重选精英个体的非线性收敛灰狼优化算法

针对灰狼优化算法（GWO）存在的求解精度较低、后期收敛速度较慢、易陷入局部最优的缺点,提出一种改进灰狼优化算法（EGWO）。该算法引进两种改进策略：用以平衡算法全局搜索性和局部开发性的非线性收敛因子调整策略和用以降低陷入局部最优风险的精英个体重选策略。通过在9个基准测试函数上的实验与标准GWO算法,以及文献提出的5种改进灰狼算法和4种其他算法进行对比,从算法寻优的精确性和鲁棒性两个方面验证两种算法改进策略的有效性。实验结果表明,两种改进策略都能提升算法性能,综合使用两种策略的EGWO在收敛速度和求解精度都明显优于其他比较算法。     

基于灰狼优化的反向学习粒子群算法

针对粒子群算法（PSO）易早熟收敛、逃离局部最优能力差、精度低等缺点,提出一种基于灰狼优化的反向学习粒子群算法。该算法对最优粒子采用反向学习策略产生反向解,扩大种群的搜索范围,增强了算法的全局搜索能力;对其非最优粒子采用新型社会学习方式,提高其搜索效率和开采性能;同时,针对PSO收敛精度较低的问题,引入灰狼优化算法,并对其收敛因子产生扰动,平衡算法全局和局部搜索性能并提高其精度。在CEC2017测试函数上进行仿真实验,结果表明,在相同的实验条件下,改进后的粒子群算法在收敛精度和收敛速度上有显著提升,且其性能明显优于标准粒子群算法。     

Cultural-based particle swarm for dynamic optimisation problems

Many practical optimisation problems are with the existence of uncertainties, among which a significant number belong to the dynamic optimisation problem (DOP) category in which the fitness function changes through time. In this study, we propose the cultural-based particle swarm optimisation (PSO) to solve DOP problems. A cultural framework is adopted incorporating the required information from the PSO into five sections of the belief space, namely situational, temporal, domain, normative and spatial knowledge. The stored information will be adopted to detect the changes in the environment and assists response to the change through a diversity-based repulsion among particles and migration among swarms in the population space, and also helps in selecting the leading particles in three different levels, personal, swarm and global levels. Comparison of the proposed heuristics over several difficult dynamic benchmark problems demonstrates the better or equal performance with respect to most of other selected state-of-the-art dynamic PSO heuristics.     

A memetic particle swarm optimisation algorithm for dynamic multi-modal optimisation problems

Many real-world optimisation problems are both dynamic and multi-modal, which require an optimisation algorithm not only to find as many optima under a specific environment as possible, but also to track their moving trajectory over dynamic environments. To address this requirement, this article investigates a memetic computing approach based on particle swarm optimisation for dynamic multi-modal optimisation problems (DMMOPs). Within the framework of the proposed algorithm, a new speciation method is employed to locate and track multiple peaks and an adaptive local search method is also hybridised to accelerate the exploitation of species generated by the speciation method. In addition, a memory-based re-initialisation scheme is introduced into the proposed algorithm in order to further enhance its performance in dynamic multi-modal environments. Based on the moving peaks benchmark problems, experiments are carried out to investigate the performance of the proposed algorithm in comparison with several state-of-the-art algorithms taken from the literature. The experimental results show the efficiency of the proposed algorithm for DMMOPs.     

A new effective operator for the hybrid algorithm for solving global optimisation problems

Hybrid algorithms have been recently used to solve complex single-objective optimisation problems. The ultimate goal is to find an optimised global solution by using these algorithms. Based on the existing algorithms (HP_CRO, PSO, RCCRO), this study proposes a new hybrid algorithm called MPC (Mean-PSO-CRO), which utilises a new Mean-Search Operator. By employing this new operator, the proposed algorithm improves the search ability on areas of the solution space that the other operators of previous algorithms do not explore. Specifically, the Mean-Search Operator helps find the better solutions in comparison with other algorithms. Moreover, the authors have proposed two parameters for balancing local and global search and between various types of local search, as well. In addition, three versions of this operator, which use different constraints, are introduced. The experimental results on 23 benchmark functions, which are used in previous works, show that our framework can find better optimal or close-to-optimal solutions with faster convergence speed for most of the benchmark functions, especially the high-dimensional functions. Thus, the proposed algorithm is more effective in solving single-objective optimisation problems than the other existing algorithms.     

