Improving nearest neighbor classification using Ensembles of Evolutionary Generated Prototype Subsets

One of the most accurate types of prototype selection algorithms, preprocessing techniques that select a subset of instances from the data before applying nearest neighbor classification to it, are evolutionary approaches. These algorithms result in very high accuracy and reduction rates, but unfortunately come at a substantial computational cost. In this paper, we introduce a framework that allows to efficiently use the intermediary results of the prototype selection algorithms to further increase their accuracy performance. Instead of only using the fittest prototype subset generated by the evolutionary algorithm, we use multiple prototype subsets in an ensemble setting. Secondly, in order to classify a test instance, we only use prototype subsets that accurately classify training instances in the neighborhood of that test instance. In an experimental evaluation, we apply our new framework to four state-of-the-art prototype selection algorithms and show that, by using our framework, more accurate results are obtained after less evaluations of the prototype selection method. We also present a case study with a prototype generation algorithm, showing that our framework is easily extended to other preprocessing paradigms as well.     

Hybrid algorithms for the twin–screw extrusion configuration problem

The twin-screw configuration problem (TSCP) arises in the context of polymer processing, where twin-screw extruders are used to prepare polymer blends, compounds or composites. The goal of the TSCP is to define the configuration of a screw from a given set of screw elements. The TSCP can be seen as a sequencing problem as the order of the screw elements on the screw axis has to be defined. It is also inherently a multi-objective problem since processing has to optimize various conflicting parameters related to the degree of mixing, shear rate, or mechanical energy input among others. In this article, we develop hybrid algorithms to tackle the bi-objective TSCP. The hybrid algorithms combine different local search procedures, including Pareto local search and two phase local search algorithms, with two different population-based algorithms, namely a multi-objective evolutionary algorithm and a multi-objective ant colony optimization algorithm. The experimental evaluation of these approaches shows that the best hybrid designs, combining Pareto local search with a multi-objective ant colony optimization approach, outperform the best algorithms that have been previously proposed for the TSCP.     

Combinations of estimation of distribution algorithms and other techniques

This paper summaries our recent work on combining estimation of distribution algorithms (EDA) and other techniques for solving hard search and optimization problems:a) guided mutation,an offspring generator in which the ideas from EDAs and genetic algorithms are combined together,we have shown that an evolutionary algorithm with guided mutation outperforms the best GA for the maximum clique problem,b)evolutionary algorithms refining a heuristic,we advocate a strategy for solving a hard optimization problem with complicated data structure,and c) combination of two different local search techniques and EDA for numerical global optimization problems,its basic idea is that not all the new generated points are needed to be improved by an expensive local search.     

Local Search-based Hybrid Algorithms for Finding Golomb Rulers

The Golomb ruler problem is a very hard combinatorial optimization problem that has been tackled with many different approaches, such as constraint programming (CP), local search (LS), and evolutionary algorithms (EAs), among other techniques. This paper describes several local search-based hybrid algorithms to find optimal or near-optimal Golomb rulers. These algorithms are based on both stochastic methods and systematic techniques. More specifically, the algorithms combine ideas from greedy randomized adaptive search procedures (GRASP), scatter search (SS), tabu search (TS), clustering techniques, and constraint programming (CP). Each new algorithm is, in essence, born from the conclusions extracted after the observation of the previous one. With these algorithms we are capable of solving large rulers with a reasonable efficiency. In particular, we can now find optimal Golomb rulers for up to 16 marks. In addition, the paper also provides an empirical study of the fitness landscape of the problem with the aim of shedding some light about the question of what makes the Golomb ruler problem hard for certain classes of algorithm.     

Using evolutionary algorithms as instance selection for data reduction in KDD: an experimental study

Evolutionary algorithms are adaptive methods based on natural evolution that may be used for search and optimization. As data reduction in knowledge discovery in databases (KDDs) can be viewed as a search problem, it could be solved using evolutionary algorithms (EAs). In this paper, we have carried out an empirical study of the performance of four representative EA models in which we have taken into account two different instance selection perspectives, the prototype selection and the training set selection for data reduction in KDD. This paper includes a comparison between these algorithms and other nonevolutionary instance selection algorithms. The results show that the evolutionary instance selection algorithms consistently outperform the nonevolutionary ones, the main advantages being: better instance reduction rates, higher classification accuracy, and models that are easier to interpret.     

