Evaluation of Network-Level Traffic State Using 2DLNMF Algorithm

Abstract

Abstract:

Abstract： Network-level traffic state reflects the macroscopical conditions of the road network. The exesting evaluation algorithms have some shortcomings such as their applicable conditions are limited to section and they just depend on a single index. As a result, based on the analysis of the correlation between the measuring index and sections and the local nonnegative matrix factorization(LNMF) algorithm, the algorithm of 2DLNMF was proposed and the features of the traffic data were extracted by choosing appropriate parameters to reduce the numbers of dimensions of the road network data. The simulation results indicate that the evaluation of 2DLNMF is more accurate and its online accuracy is up to 95.69%.

Key words: network-level traffic state, cluster, 2D-local non-negative matrix factorization (2D-LNMF), feature extraction

XU Rong,WU Cong,JIANG ShiZheng,CHEN QiMei. Evaluation of Network-Level Traffic State Using 2DLNMF Algorithm[J]. Journal of Shanghai Jiaotong University, 2015, 49(08): 1131-1136.

References

［1］Xia Jingxin, Chen Mei. Defining traffic flow phases using intelligent transportation systems generated data［J］. Journal of Intelligent Transportation Systems: Technology, Planning, and Operations，2007，11(1)：1524.

［2］Xia Jingxin, Chen Mei. A nested clustering technique for freeway operating condition classification［J］. ComputerAided Civil and Infrastructure Engineering，2007，22(6)： 430437.

［3］Sun Lu, Zhou Jie. Development of multiregime speeddensity relationships by cluster analysis［J］. Transportation Research Record: Journal of the Transportation Research Board，2005，1934(1)：6471.

［4］Han Yufei, Moutarde F. Analysis of networklevel traffic states using locality preservative nonnegative matrix factorization［C］∥Intelligent Transportation Systems. Washington：IEEE, 2011：501506.

［5］郑兴宇, 牛世继, 刘中华, 等. 一种交通流状态分析模型［J］. 上海交通大学学报，2003，37(11)：17761779.

ZHENG Xingyu, NIU Shiji, LIU Zhonghua, et al. A model for traffic flow analysis［J］. Journal of Shanghai Jiaotong University，2003，37(11)： 17761779.

［6］Shaikh F K, Shah M, Shaikh B, et al. Implementation and evaluation of vehicletovehicle traffic congestion detection［M］. Berlin：Springer International Publishing，2014：227238.

［7］Zhu G, Lu G, Yang C G, et al. Research on the comprehensive traffic state evaluation model linked with drivers’ perception under the vehicle networking［J］. Personal and Ubiquitous Computing，2014，18(8)：19551961.

［8］Li Yan, Zhang Haiyan. Image semantic information mining algorithm by nonnegative matrix factorization［C］∥Proceedings of the 9th International Symposium on Linear Drives for Industry Applications. Hangzhou：Zhejiang University，2013：797803.

［9］Xu Wei, Liu Xin, Gong Yihong. Document clustering based on nonnegative matrix factorization［C］∥Proceedings of Research and Development in Informaion Retrieval. New York：ACM，2003：267273.

［10］Lu Deji, Sun Yu, Wan Suiren. Brain tumor classification using nonnegative and local nonnegative matrix factorization［C］∥Proceedings of Signal Processing, Communication and Computing. Kunming：IEEE，2013：14.

［11］Whitney J L, Leider C N, et al. Automatic sample recognition in hiphop music based on nonnegative matrix factorization［C］∥Proceedings of Audio Processing and Semantics. Miami：AES，2013：88518860.

［12］Li S Z, Hou Xinwen, Zhang Hongjiang, et al. Learning spatially localized, partsbased representation［C］∥Proceedings of Computer Vision and Pattern Recognition. Washington：IEEE，2001：207212.

［13］Lee D C, Wuest M, McEwan A, et al. Dynamic FDG PET images of mice analyzed with a novel nonnegative matrix factorization (NMF) technique［C］∥Society of Nuclear Medicine Annual Meeting Abstracts. Reston：JNM，2013，54(Supplement 2)：1422.

［14］Tikole S, Jaravine V, Rogov V, et al. Peak picking NMR spectral data using nonnegative matrix factorization［J］. BMC bioinformatics, 2014，15(1)：46.

