Using differential evolution for fine tuning naïve Bayesian classifiers and its application for text classification

The Naive Bayes (NB) learning algorithm is simple and effective in many domains including text classification. However, its performance depends on the accuracy of the estimated conditional probability terms. Sometimes these terms are hard to be accurately estimated especially when the training data is scarce. This work transforms the probability estimation problem into an optimization problem, and exploits three metaheuristic approaches to solve it. These approaches are Genetic Algorithms (GA), Simulated Annealing (SA), and Differential Evolution (DE). We also propose a novel DE algorithm that uses multi-parent mutation and crossover operations (MPDE) and three different methods to select the final solution. We create an initial population by manipulating the solution generated by a method used for fine tuning the NB. We evaluate the proposed methods by using their resulted solutions to build NB classifiers and compare their results with the results of obtained from classical NB and Fine-Tuning Naïve Bayesian (FTNB) algorithm, using 53 UCI benchmark data sets. We name these obtained classifiers NBGA, NBSA, NBDE, and NB-MPDE respectively. We also evaluate the performance NB-MPDE for text-classification using 18 text-classification data sets, and compare its results with the results of obtained from FTNB, BNB, and MNB. The experimental results show that using DE in general and the proposed MPDE algorithm in particular are more convenient for fine-tuning NB than all other methods, including the other two metaheuristic methods (GA, and SA). They also indicate that NB-MPDE achieves superiority over classical NB, FTNB, NBDE, NBGA, NBSA, MNB, and BNB.     

Hybrid adaptive evolutionary algorithm based on decomposition

The performance of search operators varies across the different stages of the search/optimization process of evolutionary algorithms (EAs). In general, a single search operator may not do well in all these stages when dealing with different optimization and search problems. To mitigate this, adaptive search operator schemes have been introduced. The idea is that when a search operator hits a difficult patch (under-performs) in the search space, the EA scheme “reacts” to that by potentially calling upon a different search operator. Hence, several multiple-search operator schemes have been proposed and employed within EA. In this paper, a hybrid adaptive evolutionary algorithm based on decomposition (HAEA/D) that employs four different crossover operators is suggested. Its performance has been evaluated on the well-known IEEE CEC’09 test instances. HAEA/D has generated promising results which compare well against several well-known algorithms including MOEA/D, on a number of metrics such as the inverted generational distance (IGD), the hyper-volume, the Gamma and Delta functions. These results are included and discussed in this paper.     

Optimum active and inert ratios for different metamorphic grade coals

In order to quantitatively describe the difference of optimum active and inert ratio of various metamorphic grade coking coals,the rule of coke micro-strength index (MSI),determinated by adding different proportions of inert content to ten kinds of single coal,changing with active and inert ratio has been investigated.Three kinds of change rule of the MSI of ten kinds of single coal changing with active and inert ratio have been obtained in the research.It has been demonstrated that Gauss curve model is the optimal model to describe the optimum active and inert ratio of different metamorphic grade coals.On this basis,the optimum active and inert ratio of different metamorphic grade coals can be given.     

Approximations in a semigroup by using a neighbourhood system

Let S be a semigroup. We consider the relation γ and its transitive closure γ*. The relation γ is the smallest equivalence relation on S so that S/γ* is a commutative semigroup. Based on the relation γ, we define a neighbourhood system for each element of S, and we present a general framework of the study of approximations in semigroups. The connections between semigroups and operators are examined.     

Proximal extrapolated gradient methods for variational inequalities

The paper concerns with novel first-order methods for monotone variational inequalities. They use a very simple linesearch procedure that takes into account a local information of the operator. Also, the methods do not require Lipschitz continuity of the operator and the linesearch procedure uses only values of the operator. Moreover, when the operator is affine our linesearch becomes very simple, namely, it needs only simple vector–vector operations. For all our methods, we establish the ergodic convergence rate. In addition, we modify one of the proposed methods for the case of a composite minimization. Preliminary results from numerical experiments are quite promising.     

