一般來說，下雨或下雪等天氣條件會影響交通狀況。然而，相同的 氣候卻對不同的道路有不同的影響。對一個發展中國家而言，城市道路硬體 建築相對較差，也增加了道路特徵的多樣性。因此，道路特徵的辨識及分析， 對於交通管理或物流行業非常重要。氣候敏感道路（Weather Sensitive Road, WSR）被定義為易受天候狀況而影響行車速度的道路。本研究收集了印尼 雅加達居民的智慧手機產生的一整年交通壅塞時產生的數據。此數據包含了 時間與空間之維度，是在特定時間與某個位置以交通壅擠的速度之形式擷取。 本研究運用了兩種模型：K-means 分群演算法和隨機森林預測模型來進行氣 候敏感道路的分析。 K-means分群演算法以雅加達城市道路在不同天候下的 行車速率進行分群。選擇隨機森林預測模型則利用所收集之道路特徵（如經 緯度、大小、鄰近是否有學校、清真寺等）的重要性。通過將 4個群集識別 為 50個不同的天氣敏感度層級來進行實驗並以 Pareto Front方法選擇了最佳 分群數。本研究發現最好的 Pareto Front 是 4，6，11，14，16，19，21，39 和 49號的天氣敏感層級。本研究將印尼雅加達的道路分為 11個族群，並進 而研究各群道路中，影響行車速率的關鍵因素。研究顯示，最重要的四個道 路特徵分別為：經度，緯度，到最近的商場的距離，以及海拔。

Weather condition such as raining or snowing indeed influences the traffic condition. However, not every road has the similar impact from the same weather condition. Moreover, the varied road condition of developing countries urban road increases the diversity of road characteristic. Therefore, understanding the road characteristics that influence its weather sensitivity is important for traffic management or logistic industry. The Weather Sensitive Road (WSR) is identified as road that sensitive to weather. In this research, the one-year traffic congestion data generated from citizens of Jakarta’s smartphone was collected. The spatiotemporal data was captured in the form of traffic congestion speed at a particular time and on a certain location. There were two consecutive models used: K-means clustering model and the Random Forests prediction model. K-means clustering model was used to acknowledge the existing levels of weather sensitivity among Jakarta’s urban road. The Random Forests prediction model was chosen to identify the importance of road characteristics given its weather sensitivity level. The experiment was performed by identifying 4 clusters to 50 different clusters of weather sensitivity levels. The best number of clusters was chosen by the Pareto Front method. K-means performance measurements and the Random Forests performance measurement were used to consider the Pareto Front. The best set of Pareto Front is 4, 6, 11, 14, 16, 19, 21, 39, and 49 of weather sensitivity levels. The 11 clusters set was chosen to minimize the complexity while to maintain the fair number of clusters. It shows that the top 4 of important features are longitude, latitude, distance to the nearest mall, and elevation.

1. Kim, Y.-j. and J.-s.J.I.T.o.I.T.S. Hong, Urban traffic flow prediction system using a multifactor pattern recognition model. 2015. 16(5): p. 2744-2755. 2. Lv, Y., et al., Traffic flow prediction with big data: a deep learning approach. 2015. 16(2): p. 865-873. 3. Wan, J., et al., Mobile crowd sensing for traffic prediction in internet of vehicles. 2016. 16(1): p. 88. 4. Zhao, Z., et al., LSTM network: a deep learning approach for short-term traffic forecast. 2017. 11(2): p. 68-75. 5. Iles, R., Public Transport in Developing Countries. 2005. 6. Pindarwati, A. and A.W. Wijayanto. Measuring performance level of smart transportation system in big cities of Indonesia comparative study: Jakarta, Bandung, Medan, Surabaya, and Makassar. in 2015 International Conference on Information Technology Systems and Innovation (ICITSI). 2015. IEEE. 7. Ginting, F., Jakarta Transportation - United Nations ESCAP. 8. TomTom Traffic Index Full Ranking 2017; Available from: https://www.tomtom.com/en_gb/traffic-index/ranking/. 9. Shi, Z. and L. Pun-Cheng, Spatiotemporal Data Clustering: A Survey of Methods. ISPRS International Journal of Geo-Information, 2019. 8(3). 10. Zheng, Y., Trajectory Data Mining: An Overview. Acm Transactions on Intelligent Systems and Technology, 2015. 6(3). 11. Tang, J., Y. Chang, and H. Liu, Mining social media with social theories: a survey. 2014. 15(2): p. 20-29. 12. Egenhofer, M.J. and R.D. Franzosa, Point-set topological spatial relations. International journal of geographical information systems, 1991. 5(2): p. 161-174. 13. Turner, M.G., Spatial and Temporal Analysis of Landscape Patterns. Landscape Ecology, 1990. 4(1): p. 21-30. 14. Naves, L.A., et al., Geographical information system (GIS) as a new tool to evaluate epidemiology based on spatial analysis and clinical outcomes in acromegaly. Pituitary, 2015. 18(1): p. 8-15. 15. Tsoulis, D., Analytical computation of the full gravity tensor of a homogeneous arbitrarily shaped polyhedral source using line integrals. Geophysics, 2012. 77(2): p. F1-F11. 16. Herold, M., X.H. Liu, and K.C. Clarke, Spatial metrics and image texture for mapping urban land use. Photogrammetric Engineering and Remote Sensing, 2003. 69(9): p. 991-1001. 17. Niebles, J.C., H. Wang, and L. Fei-Fei, Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. International Journal of Computer Vision, 2008. 79(3): p. 299-318. 18. Birant, D. and A. Kut, ST-DBSCAN: An algorithm for clustering spatial– temporal data. Data & Knowledge Engineering, 2007. 60(1): p. 208-221.
