| Civil Engineering |
|
|
|
|
| Dynamicsanalysis of parking space occupancy series based oncomplexity measurement |
| MEI Zhen-yu, ZHANG Wei |
| College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China |
|
|
|
Abstract The analysis of the sequence was conducted based on complexity measurement in order to quantitatively analyze the dynamic characteristics of parking space occupancy time series. The principal component analysis was used to analyze the principal component spectrum of the sequence. The nonlinear characteristic of the sequence was calculated by the joint entropy of the sequence. Irregular components of the sequence were analyzed by calculating the C0 complexity of the sequence. The analysis of comparing with several typical time series shows that the time series of parking space occupancy is a kind of sequence which situated between linearity and nonlinearity, and its linear characteristic is more significant. The sequence contains more regular components, which can be seen as a ‘quasi-periodic’ sequence, but the extremely irregular components in the original series can increase the prediction error in long-term prediction. Long-term prediction of parking space series was conducted by using the idea of C0 complexity. Results show that the prediction accuracy increases by 26% to 56% after eliminating irregular components in the original series, which shows better performance.
|
|
Received: 09 January 2017
|
|
|
基于复杂性测度的泊位占有率序列动力学分析
为了定量分析停车场泊位占有率时间序列的动力学特性，对序列进行复杂性测度分析.利用主分量分析方法分析序列的主分量谱图，判断序列的混沌特性；计算序列的联合熵分析序列的非线性特性，计算序列的C0复杂度分析序列中的非规则成分，综合两种复杂性测度方法对序列的动力学特性进行分析.对比分析几种典型序列和泊位占有率序列发现，泊位占有率时间序列的线性特征更明显，序列中所含的规则成分较多，是一种“拟周期”序列.利用C0复杂度的思想剔除不规则成分，对序列进行长时预测，结果表明，剔除不规则成分后的预测精度提高了26%~56%，长时预测效果提高显著.
|
|
| [1] SHOUP D. Cruising for parking[J]. Transport Policy, 2006, 13(6):479-486.
[2] THOMPSONR G, BONSALL P. Drivers' response to parking guidance and information systems[J]. Transport Reviews, 1997, 17(2):89-104.
[3] LIU W, YANG H, YIN Y. Expirable parking reservations for managing morning commute with parking space constraints[J]. Transportation Research Part C Emerging Technologies, 2014, 44(4):185-201.
[4] MAJIDI A, POLAT H, ÇETIN A. Finding a best parking place using exponential smoothing and cloud system in a metropolitan area[C]//International Istanbul Smart Grid Congress and Fair. Istanbul:[s.n.], 2016.
[5] CALISKAN M, BARTHELS A, SCHEUERMANN B, et al. Predicting parking lot occupancy in vehicular Ad Hoc networks[C]//Vehicular Technology Conference.Dublin:[s.n.], 2007:277-281.
[6] JI Y, TANG D, BLYTHE P, et al. Short-term forecasting of available parking space using wavelet neural network model[J]. Journal of Southeast University, 2014, 9(2):202-209.
[7] ZHENG Y, RAJASEGARAR S, LECKIE C. Parking availability prediction for sensor-enabled car parks in smart cities[C]//IEEE 10th International Conference on Intelligent Sensors, Sensor Networks and Information Processing. Singapore:IEEE, 2015.
[8] JI Y, TANG D, GUO W, et al. Forecasting available parking space with largest Lyapunov exponents method[J]. Journal of Central South University, 2014, 21(4):1624-1632.
[9] 陈群,晏克非,王仁涛,等. 基于相空间重构及Elman网络的停车泊位数据预测[J]. 同济大学学报:自然科学版,2007,35(5):607-611. CHEN Qun, YAN Ke-fei, WANG Ren-tao, et al. Parking space information prediction based on phrase construction and Elman neuraI network[J]. Journal of Tongji University:Natural Science, 2007, 35(5):607-611.
[10] SHUMWAY R H, STOFFER D S. Time series analysis and its applications[M]. New York:Springer, 2009:119-160.
[11] 吕金虎,陆君安, 陈士华. 混沌时间序列分析及其应用[M]. 武汉:武汉大学出版社,2002:49-92.
[12] LI P, LI K, LIU C, et al. Detection of coupling in short physiological series by a joint distribution entropy method[J]. IEEE Transactions on Biomedical Engineering, 2016, 63(11):2231-2242.
[13] 李锦,宁新宝,马千里. 用联合熵分析短时心率变异信号的非线性动力学复杂性[J]. 生物医学工程学杂志,2007,24(2):285-289. LI Jin, NING Xin-bao, MA Qian-li. Nonlinear dynamical complexity analysis of short-term heartbeat series using joint entropy[J]. Journal of Biomedical Engineering, 2007, 24(2):285-289.
[14] 张勇,关伟. 基于联合熵和C0复杂度的交通流复杂性测度[J]. 计算机工程与应用,2010,46(15):22-24. ZHANG Yong, GUAN Wei. Complexity measure of traffic flow based on union entropy and C0 complexity[J]. Computer Engineering and Applications, 2010, 46(15):22-24.
[15] TONG C, HUANG Q, LIU H. Analysis on runoff time series dynamics character based on complexity theory[J]. Systems Engineering-theory and Practice, 2004, 9:102-107.
[16] 蔡志杰,孙洁. 改进的C0复杂度及其应用[J]. 复旦学报:自然科学版,2008,47(6):791-796. CAI Zhi-jie,SUN Jie. Modified C0 complexity and applications[J]. Journal of Fudan University:Natural Science, 2008, 47(6):791-796.
[17] 科费, 托马斯. 信息论基础[M]. 北京:机械工业出版社,2005:7-13.
[18] 史永胜,姜颖,宋云雪. 基于符号序列联合熵的航空发动机健康监控方法[J]. 航空动力学报,2011,26(3):670-674. SHI Yong-sheng, JIANG Ying, SONG Yun-xue. Aero-engine health monitoring method based on joint entropy of symbolic series[J]. Journal of Aerospace Power, 2011, 26(3):670-674.
[19] 雷敏,王志中. 非线性时间序列的替代数据检验方法研究[J]. 电子与信息学报,2001,23(3):248-254. LEI Min, WANG Zhi-zhong. Study of the surrogate data method for nonlinearity of time series[J]. Journal of Electronics and Information Technology, 2001, 23(3):248-254.
[20] GESTEL T, SUYKENS J A K, BASTAENS D E, et al. Financial time series prediction using least squares support vector machines within the evidence framework[J]. IEEE Transactions on Neural Networks, 2001, 12(4):809-821. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
