混合自适应引力搜索优化的特征选择方法

特征选择在许多领域具有重要作用,提出一种基于混合自适应引力搜索算法的特征选择方法,在最大化分类精度的同时从数据样本中选出最小特征子集。算法设计两种解更新策略进行组合式搜索,引入群体约简方法,有效地平衡算法的全局搜索和局部收敛能力,同时提出自适应调控参数,减少参数设置对算法性能的影响。在七组真实数据集中的实验结果表明,从分类精度、特征子集大小和运行时间三方面比较,提出的方法优于原始算法和已有相近算法,具有良好的综合性能,是一种有效的特征选择方法。     

基于改进引力搜索算法的K-means聚类

针对K-means算法的聚类结果极易受到聚类中心的影响而陷入局部最优解的问题,提出一种基于改进引力搜索的K-means聚类算法。首先引入自适应概念,对引力系数衰减因子进行控制,提高算法的全局探索能力和局部开发能力;然后,引入免疫克隆选择机制,以便算法能够有效跳出局部最优,并通过对12个基准测试函数的实验验证改进引力搜索算法的有效性和优越性;最后,通过结合改进的引力搜索算法和K-means算法,提出一种新的聚类算法A2F-GSA-Kmeans,并在6个测试数据集上的实验表明,该算法具有较好的聚类质量。     

非线性极大极小问题的混沌万有引力搜索算法求解*

针对非线性极大极小问题目标函数不可微的特点,提出了一种混沌万有引力搜索算法的求解方法。该算法采用基于万有引力定律的优化机制引导群体进行全局探索,并基于混沌运动的随机性、遍历性和规律性特点,利用混沌优化对当前最优位置进行精细搜索,有效抑制算法早熟收敛现象,提高优化性能。数值实验结果表明,该算法具有计算精度高、数值稳定性好等特点。     

基于引力搜索的布尔函数生成算法

布尔函数是在密码学、纠错编码和扩频通信等领域有着广泛应用的密码函数,寻找性能优良的布尔函数一直是密码学领域的重要问题之一。基于引力搜索算法设计了一种搜索布尔函数的新算法。该算法模仿万有引力定律,以n维空间中的质量点表示布尔函数,以布尔函数的密码特性作为目标适应度函数进行搜索。实验结果表明,算法使用新设计的目标适应度函数可以直接生成具有1阶弹性、1阶扩散准则和高非线性度、高代数次数以及低自相关指标等多种密码学指标的平衡布尔函数,并且进一步给出了直接生成2输出平衡布尔函数的计算机搜索算法。     

引力搜索优化ELM的企业财务危机预警方法

为提高企业财务危机的预测准确率,提出一种基于引力搜索算法优化核极限学习机(KELM)的并行模型PHGSA-KELM。模型考虑了特征选择机制和参数优化两者对KELM模型起着同等重要的作用,提出改进的引力搜索算法(HGSA)同步实现特征选择机制和KELM参数优化,同时设计的线性加权多目标函数综合考虑了分类精度和特征子集数量,改善了算法的分类性能,并且基于多核平台的多线程并行方式进一步提高了算法的计算效率。通过真实数据集的实验结果表明,提出的模型不仅获得了较少的特征子集个数,找出了与企业财务危机紧密相关的特征,得到了很高的分类准确率,并且计算效率也得到极大提高,是一种有效的企业财务危机预警模型。     

GSA-LA: gravitational search algorithm based on learning automata

ABSTRACT

Regardless of the performance of gravitational search algorithm (GSA), it is nearly incapable of avoiding local optima in high-dimension problems. To improve the accuracy of GSA, it is necessary to fine tune its parameters. This study introduces a gravitational search algorithm based on learning automata (GSA-LA) for optimisation of continuous problems. Gravitational constant G(t) is a significant parameter that is used to adjust the accuracy of the search. In this work, learning capability is utilised to select G(t) based on spontaneous reactions. To measure the performance of the introduced algorithm, numerical analysis is conducted on several well-designed test functions, and the results are compared with the original GSA and other evolutionary-based algorithms. Simulation results demonstrate that the learning automata-based gravitational search algorithm is more efficient in finding optimum solutions and outperforms the existing algorithms.     

