Evolutionary Computation Approach Research Articles

Evolutionary computational approaches for data-driven modeling of multi-dimensional memory-dependent systems

This study presents a novel approach based on advancements in Evolutionary Computation for data-driven modeling of complex multi-dimensional memory-dependent systems. The investigated example is a benchmark coupled three-dimensional system that incorporates 6 Bouc-Wen elements, and is subjected to external excitations at three points. The proposed technique of this research adapts Genetic Programming for discovering the optimum structure of the differential equation of an auxiliary variable associated with every specific degree-of-freedom of this system that integrates the imposed effect of vibrations at all other degrees-of-freedom. After the termination of the first phase of the optimization process, a system of differential equations is formed that represent the multi-dimensional hysteretic system. Then, the parameters of this system of differential equations are optimized in the second phase using Genetic Algorithms to yield accurate response estimates globally, because the separately obtained differential equations are coupled essentially, and their true performance can be assessed only when the entire system of coupled differential equations is solved. The resultant model after the second phase of optimization is a low-order low-complexity surrogate computational model that represents the investigated three-dimensional memory-dependent system. Hence, this research presents a promising data-driven modeling technique for obtaining optimized representative models for multi-dimensional hysteretic systems that yield reasonably accurate results, and can be generalized to many problems, in various fields, ranging from engineering to economics as well as biology.

A New Bi-objective Location-routing Problem for Distribution of Perishable Products: Evolutionary Computation Approach

Supply, manufacture, and distribution of perishable products are challenging jobs in supply chains. Location of warehouses and routing of vehicles are essential issues to distribute perishable products properly. In this paper, a new bi-objective mixed integer mathematical programming is proposed to reduce the total cost of the supply chain and to balance the workload of distribution centers while the due dates of delivery of perishable product are met, concurrently. The considered properties and constraints of proposed model made it well-posed to illustrate the real life situation. As the proposed model is NP-Hard, an evolutionary algorithm called Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) is customized to solve the problem. The structure of chromosome and genetic operators are customized for the problem. The performance of proposed NSGA-II and an efficient exact Multi-objective method, called e-constraint, is compared using accuracy and diversity metrics on several benchmark instances.

An improved fruit fly optimization algorithm and its application to joint replenishment problems

Fruit fly optimization algorithm (FOA) is one of the recent evolutionary computation approaches. This paper presents an effective and improved FOA (IFOA) for optimizing numerical functions and solving joint replenishment problems (JRPs). In the proposed IFOA, a new method of maintaining the population diversity is developed to enhance the exploration ability. Fruit flies with better fitness values use vision to fly toward a new location, and the others fly randomly in initial search space based on swarm collaboration. In addition, a new parameter to avoid the acquisition of local optimal solution is introduced to implement intelligent searching. Random perturbation is added to the updated initial location to jump out of the local optimum. Comparisons are carried out using 18 benchmark functions to verify the performance of the IFOA. Experimental results show that IFOA has better comprehensive performance than the original FOA, differential evolution algorithm, and particle swarm optimization algorithm. The IFOA is also utilized to solve the typical JRPs that have been proven as non-deterministic polynomial hard problems. Comparative examples reveal that the proposed IFOA can find better solutions than the current best algorithm; thus, it is a potential tool for various complex optimization problems.

A Study on the Limitations of Evolutionary Computation and other Bio-inspired Approaches for Integer Factorization

Abstract Integer Factorization is a vital number theoretic problem frequently finding application in public-key cryptography like RSA encryption systems, and other areas like Fourier transform algorithm. The problem is computationally intractable because it is a one-way mathematical function. Due to its computational infeasibility, it is extremely hard to find the prime factors of a semi prime number generated from two randomly chosen similar sized prime numbers. There has been a recently growing interest in the community with regards to evolutionary computation and other alternative approaches to solving this problem as an optimization task. However, the results still seem to be very rudimentary in nature and there's much work to be done. This paper emphasizes on such approaches and presents a critic study in details. The paper puts forth criticism and ideas in this aspect.

