A Time Scale Selection Method for Dynamic Temporal Networks
WU Miaojingxin, YANG Shengwen, ZHANG Haobo, ZHAO Fei
a. School of Machinery and Transportation; b. Key Laboratory of Environmental Protection and Safety of Motor Vehicles in Highland Mountainous Areas of Yunnan University, Southwest Forestry University, Kunming 650224, China
Abstract：To enhance the science and effectiveness of dynamic temporal networks analysis, a systematic, data-driven approach to selecting time scales is proposed. Firstly, the multi-scale entropy theory is introduced to describe the complexity and randomness of the passenger flow time series to determine the appropriate time scale selection range. Secondly, the network characteristic indexes are selected from node characteristics, edge characteristics and overall structure, and the time scale is selected by combining principal component analysis and random forest algorithm. Three networks are used as examples for validation, and the results show that the method is applicable to the data requirements of different transportation systems with high rationality and applicability.
[1] Arenas A, Díaz-Guilera A, Pérez-Vicente C J. Synchronization reveals topological scales in complex networks[J]. Physical Review Letters, 2006, 96(11): 114102. [2] Moctar A O M, Sarr I, Tanzouak J V. Snapshot setting for temporal networks analysis[C]//Proceedings of the International Conference on e-Infrastructure and e-Services for Developing Countries. Cham: Springer International Publishing, 2019: 98-107. [3] Telesford Q K, Lynall M E, Vettel J, et al. Detection of functional brain network reconfiguration during task-driven cognitive states[J]. NeuroImage, 2016, 142: 198-210. [4] Orman G K, Çolak S. Similarity based compression ratio for dynamic network modelling[C]//19th International Conference on Smart Technologies. Lappeenranta: IEEE, 2021: 227-232. [5] Peixoto T P, Rosvall M. Modelling sequences and temporal networks with dynamic community structures[J]. Nature Communications, 2017, 8(1): 582. [6] Uddin S, Choudhury N, Farhad S M, et al. The optimal window size for analysing longitudinal networks[J]. Scientific Reports, 2017, 7(1): 13389. [7] Wang X, Shang P, Fang J.Traffic time series analysis by using multiscale time irreversibility and entropy[J].Chaos, 2014, 24(3):032102. [8] 刘峰涛,贺国光. 基于近似熵和统计复杂度的交通流复杂性测度[J].中国公路学报,2007,20(4):108-112. Liu F T, He G G. Complexity measure of traffic flow based on approximate entropy and statistical complexity[J]. China Journal of Highway and Transport, 2007,20(4): 108-112. [9] Xia J, Shang P, Wang J, et al. Permutation and weighted-permutation entropy analysis for the complexity of nonlinear time series[J]. Communications in Nonlinear Science and Numerical Simulation, 2016, 31(1-3): 60-68. [10] Yin Y, Shang P. Multivariate multiscale sample entropy of traffic time series[J]. Nonlinear Dynamics, 2016, 86(1): 479-488. [11] Zhang Y, Shang P. The complexity-entropy causality plane based on multivariate multiscale distribution entropy of traffic time series[J]. Nonlinear Dynamics, 2019, 95: 617-629. [12] Costa M, Goldberger A L, Peng C K. Multiscale entropy analysis of complex physiologic time series[J]. Physical Review Letters, 2002, 89(6): 068102. [13] 张杰,曲洪权,柳长安,等. 基于双子空间PCA降维的脑力负荷分类[J]. 科学技术与工程, 2024, 24(11): 4433-4438. Zhang J, Qu H Q, Liu C A, et al. Research on classification of mental workload based on dimension reduction of PCA in two subspaces[J]. Science Technology and Engineering,2024,24(11):4433-4438. [14] 王鹏翔,沈娟,王菁旸,等. 基于PCA-LMD-WOA-ELM的短期光伏功率预测[J].智慧电力,2022, 50(6):72-78. Wang P X, Shen J, Wang J Y, et al. Short term photovoltaic power prediction based on PCA-LMD-WOAELM[J]. Smart Power, 2022, 50(6):72-78. [15] 廖列法,欧阳宗英. 改进BAS-Elman神经网络的港口货运量预测[J]. 科学技术与工程, 2021, 21(7): 2937-2944. Liao L F, Ouyang Z Y. Port freight volume forecast based on improved BAS-Elman Neural Network[J]. Science Technology and Engineering,2021,21(7):2937-2944. [16] 刘亚静,刘红健. 基于信息量-随机森林模型的地震带地质灾害易发性评价:以松潘-较场地震带为例[J]. 科学技术与工程, 2024, 24(1): 143-154. Liu Y J, Liu H J. Evaluation of geological hazard susceptibility in seismic zone based on information data-RF model: a case study of Songpan-Jiaochang seismic zone[J]. Science Technology and Engineering,2024,24(1):143-154. [17] 朱宏宇. 基于随机森林算法对福建省降雨的研究[D]. 漳州:闽南师范大学,2023. Zhu H Y. Research on rainfall in Fujian Province based on random forest algorithm[D]. Zhangzhou:Minnan Normal University,2023. [18] 曹桃云. 基于随机森林的变量重要性研究[J].统计与决策,2022,38(4):60-63. Cao T Y. A study on the importance of variables based on random forest[J]. Statistics and Decision Making,2022,38(4):60-63. [19] 武玉龙,孙东永,韩珍珍,等. 基于多尺度熵的泾河径流复杂性研究[J].华北水利水电大学学报(自然科学版), 2025,46(3):80-87. Wu Y L, Sun D Y, Han Z Z, et al. Study on the complexity of Jinghe River runoff based on multi-scale entropy[J]. Journal of North China University of Water Resources and Hydropower (Natural Science Edition), 2025,46(3):80-87. [20] 孟亦康,许野,王鑫鹏,等. 基于相似日选取和PCA-LSTM的光伏出力组合预测模型研究[J].太阳能学报,2024,45(7):453-461. Meng Y K, Xu Y, Wang X P, et al. Research on photovoltaic output portfolio prediction model based on similar day selection and PCA-LSTM[J]. Journal of Solar Energy,2024,45(7):453-461.