19. Shekhar, S., et al., Spatiotemporal Data Mining: A Computational Perspective. ISPRS International Journal of Geo-Information, 2015. 4(4): p. 2306-2338. 20. Li, Z., J. Chen, and E. Baltsavias, Advances in photogrammetry, remote sensing and spatial information sciences: 2008 ISPRS congress book. Vol. 7. 2008: CRC Press. 21. Yuan, M. Temporal GIS and spatio-temporal modeling. in Proceedings of Third International Conference Workshop on Integrating GIS and Environment Modeling, Santa Fe, NM. 1996. 22. Allen, J.F., Towards a general theory of action and time. Artificial intelligence, 1984. 23(2): p. 123-154. 23. George, B., S. Kim, and S. Shekhar. Spatio-temporal Network Databases and Routing Algorithms: A Summary of Results. 2007. Berlin, Heidelberg: Springer Berlin Heidelberg. 24. George, B. and S. Kim, Time Aggregated Graph: A Model for Spatiotemporal Networks, in Spatio-temporal Networks. 2013, Springer. p. 7-24. 25. Stoyan, D., Handbook of Spatial Statistics. A. E. Gelfand, P. J. Diggle, M. Fuentes and P. Guttorp (2010). Boca Raton, London, New York, Chapman & Hall/CRC. ISBN 978-1-4200-7287-7. Biometrical Journal, 2011. 53(1): p. 161-162. 26. Campelo, C.E.C. and B. Bennett. Representing and Reasoning about Changing Spatial Extensions of Geographic Features. 2013. Cham: Springer International Publishing. 27. Ing-Simmons, E., et al., Spatial enhancer clustering and regulation of enhancer-proximal genes by cohesin. 2015. 25(4): p. 504-513. 28. Zhang, Y.-J., J.-F. Hao, and J.J.A.e. Song, The CO2 emission efficiency, reduction potential and spatial clustering in China’s industry: Evidence from the regional level. 2016. 174: p. 213-223. 29. Manogaran, G., et al., Machine learning based big data processing framework for cancer diagnosis using hidden Markov model and GM clustering. 2018. 102(3): p. 2099-2116. 30. Kisilevich, S., et al., Spatio-temporal clustering, in Data mining and knowledge discovery handbook. 2009, Springer. p. 855-874. 31. Di Martino, F., W. Pedrycz, and S. Sessa, Spatiotemporal extended fuzzy Cmeans clustering algorithm for hotspots detection and prediction. Fuzzy Sets and Systems, 2018. 340: p. 109-126. 32. Stevenson, J.R., et al., Using Building Permits to Monitor Disaster Recovery: A Spatio-Temporal Case Study of Coastal Mississippi Following Hurricane Katrina. Cartography and Geographic Information Science, 2010. 37(1): p. 57-68. 33. Kulldorff, M., SaTScan: software for the spatial, temporal, and space-time scan statistics. Silver Spring, MD: Information Management Services. 2005, Inc. 34. Steiger, E., B. Resch, and A. Zipf, Exploration of spatiotemporal and semantic clusters of Twitter data using unsupervised neural networks. International Journal of Geographical Information Science, 2015. 30(9): p. 1694-1716.
