Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Demand Forecasting Model for Public Bicycles in Seoul Using GRU

GRU 기법을 활용한 서울시 공공자전거 수요예측 모델 개발

  • Lee, Seung-Woon (Graduate School of Business IT, Kookmin University) ;
  • Kwahk, Kee-Young (College of Business Administration / Graduate School of Business IT, Kookmin University)
  • 이승운 (국민대학교 비즈니스IT전문대학원) ;
  • 곽기영 (국민대학교 경영대학 / 비즈니스IT전문대학원)
  • Received : 2022.07.05
  • Accepted : 2022.08.12
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

After the first Covid-19 confirmed case occurred in Korea in January 2020, interest in personal transportation such as public bicycles not public transportation such as buses and subways, increased. The demand for 'Ddareungi', a public bicycle operated by the Seoul Metropolitan Government, has also increased. In this study, a demand prediction model of a GRU(Gated Recurrent Unit) was presented based on the rental history of public bicycles by time zone(2019~2021) in Seoul. The usefulness of the GRU method presented in this study was verified based on the rental history of Around Exit 1 of Yeouido, Yeongdengpo-gu, Seoul. In particular, it was compared and analyzed with multiple linear regression models and recurrent neural network models under the same conditions. In addition, when developing the model, in addition to weather factors, the Seoul living population was used as a variable and verified. MAE and RMSE were used as performance indicators for the model, and through this, the usefulness of the GRU model proposed in this study was presented. As a result of this study, the proposed GRU model showed higher prediction accuracy than the traditional multi-linear regression model and the LSTM model and Conv-LSTM model, which have recently been in the spotlight. Also the GRU model was faster than the LSTM model and the Conv-LSTM model. Through this study, it will be possible to help solve the problem of relocation in the future by predicting the demand for public bicycles in Seoul more quickly and accurately.

2020년 1월 국내에 첫 코로나19 확진자가 발생한 후 버스와 지하철 같은 대중교통이 아닌 공공자전거와 같은 개인형 이동수단에 대한 관심이 증가하였다. 서울시에서 운영하는 공공자전거인 '따릉이'에 대한 수요 역시 증가하였다. 본 연구에서는 서울시 공공자전거의 최근 3년간(2019~2021) 시간대별 대여이력을 바탕으로 게이트 순환 유닛(GRU, Gated Recurrent Unit)의 수요예측 모델을 제시하였다. 본 연구에서 제시하는 GRU 방법의 유용성은 서울시 영등포구 여의도에 위치한 여의나루 1번 출구의 대여이력을 바탕으로 검증하였다. 특히, 동일한 조건에서 다중선형회귀 모델 및 순환신경망 모델들과 이를 비교 분석하였다. 아울러, 모델 개발시 기상요소 이외에 서울시 생활인구를 변수로 활용하여 이에 대한 검증도 함께 진행하였다. 모델의 성능지표로는 MAE와 RMSE를 사용하였고, 이를 통해 본 연구에서 제안하는 GRU 모델의 유용성을 제시하였다. 분석결과 제안한 GRU 모델이 전통적인 기법인 다중선형회귀 모델과 최근 각광받고 있는 LSTM 모델 및 Conv-LSTM 모델보다 예측 정확도가 높게 나타났다. 또한 분석에 소요되는 시간도 GRU 모델이 LSTM 모델, Conv-LSTM 모델보다 짧았다. 본 연구를 통해 서울시 공공자전거의 수요예측을 보다 빠르고 정확하게 하여 향후 재배치 문제 등의 해결에 도움이 될 수 있을 것이다.

