Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

Research on Mining Technology for Explainable Decision Making

설명가능한 의사결정을 위한 마이닝 기술

  • Kyungyong Chung (Division of AI Computer Science and Engineering, Kyonggi University)
  • 정경용 (경기대학교 AI컴퓨터공학부)
  • Received : 2023.11.23
  • Accepted : 2023.12.28
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Data processing techniques play a critical role in decision-making, including handling missing and outlier data, prediction, and recommendation models. This requires a clear explanation of the validity, reliability, and accuracy of all processes and results. In addition, it is necessary to solve data problems through explainable models using decision trees, inference, etc., and proceed with model lightweight by considering various types of learning. The multi-layer mining classification method that applies the sixth principle is a method that discovers multidimensional relationships between variables and attributes that occur frequently in transactions after data preprocessing. This explains how to discover significant relationships using mining on transactions and model the data through regression analysis. It develops scalable models and logistic regression models and proposes mining techniques to generate class labels through data cleansing, relevance analysis, data transformation, and data augmentation to make explanatory decisions.

데이터 처리 기술은 의사결정을 위해 중요한 역할을 하며, 데이터 결측값 및 이상값 처리, 예측, 추천 모델 등이 포함 된다. 이는 모든 과정과 결과의 타당성, 신뢰성, 정확성에 대한 명확한 설명이 필요하다. 또한 의사결정트리, 추론 등을 이용한 설명가능한 모델을 통해 데이터의 문제를 해결하고, 다양한 유형의 학습을 고려하여 모델 경량화를 진행할 필요가 있다. 육하원칙을 적용한 다중 계층 마이닝 분류 방법은 데이터 전처리 후 트랜잭션에서 빈번하게 발생하는 변수와 속성 간의 다차원 관계를 발견하는 방법이다. 이는 트랜잭션에서 마이닝을 이용하여 유의미한 관계를 발견하고, 회귀분석을 통해 데이터를 모델링 하는 방법을 설명한다. 이에따라 확장 가능한 모델과 로지스틱 회귀모델을 개발하고, 데이터 정제, 관련성 분석, 데이터 변환, 데이터 증강을 통해 클래스 레이블을 생성하여 설명가능한 의사결정을 위한 미이닝 기술을 제안한다.

Keywords

Acknowledgement

이 논문은 2023학년도 경기대학교 연구년 수혜로 연구되었음.

References

  1. B. H. Van der Velden, H. J. Kuijf, K. G. Gilhuijs, M. A. Viergever, "Explainable artificial intelligence (XAI) in deep learning-based medical image analysis," Med. Image Anal., vol. 79, pp. 102470-102490, 2022. https://doi.org/10.1016/j.media.2022.102470
  2. D. Song, J. Yao, Y. Jiang, S. Shi, C. Cui, L. Wang, F. Dong, "A new xAI framework with feature explainability for tumors decision-making in Ultrasound data: comparing with Grad-CAM," Comput. Methods Programs Biomed., vol. 235, pp. 107527-107528, 2023. https://doi.org/10.1016/j.cmpb.2023.107527
  3. L. Weber, S. Lapuschkin, A. Binder, W. Samek, "Beyond explaining: Opportunities and challenges of XAI-based model improvement," Inf. Fusion, vol. 92, pp. 154-176, 2022. https://doi.org/10.1016/j.inffus.2022.11.013
  4. A. Singh, S. Sengupta, V. Lakshminarayanan, "Explainable deep learning models in medical image analysis", J. Imaging, vol. 6, no.6, pp. 52-70, 2020. https://doi.org/10.3390/jimaging6060052
  5. M. R. Zafar, N. Khan, "Deterministic local interpretable model-agnostic explanations for stable explainability", Mach. learn. knowl. extr. vol. 3, no. 3, pp. 525-541, 2021. https://doi.org/10.3390/make3030027
  6. T. Hong, J. Won, E. Kim, M. Kim, "The Prediction of Cryptocurrency Prices Using eXplainable Artificial Intelligence based on Deep Learning", J Intell Inform Syst, vol. 29, no. 2, pp. 129-148. 2023. https://doi.org/10.13088/JIIS.2023.29.2.129
  7. L. K. Branting, C. Pfeifer, B. Brown, L. Ferro, J. Aberdeen, B. Weiss, B. Liao, "Scalable and explainable legal prediction", Artif. Intell. Law. vol. 29, pp,. 213-238, 2021. https://doi.org/10.1007/s10506-020-09273-1
  8. J. Bai, S. Park "LEXAI : Legal Document Similarity Analysis Service using Explainable AI", .J. of KIISE, vol. 47, no. 11, pp. 1061-1070, 2020. https://doi.org/10.5626/JOK.2020.47.11.1061
  9. M. Cui, "Introduction to the k-means clustering algorithm based on the elbow method. Accounting", J. Account. Audit. Finance, vol. 1, no. 1, pp. 5-8, 2020.
  10. Z. Li, "Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost," Comput Environ Urban Syst, vol. 96, pp. 101845-101872, 2022.
  11. J. Ren, Z. Yu, G. Gao, G. Yu, J. Yu, "A CNN-LSTM-LightGBM based short-term wind power prediction method based on attention mechanism," Energy Rep., vol. 8, pp. 437-443, 2022. https://doi.org/10.1016/j.egyr.2022.02.206
  12. B. U. Jeon, K. Chung, "CutPaste-based Anomaly Detection Model using Multi-cale Feature Extraction in Time Series Streaming Data," KSII Transactions on Internet and Information Systems, Vol. 16, No. 8, pp. 2787-2800, 2022.
  13. H. Yoo, R. C. Park, K. Chung, "IoT-Based Health Big-Data Process Technologies: A Survey," KSII Transactions on Internet and Information Systems, Vol. 15, No. 3, pp. 974-992, 2021. https://doi.org/10.3837/tiis.2021.03.009