DOI QR코드

DOI QR Code

기계학습 알고리즘을 이용한 보행만족도 예측모형 개발

Developing a Pedestrian Satisfaction Prediction Model Based on Machine Learning Algorithms

  • 투고 : 2019.01.28
  • 심사 : 2019.06.04
  • 발행 : 2019.06.30

초록

In order to develop pedestrian navigation service that provides optimal pedestrian routes based on pedestrian satisfaction levels, it is required to develop a prediction model that can estimate a pedestrian's satisfaction level given a certain condition. Thus, the aim of the present study is to develop a pedestrian satisfaction prediction model based on three machine learning algorithms: Logistic Regression, Random Forest, and Artificial Neural Network models. The 2009, 2012, 2013, 2014, and 2015 Pedestrian Satisfaction Survey Data in Seoul, Korea are used to train and test the machine learning models. As a result, the Random Forest model shows the best prediction performance among the three (Accuracy: 0.798, Recall: 0.906, Precision: 0.842, F1 Score: 0.873, AUC: 0.795). The performance of Artificial Neural Network is the second (Accuracy: 0.773, Recall: 0.917, Precision: 0.811, F1 Score: 0.868, AUC: 0.738) and Logistic Regression model's performance follows the second (Accuracy: 0.764, Recall: 1.000, Precision: 0.764, F1 Score: 0.868, AUC: 0.575). The precision score of the Random Forest model implies that approximately 84.2% of pedestrians may be satisfied if they walk the areas, suggested by the Random Forest model.

키워드

참고문헌

  1. Kim, C.G., Im, H.N., and Choi, C.G., 2016. "Built Environment, Walking Trip for Different Purposes, and Pedestrian Satisfaction", Journal of Korea Planning Association, 51(4):145-159.
  2. Park, K.D., 2018. "Analysis of Walking Satisfaction of Street Image Using Deep Learning and Google Street View API", Master's Degree Dissertation, Hanyang University.
  3. Park, S.H., Choi, Y.M., Seo, H.L., and Kim, J.H., 2009. "Perception of Pedestrian Environment and Satisfaction of Neighborhood Walking: An Impact Study Based on Four Residential Communities in Seoul, Korea", Journal of the Architectural Institute of Korea Planning & Design, 25(8): 253-261.
  4. Bae, S.W. and Yu, J.S., 2018. "Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model", Housing Studies Review, 26(1): 107-133.
  5. Sung, H.G., Kim, T.H., and Kang, J.W., 2011. "A Study on Evaluation of User Satisfaction for Walking Environment Planning Elements through Structural Equation Modeling: The Case of Jongno and Kangnam Areas", Journal of Korea Planning Association, 46(5): 275-288.
  6. Song, S.W., 2018. "Assess the Accuracy of Diagnostic Tools", Korean Journal of Family Medicine, 8(1): 1-2.
  7. Shim, J.H., Cho, C.H., and Lee, S.H., 2007. "The Industrial Land Price Appraisal Based on Artificial Neural Network", Journal of Korea Planning Association, 46(1): 223-232.
  8. Lee, Y.S. and Moon, P.J., 2017. "A Comparison and Analysis of Deep Learning Framework", The Journal of the Korea Institute of Electronic Communication Sciences, 2(1): 115-122.
  9. Lee, S.G., Lee, Y.S., and Lee, C.K., 2014. "An Analysis of Street Environment Affecting Pedestrian Walking Satisfaction for Different Age Groups", Journal of Korea Planning Association, 49(8): 91-105. https://doi.org/10.17208/jkpa.2014.12.49.8.91
  10. Lee, S.G., Ko, J.H., and Lee, G.H., 2016. "An Analysis of Neighborhood Environment Affecting Walking Satisfaction: Focused on the 'Seoul Survey' 2013", Journal of Korea Planning Association, 51(1): 169-187.
  11. Lee, I.S. and Kim, H.O., 1998. "Pedestrian Path-choice Behavior in Urban Residential Area: Analysis of Environmental Satisfaction Using GIS", Journal of Korea Planning Association, 33(5): 117-129.
  12. Lee, I.S., 2000. "Development of Pedestrian Path-choice Model in Urban Residential Area: Comparison of Importance, Satisfaction, and Environmental Tradeoff Models", Journal of The Urban Design Institute of Korea, 1(1): 63-78.
  13. Lee, H.J. and Lee, S.G., 2018. "Study on On-street Parking Detection on Community Road using Google Street View API and Deep Learning", Paper presented at the 2018 Spring Congress of Korean Society for Geospatial Information Science, Jinju: Gyeongnam National University of Science and Technology, 79-88.
  14. Im, H.N., Kim, T.H., and Choi, C.G., 2014. "What Variables Make the Perceived Walking Distance Shorter than Real Physical Distance?", Journal of the Korea Planning Association, 49(7): 97-115. https://doi.org/10.17208/jkpa.2014.11.49.7.97
  15. Ji, W.S., Koo, Y.S., and Jwa, S.H., 2008. "A Study on Satisfaction for Pedestrian Environment", Gyeonggi: Gyeonggi Research Institute.
  16. Ha, J.H. and Lee, S.G., 2017. "A Study on the Prediction of Residential Location Choice and Commuting Pattern using the Multi-layered Perceptron Deep Learning Technique: Focused on the Mobility Level of the Seoul Metropolitan Household Travel Survey", Paper presented at the 2006 Fall Congress of Korea Planning Association, Wonju: Sangji University.
  17. Amerigo, M. and Aragones, J.I., 1997. "A Theoretical and Methodological Approach to the Study of Residential Satisfaction", Journal of Environmental Psychology. 17: 47-57. https://doi.org/10.1006/jevp.1996.0038
  18. Buduma, N., 2017. Fundamentals of Deep Learning: Designing Next-generation Machine Intelligence Algorithms, Sebastopol, California: O'Reilly Media.
  19. Brieman, L., 2001. "Random Forests", Machine Learning, 45(1): 5-32. https://doi.org/10.1023/A:1010933404324
  20. Kim, S.H., Park, S.J., and Lee, J.S. 2014. "Meso- or Micro-scale? Environmental Factors Influencing Pedestrian Satisfaction", Transportation Research Part D, 30: 10-20. https://doi.org/10.1016/j.trd.2014.05.005
  21. Methorst, R. and Horst, R., 2010. "Pedestrians' Performance and Satisfaction", Paper presented at the Walk21 Conference, Hague, Netherlands.
  22. Muller, A. and Guido, S., 2016. Introduction to Machine Learning with Python: A Guide for Data Scientists, Sebastopol, California: O'Reilly Media.
  23. Wang, W., Li, P., Wang, W., and Namgung, M., 2012. "Exploring Determinants of Pedestrians' Satisfaction with Sidewalk Environments: Case Study in Korea", Journal of Urban Planning and Development, 138(2): 166-172. https://doi.org/10.1061/(ASCE)UP.1943-5444.0000105

피인용 문헌

  1. Determining the Tiers of a Supply Chain Using Machine Learning Algorithms vol.13, pp.10, 2021, https://doi.org/10.3390/sym13101934