Title: An overall analysis method of urban road parking lots based on data mining

Authors: Guanlin Chen; Jiapeng Shen; Jiang He; Xu Dai; Wenyong Weng

Addresses: School of Computer and Computing Science, Zhejiang University City College, Hangzhou, 310015, China; School of Computer, Zhejiang University, Hangzhou, 310027, China ' School of Computer and Computing Science, Zhejiang University City College, Hangzhou, 310015, China; School of Computer, Zhejiang University, Hangzhou, 310027, China ' Hangzhou Digital Urban Management Information Processing Center, Hangzhou, 310014, China ' Hangzhou Digital Urban Management Information Processing Center, Hangzhou, 310014, China ' School of Computer and Computing Science, Zhejiang University City College, Hangzhou, 310015, China

Abstract: In this paper, we first propose a multiple linear regression-autoregressive moving average model (MLR-ARMA) which combines the multiple linear regression model and the autoregressive moving average model to fit and predict a single parking lot's parking demand. The experimental results show that this model performs better on predicting future parking amounts than the simple multiple linear regression model and the autoregressive integrated moving average (ARIMA) model. Then, this paper proposes an overall analysis method of urban road parking lots based on cluster analysis and uses the MLR-ARMA model to verify the clustering results. The experimental results show that when reasonable weights are assigned to different dimensions of the feature vector of parking lots, the method proposed in this paper can classify parking lots with similar usage patterns and adjacent locations into one category well, which is conducive to further analysis.

Keywords: parking management; MLR-ARMA model; data mining; cluster analysis; feature vector; linear regression.

DOI: 10.1504/IJSN.2021.116774

International Journal of Security and Networks, 2021 Vol.16 No.2, pp.105 - 111

Received: 07 Jun 2020
Accepted: 07 Aug 2020
Published online: 02 Aug 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article