Parameter selection in particle swarm optimisation: a survey

Nowadays, particle swarm optimisation (PSO) is one of the most commonly used optimisation techniques. However, PSO parameters significantly affect its computational behaviour. That is, while it exposes desirable computational behaviour with some settings, it does not behave so by some other settings, so the way for setting them is of high importance. This paper explains and discusses thoroughly about various existent strategies for setting PSO parameters, provides some hints for its parameter setting and presents some proposals for future research on this area. There exists no other paper in literature that discusses the setting process for all PSO parameters. Using the guidelines of this paper can be strongly useful for researchers in optimisation-related fields.     

Enhanced leader PSO (ELPSO): A new PSO variant for solving global optimisation problems

Particle swarm optimisation (PSO) is a well-established optimisation algorithm inspired from flocking behaviour of birds. The big problem in PSO is that it suffers from premature convergence, that is, in complex optimisation problems, it may easily get trapped in local optima. In this paper, a new PSO variant, named as enhanced leader PSO (ELPSO), is proposed for mitigating premature convergence problem. ELPSO is mainly based on a five-staged successive mutation strategy which is applied to swarm leader at each iteration. The experimental results confirm that in all terms of accuracy, scalability and convergence rate, ELPSO performs well.     

基于模糊控制的权重决策灰狼优化算法

针对灰狼优化算法后期收敛速度慢,求解精度低等问题,提出一种基于模糊控制的权重决策灰狼优化算法.首先,提出一种新的非线性收敛因子,以提高算法的全局搜索能力及收敛速度;其次,提出一种基于模糊控制的权重决策策略,通过模糊控制器对决策层的个体赋予不同权重进行种群位置更新的决策,增强算法的寻优能力.选取23个标准测试函数对该算法及对比算法进行数值实验,实验结果表明,本文提出的改进的灰狼优化算法在求解精度和算法稳定性等指标优于对比算法.     

Multi-objective Grey Wolf Optimizer for improved cervix lesion classification

Cervical cancer is one of the vital and most frequent cancers, but can be cured effectively if diagnosed in the early stage. This is a novel effort towards effective characterization of cervix lesions from contrast enhanced CT-Scan images to provide a reliable and objective discrimination between benign and malignant lesions. Performance of such classification models mostly depends on features used to represent samples in a training dataset. Selection of optimal feature subset here is NP-hard; where, randomized algorithms do better. In this paper, Grey Wolf Optimizer (GWO), which is a population based meta-heuristic inspired by the leadership hierarchy and hunting mechanism of grey wolves has been utilized for feature selection. The traditional GWO is applicable for continuous single objective optimization problems. Since, feature selection is inherently multi-objective; this paper proposes two different approaches for multi-objective binary GWO algorithms. One is a scalarized approach to multi-objective GWO (MOGWO) and the other is a Non-dominated Sorting based GWO (NSGWO). These are used for wrapper based feature selection that selects optimal textural feature subset for improved classification of cervix lesions. For experiments, contrast enhanced CT-Scan (CECT) images of 62 patients have been used, where all lesions had been recommended for surgical biopsy by specialist. Gray-level co-occurrence matrix based texture features are extracted from two-level decomposition of wavelet coefficients of cervix regions extracted from CECT images. The results of proposed approaches are compared with mostly used meta-heuristics such as genetic algorithm (GA) and firefly algorithm (FA) for multi-objective optimization. With better diversification and intensification, GWO obtains Pareto solutions, which dominate the solutions obtained by GA and FA when assessed on the utilized cervix lesion cases. Cervix lesions are up to 91% accurately classified as benign and malignant with only five features selected by NSGWO. A two-tailed t-test was conducted by hypothesizing the mean F-score obtained by the proposed NSGWO method at significance level = 0.05. This confirms that NSGWO performs significantly better than other methods for the real cervix lesion dataset in hand. Further experiments were conducted on high dimensional microarray gene expression datasets collected online. The results demonstrate that the proposed method performs significantly better than other methods selecting relevant genes for high-dimensional, multi-category cancer diagnosis with an average of 12.82% improvement in F-score value.     