35. Malleson, N. and M.A. Andresen, Spatio-temporal crime hotspots and the ambient population. Crime Science, 2015. 4(1). 36. Kulldorff, M., et al., A space-time permutation scan statistic for disease outbreak detection. PLoS Med, 2005. 2(3): p. e59. 37. Rempe, F., G. Huber, and K. Bogenberger, Spatio-Temporal Congestion Patterns in Urban Traffic Networks. Transportation Research Procedia, 2016. 15: p. 513-524. 38. Qi, H., et al., Spatial-Temporal Congestion Identification Based on Time Series Similarity Considering Missing Data. PLoS One, 2016. 11(9): p. e0162043. 39. Rhee, J., et al., Delineation of climate regions using in-situ and remotelysensed data for the Carolinas. Remote Sensing of Environment, 2008. 112(6): p. 3099-3111. 40. Santos, J.F., I. Pulido-Calvo, and M.M. Portela, Spatial and temporal variability of droughts in Portugal. Water Resources Research, 2010. 46(3). 41. Drineas, P., et al., Clustering large graphs via the singular value decomposition. 2004. 56(1-3): p. 9-33. 42. Meilă, M. The uniqueness of a good optimum for k-means. in Proceedings of the 23rd international conference on Machine learning. 2006. ACM. 43. Jain, A.K. and R.C. Dubes, Algorithms for clustering data. Vol. 6. 1988: Prentice hall Englewood Cliffs. 44. Jain, A.K., Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 2010. 31(8): p. 651-666. 45. Dhanachandra, N., K. Manglem, and Y.J. Chanu, Image Segmentation Using K -means Clustering Algorithm and Subtractive Clustering Algorithm. Procedia Computer Science, 2015. 54: p. 764-771. 46. Slamet, C., et al., Clustering the Verses of the Holy Qur'an using K-Means Algorithm. Asian Journal of Information Technology, 2016. 15(24): p. 5159-5162. 47. Botia, J.A., et al., An additional k-means clustering step improves the biological features of WGCNA gene co-expression networks. BMC Syst Biol, 2017. 11(1): p. 47. 48. Liu, D., 46. Design of Wireless Sensor Intelligent Traffic Control System based on K-means Algorithm. Revista de la Facultad de Ingeniería, 2017. 32(12). 49. Mourelo Ferrandez, S., et al., Optimization of a truck-drone in tandem delivery network using k-means and genetic algorithm. Journal of Industrial Engineering and Management, 2016. 9(2). 50. Pattanaik, V., et al. Smart real-time traffic congestion estimation and clustering technique for urban vehicular roads. in 2016 IEEE region 10 conference (TENCON). 2016. IEEE. 51. Rajput, D., P. Singh, and M. Bhattacharya. An efficient and generic hybrid framework for high dimensional data clustering. in Proceedings of International Conference on Data Mining and Knowledge Engineering, World Academy of Science, Engineering and Technology. 2010. 52. Ho, T.K. Random decision forests. in Proceedings of 3rd international conference on document analysis and recognition. 1995. IEEE. 53. Breiman, L., Random forests. Machine learning, 2001. 45(1): p. 5-32.
54. Amit, Y. and D. Geman, Shape quantization and recognition with randomized trees. Neural computation, 1997. 9(7): p. 1545-1588. 55. Gregorutti, B., B. Michel, and P. Saint-Pierre, Correlation and variable importance in random forests. Statistics and Computing, 2016. 27(3): p. 659-678. 56. Matin, S.S. and S.C. Chelgani, Estimation of coal gross calorific value based on various analyses by random forest method. Fuel, 2016. 177: p. 274-278. 57. Wang, L., Q. Shi, and M. Abdel-Aty, Predicting Crashes on Expressway Ramps with Real-Time Traffic and Weather Data. Transportation Research Record: Journal of the Transportation Research Board, 2015. 2514(1): p. 32-38. 58. Lee, J., B. Nam, and M. Abdel-Aty, Effects of Pavement Surface Conditions on Traffic Crash Severity. Journal of Transportation Engineering, 2015. 141(10). 59. Elleuch, W., A. Wali, and A.M. Alimi. Collection and exploration of GPS based vehicle traces database. in 2015 4th International Conference on Advanced Logistics and Transport (ICALT). 2015. IEEE. 60. Zhou, X., W. Wang, and L. Yu. Traffic flow analysis and prediction based on GPS data of floating cars. in Proceedings of the 2012 International Conference on Information Technology and Software Engineering. 2013. Springer. 61. Kong, X., et al., Mobility Dataset Generation for Vehicular Social Networks Based on Floating Car Data. IEEE Transactions on Vehicular Technology, 2018. 67(5): p. 3874-3886. 62. OpenStreetMap is the free wiki world map.; Available from: https://www.openstreetmap.org/. 63. World Weather Online. Available from: https://www.worldweatheronline.com/. 64. Kegelmeyer, W.P., et al., SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 2002. 16: p. 321-357. 65. Van Veldhuizen, D.A. and G.B. Lamont. Evolutionary computation and convergence to a Pareto Front. in Late breaking papers at the genetic programming 1998 conference. 1998. 66. Menze, B.H., et al., A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics, 2009. 10: p. 213. 67. Overpass Turbo API. Available from: https://overpass-turbo.eu/. 68. Jawgmaps API. Available from: https://www.jawg.io/.