数据立方体选择的改进遗传算法

数据立方体选择问题是一个NP完全问题。研究了利用遗传算法来解决立方体选择问题,提出了一个结合局部搜索机制的遗传算法。这一算法的核心思想在于,首先运用一个基于单位空间最大收益值的预处理算法来生成初始解,然后该初始解经结合了局部搜索机制的遗传算法进行提高。实验结果表明,该算法在寻优性能上优于启发式算法和经典遗传算法。     

Optimal switch location in mobile communication networks using hybrid genetic algorithms

The optimal positioning of switches in a mobile communication network is an important task, which can save costs and improve the performance of the network. In this paper we propose a model for establishing which are the best nodes of the network for allocating the available switches, and several hybrid genetic algorithms to solve the problem. The proposed model is based on the so-called capacitated p-median problem, which have been previously tackled in the literature. This problem can be split in two subproblems: the selection of the best set of switches, and a terminal assignment problem to evaluate each selection of switches. The hybrid genetic algorithms for solving the problem are formed by a conventional genetic algorithm, with a restricted search, and several local search heuristics. In this work we also develop novel heuristics for solving the terminal assignment problem in a fast and accurate way. Finally, we show that our novel approaches, hybridized with the genetic algorithm, outperform existing algorithms in the literature for the p-median problem.     

A two‐phase harmony search algorithm for continuous optimization

Harmony search (HS) algorithm is inspired by the music improvisation process in which a musician searches for the best harmony and continues to polish the harmony to improve its aesthetics. The efficiency of evolutionary algorithms depends on the extent of balance between diversification and intensification during the course of the search. An ideal evolutionary algorithm must have efficient exploration in the beginning and enhanced exploitation toward the end. In this paper, a two‐phase harmony search (TPHS) algorithm is proposed that attempts to strike a balance between exploration and exploitation by concentrating on diversification in the first phase using catastrophic mutation and then switches to intensification using local search in the second phase. The performance of TPHS is analyzed and compared with 4 state‐of‐the‐art HS variants on all the 30 IEEE CEC 2014 benchmark functions. The numerical results demonstrate the superiority of the proposed TPHS algorithm in terms of accuracy, particularly on multimodal functions when compared with other state‐of‐the‐art HS variants; further comparison with state‐of‐the‐art evolutionary algorithms reveals excellent performance of TPHS on composition functions. Composition functions are combined, rotated, shifted, and biased version of other unimodal and multimodal test functions and mimic the difficulties of real search spaces by providing a massive number of local optima and different shapes for different regions of the search space. The performance of the TPHS algorithm is also evaluated on a real‐life problem from the field of computer vision called camera calibration problem, ie, a 12‐dimensional highly nonlinear optimization problem with several local optima.     

A new particle swarm feature selection method for classification

Searching for an optimal feature subset from a high-dimensional feature space is an NP-complete problem; hence, traditional optimization algorithms are inefficient when solving large-scale feature selection problems. Therefore, meta-heuristic algorithms are extensively adopted to solve such problems efficiently. This study proposes a regression-based particle swarm optimization for feature selection problem. The proposed algorithm can increase population diversity and avoid local optimal trapping by improving the jump ability of flying particles. The data sets collected from UCI machine learning databases are used to evaluate the effectiveness of the proposed approach. Classification accuracy is used as a criterion to evaluate classifier performance. Results show that our proposed approach outperforms both genetic algorithms and sequential search algorithms.     