New design equations for estimation of ultimate bearing capacity of shallow foundations resting on rock masses

Rock masses are commonly used as the underlying layer of important structures such as bridges, dams and transportation constructions. The success of a foundation design for such structures mainly depends on the accuracy of estimating the bearing capacity of rock beneath them. Several traditional numerical approaches are proposed for the estimation of the bearing capacity of foundations resting on rock masses to avoid performing elaborate and expensive experimental studies. Despite this fact, there still exists a serious need to develop more robust predictive models. This paper proposes new nonlinear prediction models for the ultimate bearing capacity of shallow foundations resting on non-fractured rock masses using a novel evolutionary computational approach, called linear genetic programming. A comprehensive set of rock socket, centrifuge rock socket, plate load and large-scaled footing load test results is used to develop the models. In order to verify the validity of the models, the sensitivity analysis is conducted and discussed. The results indicate that the proposed models accurately characterize the bearing capacity of shallow foundations. The correlation coefficients between the experimental and predicted bearing capacity values are equal to 0.95 and 0.96 for the best LGP models. Moreover, the derived models reach a notably better prediction performance than the traditional equations.

Process characterisation of 3D-printed FDM components using improved evolutionary computational approach

Fused deposition modelling (FDM) is an additive manufacturing technique deployed to fabricate the functional components leading to shorter product development times with less human intervention. Typical characteristics such as surface roughness, mechanical strength and dimensional accuracy are found to influence the wear strength of FDM fabricated components. It would be useful to determine an explicit numerical model to describe the correlation between various output process parameters and input parameters. In this paper, we have proposed an improved approach of multi-gene genetic programming (Im-MGGP) to formulate the functional relationship between wear strength and input process variables of the FDM process. It was found that the improved approach performs better than MGGP, SVR and ANN models and is able to generalise wear strength of the FDM prototype satisfactorily. Further, sensitivity and parametric analysis is conducted to study the influence of each input variable on the wear strength of the FDM fabricated components. It was found that the input parameter, air gap, has the maximum influence on the wear strength of the FDM fabricated component.

A hybrid evolutionary computation approach with its application for optimizing text document clustering

Quantum-behaved particle swarm optimization (QPSO) is a promising global optimization algorithm inspired by concepts of quantum mechanics and particle swarm optimization (PSO). Since the particles are initialized randomly in QPSO, the blindness of initializing particles affects its capacity for complicated optimization. In this paper, we make full use of a hybrid evolutionary computation approach to resolve such an issue. In specific, the robust global search ability of genetic algorithm (GA) improves the initial strategy of particles in QPSO. What is more, the original position update approach of QPSO without the restriction of its upper bound may generate some abrupt features and cause the issue of overstepping boundary, which affects its performance for search of optimum. In this study, a new position update approach is tested to normalize the search range of particles in a proper space. Such an approach enhances its probability to find the optimal solution. Since the clustering problem can be regarded as the centers searching process by using evolutionary optimization approach, the evolutionary process of chromosomes or particles encoded by centers simulates the process of solving clustering problem. In order to testify the clustering performance of our approach, we conduct the experiments on 4 subsets of standard Reuter-21578 and 20Newsgroup datasets. Experimental results show that our method performs better than the state of art clustering algorithms in the light of the evaluations of fitness and F-measure.

Novel Adaptive Evolutionary Computation Approaches to the Dynamic Economic Load Dispatch Problems with Non-Smooth Fuel Cost Function

paper presents novel approaches to solving the dynamic economic load dispatch (DELD) problem with valve-point loading effects. In dynamic environments, optimization problems change over time. They are also called time dependent or dynamic time-linkage problems, where decisions made at a given time may affect output obtained in a later time. It is therefore expected of algorithms solving dynamic optimization problems to both locate optimal solutions of the given problem and keep track of such solutions as they change with time. An investigation was made of three optimization methods in conjunction with three smart mutation variants, on benchmark problem cases involving 5 and 10 generating units, the major test cases in the literature with comparative results for other algorithms. The results suggest that the third approach which exploits the dynamic nature of the problem was capable of superior to the other two approaches. Comparisons with all approaches so far in the literature that have addressed these problems show that these evolutionary computation approaches are superior to other algorithms.

