CAPSO: Chaos Adaptive Particle Swarm Optimization Algorithm

Abstract

As an influential technology of swarm evolutionary computing (SEC), the particle swarm optimization (PSO) algorithm has attracted extensive attention from all walks of life. However, how to rationally and effectively utilize the population resources to equilibrate the exploration and utilization is still a key dispute to be resolved. In this paper, we propose a novel PSO algorithm called Chaos Adaptive Particle Swarm Optimization (CAPSO), which adaptively adjust the inertia weight parameter w and acceleration coefficients c 1 , c 2 , and introduces a controlling factor γ based on chaos theory to adaptively adjust the range of chaotic search. This makes the algorithm have favorable adaptability, and then the particles can not only effectively prevent missing the global optimal solution, but also have a high probability of jumping out of the local optimal solution. To verify the stability, convergence speed, and accuracy of CAPSO, we conduct ample experiments on 6 test functions. In addition, to further verify the effectiveness and scalability of CAPSO, comparative experiments are carried out on the CEC2013 test suite. Finally, the results prove that CAPSO outperforms other peer algorithms to achieve satisfactory performance.

A Web Knowledge-Driven Multimodal Retrieval Method in Computational Social Systems: Unsupervised and Robust Graph Convolutional Hashing

“…Deep structure-based: Due to its rich nonlinear representation ability [6], [22], [29], the extracted features of deep networks contain richer semantic information and are more discriminative and effective [15] in multi-modal retrieval. Unsupervised Deep Cross-Modal Hashing (UDCMH) [30] combines deep learning, matrix factorization technology [31], and binary latent factor models [32] to jointly optimize feature learning and hash code learning.…”

“…I N the era of big data, Computational Social Systems (CSS) [1] has been pushed to the focus of research due to the rapid development of various technologies such as network information systems and the Internet of Things [2]- [5]. The popularity of various related applications has brought large-scale data, which has brought unprecedented challenges to the analysis of social behaviors with complex correlations [6]. Computational social science, an academic sub-discipline, is emerged as the times require [7].…”

Achieving Light-Weighted Secure Scheme for Communication in a Smart Grid

“…Most of the above studies improve and innovate on the basis of old algorithms, but few studies have gone to try to use algorithms from other fields, while chaos theory [29] possesses properties such as pseudo-randomness, ergodicity and sensitivity to initial values, which are very similar to those needed for the original language of cryptography, and the computation time of the one-dimensional logistic chaotic mapping is similar to that of the modal power operation after simulation analysis The computation time of the onedimensional logistic chaos mapping is similar to that of the modal power operation after simulation. And most of the current research on chaos theory uses it as image encryption, optimization, trend prediction, etc [30], [31], [32]. So we try to propose a secure communication scheme for smart grid based on chaos theory, our scheme adopts the hierarchical communication model for smart grid proposed in literature [10], and takes into account the limited memory and computational power of smart meters, and finally our communication scheme is proved to be of light weight by simulation.…”

Crow Search Algorithm Based on Information Interaction for Epistasis Detection

“…For each algorithm, the parameter setting is very important [7,27,28]. In the FICSA, the larger the  is, the stronger the global search capability of the algorithm will be, but the local search capability will become weaker.…”