基于混沌的弹性粒子群全局优化算法

为了克服粒子群优化容易陷入局部极小的缺陷,利用粒子速度不依赖于其与最优粒子之间距离的大小,而仅依赖其方向信息的特点,采用自适应策略弹性地修正粒子速度的幅值．同时,充分利用混沌运动的遍历性、随机性及对初值的敏感性等特性,提出一种基于混沌的弹性粒子群优化（ＣＲＰＳＯ）算法,并将其成功用于典型多极点函数优化．仿真结果表明,该算法增强了摆脱局部极值点的能力,提高了收敛速度和精度．     

Gene selection using hybrid particle swarm optimization and genetic algorithm

Selecting high discriminative genes from gene expression data has become an important research. Not only can this improve the performance of cancer classification, but it can also cut down the cost of medical diagnoses when a large number of noisy, redundant genes are filtered. In this paper, a hybrid Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) method is used for gene selection, and Support Vector Machine (SVM) is adopted as the classifier. The proposed approach is tested on three benchmark gene expression datasets: Leukemia, Colon and breast cancer data. Experimental results show that the proposed method can reduce the dimensionality of the dataset, and confirm the most informative gene subset and improve classification accuracy.     

基于离散粒子群和支持向量机的特征基因选择算法

基因芯片表达谱信息,为识别疾病相关基因及对癌症等疾病分型、诊断及病理学研究提供一新途径。在基因表达谱数据中选择特征基因可以提高疾病诊断、分类的准确率,并降低分类器的复杂度。本文研究了基于离散粒子群(binary particle swarm optimization,BPSO)和支持向量机(support vector machine,SVM)封装模式的BPSO-SVM特征基因选择方法,首先随机产生若干种群(特征子集),然后用BPSO算法优化随机产生的特征基因,并用SVM分类结果指导搜索,最后选出最佳适应度的特征基因子集以训练SVM。结果表明,基于BPSO-SVM的特征基因选择方法,的确是一种行之有效的特征基因选择方法。     

Implementing support vector regression with differential evolution to forecast motherboard shipments

In this study, we investigate the forecasting accuracy of motherboard shipments from Taiwan manufacturers. A generalized Bass diffusion model with external variables can provide better forecasting performance. We present a hybrid particle swarm optimization (HPSO) algorithm to improve the parameter estimates of the generalized Bass diffusion model. A support vector regression (SVR) model was recently used successfully to solve forecasting problems. We propose an SVR model with a differential evolution (DE) algorithm to improve forecasting accuracy. We compare our proposed model with the Bass diffusion and generalized Bass diffusion models. The SVR model with a DE algorithm outperforms the other models on both model fit and forecasting accuracy.     

基于粒子群和支持向量机为青霉素发酵建模

针对支持向量机发酵建模中,选择重要建模参数值的问题,提出利用全局搜索能力较强的粒子群优化算法,优化调整支持向量机建模过程中的重要参数,每一个粒子的位置向量对应一组支持向量机建模的参数。参数不断优化后,得到拟合预测效果较优的模型,预测青霉素发酵过程。仿真结果表明,该方法能使模型的预测效果较好。     

基于粒子群与支持向量机的隧道变形预测模型

针对粒子群算法易早熟且在算法后期易在全局最优解附近产生振荡现象,提出一种自适应调整惯性权重的优化粒子群算法。该算法引入双曲线正切函数的非线性变化思想,使惯性权重随着迭代次数的增加产生自适应调整,有利于增强粒子搜索能力及收敛速度,不易陷入局部极值点。将该算法应用于基于支持向量机的隧道变形预测模型中,对预测模型的超参数进行优化,并利用稳态与非稳态两组实测工况数据对组合算法进行工程测试,结果表明采用SaωPSO＋SVM算法可有效提高预测模型的计算精度,增强其鲁棒性,有助于隧道变形的工程建模。     

A prior-knowledge input LSSVR metamodeling method with tuning based on cellular particle swarm optimization for engineering design

