for Journals by Title or ISSN
for Articles by Keywords
Followed Journals
Journal you Follow: 0
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Journal Cover Swarm and Evolutionary Computation
  [SJR: 2.167]   [H-I: 22]   [2 followers]  Follow
   Hybrid Journal Hybrid journal (It can contain Open Access articles)
   ISSN (Print) 2210-6502
   Published by Elsevier Homepage  [3123 journals]
  • A survey on multi-objective evolutionary algorithms for the solution of
           the environmental/economic dispatch problems
    • Authors: B.Y. Qu; Y.S. Zhu; Y.C. Jiao; M.Y. Wu; P.N. Suganthan; J.J. Liang
      Pages: 1 - 11
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): B.Y. Qu, Y.S. Zhu, Y.C. Jiao, M.Y. Wu, P.N. Suganthan, J.J. Liang
      Development of efficient multi-objective evolutionary algorithms (MOEAs) has provided effective tools to solve environmental/economic dispatch (EED) problems. EED is a highly constrained complex bi-objective optimization problem. Since 1990s, numerous publications have reported the applications of MOEAs to solve the EED problems. This paper surveys the state-of-the-art of research related to this direction. It covers topics of typical MOEAs, classical EED problems, Dynamic EED problems, EED problems incorporating wind power, EED problems incorporating electric vehicles and EED problems within micro-grids. In addition, some potential directions for future research are also presented.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.06.002
      Issue No: Vol. 38 (2017)
  • An overview and comparative analysis of recent bio-inspired optimization
           techniques for wind integrated multi-objective power dispatch
    • Authors: Hari Mohan Dubey; Manjaree Pandit; B.K. Panigrahi
      Pages: 12 - 34
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Hari Mohan Dubey, Manjaree Pandit, B.K. Panigrahi
      Over the last few decades, bio-inspired (BI) evolutionary optimization techniques have experienced overwhelming popularity, extraordinary growth and large number of applications, particularly, in the field of engineering and technology. These techniques present a tough competition to traditional numerical methods which suffer from convexity and continuity assumptions and which normally employ a gradient based search that is sensitive to the initial solution. While initial BI techniques suffered from limitations such as premature convergence and dependence on control parameters, eventually, these issues were specifically addressed by improved variants and many novel BI methods. The population based computing methods are particularly attractive for solving multi-objective (MO) problems due to their capability of producing a large number of Pareto-optimal solutions in one run. In this paper, an integrated ranking index (IRI) composed of TOPSIS and fuzzy-min concept is proposed as a performance metrics to aggregate the different objectives. The performance of eight handpicked recent BI techniques is compared for the solution of wind integrated multi-objective optimal power dispatch (MOOD) problem for simultaneous minimization of fuel cost and emission. Due to the uncertain nature of wind power (WP), the effect of its over and underestimation on both economic as well as environmental aspects, has also been considered. Six standard test cases having non-convex, multi-modal and discontinuous objective functions, dynamic operation and complex equality/inequality constraints, are selected for testing Flower Pollination Algorithm (FPA), Mine Blast Algorithm (MBA), Backtracking Search Algorithm (BSA), Symbiotic Organisms Search (SOS), Ant Lion Optimizer (ALO), Moth-Flame Optimization (MFO), Stochastic Fractal Search (SFS) and Lightning Search Algorithm (LSA).