Keywords

References

  1. Bae, Y. I., and H. R. Shin, "Covid-19 accelerates untact society," Gyeonggi Research Institute, 2020, Available at https://www.gri.re.kr/, (Downloaded 5 May, 2022).
  2. Baik, G. E., and J. H. Cho, "Data mart design and implementation research for public bicycle rental pattern analysis," Proceedings of Korean Academic Society Of Business Administration Conference, (2021), 199~212.
  3. Cao, K., H. G. Kim, C. H. Hwang, and H. K. Jung, "CNN-LSTM Coupled Model for Prediction of Waterworks Operation Data," Journal of Information Processing Systems, Vol.14, No.6 (2018), 1508~1520. https://doi.org/10.3745/JIPS.02.0104
  4. Gwak. J. H., H. R. Oh, S. Y. Na, S. J. Lee, and D. G. Ku, "The change of traffic behavior in seoul by covid-19: focusing on shared bicycle," Proceedings of the Korea Society of Transportation Conference, (2020), 440~441.
  5. Han, E. R., J. Y. Hong, and D. J. Park, "A study on the real-time demand forecasting model for public bicycles in seoul using the LSTM Model". Proceedings of the Korean Society of Transportation Conference, (2021), 559~564.
  6. Hochreiter, S., and J. Schmidhuber, "Long Short-Term Memory", Neural computation, Vol.9, No.8 (1997), 1735~1780. https://doi.org/10.1162/neco.1997.9.8.1735
  7. Hong, S.M., and H. C. Kim, "Demand prediction of bicycle-sharing system in the Bay Area using machine learning," Proceeding of Korea Software Congress, (2017), 1977~1979.
  8. James, G., D. Witten, T. Hastie, and R. Tibshirani, "An Introduction to Statistical Learning," New York : springer, (2013), 112.
  9. Jang, J.M., S. B. Lee, Y. I. Lee, and M. Y. Lee, "Effects of Seasonal and Membership Characteristics on Public Bicycle Traffic: Focusing on the Seoul Bike", International journal of highway engineering, Vol20, No.4(2018), 47~58.
  10. Jeong, H.R., and C. W. Lim, "A review of artificial intelligence based demand forecasting techniques," The Korean Journal of Applied Statistics, Vol.32, No.6(2019), 795~835. https://doi.org/10.5351/KJAS.2019.32.6.795
  11. Kim, D. H., and H. J. Lim, "Development of demand forecasting algorithms based on ARIMA model variations for public shared bike service in Seoul," International Telecommunications Policy Review, Vol.21, No.1(2022), 49~74.
  12. Kim, J. H., J. H. Choi, and C. W. Kang, "Time series prediction using recurrent neural network," Journal of The Korean Data Analysis Society, Vol.21, No.4(2019), 1771~1779. https://doi.org/10.37727/jkdas.2019.21.4.1771
  13. Kim, J. H., and J. Y. Kim, "Comparative analysis of performance of BI-LSTM and GRU algorithm for predicting the number of Covid-19 confirmed cases," Journal of the Korea Institute of Information and Communication Engineering, Vol.26, No.2(2022), 187~192. https://doi.org/10.6109/JKIICE.2022.26.2.187
  14. Kim, K. S., and Y. J. Seo, "A proposal for an artificial intelligence model for predicting the Number of public rental bike in the covid-19 era," Journal of Korean Institute of Information Technology, Vol.19, No.10(2021), 11~18.
  15. Kim, S. J., J. H. Jang, C. S. Park, H. M. Lee, and J. D. Lee, "Shared mobility, utilization analysis and relocation methods to increase efficiency of Ddareungi," Proceedings of the Korean Society of Computer Information Conference, (2021), 91~93.
  16. Kim, S. Y., J. H. Sim, and Y. J. Chung, "The Effect of Changes in Airbnb Host's Marketing Strategy on Listing Performance in the COVID-19 Pandemic", Journal of Intelligence and Information Systems, Vol.27, No.3(2021), 1~27. https://doi.org/10.13088/JIIS.2021.27.3.001
  17. Kim, T.S., W. K. Lee, and S. Y. Sohn, "Bike sharing demands prediction based on GCN," Proceedings of Korea Computer Congress, (2018), 832~834.
  18. Kim, Y. S., S. O. Park, and G. W. Park, "Analysis of the seoul public bike usage for new rental locations," The Korean Journal of applied Statistics, Vol.33, No.6(2020), 739~751. https://doi.org/10.5351/KJAS.2020.36.6.739
  19. Ku, D. G., J. Y. Kim, and S. J. Lee, "Prediction of Taxi passenger demand using deep learning," Proceedings of the Korean Society of Transportation Conference, (2017), 86~97.
  20. Laptev, N., J. Yosinski, L. E. Li, and S. Smyl, "Time-series extreme event forecasting with neural networks at uber," International conference on machine learning, (2017), 1~5.
  21. Lee, D. Y., J. S. Lee, S. P. Jun, and K. H. Kim, "The Classification System and Information Service for Establishing a National Collaborative R&D Strategy in Infectious Diseases:Focusing on the Classification Model for Overseas Coronavirus R&D Projects", Journal of Intelligence and Information Systems, Vol.26, No.3(2020), 127~147. https://doi.org/10.13088/JIIS.2020.26.3.127
  22. Lee, G. H., and H. J. Park, "Analysis of data and forecast of public bicycle demand according to weather factor and public bicycle rental rate," Proceedings of the Korean Information Science Society Conference, (2019), 960~962.
