對多數駕駛來說，在都市中尋找一個理想的停車位是非常困難的。當駕駛到達了目的地附近時，便會於目的地附近尋找停車位。研究顯示，30%的交通阻塞是由於尋找停車位而引起，而此行為也造成了額外的汽油耗損及廢氣排放。隨著科技的進步，結合行動裝置與感測技術的智慧停車應用系統已隨手可得，這些系統整合了多種車位資訊，如停車位地點、剩餘空車位數、收費方式等資訊，提供駕駛查詢適合自己的停車位。然而，現行的系統仍然面對兩個難題，首先駕駛無法得知抵達停車位後，是否仍有空車位；再者若是駕駛們同時選擇前往相同的空車位，容易造成空車位衝突而再次導致新的交通阻塞問題。因此，本研究提出一個基於車位使用預測的智慧停車推薦系統，我們先將停車位使用率分成4個等級，並使用樸素貝氏分類器與決策樹建立空車位預測模型，預測一小時後車位的使用率是屬於何等級；接著我們基於Gale-Shapley演算法之概念，根據駕駛目前的位置與指定的目的地，分配都市的車位資源，大幅提升停車位推薦的成功率。為了驗證本研究之效果，我們使用由舊金山市SFPark系統所提供的路邊停車格空車位資料作為實驗資料，結果顯示結合預測模型與車位資源分配的智慧停車推薦系統，能夠明顯降低駕駛停車時的總行駛距離與行走至目的地的總距離，進而降低汽油消耗與廢氣排放，提供人們更乾淨的生活空間。

It’s very difficult to find an appropriate parking space in urban area for drivers. When drivers arrive at the places which are near to their destinations, they usually have to keep finding an available parking space close to their destinations. The literature study showed that 30% of the traffic congestion in the city is caused by the cars which are searching for the parking spaces, and such behavior may lead to unnecessary fuel consumption and exhaust emissions. With the ever-changing nature of technology, smart parking guidance systems which are composed of smart device and sensor technology are readily available. Such systems provide drivers with many kinds of parking space information such as locations, real-time available counts, and parking costs. However, the current system is still facing two problems. First, the drivers can’t know whether there is an available parking space at the arrival time. Second, if several drivers decide to go to the same available parking space, such condition may cause the collision of parking resource and traffic congestion. Therefore, in this thesis, we first propose a smart parking allocation approach based on parking occupancy prediction. In this approach, we divide the parking occupancy rate into 4 levels, and utilize Naïve Bayes classifier and decision tree to learn the parking occupancy prediction model. Then, we predict the level of parking occupancy rate for each street block in the next hour according to the prediction model. After that, based on the concept of Gale-Shapely algorithm, we allocate the urban parking spaces to drivers according to their present locations and specific destination, and improve the parking successful rate. To evaluate the performance of proposed approach, we carried out the experiment by the on-street parking data collected by the SFPark system in San Francisco, USA. The results show that our proposed smart parking guidance system can significantly reduce the total driving distance to the guided parking space; furthermore, it can reduce the extraneous fuel consumption and exhaust emissions, and provide us a cleaner environment.

[1] S. Abidi, S. Krichen, E. Alba, and J. M. Molina, “A New Heuristic for Solving The Parking Assignment Problem,” Procedia Computer Science, vol. 60, pp. 312-321, Sept. 2015.
[2] F. Caicedo, C. Blazquez, and P. Miranda, “Prediction of Parking Space Availability in Real Time,” Expert Systems with Applications, vol. 39, no. 8, pp. 7281-7290, June 2012.
[3] M. Caliskan, A. Barthels, B. Scheuermann, and M. Mauve, “Predicting Parking Lot Occupancy in Vehicular Ad Hoc Networks,” Proceedings of the 65th IEEE Conference on Vehicular Technology, pp. 277-281, Apr. 2007.
[4] B. Chen, F. Pinelli, M. Sinn, A. Botea, and F. Calabrese, “Uncertainty in Urban Mobility: Predicting Waiting Times for Shared Bicycles and Parking Lots,” Proceedings of the 16th IEEE International Conference on Intelligent Transportation Systems, pp. 53-58, Oct. 2013.