Ile-1781-Leu and Asp-2078-Gly Mutations in ACCase Gene,Endow Cross-resistance to APP,CHD, and PPZ in Phalaris minor from Mexico

Herbicides that inhibit acetyl coenzyme A carboxylase (ACCase) are commonly used in Mexico to control weedy grasses such as little seed canarygrass (Phalaris minor). These herbicides are classified into three major families (ariloxyphenoxypropionates (APP), cyclohexanodiones (CHD), and, recently, phenylpyrazolines (PPZ)). In this work, the resistance to ACCase (APP, CHD, and PPZ) inhibiting herbicides was studied in a biotype of Phalaris minor (P. minor) from Mexico, by carrying out bioassays at the whole-plant level and investigating the mechanism behind this resistance. Dose-response and ACCase in vitro activity assays showed cross-resistance to all ACCase herbicides used. There was no difference in the absorption, translocation, and metabolism of the ¹⁴C-diclofop-methyl between the R and S biotypes. The PCR generated CT domain fragments of ACCase from the R biotype and an S reference were sequenced and compared. The Ile-1781-Leu and Asp-2078-Gly point mutations were identified. These mutations could explain the loss of affinity for ACCase by the ACCase-inhibing herbicides. This is the first report showing that this substitution confers resistance to APP, CHD, and PPZ herbicides in P. minor from Mexico. The mutations have been described previously only in a few cases; however, this is the first study reporting on a pattern of cross-resistance with these mutations in P. minor. The findings could be useful for better management of resistant biotypes carrying similar mutations.     

地震照明分析技术在深海地震数据采集设计中的应用

中国南海北部陆缘深水海域是形成大型油气区的有利区域。但由于该区水深急剧变化,峡谷纵横,构成了海底崎岖的地形地貌带,给该区的油气勘探带来了困难。本文利用高斯射线束地震波正演模拟方法,研究了南海白云凹陷深水崎岖海底区地震波对地下目的层的激发照明以及检波器接收照明能量的分布特征。针对不同接收缆数、不同排列长度及不同激发方向对海底崎岖界面和深部目的层的激发与接收照明能量的模拟分析,初步认识崎岖海底和下伏目的层地震波能量的分布特征,以及不同观测系统参数对地震采集能量的影响程度,为南海崎岖深海区地震采集参数设计提供了依据。     

注二氧化碳混相驱试井模型及压力分析

基于注二氧化碳混相驱试井分析理论,分析了二氧化碳与原油混相过程中混合物组分的扩散模型和温度、粘度的变化规律,研究了此过程中组分突变与温度突变（粘度突变）对压力的影响,将压力变化分成了求解两区复合试井模型得到的压降和由温度与粘度突变引起的附加压降。通过推导,给出了井底的整体压力响应;利用数值反演方法,计算了考虑组分与粘度...     

基于自适应遗传算法的压裂水平井参数优化

鉴于低渗透油藏水平井压裂设计中参数多且交叉影响,采用常规方法进行正交优化存在较多局限性,结合油田生产实际,选择油井的累积产油量、累积注水量和累积产水量作为分析对象,提出一种以生产净现值最大化为目标,基于自适应遗传算法的水平井压裂参数优化方法.该方法根据个体适应值大小自动选择合适的交叉与变异概率,有效避免了传统遗传算法的“早熟”和盲目搜索等问题;通过编程实现了对水平段长度、裂缝半长、裂缝条数以及裂缝导流能力的自动优化求解.以长庆油区某油田的实际资料为基础,分析了五点井网下水平井压裂参数优化过程,分析结果表明,该方法参数覆盖范围更广,与枚举法需计算4 096次才能确定最优解相比,新方法只需迭代200次,大大提高了求解速度,增强了算法的实用性.     

稀疏性正则化的图像泊松去噪算法

去除医学、天文图像中的泊松噪声是一个重要问题,基于图像在过完备字典下的稀疏表示,在BayesianMAP框架下建立了稀疏性正则化的图像泊松去噪凸变分模型,采用负log的泊松似然函数作为模型的数据保真项,模型中非光滑的正则项约束图像表示系数的稀疏性,并附加非负件约束,保证去噪图像的非负性.基于分裂Bregman方法,提出...