Going weighted: Parameterized algorithms for cluster editing

The goal of the Cluster Editing problem is to make the fewest changes to the edge set of an input graph such that the resulting graph is a disjoint union of cliques. This problem is NP-complete but recently, several parameterized algorithms have been proposed. In this paper, we present a number of surprisingly simple search tree algorithms for Weighted Cluster Editing assuming that edge insertion and deletion costs are positive integers. We show that the smallest search tree has size O(1.82^k) for edit cost k, resulting in the currently fastest parameterized algorithm, both for this problem and its unweighted counterpart. We have implemented and compared our algorithms, and achieved promising results.¹     

A hybrid harmony search algorithm for the spread spectrum radar polyphase codes design problem

In this paper we present the application of a hybrid harmony search (HS) algorithm to the Spread-Spectrum Radar Polyphase (SSRP) codes design. Such a design can be formulated as a non-linear max–min optimization problem, hard to be solved using classical numerical techniques. Soft-computing approaches have then been successfully applied to solve the SSRP in the past, such as evolutionary computation techniques, variable neighborhood approaches or tabu search algorithms. In this paper we elaborate on the proposed hybrid HS approach, which consists of a naive implementation of the HS algorithm along with an adaptive-step gradient-guided local search procedure. Intensive computer simulations show that the proposed hybrid HS algorithm is able to outperform existing algorithms for the SSRP design problem (including the best reported so far), with significant differences in large-size SSRP instances.     

Scaling Up Inductive Logic Programming: An Evolutionary Wrapper Approach

Inductive logic programming (ILP) algorithms are classification algorithms that construct classifiers represented as logic programs. ILP algorithms have a number of attractive features, notably the ability to make use of declarative background (user-supplied) knowledge. However, ILP algorithms deal poorly with large data sets (>10⁴ examples) and their widespread use of the greedy set-covering algorithm renders them susceptible to local maxima in the space of logic programs.This paper presents a novel approach to address these problems based on combining the local search properties of an inductive logic programming algorithm with the global search properties of an evolutionary algorithm. The proposed algorithm may be viewed as an evolutionary wrapper around a population of ILP algorithms.The evolutionary wrapper approach is evaluated on two domains. The chess-endgame (KRK) problem is an artificial domain that is a widely used benchmark in inductive logic programming, and Part-of-Speech Tagging is a real-world problem from the field of Natural Language Processing. In the latter domain, data originates from excerpts of the Wall Street Journal. Results indicate that significant improvements in predictive accuracy can be achieved over a conventional ILP approach when data is plentiful and noisy.     

The impact of parametrization in memetic evolutionary algorithms

Memetic (evolutionary) algorithms integrate local search into the search process of evolutionary algorithms. As computational resources have to be spread adequately among local and evolutionary search, one has to care about when to apply local search and how much computational effort to devote to local search. Often local search is called with a fixed frequency and run for a fixed number of iterations, the local search depth. There is empirical evidence that these parameters have a significant impact on performance, but a theoretical understanding as well as concrete design guidelines are missing.     

Prototype selection algorithms for distributed learning

Distributed learning from data is one of the typical tasks solved by distributed data-mining techniques and is seen as a fundamental computational problem. One of the approaches suitable for distributed learning is to select, by data reduction, relevant local patterns, called also prototypes, from geographically distributed databases. Next, locally selected prototypes can be moved to other sites and merged into the global knowledge model. The paper presents three agent-based population learning algorithms for distributed learning. The proposed algorithms are based on agent collaborations in distributed prototype selection processes and on agent collaborations when the learning global model is created. The basic property of the presented algorithms is that the prototypes are selected by agent-based population learning algorithm from data clusters induced at distributed sites. The main goal of the paper is to empirically compare how the way of inducing such clusters can influence the distributed learning performance. The paper investigates the agent-based population learning algorithms used to solve distributed data reduction and gives a brief discussion of the procedures for clusters initialization. Finally, computational experiment results are shown.     

Parameter tuning of PBIL and CHC evolutionary algorithms applied to solve the Root Identification Problem

Evolutionary algorithms are among the most successful approaches for solving a number of problems where systematic searches in huge domains must be performed. One problem of practical interest that falls into this category is known as The Root Identification Problem in Geometric Constraint Solving, where one solution to the geometric problem must be selected among a number of possible solutions bounded by an exponential number. In previous works we have shown that applying genetic algorithms, a category of evolutionary algorithms, to solve the Root Identification Problem is both feasible and effective.In this work, we report on an empirical statistical study conducted to establish the influence of the driving parameters in the PBIL and CHC evolutionary algorithms when they are used to solve the Root Identification Problem. We identify a set of values that optimize algorithms performance. The driving parameters considered for the PBIL algorithm are population size, mutation probability, mutation shift and learning rate. For the CHC algorithm we studied population size, divergence rate, differential threshold and the set of best individuals. In both cases we applied unifactorial and multifactorial analysis, post hoc tests and best parameter level selection. Experimental results show that CHC outperforms PBIL when applied to solve the Root Identification Problem.     

