Acceleration Sensors", Sensors, 20(5), pp.1441~ (2020)[DOI]
  46. Xu, C, "Keep it simple: random oversampling for imbalanced data", Mathematics, 11(7), pp.3312~ (2023)[DOI]
  47. Tan, H, "GAN-based Medical Image Augmentation for Improving CNN Performance in Myositis Ultrasound Image Classification", IEEE International Conference on Electronic Technology, Information, and Computer (ICETIC), pp.102~110 (2023)

관련 논문AI추천

Enhancing Imbalanced Binary Classification in Employment Big Data Using TabNet-Driven Generative Adversarial Networks변해원한국기계기술학회 · 한국기계기술학회지2024 · 제26권 제3호Applying TabTransformer and Conditional GAN Algorithms for Enhancing Job Satisfaction Prediction of South Korean College Graduates변해원한국기계기술학회 · 한국기계기술학회지2024 · 제26권 제5호Predictive Modeling for Employee Turnover Intention in South Korea Using CopulaGAN and Isolation Forests변해원한국기계기술학회 · 한국기계기술학회지2024 · 제26권 제6호A Study on the Performance Improvement of Machine LearningClassification Model by Resolving Imbalance in Financial Data: Focusing on Credit Card Accidents김상회, 류혜선, 오경주자연과학연구소 · Quantitative Bio-Science2023 · 제42권 제1호Development of a Prediction Model for Turnover Intentions among Female Wage Workers in South Korea Using Machine Learning and SMOTEENN변해원한국기계기술학회 · 한국기계기술학회지2024 · 제26권 제6호CT-GAN을 활용한 중소기업 채무불이행 예측 연구임병화, 임창민한국금융정보학회 · 금융정보연구2025 · 제14권 제1호

이 간행물의 다른 논문 (49건)

경량화 소재를 적용한 시트 프레임 중량 최적화 해석 연구박동규pp. 821-827Applying TabTransformer and Conditional GAN Algorithms for Enhancing Job Satisfaction Prediction of South Korean College Graduates변해원pp. 828-839표면결함 평가를 위한 유도전류 비파괴검사기법김훈, 문봉호pp. 840-845소방용 모바일 로봇의 발전출력 분석변상호, 이상호, 박다인, 김영렬pp. 846-851설계 제약 조건에 따른 고출력 안테나 소자 온도 평준화를 위한 수치적 방열설계 연구이재훈, 정의봉pp. 852-857
원문 보기