A novel hybrid algorithm of gravitational search algorithm with genetic algorithm for multi-level thresholding

The multi-level thresholding is a popular method for image segmentation. However, the method is computationally expensive and suffers from premature convergence when level increases. To solve the two problems, this paper presents an advanced version of gravitational search algorithm (GSA), namely hybrid algorithm of GSA with genetic algorithm (GA) (GSA-GA) for multi-level thresholding. In GSA-GA, when premature convergence occurred, the roulette selection and discrete mutation operators of GA are introduced to diversify the population and escape from premature convergence. The introduction of these operators therefore promotes GSA-GA to perform faster and more accurate multi-level image thresholding. In this paper, two common criteria (1) entropy and (2) between-class variance were utilized as fitness functions. Experiments have been performed on six test images using various numbers of thresholds. The experimental results were compared with standard GSA and three state-of-art GSA variants. Comparison results showed that the GSA-GA produced superior or comparative segmentation accuracy in both entropy and between-class variance criteria. Moreover, the statistical significance test demonstrated that GSA-GA significantly reduce the computational complexity for all of the tested images.     

基于引力搜索算法的证券投资组合问题研究

引力搜索算法是模拟万有引力定律进行搜索的一种新颖的优化算法,已有研究表明该算法比传统的一些优化算法拥有较好的收敛性能,但该算法在局部搜索能力上有所欠缺。提出一种基于惯性递减权重的引力搜索算法（gGSA）,该算法能够在局部进行进一步的探索,强化局部搜索能力。该算法应用到基于VaR的证券最优投资组合模型中,解决证券投资组合优化的问题,并以上证50指数中成分股于2012年上半年日收盘价格作为测试数据集进行计算,结果表明改进算法所得到的投资比例能够获得较好的收益率。     

一种改进的基于神经网络的文本分类算法

提出并实现了一种结合前馈型神经网络和K最近邻的文本分类算法。其中,在选取特征项时考虑到Web文本不同标签组所代表的意义和权重有所区别,采用了一种改进的TFIDF特征选择法。最后对设计的分类器进行了开放性测试,实验结果表明该分类器显著地提高了文本分类的查全率和查准率。     

A prototype classifier based on gravitational search algorithm

In recent years, heuristic algorithms have been successfully applied to solve clustering and classification problems. In this paper, gravitational search algorithm (GSA) which is one of the newest swarm based heuristic algorithms is used to provide a prototype classifier to face the classification of instances in multi-class data sets. The proposed method employs GSA as a global searcher to find the best positions of the representatives (prototypes). The proposed GSA-based classifier is used for data classification of some of the well-known benchmark sets. Its performance is compared with the artificial bee colony (ABC), the particle swarm optimization (PSO), and nine other classifiers from the literature. The experimental results of twelve data sets from UCI machine learning repository confirm that the GSA can successfully be applied as a classifier to classification problems.     

A novel hybrid gravitational search and pattern search algorithm for load frequency control of nonlinear power system

In this paper, a hybrid gravitational search algorithm (GSA) and pattern search (PS) technique is proposed for load frequency control (LFC) of multi-area power system. Initially, various conventional error criterions are considered, the PI controller parameters for a two-area power system are optimized employing GSA and the effect of objective function on system performance is analyzed. Then GSA control parameters are tuned by carrying out multiple runs of algorithm for each control parameter variation. After that PS is employed to fine tune the best solution provided by GSA. Further, modifications in the objective function and controller structure are introduced and the controller parameters are optimized employing the proposed hybrid GSA and PS (hGSA-PS) approach. The superiority of the proposed approach is demonstrated by comparing the results with some recently published modern heuristic optimization techniques such as firefly algorithm (FA), differential evolution (DE), bacteria foraging optimization algorithm (BFOA), particle swarm optimization (PSO), hybrid BFOA-PSO, NSGA-II and genetic algorithm (GA) for the same interconnected power system. Additionally, sensitivity analysis is performed by varying the system parameters and operating load conditions from their nominal values. Also, the proposed approach is extended to two-area reheat thermal power system by considering the physical constraints such as reheat turbine, generation rate constraint (GRC) and governor dead band (GDB) nonlinearity. Finally, to demonstrate the ability of the proposed algorithm to cope with nonlinear and unequal interconnected areas with different controller coefficients, the study is extended to a nonlinear three unequal area power system and the controller parameters of each area are optimized using proposed hGSA-PS technique.     