An improved particle swarm optimiser based on swarm success rate for global optimisation problems

Inertia weight is one of the control parameters that influences the performance of particle swarm optimisation (PSO) in the course of solving global optimisation problems, by striking a balance between exploration and exploitation. Among many inertia weight strategies that have been proposed in literature are chaotic descending inertia weight (CDIW) and chaotic random inertia weight (CRIW). These two strategies have been claimed to perform better than linear descending inertia weight (LDIW) and random inertia weight (RIW). Despite these successes, a closer look at their results reveals that the common problem of premature convergence associated with PSO algorithm still lingers. Motivated by the better performances of CDIW and CRIW, this paper proposed two new inertia weight strategies namely: swarm success rate descending inertia weight (SSRDIW) and swarm success rate random inertia weight (SSRRIW). These two strategies use swarm success rates as a feedback parameter. Efforts were made using the proposed inertia weight strategies with PSO to further improve the effectiveness of the algorithm in terms of convergence speed, global search ability and improved solution accuracy. The proposed PSO variants, SSRDIW_PSO and SSRRIW_PSO were validated using several benchmark unconstrained global optimisation test problems and their performances compared with LDIW-PSO, CDIW-PSO, RIW-PSO, CRIW-PSO and some other existing PSO variants. Empirical results showed that the proposed variants are more efficient.     

Simplified particle swarm algorithm based on nonlinear decrease extreme disturbance and Cauchy mutation

Abstract

Concerning the drawbacks that particle swarm optimisation algorithm is easy to fall into the local optima, and has low solution precision, the simplified particle algorithm which based on the nonlinear decrease extreme disturbance and Cauchy mutation is proposed. The algorithm simplifies particle updating formula, and uses logistic chaotic sequence to initialise the particle position, which can improve the global search ability of population; nonlinear decrease extreme disturbance strategy enhanced the diversity of the population and avoid the particles trapping in local optimum; a novel Cauchy mutation is used for the optimal particle variation to generate more optimal guiding particle movement. The experimental simulation on seven typical test functions shows that the proposed algorithm can effectively avoid falling into local optimal solution, the search speed and optimisation accuracy have improved significantly. The algorithm is suitable to solve the function optimisation problem.     

An overview of population-based algorithms for multi-objective optimisation

In this work we present an overview of the most prominent population-based algorithms and the methodologies used to extend them to multiple objective problems. Although not exact in the mathematical sense, it has long been recognised that population-based multi-objective optimisation techniques for real-world applications are immensely valuable and versatile. These techniques are usually employed when exact optimisation methods are not easily applicable or simply when, due to sheer complexity, such techniques could potentially be very costly. Another advantage is that since a population of decision vectors is considered in each generation these algorithms are implicitly parallelisable and can generate an approximation of the entire Pareto front at each iteration. A critique of their capabilities is also provided.     

Centroid particle swarm optimisation for high-dimensional data classification

ABSTRACT

This paper proposes a new variant of Particle Swarm Optimization (PSO), dubbed CentroidPSO, to tackle data classification problem in high dimensional domains. It is inspired by the center-based sampling theory, which states that the center region of a search space contains points with higher probability to be closer to the optimal solution. The experimental results show striking performance of the CentroidPSO as compared to the standard PSO, four closely related PSO variants, and three recent evolutionary computation approaches. Moreover, a comparison with three machine learning approaches indicate that the CentroidPSO is a very competitive and promising classifier.     

Chaotic bat swarm optimisation (CBSO)

Bat swarm optimisation (BSO) is a novel heuristic optimisation algorithm that is being used for solving different global optimisation problems. The paramount problem in BSO is that it severely suffers from premature convergence problem, that is, BSO is easily trapped in local optima. In this paper, chaotic-based strategies are incorporated into BSO to mitigate this problem. Ergodicity and non-repetitious nature of chaotic functions can diversify the bats and mitigate premature convergence problem. Eleven different chaotic map functions along with various chaotic BSO strategies are investigated experimentally and the best one is chosen as the suitable chaotic strategy for BSO. The results of applying the proposed chaotic BSO to different benchmark functions vividly show that premature convergence problem has been mitigated efficiently. Actually, chaotic-based BSO significantly outperforms conventional BSO, cuckoo search optimisation (CSO), big bang-big crunch algorithm (BBBC), gravitational search algorithm (GSA) and genetic algorithm (GA).     

