Predicting vacant parking space availability: an SVR method with fruit fly optimisation

• Published in: IET intelligent transport systems Vol. 12; no. 10; pp. 1414 - 1420
• Main Authors: Fan, Junkai, Hu, Qian, Tang, Zhenzhou
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.12.2018
• Subjects: backpropagation; commonly used prediction models; extreme learning machine; FOA‐SVR method; FOA‐SVR prediction model; fruit fly optimisation; fruit fly population; learning (artificial intelligence); neural nets; novel prediction model; optimal parameters; optimisation; parking lots; prediction scenarios; regression analysis; Research Article; support vector machines; support vector regression; SVR parameters; vacant parking space availability; vacant parking spaces; novel prediction model; support vector machines; commonly used prediction models; vacant parking space availability; regression analysis; FOA-SVR prediction model; fruit fly population; support vector regression; optimisation; fruit fly optimisation; optimal parameters; extreme learning machine; prediction scenarios; backpropagation; parking lots; FOA-SVR method; SVR parameters; vacant parking spaces; learning (artificial intelligence); neural nets
• ISSN: 1751-956X; 1751-9578; 1751-9578
• DOI: 10.1049/iet-its.2018.5031

In this study, a novel prediction model for the number of vacant parking spaces after a specific period of time is proposed based on support vector regression (SVR) with fruit fly optimisation algorithm (FOA). In the proposed model, the SVR parameters are initialised as the fruit fly population, and FOA is utilised to search the optimal parameters for SVR. Sufficient experiments within various scenarios, i.e. predicting the vacant parking space availability in parking lots with various capacities after various periods of time, have been conducted to verify the effectiveness of the proposed FOA-SVR prediction model. Three other commonly used prediction models, i.e. backpropagation neural network (NN), extreme learning machine and wavelet NN, are used as the comparison models. The experimental results show that the proposed FOA-SVR method has higher accuracy and stability in all the prediction scenarios.