Automated emotion recognition employing a novel modified binary quantum‐behaved gravitational search algorithm with differential mutation

The present paper proposes a supervised learning based automated human facial emotion recognition strategy with a feature selection scheme employing a novel variation of the gravitational search algorithm (GSA). The initial feature set is generated from the facial images by using the 2‐D discrete cosine transform (DCT) and then the proposed modified binary quantum GSA with differential mutation (MBQGSA‐DM) is utilized to select a sub‐set of features with high discriminative power. This is achieved by minimising the cost function formulated as the ratio of the within class and interclass distances. The overall system performs its final classification task based on selected feature inputs, utilising a back propagation based artificial neural network (ANN). Extensive experimental evaluations are carried out utilising a standard, benchmark emotion database, that is, Japanese Female Facial Expresssion (JAFFE) database and the results clearly indicate that the proposed method outperforms several existing techniques, already known in literature for solving similar problems. Further validation has also been carried out on a facial expression database developed at Jadavpur University, Kolkata, India and the results obtained further strengthen the notion of superiority of the proposed method.     

一种基于折半层次搜索的包分类算法

折半层次搜索(BSOL)算法是一种高效的包分类算法,容易拓展至多维包分类,并支持range类型的规则。但由于其核心结构是在特里树（Trie）的每一层创建hash表,因此当hash装载因子较大或hash冲突较大时,会影响其效率。分析折半层次搜索算法的优缺点,引入布鲁姆过滤器,提出了一种新的改进算法,为Trie树的每一层建立了一个布鲁姆过滤器,在进行hash查找之前先进行一次布鲁姆查询运算,能够在hash冲突较大的情况下依然具有良好的性能。仿真实验结果表明,在数据包的命中率低于90%并且hash装载因子较大的情况下,新算法在运行时间上要优于以前的算法。     

基于混合搜索的多种群人工蜂群算法

针对经典人工蜂群（ABC）算法搜索策略存在搜索机制单一、群体全局搜索与局部搜索运算耦合性较高的问题,提出一种基于混合搜索的多种群人工蜂群（MPABC） 算法。首先,将种群按照适应度值进行排序,得到一个有序队列,进而将其划分为随机子群、核心子群和平衡子群三类有序子群;其次,针对不同子群结合相应的个体选择机制与搜索策略,构建出不同的差异向量;最后,在群体的搜索过程中,通过三类子群实现对具有不同适应度函数值个体的有效控制,来增强群体全局搜索和局部搜索的平衡能力。通过对16个标准测试函数进行仿真实验并与具有可变搜索策略的人工蜂群（ABCVSS）算法、基于选择概率的改进人工蜂群（MABC）算法、基于粒子群策略的多精英人工蜂群（PS-MEABC）算法、基于符号函数的多搜索策略人工蜂群（MSSABC）算法和优化高维复杂函数的改进人工蜂群（IABC）算法共五种典型的蜂群算法进行了对比,实验结果显示MPABC具有较好的优化效果;与ABC算法相比,MPABC在求解高维（100维）复杂问题上的收敛速度提高了约23%,且求解精度更优。     

混合引力搜索与高斯扰动的精英布谷鸟算法

针对布谷鸟算法（CS）的不足,提出了混合引力搜索与高斯扰动的精英布谷鸟搜索算法（GGECS）。该算法提出了自适应控制策略,将布谷鸟算法中的步长因子和发现概率进行动态地调整,并使用帕累托法则进行精英分类,分别对属于不同类别的鸟巢进行引力搜索和高斯扰动,从而提高算法的种群多样性,避免算法陷入局部最优解,提高了算法的寻优精度和收敛速度。使用8个标准测试函数进行仿真实验。结果表明,该算法较CS和ICS算法具有更好的全局搜索能力,其测试函数最优解也更为接近最优解的理论值。     

A new local search based hybrid genetic algorithm for feature selection

This paper presents a new hybrid genetic algorithm (HGA) for feature selection (FS), called as HGAFS. The vital aspect of this algorithm is the selection of salient feature subset within a reduced size. HGAFS incorporates a new local search operation that is devised and embedded in HGA to fine-tune the search in FS process. The local search technique works on basis of the distinct and informative nature of input features that is computed by their correlation information. The aim is to guide the search process so that the newly generated offsprings can be adjusted by the less correlated (distinct) features consisting of general and special characteristics of a given dataset. Thus, the proposed HGAFS receives the reduced redundancy of information among the selected features. On the other hand, HGAFS emphasizes on selecting a subset of salient features with reduced number using a subset size determination scheme. We have tested our HGAFS on 11 real-world classification datasets having dimensions varying from 8 to 7129. The performances of HGAFS have been compared with the results of other existing ten well-known FS algorithms. It is found that, HGAFS produces consistently better performances on selecting the subsets of salient features with resulting better classification accuracies.     