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.012
      Issue No: Vol. 38 (2017)
  • Evolutionary heterogeneous clustering for rating prediction based on user
           collaborative filtering
    • Authors: Jianrui Chen; Uliji; Hua Wang; Zaizai Yan
      Pages: 35 - 41
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Jianrui Chen, Uliji, Hua Wang, Zaizai Yan
      Recommender systems play an important role in our life, which would help users to find what they are interested in. Collaborative filtering is the most widely used and successful method for personalized recommendation. In this paper, a novel heterogeneous evolutionary clustering is presented. The goal of our algorithm is to gather users with similar interest into the same cluster and to help users find items that fit their personal tastes best. The suggestions from friends with similar interest may be adopted with high probability. Firstly, items and users are regarded as heterogeneous individuals in the network. According to the constructed network model, states of individuals evolve over time. Individuals with higher scores would cluster into together and individuals with lower scores would get away. After many iterations, states of items and users would be stable. In light of stable states of heterogeneous individuals, they are clustered into several groups. Secondly, user-based collaborative filtering are adopted in each cluster. Similarities between individuals only in same cluster are computed not for all individuals in system. The target rating is calculated according to user-based collaborative filtering in its cluster. Diverse simulations show the efficiency of our proposed methods. Moreover, the presented method gains better prediction results than two existing preferable algorithms.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.05.008
      Issue No: Vol. 38 (2017)
  • An effective invasive weed optimization algorithm for scheduling
           semiconductor final testing problem
    • Authors: Hong-Yan Sang; Pei-Yong Duan; Jun-Qing Li
      Pages: 42 - 53
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Hong-Yan Sang, Pei-Yong Duan, Jun-Qing Li
      In this paper, we address a semiconductor final testing problem from the semiconductor manufacturing process. We aim to determine both the assignment of machines and the sequence of operations on all the machines so as to minimize makespan. We present a cooperative co-evolutionary invasive weed optimization (CCIWO) algorithm which iterates with two coupled colonies, one of which addresses the machine assignment problem and the other deals with the operation sequence problem. To well balance the search capability of the two colonies, we adopt independent size setting for each colony. We design the reproduction and spatial dispersal methods for both the colonies by taking advantage of the information collected during the search process and problem-specific knowledge. Extensive experiments and comparison show that the proposed CCIWO algorithm performs much better than the state-of-the-art algorithms in the literature for solving the semiconductor final testing scheduling problem with makespan criteria.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.05.007
      Issue No: Vol. 38 (2017)
  • A knowledge-guided multi-objective fruit fly optimization algorithm for
           the multi-skill resource constrained project scheduling problem
    • Authors: Ling Wang; Xiao-long Zheng
      Pages: 54 - 63
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Ling Wang, Xiao-long Zheng
      In this paper, a knowledge-guided multi-objective fruit fly optimization algorithm (MOFOA) is proposed for the multi-skill resource-constrained project scheduling problem (MSRCPSP) with the criteria of minimizing the makespan and the total cost simultaneously. First, a solution is represented by two lists, i.e. resource list and task list. Second, the minimum total cost rule is designed for the initialization according to the property of the problem. Third, the smell-based search is implemented via the neighborhood based search operators that are specially designed for the MSRCPSP, while the vision-based search adopts the technique for the order preference by similarity to an ideal solution (TOPSIS) and the non-dominated sorting collaboratively to complete the multi-objective evaluation. In addition, a knowledge-guided search procedure is introduced to enhance the exploration of the FOA. Finally, the design-of-experiment (DOE) method is used to investigate the effect of parameter setting, and numerical tests based on benchmark instances are carried out. The results compared to other algorithms demonstrate the effectiveness of the MOFOA with knowledge-guided search in solving the multi-objective MSRCPSP.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.06.001
      Issue No: Vol. 38 (2017)
  • An improved migrating birds optimization for an integrated lot-streaming
           flow shop scheduling problem
    • Authors: Tao Meng; Quan-Ke Pan; Jun-Qing Li; Hong-Yan Sang
      Pages: 64 - 78
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Tao Meng, Quan-Ke Pan, Jun-Qing Li, Hong-Yan Sang
      Lot-streaming is an effective technology to enhance the production efficiency by splitting a job or a lot into several sublots. It is commonly assumed that lot-splitting (i.e. job-splitting) is specified in advance and fixed during the optimization procedure in recent studies on lot-streaming flow shop scheduling problems. In many real-world production processes, however, it is not easy to determine the optimal lot-splitting beforehand. Therefore, in this paper we consider an integrated lot-streaming flow shop scheduling problem in which lot-splitting and job scheduling are needed to be optimized simultaneously. We provide a mathematical model for the problem and present an improved migrating birds optimization (IMMBO) to minimize the maximum completion time or makespan. In the IMMBO algorithm, a harmony search based scheme is designed to construct neighborhood of solutions, which makes good use of optimization information from the population and can tune the search scope adaptively. Moreover, a leaping mechanism is introduced to avoid being trapped in the local optimum. Extensive numerical simulations are conducted and comparisons with other state-of-the-art algorithms verify the effectiveness of the proposed IMMBO algorithm.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.06.003