Energy efficient load balancing approach for avoiding energy hole problem in WSN using Grey Wolf Optimizer with novel fitness function

In general architecture of Wireless Sensor Networks (WSNs), gateways far from the Base Station (BS) communicate with the BS via the gateways close to the BS. The energy of gateways which are close to the BS drains faster due to the heavy traffic load. This leads to the energy hole problem around the BS. Therefore, proper clustering of sensor nodes and routing of data are essential for efficient conservation of energy and for avoiding inadvertent network failure due to a power drain. In this paper, we apply the Grey Wolf Optimization (GWO) approach for energy-efficient clustering and routing in WSN. Also, we propose two novel fitness functions for clustering and routing problems. The fitness function for routing is formulated such that overall distance traversal and number of hops are minimized. The fitness function for clustering distributes the overall load according to the distance of gateways to the BS. The proposed GWO-based approach is resulted with higher values of both clustering and routing fitness functions as compared to the existing algorithms, namely, genetic algorithm, particle swarm optimization and multi-objective fuzzy clustering.     

一种基于并行搜索策略的苍狼算法

作为一种新型群体智能方法,苍狼算法模拟了苍狼在群体捕食过程中的搜索跟踪、包围、攻击等行为。分析了该算法的优化机理,并对算法优化过程进行了数学定义及描述。提出了一种基于并行搜索策略的改进型苍狼算法,将狼群分组,在整个搜索过程中同时进行局部开发和全局探索活动,以更好地满足目标搜寻的要求。通过典型的基准测试函数对算法进行了性能仿真测试。实验结果表明,与其他群体智能优化方法相比,改进型苍狼算法在收敛速度、收敛精度及鲁棒性等方面均具有一定优势。     

基于改进型灰狼算法的RFID网络规划

随着物联网技术的飞速发展,射频识别(Radio Frequency Identification,RFID)系统因具有非接触、快速识别等优点而成为了解决物联网问题的首选方案.RFID网络规划问题要考虑多个目标,被证明是多目标优化的问题.群体智能(Swarm In-telligence,SI)算法在解决多目标优化问题方面...     

Improved butterfly optimisation algorithm based on guiding weight and population restart

ABSTRACT

Butterfly Optimisation Algorithm (BOA) is a kind of meta-heuristic swarm intelligence algorithm based on butterfly foraging strategy, but it still needs to be improved in the aspects of convergence speed and accuracy when solving with high-dimensional optimisation problems. In this paper, an improved butterfly optimisation algorithm is proposed, in which guiding weight and population restart strategy are applied to the original algorithm. By adding guiding weight to the global search equation, the convergence speed and accuracy of the algorithm are improved, and the possibility of jumping out of the local optimal solution is increased by the population restart strategy. In order to verify the performance of the proposed algorithm, 24 benchmark functions commonly used for optimisation algorithm experiments are applied in this paper, including 12 unimodal functions and 12 multimodal functions. Experimental results show that the proposed algorithm improves the convergence speed, accuracy and the ability to jump out of the local optimal solution.     

Feature Selection Using Grey Wolf Optimization with Random Differential Grouping

Big data are regarded as a tremendous technology for processing a huge variety of data in a short time and with a large storage capacity. The user’s access over the internet creates massive data processing over the internet. Big data require an intelligent feature selection model by addressing huge varieties of data. Traditional feature selection techniques are only applicable to simple data mining. Intelligent techniques are needed in big data processing and machine learning for an efficient classification. Major feature selection algorithms read the input features as they are. Then, the features are preprocessed and classified. Here, an algorithm does not consider the relatedness. During feature selection, all features are misread as outputs. Accordingly, a less optimal solution is achieved. In our proposed research, we focus on the feature selection by using supervised learning techniques called grey wolf optimization (GWO) with decomposed random differential grouping (DrnDG-GWO). First, decomposition of features into subsets based on relatedness in variables is performed. Random differential grouping is performed using a fitness value of two variables. Now, every subset is regarded as a population in GWO techniques. The combination of supervised machine learning with swarm intelligence techniques produces best feature optimization results in this research. Once the features are optimized, we classify using advanced kNN process for accurate data classification. The result of DrnDG-GWO is compared with those of the standard GWO and GWO with PSO for feature selection to compare the efficiency of the proposed algorithm. The accuracy and time complexity of the proposed algorithm are 98% and 5 s, which are better than the existing techniques.