Word sense disambiguation using evolutionary algorithms – Application to Arabic language

Natural language processing is related to human–computer interaction, where several challenges involve natural language understanding. Word sense disambiguation problem consists in the computational assignment of a meaning to a word according to a particular context in which it occurs. Many natural language processing applications, such as machine translation, information retrieval, and information extraction, require this task which occurs at the semantic level. Evolutionary computation approaches can be effective to solve this problem since they have been successfully used for many real-world optimization problems. In this paper, we propose to solve the word sense disambiguation problem using genetic and memetic algorithms, and apply them to Modern Standard Arabic. We demonstrate the performance of several models of our algorithms by carrying out experiments on a large Arabic corpus, and comparing them against a naïve Bayes classifier. Experimental results show that genetic algorithms can achieve more precise prediction than memetic algorithms and naïve Bayes classifier, attaining 79%.

A genetic strategy to design cellular automata based block ciphers

We propose an evolutionary computation approach to design a fast and secure block cipher using non-uniform second-order cellular automata. We build a flexible block ciphering model that permit the construction of a huge space of possible instances defined each one by a finite set of elementary transition rules. The constructed space is explored using a genetic algorithms strategy in order to find an optimal solution with respect to the strict avalanche criterion used as fitness measurements. The genetically designed cipher is benchmarked experimentally using conventional statistical tests, and shown to have very admissible characteristics leading to a very acceptable level of cryptographic security. Moreover, performances analysis shows that the designed cipher permit to achieve a high encryption/decryption speed, and compete many of the existing standardized ciphers.

An evolutionary computational approach for formulation of compression index of fine-grained soils

This study presents a robust evolutionary computational technique, called multi-expression programming (MEP), to derive a highly nonlinear model for the prediction of compression index of fine-grained soils. The proposed model relates the soil compression index to its liquid limit, plastic limit and void ratio. The experimental database used for developing the models was established upon 108 consolidation tests conducted on different soils sampled from different construction sites in Iran. The generalization capability of the model was verified via several statistical criteria. The parametric and sensitivity analyses were performed and discussed. The results indicate that the MEP approach accurately characterizes the soil compression index leading to a very good prediction performance. The correlation coefficients between the experimental and predicted soil compression index values are equal to 0.935 and 0.901 for the calibration and testing data sets, respectively. The developed model has a significantly better performance than the existing empirical equations for the soil compression index.

Automatic programming via iterated local search for dynamic job shop scheduling.

Dispatching rules have been commonly used in practice for making sequencing and scheduling decisions. Due to specific characteristics of each manufacturing system, there is no universal dispatching rule that can dominate in all situations. Therefore, it is important to design specialized dispatching rules to enhance the scheduling performance for each manufacturing environment. Evolutionary computation approaches such as tree-based genetic programming (TGP) and gene expression programming (GEP) have been proposed to facilitate the design task through automatic design of dispatching rules. However, these methods are still limited by their high computational cost and low exploitation ability. To overcome this problem, we develop a new approach to automatic programming via iterated local search (APRILS) for dynamic job shop scheduling. The key idea of APRILS is to perform multiple local searches started with programs modified from the best obtained programs so far. The experiments show that APRILS outperforms TGP and GEP in most simulation scenarios in terms of effectiveness and efficiency. The analysis also shows that programs generated by APRILS are more compact than those obtained by genetic programming. An investigation of the behavior of APRILS suggests that the good performance of APRILS comes from the balance between exploration and exploitation in its search mechanism.

Application of evolutionary computational approach in design of horizontal three-phase gravity separators

Abstract We introduce in this work an evolutionary computational algorithm with sophisticated procedures for optimization of three-phase gravity separators. A model horizontal gas/oil/water separator, considered as target design, having well-defined length, diameter, effective length, baffle height, and water channel length, is hereby presented that features optimal design corresponding to minimum volume. The developed computer code is executed to monitor and update evolution in the volume of model separator towards target design. In this way, the implemented evolutionary algorithm manipulates volume genotype to create new alternatives by recombination and mutation of previous generations. This ended in near-to-optimal solutions irrespective of the properties of the first generation adapted to the model separator. The outputs from this theoretical investigation provide a broader image on the level of separation in gravity separators that can be utilized for actual design.