      Issue No: Vol. 38 (2017)
  • Adaptive artificial immune networks for mitigating DoS flooding attacks
    • Authors: Jorge Maestre Vidal; Ana Lucila Sandoval Orozco; Luis Javier García Villalba
      Pages: 94 - 108
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Jorge Maestre Vidal, Ana Lucila Sandoval Orozco, Luis Javier García Villalba
      Denial of service attacks pose a threat in constant growth. This is mainly due to their tendency to gain in sophistication, ease of implementation, obfuscation and the recent improvements in occultation of fingerprints. On the other hand, progress towards self-organizing networks, and the different techniques involved in their development, such as software-defined networking, network-function virtualization, artificial intelligence or cloud computing, facilitates the design of new defensive strategies, more complete, consistent and able to adapt the defensive deployment to the current status of the network. In order to contribute to their development, in this paper, the use of artificial immune systems to mitigate denial of service attacks is proposed. The approach is based on building networks of distributed sensors suited to the requirements of the monitored environment. These components are capable of identifying threats and reacting according to the behavior of the biological defense mechanisms in human beings. It is accomplished by emulating the different immune reactions, the establishment of quarantine areas and the construction of immune memory. For their assessment, experiments with public domain datasets (KDD’99, CAIDA’07 and CAIDA’08) and simulations on various network configurations based on traffic samples gathered by the University Complutense of Madrid and flooding attacks generated by the tool DDoSIM were performed.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.002
      Issue No: Vol. 38 (2017)
  • Accelerated multi-gravitational search algorithm for size optimization of
           truss structures
    • Authors: Mohsen Khatibinia; Hessam Yazdani
      Pages: 109 - 119
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Mohsen Khatibinia, Hessam Yazdani
      Weak local exploitation capability of the gravitational search algorithm (GSA) and its slow convergence rate in final iterations have been demonstrated in the literature. This paper presents a modified GSA denoted here as the accelerated multi-gravitational search algorithm (AMGSA) that exhibits an improved convergence rate. In AMGSA, the simplex crossover (SPX) and the operator mutation of the breeder genetic algorithm (BGA) are incorporated with the multi-gravitational search algorithm (MGSA) to achieve an algorithm with a good exploration-exploitation balance. MGSA is adopted to prevent stagnation of the search into a local optimum (i.e. to improve the exploration capability), while the SPX and the BGA mutation operator are used to bias the search toward promising areas of the search space (i.e. to promote local exploitation). The performance of AMGSA is evaluated using several benchmark truss optimization examples. Results indicate that AMGSA not only exhibits an improved balance between the exploration and exploitation schemes but also shows competitive promise in effectively and efficiently solving large-scale optimization problems as it requires a significantly lower number of structural analyses compared to other algorithms that it is checked against.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.001
      Issue No: Vol. 38 (2017)
  • A novel differential particle swarm optimization for parameter selection
           of support vector machines for monitoring metal-oxide surge arrester
    • Authors: Thi Thom Hoang; Ming-Yuan Cho; Mahamad Nabab Alam; Quoc Tuan Vu
      Pages: 120 - 126
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Thi Thom Hoang, Ming-Yuan Cho, Mahamad Nabab Alam, Quoc Tuan Vu
      Since metal-oxide surge arresters are the important over-voltage protection equipments used in power systems, their operating conditions must be monitored on a timely basis to give an alarm as soon as possible in order to increase the reliability of a power system. The paper proposes a novel differential particle swarm optimization-based (DPSO-based) support vector machine (SVM) classifier for the purpose of monitoring the surge arrester conditions. A DPSO-based technique is investigated to give better results, which optimizes the parameters of SVM classifiers. Three features are extracted as input vectors for evaluating five arrester conditions, including normal (N), pre-fault (A), tracking (T), abnormal (U) and degradation (D). Meanwhile, a comparative study of fault diagnosis is carried out by using a DPSO-based ANN classifier. The results obtained using the proposed method are compared to those obtained using genetic algorithm (GA) and particle swarm optimization (PSO). The experiments using an actual dataset will expectably show the superiority of the proposed approach in improving the performance of the classifiers.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.006
      Issue No: Vol. 38 (2017)
  • Maximum likelihood estimation for the parameters of skew normal
           distribution using genetic algorithm
    • Authors: Abdullah Yalçınkaya; Birdal Şenoğlu; Ufuk Yolcu
      Pages: 127 - 138
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Abdullah Yalçınkaya, Birdal Şenoğlu, Ufuk Yolcu