[5] T. Fabusuyi, R. C. Hampshire, V. A. Hill, and K. Sasanuma, “Decision Analytics for Parking Availability in Downtown Pittsburgh,” Interfaces, vol. 44, no. 3, pp. 286-299, June 2014.
[6] D. Gale and L. S. Shapley, “College Admissions and the Stability of Marriage,” American Mathematical Monthly, vol. 120, no. 5, pp. 386-391, May 2013.
[7] J. Jin, J. Gubbi, T. Luo, and M. Palaniswami, “Network architecture and QoS issues in the Internet of Things for a Smart City,” Proceedings of the International Symposium on Communications and Information Technologies, pp. 974–979, Oct. 2012.
[8] C. Liu, “Development of Prediction Model for Real-Time Parking Availability for On-Street Paid Parking,” Master’s dissertation, University of Pittsburgh, 2016.
[9] D. Mackowski, Y. Bai, and Y. Ouyang, “Parking Space Management via Dynamic Performance-Based Pricing,” Transportation Research Procedia, vol. 7, pp. 170-191, July 2015.
[10] C. Rhodes, W. Blewitt, C. Sharp, G. Ushaw, and G. Morgan, “Smart Routing: A Novel Application of Collaborative Path-finding to Smart Parking Systems,” Proceedings of the 16th IEEE Conference on Business Informatics, Vol. 1, pp. 119-126, July 2014.
[11] F. Richter, S. Di Martino, and D. C. Mattfeld, “Temporal and Spatial Clustering for a Parking Prediction Service,” Proceedings of the 26th IEEE International Conference on Tools with Artificial Intelligence, pp.278-282, Nov. 2014.
[12] J. H. Shin and H. B. Jun, “A Study on Smart Parking Guidance Algorithm.”　Transportation Research Part C: Emerging Technologies, vol. 44, pp. 299-317, July 2014.
[13] D. Shoup, “Free Parking or Free Markets,” Access Magazine, vol. 1, no. 38, pp. 28-35, Apr. 2011.
[14] T. Tiedemann, T. V¨ogele, M. M. Krell, J. H. Metzen, and F. Kirchner, “Concept of a Data Thread Based Parking Space Occupancy Prediction in a Berlin Pilot Region,” Proceedings of the 29th AAAI Conference on Artificial Intelligence Workshops, pp. 58-63, Jan. 2015.
[15] E. I. Vlahogianni, K. Kepaptsoglou, V. Tsetsos, and M. G. Karlaftis, “Exploiting New Sensor Technologies for Real-time Parking Prediction in Urban Areas,” Transportation Research Board 93rd Annual Meeting Compendium of Papers, pp. 14-1673, Jan. 2014.
[16] E. I. Vlahogianni, K. Kepaptsoglou, V. Tsetsos, and M. G. Karlaftis, “A Real-Time Parking Prediction System for Smart Cities,” Journal of Intelligent Transportation Systems, vol. 20, no. 2, pp. 192-204, Apr. 2016.
[17] E. H. K. Wu, C. Y. Liu, J. Sahoo, M. H. Jin, and S. H. Lin, “Agile Urban Parking Recommendation Service for Intelligent Vehicular Guiding System,” IEEE Intelligent Transportation Systems Magazine, vol. 6, no. 1, pp. 35-49, Jan. 2014.
[18] F. Yu, J. Guo, X. Zhu, and G. Shi, “Real Time Prediction of Unoccupied Parking Space Using Time Series Model,” Proceedings of the IEEE International Conference on Transportation Information and Safety, pp.370-374, Jun. 2015.
[19] Y. Zheng, S. Rajasegarar, and C. Leckie, “Parking Availability Prediction for Sensor-enabled Car Parks in Smart Cities,” Proceedings of the 10th IEEE International Conference on Intelligent Sensors, Sensor Networks and Information Processing, pp. 1-6, Apr. 2015.
[20] A. Ziat, B. Leroy, N. Baskiotis, and L. Denoyer, “Joint prediction of road-traffic and parking occupancy over a city with representation learning,” Proceedings of the 19th IEEE International Conference on Intelligent Transportation Systems, pp. 725-730, Nov. 2016.