Improved CS Algorithm and its Application in Parking Space Prediction
- PDF / 1,518,192 Bytes
- 9 Pages / 595.22 x 842 pts (A4) Page_size
- 45 Downloads / 252 Views
Journal of Bionic Engineering http://www.springer.com/journal/42235
Improved CS Algorithm and its Application in Parking Space Prediction Rui Guo1,2, Xuanjing Shen1,2, Hui Kang1,2* 1. College of Computer Science and Technology, Jilin University, Changchun 130012, China 2. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
Abstract This paper simulates the cuckoo incubation process and flight path to optimize the Wavelet Neural Network (WNN) model, and proposes a parking prediction algorithm based on WNN and improved Cuckoo Search (CS) algorithm. First, the initialization parameters are provided to optimize the WNN using the improved CS. The traditional CS algorithm adopts the strategy of overall update and evaluation, but does not consider its own information, so the convergence speed is very slow. The proposed algorithm employs the evaluation strategy of group update, which not only retains the advantage of fast convergence of the dimension-by-dimension update evaluation strategy, but also increases the mutual relationship between the nests and reduces the overall running time. Then, we use the WNN model to predict parking information. The proposed algorithm is compared with six different heuristic algorithms in five experiments. The experimental results show that the proposed algorithm is superior to other algorithms in terms of running time and accuracy. Keywords: wavelet neural network, cuckoo search algorithm, available parking spaces prediction, bionic Copyright © Jilin University 2020.
1 Introduction An optimization algorithm is the process of searching for a vector in a given domain, which is the best solution among many possible feasible solutions. The traditional optimization techniques can hardly solve intricate problems. With the development of bionics, many scholars turned to nature to learn, and proposed a variety of natural heuristic algorithms, which can often be used to tackle the issue of optimization. Recently, optimization algorithms based on krill migration algorithms have shown good results[1–5]. For instance, Wang et al. used a Biogeography-Based Krill Herd (BBKH) algorithm to solve complicated optimization tasks, which introduced a new Krill Migration (KM) operator, effectively solving the optimization problem[6]. Wang et al. presented a robust optimization algorithm based on hybridization of KH and Artificial Bee Colony (ABC) methods[7]. In addition, Rizk et al. proposed Parallel Hurricane Optimization Algorithm (PHOA) for solving Economic Emission Load Dispatch (EELD) problem in modern power systems[8]. In Ref. [9], a Non-dominated Sorting Genetic Algorithm, the third version (NSGA-III) was proposed, introducing an adaptive mutation opera*Corresponding author: Hui Kang E-mail: [email protected]
tor to enhance the performance of the standard NSGA-III algorithm. The Evolutionary Multi-objective Optimization (EMO) algorithm to deal with Multiobjective Otimization Problems (MOPs) was used by Wang et al.[10]. I
Data Loading...
