基于模糊C均值聚類(lèi)和隨機(jī)森林的短時(shí)交通狀態(tài)預(yù)測(cè)方法

陳忠輝; 凌獻(xiàn)堯; 馮心欣; 鄭海峰; 徐藝文

doi:10.11999/JEIT171090

基于模糊C均值聚類(lèi)和隨機(jī)森林的短時(shí)交通狀態(tài)預(yù)測(cè)方法

doi: 10.11999/JEIT171090

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61601126, 61571129, U1405251)，福建省基金(2016J01299)

計(jì)量
- 文章訪(fǎng)問(wèn)數(shù): 1919
- HTML全文瀏覽量: 297
- PDF下載量: 175
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-11-20
- 修回日期: 2018-04-16
- 刊出日期: 2018-08-19

Short-term Traffic State Prediction Approach Based on FCM and Random Forest

Funds:

The National Natural Science Foundation of China (61601126, 61571129, U1405251), The Foundation of Fujian Province (2016J01299)

摘要

摘要: 交通擁堵長(zhǎng)期以來(lái)是城市面臨的主要問(wèn)題之一，解決交通擁堵瓶頸刻不容緩。準(zhǔn)確的短時(shí)交通狀態(tài)預(yù)測(cè)有利于市民預(yù)知交通出行信息，及時(shí)采取措施避免陷入擁堵困境。該文提出一種基于模糊C均值聚類(lèi)(FCM)和隨機(jī)森林的短時(shí)交通狀態(tài)預(yù)測(cè)方法。首先，利用一種新穎的融合時(shí)空信息的自適應(yīng)多核支持向量機(jī)(AMSVM)來(lái)預(yù)測(cè)短時(shí)交通流參數(shù)，包括流量、速度和占有率。其次，基于FCM算法分析歷史交通流，獲取歷史交通狀態(tài)信息。最后，利用隨機(jī)森林算法分析所預(yù)測(cè)的短時(shí)交通流參數(shù)，得到最終預(yù)測(cè)的短時(shí)交通狀態(tài)。該方法在融合時(shí)空信息的同時(shí)采用隨機(jī)森林算法應(yīng)用于短時(shí)交通狀態(tài)預(yù)測(cè)這一全新的研究領(lǐng)域。實(shí)驗(yàn)結(jié)果表明，F(xiàn)CM對(duì)歷史交通狀態(tài)的評(píng)估方式適用于不同的高速路和城市道路場(chǎng)景。其次，隨機(jī)森林比其它常見(jiàn)的機(jī)器學(xué)習(xí)方法具有更高的預(yù)測(cè)精度，從而提供實(shí)時(shí)可靠的短時(shí)交通出行信息。
- 短時(shí)交通狀態(tài)預(yù)測(cè) /
- 隨機(jī)森林 /
- 模糊C均值聚類(lèi) /
- 自適應(yīng)多核支持向量機(jī)
Abstract: Traffic congestion is a problem faced by cities, and it is urgent for solving this issue. Accurate short-term traffic state prediction is benefit for citizens to know the traffic information in advance, and take the measures in time to avoid the congestion. In this paper, a short-term traffic state prediction approach is proposed based on Fuzzy C-Means (FCM) clustering and Random Forest. Firstly, a novel Adaptive Multi-kernel Support Vector Machine (AMSVM) which incorporates the spatial-temporal information is used to predict the short-term traffic parameters, including the volume, the speed and the occupancy. Secondly, the historical traffic data are analyzed based on FCM algorithm, and the historical traffic state information is got. Lastly, the Random Forest (RF) algorithm is utilized to analyze the predicted short-term traffic parameters, then the final predicted short-term traffic state is obtained. This method incorporates the spatial-temporal information as well as applying the Random Forest to a new research field of short-term traffic state prediction. The experimental results demonstrate that the evaluation method of historical traffic state based on FCM is suitable for both freeway and urban road scenarios. Besides, the Random Forest has higher prediction accuracy than other common machine learning methods, thus providing the short-term traffic information timely and reliably.
- Short-term traffic state prediction /
- Random Forest (RF) /
- Fuzzy C-Means (FCM) clustering /
- Adaptive Multi-kernel Support Vector Machine (AMSVM)

HTML全文

參考文獻(xiàn)(18)

KRAUSE B, ALTROCK C, and POZYBILL M. Intelligent highway by fuzzy logic: Congestion detection and traffic control on multi-lane roads with variable road signs[C]. Proceedings of the 1996 5th IEEE International Conference on Fuzzy Systems, New Orleans, USA, 1996, 3: 1832-1837.

巫威眺, 靳文舟, 林培群. 基于BP神經(jīng)網(wǎng)絡(luò)的道路交通狀態(tài)判別方法研究[J]. 交通信息與安全, 2011, 29(4): 71-74. doi: 10.3963/j.ISSN 1674-4861.2011.04.016. WU Weitiao, JIN Wenzhou, and LIN Peiqun. The method of traffic state identification based on BP Neural Network[J]. Journal of Transport Information and Safety, 2011, 29(4): 71-74. doi: 10.3963/j.ISSN1674-4861.2011.04.016.