A hybrid approach based on an improved gravitational search algorithm and orthogonal crossover for optimal shape design of concrete gravity dams

A hybrid approach based on an improved gravitational search algorithm (IGSA) and orthogonal crossover (OC) is proposed to efficiently find the optimal shape of concrete gravity dams. The proposed hybrid approach is called IGSA-OC. The hybrid of IGSA and the OC operator can improve the global exploration ability of the IGSA method, and increase its convergence rate. To find the optimal shape of concrete gravity dams, the interaction effects of dam–water–foundation rock subjected to earthquake loading are considered in this study. The computational cost of the optimal shape of concrete gravity dams subjected earthquake loads is usually high. Due to this problem, the weighted least squares support vector machine (WLS-SVM) regression as an efficient metamodel is utilized to considerably predict dynamic responses of gravity dams by spending low computational cost. To testify the robustness and efficiency of the proposed IGSA-OC, first, four well-known benchmark functions in literatures are optimized using the proposed IGSA-OC, and provides comparisons with the standard gravitational search algorithm (GSA) and the other modified GSA methods. Then, the optimal shape of concrete gravity dams is found using IGSA-OC. The solutions obtained by the IGSA-OC are compared with those of the standard GSA, IGSA and particle swarm optimization (PSO). The numerical results demonstrate that the proposed IGSA-OC significantly outperforms the standard GSA, IGSA and PSO.     

Design of a fuzzy-PID controller for a nonlinear hydraulic turbine governing system by using a novel gravitational search algorithm based on Cauchy mutation and mass weighting

Hydraulic turbine governing system (HTGS) is a complicated nonlinear system, which regulates frequency and power of hydropower generating unit. In previous study, control model of HTGS is always overly simplified and the elastic water hammer model is seldom considered. In this paper, a nonlinear HTGS model with elastic water hammer effect has been studied and a fuzzy-PID controller is designed to improve control quality of this system. In order to optimize the fuzzy-PID controller, a novel gravitational search algorithm based on Cauchy mutation and mass weighing (GSA-CW) has been proposed with two improvements: a weighting strategy is designed to accelerate the convergence by assigning weights to agents in mass calculation; a combined mutation strategy based on Cauchy and Gaussian distribution is proposed to balance the exploration and exploitation ability of the proposed algorithm. At first, the searching ability of the GSA-CW has been verified on a set of 13 complex benchmark functions by statistical analysis. And then, the GSA-CW is applied to optimize the fuzzy-PID controller, while different meta-heuristics and different PID controllers are employed for comparison. Experimental results indicate that the fuzzy-PID controller optimized by the GSA-CW is more effective to improve the control quality of the nonlinear HTGS.     

Evolving quantum circuits at the gate level with a hybrid quantum-inspired evolutionary algorithm

This paper proposes an approach to evolve quantum circuits at the gate level, based on a hybrid quantum-inspired evolutionary algorithm. This approach encodes quantum gates as integers and combines the cost and correctness of quantum circuits into the fitness function. A fast algorithm of matrix multiplication with Kronecker product has been proposed to speed up the calculation of matrix multiplication in individuals evaluation. This algorithm is shown to be better than the known best algorithm for matrix multiplication when a certain condition holds. The approach of evolving quantum circuits is validated by some experiments and the effects of some parameters are investigated. And finally, some features of the approach are also discussed.     

一种基于混合粒子群优化算法的深度卷积神经网络架构搜索方法

神经架构搜索（neural architecture search,NAS）技术自动寻找神经网络中各层的最佳组合和连接方式,以及各种超参数的最佳分布。该方法从搜索空间生成若干不同的卷积神经网络（CNN）,使用混合粒子群优化（hybrid particle swarm optimization,HPSO）算法,将一定数目的神经网络个体视做一个群体,将每个网络个体在评价指标下的表现值视做适应度,在给定的世代数范围内,每个神经网络个体都学习自身的历史最佳适应度个体,和整个群体的最佳适应度个体,迭代改善自身的网络架构。实验结果表明,算法运行中出现的最优网络架构,在图像分类任务的多个基准数据集上,与手工设计的神经网络和以遗传算法为基础的NAS算法相比,在网络参数数量和准确率的平衡上取得了有竞争力的结果。