In silicoevolution of thehunchbackgene indicates redundancy in cis-regulatory organization and spatial gene expression

Biological development depends on the coordinated expression of genes in time and space. Developmental genes have extensive cis-regulatory regions which control their expression. These regions are organized in a modular manner, with different modules controlling expression at different times and locations. Both how modularity evolved and what function it serves are open questions. We present a computational model for the cis-regulation of the hunchback (hb) gene in the fruit fly (Drosophila). We simulate evolution (using an evolutionary computation approach from computer science) to find the optimal cis-regulatory arrangements for fitting experimental hb expression patterns. We find that the cis-regulatory region tends to readily evolve modularity. These cis-regulatory modules (CRMs) do not tend to control single spatial domains, but show a multi-CRM/multi-domain correspondence. We find that the CRM-domain correspondence seen in Drosophila evolves with a high probability in our model, supporting the biological relevance of the approach. The partial redundancy resulting from multi-CRM control may confer some biological robustness against corruption of regulatory sequences. The technique developed on hb could readily be applied to other multi-CRM developmental genes.

Hybrid Immune Algorithm with EDA for Multi-Objective Optimization

PDF HTML阅读 XML下载 导出引用 引用提醒 基于免疫算法和EDA 的混合多目标优化算法 DOI: 10.3724/SP.J.1001.2013.04341 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: 国家自然科学基金(61303119); 国家教育部博士点基金(20090203120016, 20100203120008); 博士后面上基金(20090461283, 20090451369, 200801426, 20080431228, 201104658); 陕西省自然科学基础研究计划(2011JQ8010, 2009JQ8015); 中央高校基本科研业务费专项资金(K5051203007, K5051203002) Hybrid Immune Algorithm with EDA for Multi-Objective Optimization Author: Affiliation: Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:在免疫多目标优化算法的基础上,引入了分布估计算法(EDA)对进化种群进行建模采样的思想,提出了一种求解复杂多目标优化问题的混合优化算法HIAEDA(hybrid immune algorithm with EDA for multi-objectiveoptimization).HIAEDA 的进化过程混合了两种后代产生策略:一种是基于交叉变异的克隆选择算子,用于在父代种群周围进行局部搜索的同时开辟新的搜索区域;另一种是基于EDA 的模型采样算子,用于学习多目标优化问题决策变量之间的相关性,提高算法求解复杂多目标优化问题的能力.在分析两种算子搜索行为的基础上,讨论了两者在功能上的互补性,并利用有限马尔可夫链的性质证明了HIAEDA 算法的收敛性.对测试函数和实际工程问题的仿真实验结果表明,HIAEDA 与NSGAII 算法和基于EDA 的进化多目标优化算法RM-MEDA 相比,在收敛性和多样性方面均表现出明显优势,尤其是对于决策变量之间存在非线性关联的复杂多目标优化问题,优势更为突出. Abstract:The estimation of distribution algorithm (EDA) is a new type of evolutionary computation approach which reproduces offspring individuals by modeling and sampling the probability distribution of the evolving population. In this paper, the idea of EDA is introduced into the immune multi-objective optimization algorithm to form a hybrid algorithm termed as HIAEDA (hybrid immune algorithm with EDA for multi-objective optimization). It is proposed for solving complex multi-objective optimization problems (MOPs). In HIAEDA, two types of reproducing strategies are combined. One is a recombination and mutation based immune clonal selection operator. It performs a local search around the parent population and develops new searching areas. The other is a EDA based modeling and sampling operator. It learns the variable linkages and promotes the algorithm's capability of solving complex problems. By analyzing the searching behavior of the two operators, the paper comes to the conclusion that their functions are complementary to each other. The convergence of HIAEDA is proved using the theory of the finite Markov chain. Experimental results on benchmarking and real problems show that HIAEDA outperforms the outstanding NSGAII and the EDA based RM-MEDA in terms of both convergence and diversity, especially when solving complex MOPs with nonlinear relationship between decision variables. 参考文献 相似文献 引证文献

Word Sense Disambiguation Using an Evolutionary Approach

Word sense disambiguation is a combinatorial problem consisting in the computational assignment of a meaning to a word according to a particular context in which it occurs. Many natural language processing applications, such as machine translation, information retrieval, and information extraction, require this task which occurs at the semantic level. Evolutionary computation approaches can be effective to solve this problem since they have been successfully used for many NP-hard optimization problems. In this paper, we investigate main existing methods for the word sense disambiguation problem, propose a genetic algorithm to solve it, and apply it to Modern Standard Arabic. We evaluated its performance on a large corpus and compared it against those of some rival algorithms. The genetic algorithm exhibited more precise prediction results.

