Journal of Cadastre & Land InformatiX (지적과 국토정보)

LX Spatial Information Research Institute (한국국토정보공사 공간정보연구원)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Methodology of Extracting the vulnerable districts of the Aged Welfare Using Artificial Intelligence and Geospatial Information

인공지능과 국토정보를 활용한 노인복지 취약지구 추출방법에 관한 연구

  • Park, Jiman (LX Education Institute) ;
  • Cho, Duyeong (Korea Land and Geospatial InformatiX Corporation) ;
  • Lee, Sangseon (Korea Land and Geospatial InformatiX Corporation) ;
  • Lee, Minseob (Korea Land and Geospatial InformatiX Corporation) ;
  • Nam, Hansik (Korea Land and Geospatial InformatiX Corporation) ;
  • Yang, Hyerim (Korea Land and Geospatial InformatiX Corporation)
  • Received : 2018.05.04
  • Accepted : 2018.06.27
  • Published : 2018.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

The social influence of the elderly population will accelerate in a rapidly aging society. The purpose of this study is to establish a methodology for extracting vulnerable districts of the welfare of the aged through machine learning(ML), artificial neural network(ANN) and geospatial analysis. In order to establish the direction of analysis, this progressed after an interview with volunteers who over 65-year old people, public officer and the manager of the aged welfare facility. The indicators are the geographic distance capacity, elderly welfare enjoyment, officially assessed land price and mobile communication based on old people activities where 500 m vector areal unit within 15 minutes in Yongin-city, Gyeonggi-do. As a result, the prediction accuracy of 83.2% in the support vector machine(SVM) of ML using the RBF kernel algorithm was obtained in simulation. Furthermore, the correlation result(0.63) was derived from ANN using backpropagation algorithm. A geographically weighted regression(GWR) was also performed to analyze spatial autocorrelation within variables. As a result of this analysis, the coefficient of determination was 70.1%, which showed good explanatory power. Moran's I and Getis-Ord Gi coefficients are analyzed to investigate spatially outlier as well as distribution patterns. This study can be used to solve the welfare imbalance of the aged considering the local conditions of the government recently.

급속한 고령화 사회에서 노인인구가 갖는 사회적 영향력은 더욱 가속화될 것이다. 본 연구에서는 인공지능 방법론 중 머신러닝, 인공신경망, 국토정보 분석을 통해 노인복지 취약지구를 추출하는 방법론을 정립하는데 목적을 두었다. 분석방향 정립을 위해 65세 이상 노인, 공무원, 노인복지 시설물 담당자와 인터뷰 후 방향을 설정하였다. 경기도 용인시를 대상으로 500 m 공간단위 벡터 기반 격자에 15분 이내 지리적 거리 수용력, 노인복지 향유도, 공시지가, 이동통신 기반 노인활동을 지표로 설정하였다. 10단계 군집형성 후 모의학습 결과 RBF 커널 알고리즘을 활용한 머신러닝 서포트 벡터머신에서 83.2%의 예측정확도가 나타났다. 그리고 역전파 알고리즘을 활용한 인공신경망에서 높은 상관성 결과(0.63)가 나타났다. 변수간 공간적 자기상관성을 분석하기 위해 지리적 가중회귀분석을 수행했다. 분석결과 결정계수가 70.1%로 모형으로 나타나 설명력이 우수한 것으로 나타났다. 변수의 공간적 이상값 여부와 분포패턴을 검토하기 위해 국지적인 공간적 자기상관성 지수인 Moran's I 계수와 Getis-Ord Gi 계수를 분석하였다. 분석결과 용인시 신도시인 수지 기흥구에서 노인복지 취약지구가 발생하는 특성을 보였다. 본 연구의 인공지능 모의방법과 국토정보 분석의 연계는 최근 정부의 지역여건을 고려한 노인복지 불균형을 해결하는데 활용될 수 있을 것이다.

