본문 바로가기
KERD
논문KCI 등재

과학영재교육에서의 머신러닝 활용 튜토리얼 : 서울 지역 일별 기온 변화 데이터를 중심으로

A Tutorial for applying Machine Learning to the Science Education for the Gifted : Focus on the Daily Temperature of Seoul

0

조회

0

다운로드

9

인용

0

참고문헌

키워드

초록

본 연구는 인공지능과 빅데이터를 활용해 어떻게 과학영재교육에 활용할 수 있는 방법과 기대 효과를 도출하기 위해 이뤄졌다. 본 연구에서는 서울 지역의 일별 기온 데이터의 분석 과정을 중심으로 머신러닝의 수행과정과 과학적 탐구의 요소나 속성 등을 비교하며 어떻게 교수학습이 가능한지 소개하였다. 기온 데이터를 활용해 장기적 기온 변화를 예측하는 4가지 모델을 개발하고, 정확도를 서로 비교하였다. 이와 같은 과정을 통해 과학영재교육에서 인공지능 활용이 갖는 장점은 다음과 같다. 첫째, 학생들이 경험하는 문제 발견 과정에서의 어려움을 줄일 수 있다. 둘째, 데이터의 중요성을 이해하고 데이터의 가공 및 분석 방법을 학습할 수 있다. 셋째, 다양한 모델을 적용한 분석과 반복적인 시행을 통해 실제 탐구에서 경험하는 노력이나 비용 등을 줄이는 경제적 효과를 갖고 있다. 이러한 결과를 토대로 본 연구에서는 과학영재교육에서 인공지능을 활용하는 데 필요한 과제들에 대해 제시하고자 하였다.

Abstract

The purpose of this study was to investigate how big data and artificial intelligence (AI) could be applied to science education for the gifted and to suggest the expected outcomes through machine learning approach to scientific inquiry. Thus, the researcher illustrated the process to predict long-term temperature changes in Seoul depending on different methods of machine learning using open source of data provided by the Korea Meteorological Agency, and compared characteristics of scientific inquiry and machine learning process. In this study, four different models were developed and evaluated as listed: Random Forest, Gradient Boosting, Support Vector Machine and Long Short Term Memory. According to the results of this study, machine learning approach helped to relived gifted students’ difficulties in identifying problems, provided them with opportunities to learn the significance of data and data engineering, and helped to implement a variety of studies and investigations compared to the traditional experimental activities. Based on the points addressed, this study gave some implications for doing AI-based education for the scientifically gifted.

참고문헌 (54)