Engineering design is usually a daunting optimization task which often involving time-consuming, even computation-prohibitive process. To reduce the computational expense, metamodels are commonly used to replace the actual expensive simulations or experiments. In this paper, a new and efficient metamodeling method named prior-knowledge input least square support vector regression (PKI-LSSVR) is developed, in which samples from different levels of fidelity are incorporated to gain an accurate approximation with limited times of the high-fidelity (HF) expensive simulations. The low-fidelity (LF) output serves as a prior-knowledge of the real response function, and then is used as the input variables of least square support vector regression (LSSVR). When the corresponding HF response is gained, a function that maps the LF outputs to HF outputs is constructed via LSSVR. The predictive accuracy of LSSVR models is highly dependent on their learning parameters. Therefore, a novel optimization method, cellular particle swarm optimization (CPSO), is exploited to seek the optimal hyper-parameters for PKI-LSSVR in order to improve its generalization capability. To get a better optimization performance, a new neighborhood function is developed for CPSO where the global and local search is efficiently balanced by adaptively varied neighbor radius. Several numerical experiments and one engineering case verify the efficiency of the proposed PKI-LSSVR method. Sample quality merits including sample sizes and noise, and metamodel performance evaluation measures incorporating accuracy, robustness, and efficiency are considered.     

Parameter selection of support vector regression based on hybrid optimization algorithm and its application

Choosing optimal parameters for support vector regression （SVR） is an important step in SVR. design, which strongly affects the pefformance of SVR. In this paper, based on the analysis of influence of SVR parameters on generalization error, a new approach with two steps is proposed for selecting SVR parameters, First the kernel function and SVM parameters are optimized roughly through genetic algorithm, then the kernel parameter is finely adjusted by local linear search, This approach has been successfully applied to the prediction model of the sulfur content in hot metal. The experiment results show that the proposed approach can yield better generalization performance of SVR than other methods,     

A hybrid algorithm based on particle swarm and chemical reaction optimization

In this paper, a hybrid method for optimization is proposed, which combines the two local search operators in chemical reaction optimization with global search ability of for global optimum. This hybrid technique incorporates concepts from chemical reaction optimization and particle swarm optimization, it creates new molecules (particles) either operations as found in chemical reaction optimization or mechanisms of particle swarm optimization. Moreover, some technical bound constraint handling has combined when the particle update in particle swarm optimization. The effects of model parameters like InterRate, γ, Inertia weight and others parameters on performance are investigated in this paper. The experimental results tested on a set of twenty-three benchmark functions show that a hybrid algorithm based on particle swarm and chemical reaction optimization can outperform chemical reaction optimization algorithm in most of the experiments. Experimental results also indicate average improvement and deviate over chemical reaction optimization in the most of experiments.     

Association rule mining using binary particle swarm optimization

In this paper, we developed a binary particle swarm optimization (BPSO) based association rule miner. Our BPSO based association rule miner generates the association rules from the transactional database by formulating a combinatorial global optimization problem, without specifying the minimum support and minimum confidence unlike the a priori algorithm. Our algorithm generates the best M rules from the given database, where M is a given number. The quality of the rule is measured by a fitness function defined as the product of support and confidence. The effectiveness of our algorithm is tested on a real life bank dataset from commercial bank in India and three transactional datasets viz. books database, food items dataset and dataset of the general store taken from literature. Based on the results, we infer that our algorithm can be used as an alternative to the a priori algorithm and the FP-growth algorithm.     

改进混沌PSO算法的BP网络优化

提出了一种改进混沌粒子群算法(MCPSO)与BP算法的混合算法(MCPSO—BP),该算法综合了改进粒子群算法全局寻优的高效性,混沌算法局部搜索的遍历性和BP算法快速的局部搜索能力。仿真结果表明,MCPSO—BP算法网络结构简单,收敛速度快,并具有良好的逼近能力和泛化能力。     

基于改进在线支持向量回归的离子浓度预测模型

针对湿法炼锌净化过程中杂质离子浓度检测的大滞后特性和模型失效问题.提出了基于在线支持向量回归的离子浓度预测模型.该模型对每个新样本进行增量学习,并能删除数据集中的一个旧样本.进而提出用分块矩阵的方法解决更新算法计算复杂的问题.将该建模方法应用于离子浓度的预测,结果表明预测模型具有较好的泛化性能,模型更新时间明显缩短,有效地提高了适应工况的实时性.     