A memetic algorithm applied to the design of water distribution networks

The optimal design of water distribution networks is a real optimization problem that consists of finding the best way to convey water from the sources to the users, satisfying their requirements. Many researchers have reported algorithms for minimizing the network cost applying a large variety of techniques, such as linear programming, non-linear programming, global optimization methods and meta-heuristic approaches. However, a totally satisfactory and efficient method is not available as yet. Many works have assessed the performance of these techniques using small or medium-sized benchmark networks proposed in the literature, but few of them have tested these methods with large-scale real networks. This paper introduces a new memetic algorithm for the optimal design of water distribution networks. In order to establish an accurate conclusion, five other approaches have also been adapted, namely simulated annealing, mixed simulated annealing and tabu search, scatter search, genetic algorithms and binary linear integer programming. The results obtained in three water distribution networks show that the memetic algorithm performs better than the other methods, especially when the size of the problem increases.     

A Neurogenetic approach for the resource-constrained project scheduling problem

A variety of metaheuristic approaches have emerged in recent years for solving the resource-constrained project scheduling problem (RCPSP), a well-known NP-hard problem in scheduling. In this paper, we propose a Neurogenetic approach which is a hybrid of genetic algorithms (GA) and neural-network (NN) approaches. In this hybrid approach the search process relies on GA iterations for global search and on NN iterations for local search. The GA and NN search iterations are interleaved in a manner that allows NN to pick the best solution thus far from the GA pool and perform an intensification search in the solution's local neighborhood. Similarly, good solutions obtained by NN search are included in the GA population for further search using the GA iterations. Although both GA and NN approaches, independently give good solutions, we found that the hybrid approach gives better solutions than either approach independently for the same number of shared iterations. We demonstrate the effectiveness of this approach empirically on the standard benchmark problems of size J30, J60, J90 and J120 from PSPLIB.     

Optimized QoS-aware replica placement heuristics and applications in astronomy data grid

This paper studies the Quality-of-Service (QoS)-aware replica placement problem in a general graph model. Since the problem was proved NP-hard, heuristic algorithms are the current solutions to the problem. However, these algorithms cannot always find the effective replica placement strategy. We propose two algorithms that can obtain better results within the given time period. The first algorithm is called Cover Distance algorithm, which is based on the Greedy Cover algorithm. The second algorithm is an optimized genetic algorithm, in which we use random heuristic algorithms to generate initial population to avoid enormous useless searching. Then, the 0-Greedy-Delete algorithm is used to optimize the genetic algorithm solutions. According to the performance evaluation, our Cover Distance algorithm can obtain relatively better solution in time critical scenarios. Whereas, the optimized genetic algorithm is better when the replica cost is of higher priority than algorithm execution time. The QoS-aware data replication heuristic algorithms are applied into the data distribution service of an astronomy data grid pipeline prototype, and the operation process is studied in detail.     

A new hybrid parallel genetic algorithm for the job‐shop scheduling problem

The job‐shop scheduling problem (JSSP) is considered one of the most difficult NP‐hard problems. Numerous studies in the past have shown that as exact methods for the problem solution are intractable, even for small problem sizes, efficient heuristic algorithms must achieve a good balance between the well‐known themes of exploitation and exploration of the vast search space. In this paper, we propose a new hybrid parallel genetic algorithm with specialized crossover and mutation operators utilizing path‐relinking concepts from combinatorial optimization approaches and tabu search in particular. The new scheme relies also on the recently introduced concepts of solution backbones for the JSSP in order to intensify the search in promising regions. We compare the resulting algorithm with a number of state‐of‐the‐art approaches for the JSSP on a number of well‐known test‐beds; the results indicate that our proposed genetic algorithm compares fairly well with some of the best‐performing genetic algorithms for the problem.