Keywords

References

  1. 국가법령정보센터(Korean Law Information Center of Ministry of Government Legislation). 2017. 노인복지법(WELFARE OF OLDER PERSONS ACT)[http://www.law.go.kr]. Lasted accessed 1 May 2018.
  2. Kim DH, Kang HG, Kim JK, Park J, Kang MK, Sung HJ, Kim EB, 2014. A Study on the Urban Policies Using Space Big Data. KRIHS. 2014-19.
  3. Kim HY, Jun CM. 2012. Land price analysis using spatial syntax and geographically weighted regression, Journal of the Korean Geographical Society. 15(2). p. 35-45.
  4. Kim, HS, Kwon OY, Lee, HJ. 2002. Comparison of Balance and Gait Between Fallers and Non-Fallers in Elderly. The Journal of Korean Society of Physical Therapy. 9(1). p. 3-15.
  5. Nam, WS, Bong IS, Lee, JE. 2012. The Actual Conditions and Supporting Plan of Gyeonggi-do. Journal of the Policy Research. 2012-18. p. 1-129.
  6. Seo SJ, Cha JY, Choi SA, Hyun TH, Park SY. 2015. Realization of the space welfare and improvement of the public building policy for improvement of national life. National Building Policy Committee.
  7. 서울 정책지도 갤러리(Gallery of seoul policy map). 2018. [http://map.seoul.go.kr]. Lasted accessed 1 May 2018.
  8. Son HK, Park KH. 2008. Spatial statistical techniques for searching hotspots. Journal of Korean Geographical Society. 43(3): 392-411.
  9. Ahn, KS. 2016. Comparison and Experiments of k-Nearest Neighbor and Support Vector Machine Classifier based on Machine Learning. Master Thesis. Dankook University. p. 17.
  10. Lee JY. 2001. Land price analysis using spatial statistical analysis of GIS. Master Thesis. KyungHee University. p. 21-53.
  11. Lee HY, Ahn EK. 2016. A Study on the Extraction Method of Poverty and Vulnerable Area by Using Land Information. Journal of Cadastre & Land Informatix. 46(2):5-25. https://doi.org/10.22640/LXSIRI.2016.46.2.5
  12. Im ES, Lee HS, Lee YJ, Jo JI. 2014. Introduction and utilization of spatial statistics convergence model in response to change in demand of national policy. National Policy Brief. 2014-469.
  13. Won, SH, Lee CK, Park JM. 2017. Forecasting of Land Price Using Machine Learning Method. The Geographical Journal of Korea. 51(4): 347-355.
  14. Jun JW, 2011. Comparing the performance of the least squares and penalized soft vector machines. Master Thesis. Dankook University. p. 21-25.
  15. Jung, KH. 2017. Diagnosis and Future Development of the Elderly Welfare Policy. Health and Welfare Forum. p. 18-36.
  16. Jung SH. 2003. A Study on the Selection of Standard Land for Public Land by Analyzing the Spatial Distribution of Land Characteristics and Land Price. Master Thesis. KyungHee University. p. 21-53.
  17. Park. IS, Lee SH, Im TY, Song SH, Woo UJ. 2007. A Study on the Greenhouse Pleasure as a Performance Index of Residential Area: Focusing on the Development of Indicators Comprising Quantitative Performance & Approach Performance of Green Park. Journal of Seoul City Studies. 8(3):161-172.
  18. Choi SJ, Jang IH, 2010. Elderly Welfare in Aging Society. Souel National Univ. Press.
  19. 통계청(Statistic Korea). 2016. 장래인구추계(Future Population Estimation): 2015-2065.
  20. Anselin. 1995. Local Indicators of Spatial Autocorrelation. London: Pind Limited. p. 136-151.
  21. Fotheringham A.S, Brundson, C, Charlton M.B. 2002. Geographically Weighted Regression: the Analysis of Spatially Varying Relationships, West Sussex, John Wiley and Sons Ltd.
  22. Forrester J.W. 1961. Industrial Dynamic. Cambridge, MA, MIT Press.
  23. Ord K, Snyder R, Beaumont A, 2010. Forecasting the Intermittent Demand for Slow-Moving Items, Monash Econometrics and Business Statistics Working Papers. 12(10), Department of Econometrics and Business Statistics.
  24. Sharama R, Ghosh P.K. 2013. Decision tree approach for classification of remotely sensed satellite data using open source support. Jounal of Earth System Science. No.5 1242.
  25. Tobler WR. 1970. Computer Movie Simulating Urban Growth in the Detroit Region. Economic geography. 46:234-240. https://doi.org/10.2307/143141
  26. Karatzoglou K, Hidasi B, Quadrana M, Tikk D. 2016. Parallel Recurrent Neural Network Architectures for Feature: rich Session based Recommendations. Proceedings of the ACM Conference on Recommender Systems. ACM New York. p. 241-248.