  1. "NCS 및 학습모듈 : 인공지능" (2021)[URL]
  2. 김수환, "해외 인공지능 교육동향과학습도구 분석", 한국컴퓨터교육학회 학술대회발표논문집, 23(2), pp.25~28 (2019)
  3. 김수환, "K-12 학생 및 교사를 위한 인공지능 교육에 대한 고찰", 컴퓨터교육학회 논문지, 23(4), pp.1~11 (2020), 한국컴퓨터교육학회[DOI]
  4. Youngmin Kim, "An Analysis on Problem-Finding Patterns of Well-Known Creative Scientists", Journal of The Korean Association For Research In Science Education, 33(7), pp.1285~1299 (2013), The Korean Association for Science Education[DOI]
  5. 김영민, "과학과 과학교육에서 문제 발견과 귀추" (2017), 북스힐
  6. 김영화, "뉴턴의 빛과 색 이론 형성 과정에서의 과학적 문제 발견과 귀추적 사고", 새물리, 56(3), pp.162~170 (2008), 한국물리학회
  7. 김하늘, "한국형 데이터 시각화 리터러시 평가 개발 및 연구 동향 분석", 한국정보통신학회논문지, 25(11), pp.1696~1707 (2021), 한국정보통신학회
  8. 2021년 KISTEP 미래유망기술 선정에 관한 연구, "박노언", 한국과학기술기획평가원, ~ (2021)
  9. 박미진, "How the Science Gifted Connect and Integrate Science Concepts in the Process of Problem Finding", Journal of Science Education, 42(2), pp.256~271 (2018), Science Education Research Institute[DOI]
  10. 박병익, "서울의 겨울철 일평균 기온에 나타난 계절 추이의 변화", 대한지리학회지, 46(2), pp.152~167 (2011), 대한지리학회
  11. 성상하, "미세먼지 예측을 위한 기계학습 모델 간 성능 비교 연구:국내 발생 데이터를 중심으로", 한국혁신학회지, 15(4), pp.339~357 (2020), 한국혁신학회
  12. 디지털 대전환 시대의 모든아이를 위한 보편적 정보 교육 확대 방안, "소프트웨어정책연구소", 소프트웨어정책연구소, ~ (2021)
  13. Jiyoung Song, "Analysis of Characteristics of Middle School Science Gifted Students Facing Discrepant Experimental Cases", Korean Science Education Society for the Gifted, 10(2), pp.63~74 (2018), Korean Science Education Society for the Gifted[DOI]
  14. 장진아, "인공지능 챗봇 관련 국내 연구 동향 및 챗봇 활용 현황 분석: 과학 교육에서의 활용을 위한 시사점을 중심으로", 학습자중심교과교육연구, 21(13), pp.729~743 (2021), 학습자중심교과교육학회
  15. Eunyoung Jeong, "Science Integrated Process Skill of the Students in Science Education Center for the Gifted", Journal of Science Education, 37(3), pp.525~537 (2013), Science Education Research Institute[DOI]
  16. 조헌국, "2015 개정 교육과정에서 나타나는 과학적 탐구 요소 분석: 과학탐구실험을 중심으로", Journal of Research in Curriculum Instruction, 22(3), pp.208~218 (2018), Research Institute of Curriculum and Instruction[DOI]
  17. Hunkoog JHO, "Implications for Scientific Inquiry Through the Case Studies on the Physicists??Problem Identification", New Physics: Sae Mulli, 71(1), pp.86~97 (2021), Korean Physical Society[DOI]
  18. 4차 산업혁명 대응을위한 인공지능 인재양성 방안 연구, "추형석", 소프트웨어정책연구소, ~ (2019)
  19. 과학교육 종합계획(2020~2024), "한국과학창의재단", 교육부, ~ (2020)
  20. IT기반 미래사회 기반연구, "한국정보화진흥원", 과학기술정보통신부, ~ (2019)
  21. 한지윤, "인공지능교육 관련 연구 동향 분석 : 키워드 네트워크 분석", 인공지능연구 논문지, 1(2), pp.20~33 (2020)
  22. Jihyun Han, "Variance Analysis of RCP4.5 and 8.5 Ensemble Climate Scenarios for Surface Temperature in South Korea", Journal of Climate Change Research, 9(1), pp.103~115 (2018), The Korean Society of Climate Change Research[DOI]
  23. Kyeong Hur, "A Study on Elementary Education Examples for Data Science using Entry", Journal of The Korean Association of Information Education, 24(5), pp.473~481 (2020), Korean Association of Information Education[DOI]
  24. "AI for kids" (2021)[URL]
  25. Aggarwal, C. C., "Neural networks and deep learning : A textbook" (2018), Springer
  26. P. Arpaia, "Machine learning for beam dynamics studies at the CERN Large Hadron Collider", Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 985, pp.164652~ (2021), Elsevier BV[DOI]
  27. "The artificial intelligence for K-12 initiatives" (2021)[URL]
  28. Bailer-Jones, D., "Scientific models in philosophy of science" (2009), The University of Pittsburgh Press
  29. Leo Breiman, "Random forests", Machine Learning, 45(1), pp.5~32 (2001), Springer Science and Business Media LLC[DOI]
  30. Brunton, S. L., "Data-driven science and engineering : Machine learning, dynamical systems and control" (2019), Cambridge University Press
  31. Buck, S. F., "A method of estimation of missing values in multivariate data suitable for use with an electronic computer", Journal of the Royal Statistical Society, 22(2), pp.302~306 (1960)
  32. Carpenter, J. R., "Multiple imputation and its application" (2013), John Wiley & Sons
  33. Chen, T., "XGBoost: A scalable tree boosting system", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)
  34. ShaoHui Chi, "Investigating disciplinary context effect on student scientific inquiry competence", International Journal of Science Education, 41(18), pp.2736~2764 (2019), Informa UK Limited[DOI]
  35. Cohen, M. X., "Analyzing neural time series data : Theory and practice" (2014), The MIT Press
  36. Comparat, J., "The final SDSS-IV", SPIDERS x-ray point source spectroscopic catalogue, 2020, pp.636, 22~
  37. Drucker, H., "Support vector regression machines", Neural Information Processing Systems, 9, pp.155~161 (1997)[DOI]
  38. Su-Chi Fang, "Investigating the effects of structured and guided inquiry on students’ development of conceptual knowledge and inquiry abilities: a case study in Taiwan", International Journal of Science Education, 38(12), pp.1945~1971 (2016), Informa UK Limited[DOI]
  39. Discriminatory analysis:Nonparametric discrimination consistency properties, "Fix, E.", USAF School of Aviation Medicine, ~, pp.No. 21-49-004 (1951)
  40. "Top strategic technology trends for 2022:12 trends shaping the future of digital business" (2021)[URL]
  41. Goodfellow, I., "Deep learning" (2016), The MIT Press
  42. Hapke, H., "Building machine learning pipelines : Automating model life cycles with tensorflow" (2020), O’Reilly
  43. Hebb, D. O., "The organization of behavior : A neuropsychological theory" (2009), Lawrence Erlbaum Associates
  44. "The 5 V’s of big data" (2016)[URL]
  45. Marcano-Cedeño, A., "Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network", IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society, pp.2845~2850 (2010)
  46. Moore, C., "Creating scientists : Teaching and assessing science practice for the NGSS" (2018), Routledge
  47. National Research Council, "How students learn : History, mathematics, and science in the classroom" (2005), The National Academy Press
  48. National Research Council, "A framework for K-12science education : Practices, crosscutting concepts, and core ideas" (2011), National Academy Press
  49. Pickover, C. A., "Artificial intelligence : An illustrated history – From medieval robots to neural networks" (2019), Sterling
  50. Vlachas, P. R., "Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks", Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 474, pp.20170844~ (2018)
  51. Westfall, P. H., "Understanding regression analysis" (2020), CRC Press
  52. Wilke, C. O., "Fundamentals of data visualization : A primer on making informative and compelling figures" (2019), O’Reilly
  53. World Economic Forum, "Top 10 emerging technologies of 2020" (2020), World Economic Forum
  54. Zheng, A., "Feature engineering for machine learning" (2018), O’Reilly

관련 논문AI추천

이 간행물의 다른 논문 (11건)