머신러닝 모델 학습에서 핵심 데이터속성 기초교육사례
Basic Educational Cases for Key Data Attributes in Machine Learning Model Training
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 머신러닝 모델이 학습데이터, 즉, 독립변수(원인)들로부터 결과를 분류하는 데 있어, 판별 기준이 된 핵심 데 이터 항목(속성, 원인)의 의미와 탐색방법을 교육하는 기초 사례를 제안하였다. 제안하는 교육 사례는 특정 학습데이터를 이해 하는 데 사전지식이 필요 없고, 핵심 데이터 항목의 의미를 쉽게 이해할 수 있도록 이미지 데이터를 사용하였다. 사용된 이미지 데이터는 81개 데이터 항목(원인, Feature)과 이에 따른 분류 결과(Target)를 포함한다. 첫번째로, 수집된 81개 항목의 범주형 데 이터로부터 나타난 특성을 기준으로 분류한 사례에서, 핵심 데이터 항목의 의미와 탐색방법을 설명하였다. 두번째로, 수집된 81개 항목의 수치형 데이터로부터 나타난 특성을 기준으로 분류한 사례에서, 핵심 데이터 항목의 의미와 탐색방법을 설명하였 다. 본 논문에서는 데이터분석에 있어 Orange3를 사용하였다. 본 교육사례는 수집한 원인데이터 항목들 중에서 핵심 항목들을 찾고 그의미를 해석하는 교육에 효과적으로 활용할 수있다.
Abstract
In this paper, we propose a basic case study that teaches the meaning and exploration method of key data items (attributes, causes) that serve as criteria for machine learning models to classify results from learning data, i.e., independent variables (causes). The proposed educational case uses image data so that no prior knowledge is required to understand specific learning data and the mean- ing of key data items can be easily understood. The image data used includes 81 data items (causes, features) and the classification results (targets) based on them. First, in the case of classification based on the characteristics from the collected 81 categorical data items, the meaning and exploration method of key data items were explained. Second, in the case of classification based on the characteristics from the collected 81 numerical data items, the meaning and exploration method of key data items were explained. In this paper, Orange3 was used for data analysis. This educational case study can be effectively utilized for education on finding key items among the collected cause data items and interpreting their meanings.
참고문헌 (16)
- Ministry of Science and ICT, "The 4th industrial revolution in history", R & D kiosk, (40) (2017)
- Ministry of Science and ICT, "The various aspects of the fourth industrial revolution, the realized future", R & D kiosk, (41) (2017)
- Ministry of Science and ICT, "Beyond an IT powerhouse to an AI powerhouse", Report Material, ~ (2019)
- Artificial intelligence national strategy, "Joint Ministries", ~ (2019)
- Y. J. Jang, "Searching for the direction of data science education in the era of the 4th industrial revolution", Integrated Humanities Research, 9(10), pp.155~180 (2017)
- Y. S. Park, "Study on the direction of universal big data and big data education-based on the survey of big data experts", Journal of the Korean Association of Information Education, 24(2), pp.201~214 (2020)
- Y. M. Kim, "Effect of data science education program using spreadsheet on improvement of el-ementary school computational thinking", Journal of the Korean Association of Information Education, 21(2), pp.219~230 (2017)
- J. S. Lee, "A study on visualization methods and expressions of information design for big data", Basic Formulation Studies, 14(3), pp.259~269 (2013)
- K. Hur, "Curriculum of basic data science practices for non-majors", Journal of Practical Engineering Education, 12(2), pp.265~273 (2020)
- "Orange3" (2023)[URL]
- K. Hur, "A machine learning model learning and utilization education curriculum for non-majors", Journal of Practical Engineering Education, 15(1), pp.31~38 (2023)
- J. S. Lim, "I analyze data using Orange3 : Learning AI with Orange3" (2022), Cmath
- "MNIST(Mixed National Institute of Standard and Technology)" (2024)[URL]
- Yosiyuki Wakui, "Learning deeplearning with excel" (2020), Seongandang
- S. E. Moon, "Machine learning and deep learning technology trends", Information and Communication Magazine, 33(10), pp.49~56 (2016)
- B. T. Jang, "Next-generation machine learning technologies", Magazine of Korean Institute of Information Scientists and Engineers, 25(3), pp.96~107 (2007)