  23. Lee, G. J., S. H. Choo, K. Y. Kim, and J. Y. Joung, "Analysis of Factors Affecting Perceived Risk of COVID-19 Infection in Public Transportation," Journal of Korean Society of Transportation, Vol.39, No.5(2021), 643~661.
  24. Lee, J. H., J. H. Jung, and J. H. Kim, "The prediction of sharing bike on station using deep learning approach: a case study of seodaemun-gu, seoul," Proceedings of the Korean Society of Transportation Conference, (2021), 434~435.
  25. Lee, J. J., H. J. Hong, J. M. Song, and E. S. Yeom, "Forecasting of erythrocyte sedimentation rate using gated recurrent unit (GRU) neural network," Journal of The Korean Society of Visualization, Vol.19, No.1(2021), 57~61. https://doi.org/10.5407/JKSV.2021.19.1.057
  26. Lee, M. H., Y. R. Yoon, and H. J. Moon, "Performance Evaluation of an Indoor Temperature Forecasting Model based on GRU for Floor Heating System Operation," Journal of The Korean Society of Living Environmental System, Vol.27, No.3(2020), 272~282. https://doi.org/10.21086/ksles.2020.06.27.3.272
  27. Lee, S. J., S. I. Shin, D. H. Nam, J. H. Kim, and J. T. Park, "The Analysis Correlation Subway and Bike Sharing Ridership before and during COVID-19 Pandemic in Seoul," Journal of Korea Institute of Intelligent Transportation Systems, Vol.20, No.6(2021), 14~25. https://doi.org/10.12815/kits.2021.20.6.14
  28. Lee, S. M., Y. G. Sun, J. Y. Lee, D. G. Lee, E. I. Cho, D. H. Park, Y. B. Kim, I. S. Sim, and J. Y. Kim, "Short-term power consumption forecasting based on IoT power meter with LSTM and GRU deep learning," Journal of the institute of internet, broadcasting and communication, Vol.19, No.5(2019), 79~85. https://doi.org/10.7236/JIIBC.2019.19.5.79
  29. Lee, S.W. "Forecasting the Demand for Public Bikes in Seoul Using GRU Model: Around Exit 1 of Yeouinaru Station", Master dissertation, Kookmin University, (2022), Seoul.
  30. Lee, T. Y., H. Y. Oh, G. Kim, S. B. Jeon, and M. H. Jeon, "Prediction of highway section speed using GRU", Proceedings of the Korea Topological Spatial Information Society Conference, (2020), 36~37.
  31. Lee, W. S., and H. K. Kim, "Prediction model of average temperature based on characteristic of urban-space using LSTM and GRU: The case of wonju city," The Korea Spatial Planning Review, Vol.109, (2021), 89~104. https://doi.org/10.15793/KSPR.2021.109..006
  32. Lim, H. J., and K. H. Chung, "Development of demand forecasting model for seoul shared bicycle," Journal of the Korea Contents Association, Vol.19, No.1(2019), 132~140. https://doi.org/10.5392/JKCA.2019.19.01.132
  33. Mehdizadeh Dastjerdi, A. and C. Morency, "Bike-Sharing Demand Prediction at Community Level under COVID-19 Using Deep Learning", Sensors, Vol.22, No.3(2022), 1060. https://doi.org/10.3390/s22031060
  34. Min, J. W., H. S. Moon, and M. S. Lee, "Demand forecast for public bicycles('Tashu') in Daejeon using random forest," Proceeding of the Korean Institute of Information Science Society Conference, Vol.2017, No.6(2017), 969~971.
  35. Min, S. A., and Y. S. Jung, "Comparative study of prediction models for public bicycle demand in Seoul," Journal of the Korean Data And Information Science Society, Vol.32, No.3(2021), 585~592. https://doi.org/10.7465/jkdi.2021.32.3.585
  36. Park, S. Y., and Y. O. Kang, "Modeling tourist trajectory prediction using GRU", Proceeding of the Korea Association of Geographic Information Studies Conference, (2021), 99~101.
  37. Seo, J. H., and H. S. Yong, "Performance evaluation of recurrent neural network algorithms for recommendation system in e-commerce," KIISE Transactions on Computing Practices, Vol.23, No.7(2017), 440~445. https://doi.org/10.5626/KTCP.2017.23.7.440
  38. Seoul Open Data Plaza, "https:// data.seoul.go.kr/dataVisual/seoul/seoulLivingPopulation.do/," accessed: Apr 3, 2022.
  39. Shim, H. W., and Y. I. Lee, "A Study on Improvement of Seoul Bike Sharing Service Usage Rate based on Network Centrality Analysis: Focused on Jongno-gu in Seoul," Journal of Korean Society of Transportation, Vol.37, No.2(2019), 124~134. https://doi.org/10.7470/jkst.2019.37.2.124
  40. Yoon, Y. B., N. Y. Kim, M. J. Ryu, H. J. Yang, and Y. R. Hong, "A system for predicting demand for taxi passengers using big data and providing information on the analysis of travel patterns," Proceedings of The Korean Institute of Industrial Engineers Conference, (2018), 2822~2836.
  41. Yoon, S, U., and K. H, Nam, "Information types and characteristics within the Wireless Emergency Alert in COVID-19: Focusing on Wireless Emergency Alerts in Seoul", Journal of Intelligence and Information Systems, Vol.28, No.1(2022), 45~68. https://doi.org/10.13088/JIIS.2022.28.1.045
  42. Yum, C. S., and J. B. Hong, "An empirical study on the factors influencing customer satisfaction of internet banking," IE interfaces, Vol.17, No.3(2004), 305~313.