隨著人口成長所帶來的影響使得交通繁忙進而導致交通事故不斷增加，尤其在特別的路口，如交通量大、路口設計不良等等，更容易導致交通事故的發生。在這篇論文當中，我們提出一個轉彎預測演算法去預測車輛在特別的路口(T字型、Y字型或超過四條路口交會)將會行駛於哪一條道路，本系統使用路口雷達來蒐集車輛的動態資訊，並用蒐集到的資料計算出車輛相對於道路的偏轉角度，再以平滑技術來過濾掉偏轉角度中較大起伏的噪音數值。在預測系統中，我們使用袋裝與隨機森林演算法來建構預測模型，來預測車輛在未來相對於道路的偏轉角度，進而判斷該車輛未來將行駛於哪一條道路，並在必要時警示其他車輛減少交通事故的發生。為了評估預測模型的效能，實驗中我們採用雷達蒐集位於高雄凱旋路口及鎮興路口的真實資料集，實驗結果顯示隨機森林演算法在所有資料集中有最高的準確率。

The effect of growing population brings heavy traffic which in turn leads to increased number of traffic accidents. In particular, the majority of traffic accidents happen at special intersections in situations such as heavy traffic, poor intersection design, etc. In this thesis, we propose a turn prediction system to predict which road a vehicle will take at special intersection, e.g., T-junction, Y-junction, or junction where more than 4 roads meet. The proposed system uses the radar installed at the intersection to collect vehicle dynamics. The collected data is processed to calculate deflection angles of vehicles corresponding to the road. The smoothing technique is adopted to filter the noise of calculated deflection angles. The ensemble methods are utilized to construct the model to predict future deflection angles of vehicles corresponding to the road. According to the predicted deflection angle, we can predict which road a vehicle will take at a special intersection and alert other vehicles when necessary. To assess the performance of the model prediction, a real-world experiment is carried out, which utilizes radar to collect the dataset at Kaixuan 4th Rd. and Zhenxing Rd., Qianzhen Dist., Kaohsiung City, Taiwan. The experiment results show that the accuracy of the Random Forest algorithm is the highest among all datasets.

[1] T. Anagnostopoulos, C. B. Anagnostopoulos, S. Hadjiefthymiades, A. Kalousis, and
M. Kyriakakos. Path prediction through data mining. In IEEE International Con-
ference on Pervasive Services, 2007.
[2] H. Andersen, Z. J. Chong, Y. H. Eng, S. Pendleton, and M. H. Ang. Geometric path
tracking algorithm for autonomous driving in pedestrian environment. In 2016 IEEE
International Conference on Advanced Intelligent Mechatronics (AIM), 2016.
[3] Eric Bauer and Ron Kohavi. An empirical comparison of voting classication algo-
rithms: Bagging, boosting, and variants. Machine learning, 1999.
[4] Leo Breiman. Random forests. Machine learning, 2001.
[5] D. Caveney. Numerical integration for future vehicle path prediction. In 2007 Amer-
ican Control Conference, 2007.
[6] D. Caveney. Vehicular path prediction for cooperative driving applications through
digital map and dynamic vehicle model fusion. In 2009 IEEE 70th Vehicular Tech-
nology Conference Fall, 2009.
[7] A. Chusyairi, N. S. P. Ramadar, and Bagio. The use of exponential smoothing
method to predict missing service e-report. In 2017 2nd International conferences
on Information Technology, Information Systems and Electrical Engineering (ICI-
TISEE), 2017.
[8] David R Cox. The regression analysis of binary sequences. Journal of the Royal
Statistical Society. Series B (Methodological), 1958.
41
[9] N. Deo, A. Rangesh, and M. M. Trivedi. How would surrounding vehicles move? a
unied framework for maneuver classication and motion prediction. IEEE Trans-
actions on Intelligent Vehicles, 2018.
[10] Thomas G Dietterich. Ensemble methods in machine learning. In International
workshop on multiple classier systems. Springer, 2000.
[11] Clif Droke. Moving averages simplied. Marketplace Books, 2001.
[12] Huanzhen Fan, Li Ai, Gongjing Yu, Hongzheng Fang, and Kai Luo. Lifetime pre-
diction based on opitimal loess smoothing and ukf for lithium-ion batteries. In 2015
Prognostics and System Health Management Conference (PHM), 2015.
[13] T. Gandhi and M. M. Trivedi. Image based estimation of pedestrian orientation for
improving path prediction. In 2008 IEEE Intelligent Vehicles Symposium, 2008.
[14] Michael F Goodchild. Geographic information system. In Encyclopedia of Database
Systems, pages 1231{1236. Springer, 2009.
[15] A Shalom Hakkert and David Mahalel. Estimating the number of accidents at inter-
sections from a knowledge of the trac
ows on the approaches. Accident Analysis
& Prevention, 1978.
[16] Tin Kam Ho. Random decision forests. In Proceedings of 3rd International Confer-
ence on Document Analysis and Recognition, 1995.
[17] P. M. Hsu and Z. W. Zhu. Car trajectory prediction in image processing and con-
trol manners. In 2016 IEEE International Conference on Intelligent Transportation
Engineering (ICITE), 2016.