張亮亮, 賈元華, 牛忠海, 等. 交通狀態(tài)劃分的參數(shù)權(quán)重聚類(lèi)方法研究[J]. 交通運(yùn)輸系統(tǒng)工程與信息, 2014, 14(6): 147-151. doi: 10.16097/j.cnki.1009-6744.2014.06.022. ZHANG Liangliang, JIA Yuanhua, NIU Zhonghai, et al. Traffic state classification based on parameter weighting and clustering method[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(6): 147-151. doi: 10.16097/j.cnki.1009-6744.2014.06.022.

KONG Xiangjie, XU Zhenzhen, SHEN Guojiang, et al. Urban traffic congestion estimation and prediction based on floating car trajectory data[J]. Future Generation Computer Systems, 2016, 61(C): 97-107. doi: 10.1016/j.future.2015. 11.013.

DENG Chao, WANG Fan, SHI Huimin, et al. Real-time freeway traffic state estimation based on cluster analysis and Multiclass Support Vector Machine[C]. 2009 International Workshop on Intelligent Systems and Applications, Wuhan, China, 2009: 1-4. doi: 10.1109/IWISA.2009.5073027.

OH S, BYON Y J, and YEO H. Improvement of search strategy with K-Nearest Neighbors approach for traffic state prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(4): 1146-1156. doi: 10.1109/TITS.2015.2498408.

RICARDO G R, MARIA L L G, and MARIA S R. An approach to dynamical classification of daily traffic patterns [J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(3): 191-212. doi: 10.1111/mice.12226.

CHEN Yuanyuan, L Yisheng, LI Zhenjiang, et al. Long short-term memory model for traffic congestion prediction with online open data[C]. 19th IEEE International Conference on Intelligent Transportation Systems, Rio de Janeiro, Brazil, 2016: 132-137. doi: 10.1109/ITSC.2016. 7795543.

高林, 劉英, 盛子豪. 隨機(jī)森林算法在交通狀態(tài)判別中的應(yīng)用[J]. 實(shí)驗(yàn)技術(shù)與管理, 2017, 34(4): 43-46. doi: 10.16791/ j.cnki.sjg.2017.04.012. GAO Lin, LIU Ying, and SHENG Zihao. Application of Random Forest algorithm to traffic state identification[J]. Experiment Technology and Management, 2017, 34(4): 43-46. doi: 10.16791/j.cnki.sjg.2017.04.012.

馮心欣, 凌獻(xiàn)堯, 林燁婷, 等. 可優(yōu)化的自適應(yīng)多核支持向量機(jī)的短時(shí)交通流預(yù)測(cè)方法[P]. 中國(guó)專(zhuān)利, 106971548A, 2017. FENG Xinxin, LING Xianyao, LIN Yeting, et al. Optimized adaptive Multi-kernel Support Vector Machine for short-term traffic flow prediction[P]. China Patent, 106971548A, 2017.

LING Xianyao, FENG Xinxin, CHEN Zhonghui, et al. Short-term traffic flow prediction with optimized Multi-kernel Support Vector Machine[C]. 2017 IEEE Congress on Evolutionary Computation, Donostia-San Sebastian, Spain, 2017: 294-300. doi: 10.1109/CEC.2017. 7969326.

ZHU Guangyu, CHEN Jianjun, and ZHANG Peng. Fuzzy C-means clustering identification method of urban road traffic state[C]. 12th International Conference on Fuzzy Systems and Knowledge Discovery, Zhangjiajie, China, 2015: 302-307. doi: 10.1109/FSKD.2015.7381958.

吳啟順, 蔡曉禹, 蔡明. 基于FCM快速路交通狀態(tài)判別加權(quán)指數(shù)研究[J]. 科學(xué)技術(shù)與工程, 2017, 17(6): 289-295. WU Qishun, CAI Xiaoyu, and CAI Ming. A study of weighting exponent in expressway traffic state estimation based on Fuzzy C-means[J]. Science Technology and Engineering, 2017, 17(6): 289-295.

BREIMAN L. Random Forests[J]. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324.

董師師, 黃哲學(xué). 隨機(jī)森林理論淺析[J]. 集成技術(shù), 2013, 2(1): 1-7. DONG Shishi and HUANG Zhexue. A brief theoretical overview of Random Forests[J]. Journal of Integration Technology, 2013, 2(1): 1-7.

ZHOU Zhihua and FENG Ji. Deep Forest: Towards an alternative to Deep Neural Networks[C]. 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia, 2017: 3553-3559.

CALTRANS PEMS. Traffic flow database[OL]. http:// pems.dot.ca.gov/?dnode=VDScontent=loopstab=dettimeseriesstation id=1017510, 2016.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪(fǎng)問(wèn)統(tǒng)計(jì)