［15］California department of transportation. Caltrans PeMS ［EB/OL］. (20130606) ［20140218］ http:∥pems.dot.ca.gov/.

[1]	FAN Hong, WEI Xinwu, JIA Qingshan, LUO Jiayi. Collaborative Optimization Scheduling Method for Electric-Gas-Thermal Multi-Energy System Under Energy-Transportation Integration [J]. Journal of Shanghai Jiao Tong University, 2026, 60(2): 211-223.
[2]	GUO Qi, YAN Jun, HAO Qianpeng, HAN Dong, YANG Zhihao, YAN Xinyue, ZHANG Haipeng, LI Ran. Short-Term Wind Power Prediction Method Based on Closed-Loop Clustering and Multi-Objective Optimization [J]. Journal of Shanghai Jiao Tong University, 2026, 60(2): 246-255.
[3]	LIU Qi, HE Yifei, GU Ming, CHEN Zihao, LI Yunhao, WANG Tao. Density Cluster-Based Clutter Removal Technology for Millimeter-Wave Radar Target Point Cloud [J]. Air & Space Defense, 2026, 9(1): 63-72.
[4]	SHEN Fu, YANG Zhiwen, XU Xiaoyuan, ZHANG Wei, WANG Zhe, CAO Yang. Unit Model of Integrated Energy System Based on Statistical Clustering [J]. Journal of Shanghai Jiao Tong University, 2025, 59(9): 1348-1358.
[5]	ZHU Feng, SHAN Chao, WU Ning, CAI Qixin, ZHU Yunan, LIU Yunpeng, ZUO Qiang. Feature Extraction and Anomaly Identification Method for Power Customer Price in Power Market Enviroment [J]. Journal of Shanghai Jiao Tong University, 2025, 59(7): 995-1006.
[6]	ZHANG Guo, CHEN Tao, WANG Jianping. CSC-YOLO: An Image Recognition Model for Surface Defect Detection of Copper Strip and Plates [J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 1037-1049.
[7]	LIU Biao, LIU Guangyu, FENG Wei, WANG Shuai, ZHOU Bao, ZHAO Enming. Undecimated Dual-Tree Complex Wavelet Transform and Fuzzy Clustering-Based Sonar Image Denoising Technique [J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 998-1008.
[8]	SHAO Yanli, YING Yong, CHEN Xi, DONG Siyu, WEI Dan. Multi-Scene Smoke Detection Based on Multi-Feature Extraction Method [J]. J Shanghai Jiaotong Univ Sci, 2025, 30(5): 866-879.
[9]	LIU Hongyu, WU Dajian. Research on the Identification of Technological Opportunities in Marine New Materials in China [J]. Ocean Engineering Equipment and Technology, 2025, 12(3): 123-127.
[10]	ZHANG Rongfu, WANG Jinqiang, LIU Minxia. Optimal Design Method of Complex System Based on Resource Optimization [J]. Air & Space Defense, 2025, 8(3): 86-94.
[11]	Cai Zhenhua, Li Canbing, Wu Qiuwei, Yang Tongguang, Li Zhenkai. Genetic Clustering-Based Equivalent Model of Wind Farm with Doubly Fed Induction Generator [J]. J Shanghai Jiaotong Univ Sci, 2025, 30(2): 300-308.
[12]	LI Jiayang, ZHAO Jiuyi, QIAN Yong, LI Guoyu, XU Zhiren, PAN Chao, SHENG Gehao. Location of Partial Discharge in GIS Based on Electromagnetic Wave Time Reversal [J]. Journal of Shanghai Jiao Tong University, 2025, 59(12): 1763-1772.
[13]	ZHANG Jiamin, CAI Ye, TANG Xiafei, TAN Yudong, CAO Yijia, LI Junxiong. Information Gap Decision Theory-Spectrum Clustering Typical Scenario Generation Considering Source Load Uncertainty [J]. Journal of Shanghai Jiao Tong University, 2025, 59(11): 1625-1636.
[14]	HE Tong, WEI Yali, LU Qing, BI Qian. Path Planning and Control of UAV Cluster Cooperative Reconnaissance Multi-Point Targets [J]. Air & Space Defense, 2025, 8(1): 31-40.
[15]	WU Tong, QI Tongshuai, XIE Weipeng. Research on Anti-UAV Cluster Technology [J]. Air & Space Defense, 2025, 8(1): 17-23.