DOI QR코드

DOI QR Code

Data Processing of AutoML-based Classification Models for Improving Performance in Unbalanced Classes

불균형 클래스에서 AutoML 기반 분류 모델의 성능 향상을 위한 데이터 처리

  • Lee, Dong-Joon (Division of AI Computer Science and Engineering, Kyonggi University) ;
  • Kang, Ji-Soo (Department of Computer Science, Kyonggi University) ;
  • Chung, Kyungyong (Division of AI Computer Science and Engineering, Kyonggi University)
  • 이동준 (경기대학교 AI컴퓨터공학부) ;
  • 강지수 (경기대학교 컴퓨터과학과) ;
  • 정경용 (경기대학교 AI컴퓨터공학부)
  • Received : 2021.05.17
  • Accepted : 2021.06.20
  • Published : 2021.06.28

Abstract

With the recent development of smart healthcare technology, interest in daily diseases is increasing. However, healthcare data has an imbalance between positive and negative data. This is caused by the difficulty of collecting data because there are relatively many people who are not patients compared to patients with certain diseases. Data imbalances need to be adjusted because they affect performance in ongoing learning during disease prediction and analysis. Therefore, in this paper, We replace missing values through multiple imputation in detection models to determine whether they are prevalent or not, and resolve data imbalances through over-sampling. Based on AutoML using preprocessed data, We generate several models and select top 3 models to generate ensemble models.

최근 스마트 헬스케어 기술의 발전에 따라 일상적인 질환에 대한 관심이 증가하고 있다. 이에 따라 헬스케어 데이터를 통해 예측 모델로 질병을 분석하거나 예측하는 연구들이 증가하고 있다. 그러나 헬스케어 데이터에는 양성 데이터와 음성 데이터의 불균형이 존재한다. 이는 특정 질환을 가진 환자에 비하여 상대적으로 환자가 아닌 사람이 많아 데이터 수집에 어려움이 있어 발생하는 현상이다. 데이터 불균형은 질병 예측 및 탐지 시 진행하는 모델의 성능에 영향을 끼치기 때문에 이를 제거할 필요가 있다. 따라서 본 연구에서는 오버샘플링과 결측값 대치를 통해서 데이터 불균형을 해소한다. AutoML을 기반으로 여러 모델의 성능을 파악하고 모델 중 상위 3개의 모델을 앙상블한다.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. 2019R1F1A1058651).

References

  1. J. C. Kim & K. Chung. (2020). Hybrid Multi-Modal Deep Learning using Collaborative Concat Layer in Health Bigdata. IEEE Access, 8, 192469-192480. DOI : 10.1109/ACCESS.2020.3031762
  2. H. Asri, H. Mousannif, H. Al Moatassime & T. Noel. (2015, June). Big data in healthcare: challenges and opportunities. In International Conference on Cloud Technologies and Applications (CloudTech), 1-7.
  3. J. C. Kim & K. Chung. (2020). Multi-modal stacked denoising autoencoder for handling missing data in healthcare big data. IEEE Access, 8, 104933-104943. DOI : 10.1109/ACCESS.2020.2997255
  4. S. V. Buuren & K. Groothuis-Oudshoorn. (2010). mice: Multivariate imputation by chained equations in R. Journal of statistical software, 1-68.
  5. N. V. Chawla, K. W. Bowyer, L. O. Hall & W. P. Kegelmeyer. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357. DOI : 10.1613/jair.953
  6. A. Truong, A. Walters, J. Goodsitt, K. Hines, C. B. Bruss & R. Farivar. (2019). Towards automated machine learning: Evaluation and comparison of AutoML approaches and tools. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence(ICTAI), 1471-1479. DOI : 10.1109/ICTAI.2019.00209
  7. D. J. Lee, J. S. Kang, M. J. Kim, J. W. Baek & K. Chung. (2021). Data Imbalance Processing through Over-sampling in Binary Classification Model. Korean Society For Internet Information Spring Conference, 77-78.
  8. Y. A. Shreider (2014). The Monte Carlo method: the method of statistical trials(Vol. 87). Elsevier.
  9. I. R. White, P. Royston & A. M. Wood. (2011). Multiple imputation using chained equations: issues and guidance for practice. Statistics in medicine, 30(4), 377-399. DOI : 10.1002/sim.4067
  10. C. Gong & L. Gu. (2016). A novel SMOTE-based classification approach to online data imbalance problem. Mathematical Problems in Engineering, 1-14.
  11. The Fifth Korea National Health and Nutrition Examination Survey (KNHANES V-2). (2015). Korea Centers for Disease Control and Prevention.
  12. B. L. Drinkwater, B. Bruemner & C. H. Chesnut. (1990). Menstrual history as a determinant of current bone density in young athletes. Jama, 263(4), 545-548. DOI : 10.1001/jama.1990.03440040084033
  13. Y. Liu, E. B. Gold, B. L. Lasley & W. O. Johnson. (2004). Factors affecting menstrual cycle characteristics. American journal of epidemiology, 160(2), 131-140. DOI : 10.1093/aje/kwh188
  14. J. Hao & T. K. Ho. (2019). Machine learning made easy: A review of scikit-learn package in Python programming language. Journal of Educational and Behavioral Statistics, 44(3), 348-361. DOI : 10.3102/1076998619832248
  15. S. E. Ryu, D. H. Shin & K. Chung. (2020). Prediction model of dementia risk based on XGBoost using derived variable extraction and hyper parameter optimization. IEEE Access, 8, 177708-177720. DOI : 10.1109/ACCESS.2020.3025553