42
[18] Jihua Huang and Han-Shue Tan. Vehicle future trajectory prediction with a dgps/ins-
based positioning system. In 2006 American Control Conference, 2006.
[19] Jin Huang and C. X. Ling. Using auc and accuracy in evaluating learning algorithms.
IEEE Transactions on Knowledge and Data Engineering, 2005.
[20] Prnay Jain, Shubham Varma, Hari Prabhat Gupta, Tanima Dutta, et al. A su-
pervised approach towards network control system modelling. In Communication
Systems and Networks (COMSNETS), 2017 9th International Conference on. IEEE,
2017.
[21] W. Kim, C. M. Kang, Y. S. Son, S. H. Lee, and C. C. Chung. Vehicle path prediction
using yaw acceleration for adaptive cruise control. IEEE Transactions on Intelligent
Transportation Systems, 2018.
[22] Ron Kohavi et al. A study of cross-validation and bootstrap for accuracy estimation
and model selection. In Ijcai. Montreal, Canada, 1995.
[23] Sotiris Kotsiantis, Dimitris Kanellopoulos, Panayiotis Pintelas, et al. Handling imbal-
anced datasets: A review. GESTS International Transactions on Computer Science
and Engineering, 2006.
[24] Y. Lin, P. Wang, and M. Ma. Intelligent transportation system(its): Concept, chal-
lenge and opportunity. In 2017 ieee 3rd international conference on big data security
on cloud (bigdatasecurity), ieee international conference on high performance and
smart computing (hpsc), and ieee international conference on intelligent data and
security (ids), 2017.
[25] P. Lytrivis, G. Thomaidis, and A. Amditis. Cooperative path prediction in vehicular
43
environments. In 2008 11th International IEEE Conference on Intelligent Trans-
portation Systems, 2008.
[26] P. Lytrivis, G. Thomaidis, M. Tsogas, and A. Amditis. An advanced cooperative path
prediction algorithm for safety applications in vehicular networks. IEEE Transactions
on Intelligent Transportation Systems, 2011.
[27] Narin Persad-Maharaj, Sean J Barbeau, Miguel A Labrador, Philip L Winters, Rafael
Perez, and Nevine Labib Georggi. Real-time travel path prediction using gps-enabled
mobile phones. In Proc. 15th World Congress on Intelligent Transportation Systems.
Citeseer, 2008.
[28] Tomaso Poggio, Harry Voorhees, and Alan Yuille. A regularized solution to edge
detection. Journal of Complexity, 1988.
[29] Z. K. Pourtaheri and S. H. Zahiri. Ensemble classiers with improved overtting. In
2016 1st Conference on Swarm Intelligence and Evolutionary Computation (CSIEC),
2016.
[30] H. S. Tan and J. Huang. Dgps-based vehicle-to-vehicle cooperative collision warning:
Engineering feasibility viewpoints. IEEE Transactions on Intelligent Transportation
Systems, 2006.
[31] Sebastian Thrun, Mike Montemerlo, Hendrik Dahlkamp, David Stavens, Andrei
Aron, James Diebel, Philip Fong, John Gale, Morgan Halpenny, Gabriel Homann,
et al. Stanley: The robot that won the darpa grand challenge. Journal of eld
Robotics.
[32] R. Toledo-Moreo and M. A. Zamora-Izquierdo. Imm-based lane-change prediction
44
in highways with low-cost gps/ins. IEEE Transactions on Intelligent Transportation
Systems, 2009.
[33] S. H. Tsang, E. G. Hoare, P. S. Hall, and N. J. Clarke. Automotive radar image
processing to predict vehicle trajectory. In Proceedings 1999 International Conference
on Image Processing (Cat. 99CH36348), 1999.
[34] Tzu-Tsung Wong and Nai-Yu Yang. Dependency analysis of accuracy estimates in
k-fold cross validation. IEEE Transactions on Knowledge and Data Engineering,
2017.
[35] Xin Yan and Xiaogang Su. Linear regression analysis: theory and computing. World
Scientic, 2009.
[36] J. Yang, H. Bao, N. Ma, and Z. Xuan. An algorithm of curved path tracking with
prediction model for autonomous vehicle. In 2017 13th International Conference on
Computational Intelligence and Security (CIS), 2017.
[37] Bee Wah Yap, Khatijahhusna Abd Rani, Hezlin Aryani Abd Rahman, Simon Fong,
Zuraida Khairudin, and Nik Nik Abdullah. An application of oversampling, under-
sampling, bagging and boosting in handling imbalanced datasets. In Proceedings
of the rst international conference on advanced data and information engineering
(DaEng-2013). Springer, 2014.
[38] Y. Yoo, K. Yun, S. Yun, J. Hong, H. Jeong, and J. Y. Choi. Visual path prediction in
complex scenes with crowded moving objects. In 2016 IEEE Conference on Computer
Vision and Pattern Recognition (CVPR), 2016.
45
[39] Tong Zhang, Bin Yu, et al. Boosting with early stopping: Convergence and consis-
tency. The Annals of Statistics, 2005.
46