PATH PLANNING OF AN AUTONOMOUS MOBILE MULTI-SENSOR PLATFORM IN A 3D ENVIRONMENT USING NEWTONIAN IMPERIALIST COMPETITIVE OPTIMIZATION METHOD

Abstract. This paper addresses an innovative evolutionary computation approach to 3D path planning of autonomous UAVs in real environment. To solve this Np-hard problem, Newtonian imperialist competitive algorithm (NICA) was developed and extended for path planning problem. This paper is related to optimal trajectory-designing before UAV missions. NICA planner provides 3D optimal paths for UAV planning in real topography of north Tehran environment. To simulate UAV path planning, a real DTM is used to algorithm. For real-world applications, final generated paths should be smooth and also physical flyable that made the path planning problems complex and more constrained. The planner progressively presents a smooth 3D path from first position to mission target location. The objective function contains distinctive measures of the problem. Our main goal is minimization of the total mission time. For evaluating of NICA efficiency, it is compared with other three well-known methods, i.e. ICA, GA, and PSO. Then path planning of UAV will done. Finally simulations proved the high capabilities of proposed methodology.

Symbol representations and signal dynamics in evolving droplet computers

We investigate several evolutionary computation approaches as a mechanism to “program” networks of excitable chemical droplets. For this kind of systems, we assigned a specific task and concentrated on the characteristics of signals representing symbols. Given a Boolean function as target functionality, 2D networks composed of 10 × 10 droplets were considered in our simulations. Three different set-ups were tested: Evolving network structures with fixed on/off rate coding signals, co-evolution of networks and signals, and network evolution with fixed but pre-evolved signals. Evolutionary computation served in this work not only for designing droplet networks and input signals but also to estimate the quality of a symbol representation: we assume that a signal leading to faster evolution of a successful network for a given task is better suited for the droplet computing infrastructure. Results show that complicated functions like XOR can evolve using only rate coding and simple droplet types, while other functions involving negations like the NAND or the XNOR function evolved slower using rate coding. Furthermore we discovered symbol representations that performed better than the straight forward on/off rate coding signals for the XNOR and AND Boolean functions. We conclude that our approach is suitable for the exploration of signal encoding in networks of excitable droplets.

Evolutionary Computation and QSAR Research

The successful high throughput screening of molecule libraries for a specific biological property is one of the main improvements in drug discovery. The virtual molecular filtering and screening relies greatly on quantitative structure-activity relationship (QSAR) analysis, a mathematical model that correlates the activity of a molecule with molecular descriptors. QSAR models have the potential to reduce the costly failure of drug candidates in advanced (clinical) stages by filtering combinatorial libraries, eliminating candidates with a predicted toxic effect and poor pharmacokinetic profiles, and reducing the number of experiments. To obtain a predictive and reliable QSAR model, scientists use methods from various fields such as molecular modeling, pattern recognition, machine learning or artificial intelligence. QSAR modeling relies on three main steps: molecular structure codification into molecular descriptors, selection of relevant variables in the context of the analyzed activity, and search of the optimal mathematical model that correlates the molecular descriptors with a specific activity. Since a variety of techniques from statistics and artificial intelligence can aid variable selection and model building steps, this review focuses on the evolutionary computation methods supporting these tasks. Thus, this review explains the basic of the genetic algorithms and genetic programming as evolutionary computation approaches, the selection methods for high-dimensional data in QSAR, the methods to build QSAR models, the current evolutionary feature selection methods and applications in QSAR and the future trend on the joint or multi-task feature selection methods.

Evolutionary computation approaches for real offshore wind farm layout: A case study in northern Europe

This paper presents the layout optimization of a real offshore wind farm in northern Europe, using evolutionary computation techniques. Different strategies for the wind farm design are tested, such as regular turbines layout or free turbines disposition with fixed number of turbines. Also, different layout quality models have been applied, in order to obtain solutions with different characteristics of high energy production and low interlink cost. In all the cases, evolutionary algorithms are developed and detailed in the paper. The experiments carried out in the real problem show that the free design with fixed number of turbines is more appropriate and obtains better quality layouts than the regular design.