量子粒子群优化算法在训练支持向量机中的应用

训练支持向量机的本质问题就是求解二次规划问题，但对大规模的训练样本来说，求解二次规划问题困难很大。遗传算法和粒子群算法等智能搜索技术可以在较少的时间开销内给出问题的近似解。量子粒子群优化（QPSO）算法是在经典的微粒群算法的基础上所提出的一种有较高收敛性和稳定性的进化算法。将操作简单而收敛快速的QPSO算法运用于训练支持向量机，优化求解二次规划问题．为解决大规模的二次规划问题开辟了一条新的途径。     

A parameter selection strategy for particle swarm optimization based on particle positions

In this study, we found that engineering experience can be used to determine the parameters of an optimization algorithm. We came to this conclusion by analyzing the dynamic characteristics of PSO through a large number of experiments. We constructed a relationship between the dynamic process of particle swarm optimization and the transition process of a control system. A novel parameter strategy for PSO was proven in this paper using the overshoot and the peak time of a transition process. This strategy not only provides a series of flexible parameters for PSO but it also provides a new way to analyze particle trajectories that incorporates engineering practices. In order to validate the new strategy, we compared it with published results from three previous reports, which are consistent or approximately consistent with our new strategy, using a suite of well-known benchmark optimization functions. The experimental results show that the proposed strategy is effective and easy to implement. Moreover, the new strategy was applied to equally spaced linear array synthesis examples and compared with other optimization methods. Experimental results show that it performed well in pattern synthesis.     

Middle-long power load forecasting based on particle swarm optimization

Middle-long forecasting of electric power load is crucial to electric investment, which is the guarantee of the healthy development of electric industry. In this paper, the particle swarm optimization (PSO) is used as a training algorithm to obtain the weights of the single forecasting method to form the combined forecasting method. Firstly, several forecasting methods are used to do middle-long power load forecasting. Then the upper forecasting methods are measured by several indices and the entropy method is used to form a comprehensive forecasting method evaluation index, following which the PSO is used to attain a combined forecasting method (PSOCF) with the best objective function value. We then obtain the final result by adding all the results of every single forecasting method. Taking actual load data of a power grid company in North China as a sample, the results show that PSOCF model improves the forecasting precision compared to the traditional models.     

基于支持向量机的污水处理软测量算法的研究

针对污水处理过程中生化需氧量BOD难以实时在线测量的问题,建立了用于预估BOD的支持向量机（SVM）的软测量模型。考虑到该支持向量机模型的测量精度取决于其两个参数C、σ能否获得最优值,采用遗传算法和粒子群优化算法,实现对这两个参数的寻优。仿真结果表明：该软测量模型的测量精度较高,可用于污水处理厂对BOD进行在线测量。     

一种基于种群速度的自适应粒子群算法

分析了粒子群算法的收敛性,指出早熟是由于粒子速度降低而失去继续搜索可行解的能力.进而提出一种基于种群速度动态改变惯性权重的粒子群算法,该算法以种群粒子平均速度为信息动态改变惯性权重,避免了粒子速度过早接近0.通过5个标准测试函数的仿真实验并与其他算法相比,结果表明该算法在进化中期能很好地保持种群多样性,有效地改善算法的平均最优值和成功率.     

梯度微粒群优化算法及其收敛性分析

针对标准微粒群优化算法微粒运动轨迹的收敛性进行了分析.给出并证明了微粒运动轨迹收敛的充分条件.提出一种简便的等高线图判别法,该方法能够通过参数的位置判断微粒轨迹是否收敛并衡量收敛速度.为提高算法的收敛速度.构造出一种梯度微粒群优化算法,给出并证明了该方法收敛的充分条件.仿真结果表明,梯度微粒群优化算法具有优良的搜索性能.     

A symbolic fault-prediction model based on multiobjective particle swarm optimization

In the literature the fault-proneness of classes or methods has been used to devise strategies for reducing testing costs and efforts. In general, fault-proneness is predicted through a set of design metrics and, most recently, by using Machine Learning (ML) techniques. However, some ML techniques cannot deal with unbalanced data, characteristic very common of the fault datasets and, their produced results are not easily interpreted by most programmers and testers. Considering these facts, this paper introduces a novel fault-prediction approach based on Multiobjective Particle Swarm Optimization (MOPSO). Exploring Pareto dominance concepts, the approach generates a model composed by rules with specific properties. These rules can be used as an unordered classifier, and because of this, they are more intuitive and comprehensible. Two experiments were accomplished, considering, respectively, fault-proneness of classes and methods. The results show interesting relationships between the studied metrics and fault prediction. In addition to this, the performance of the introduced MOPSO approach is compared with other ML algorithms by using several measures including the area under the ROC curve, which is a relevant criterion to deal with unbalanced data.