      Skew Normal (SN) distribution is widely used for modeling data sets having near normal and skew distribution. Maximum likelihood (ML) is the most popular method used to obtain estimators of model parameters. However, likelihood equations do not have explicit solutions in the context of SN. Therefore, we use the Genetic Algorithm (GA) which is a well known search technique inspired by the principles of biological systems, such as evolution, mutation and suchlike, to overcome problems encountered in solving likelihood equations. The GA has routinely high performance where traditional search techniques fail. We compare the efficiencies of ML estimators of model parameters using the GA with corresponding ML estimators obtained using other iterative techniques, such as Newton-Raphson (NR), Nelder Mead (NM), and Iteratively Re-weighting Algorithm (IRA). Simulation results show that ML estimators using the GA of the parameters of SN distribution are the most efficient among others with respect to bias, mean square error (MSE) and deficiency (Def) criteria.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.007
      Issue No: Vol. 38 (2017)
  • Evolutionary algorithms based synthesis of low sidelobe hexagonal arrays
    • Authors: Sudipta Das; Rajesh Bera; Durbadal Mandal; Sakti Prasad Ghoshal; Rajib Kar
      Pages: 139 - 157
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Sudipta Das, Rajesh Bera, Durbadal Mandal, Sakti Prasad Ghoshal, Rajib Kar
      In this work a procedure namely Findpeaks2 is proposed to detect the maximum sidelobe level (SLL) from the samples of three dimensional radiation pattern. This procedure detects all sidelobe peaks form the samples of the radiation pattern in the entire visible region. For illustration, a low sidelobe radiation pattern synthesis problem is formulated for two concentric regular hexagonal antenna array (CRHAA) geometries, having 6- and 8- rings. To verify the extent of applicability of the proposed procedure, both broadside and scanned array configurations are considered. Feed current amplitudes are considered as the optimizing variables. Two variations of current distributions are considered, i) identical feed for all the elements on a ring (hence the one variable per ring needs to be optimized), and ii) asymmetric excitation distribution (set of excitation amplitude of all elements as optimizing variables). The design objective has been considered to optimize the radiation patterns with very low interference from the entire sidelobe region. To restrict the fall of directivity value, a constraint on the lower limit of directivity value is considered. The impacts of symmetry and the constraint on directivity on the search of these algorithms are studied. Evolutionary algorithms like Real Coded Genetic Algorithm (RGA), Firefly Algorithm (FFA), Flower Pollination Algorithm (FPA), an adaptive variant of Particle Swarm Optimization Algorithm namely (APSO), and two recently proposed variants of DE namely Exponentially Weighted Moving Average Differential Evolution (EWMA-DE), and Differential Evolution with Individual Dependent Mechanism (IDE) are employed for this pattern optimization problem.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.003
      Issue No: Vol. 38 (2017)
  • DABE: Differential evolution in analogy-based software development effort
    • Authors: Tirimula Rao Benala; Rajib Mall
      Pages: 158 - 172
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Tirimula Rao Benala, Rajib Mall
      Several feature weight optimization techniques have been proposed for similarity functions in analogy-based estimation (ABE); however, no consensus regarding the method and settings suitable for producing accurate estimates has been reached. We investigate the effectiveness of differential evolution (DE) algorithm, for optimizing the feature weights of similarity functions of ABE by applying five successful mutation strategies. We have named this empirical analysis as DE in analogy-based software development effort estimation (DABE). We have conducted extensive simulation study on the PROMISE repository test suite to estimate the effectiveness of our proposed DABE technique. We find significant improvements in predictive performance of our DABE technique over ABE, particle swarm optimization-based feature weight optimization in ABE, genetic algorithm-based feature weight optimization in ABE, self-adaptive DE-based feature weight optimization ABE, adaptive differential evolution with optional external archive-based feature weight optimization ABE, functional link artificial neural network,artificial neural network with back propagation learning based software development effort estimation (SDEE), and radial basis function-based SDEE.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.009
      Issue No: Vol. 38 (2017)
  • A Robust Stochastic Fractal Search approach for optimization of the
           surface grinding process
    • Authors: Soheyl Khalilpourazari; Saman Khalilpourazary
      Pages: 173 - 186
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Soheyl Khalilpourazari, Saman Khalilpourazary
      Grinding process is one of the most important machining processes in industry. The mathematical model of the optimization of the grinding process includes three objective functions and a weighted objective function with a set of operational constraints. Due to nonlinearity and complexity of the mathematical model, optimization of grinding process is a challenging task. This paper aims to optimize the surface grinding process parameters to increase final surface quality and production rate while minimizing total process costs. A novel Robust Stochastic Fractal Search is proposed to solve the problem efficiently. To increase the efficiency of the algorithm, a robust design methodology named Taguchi method is utilized to tune the parameters of the Stochastic Fractal Search. Since, the basic version of the Stochastic Fractal Search is proposed for unconstrained optimization, in this research, an efficient constraint handling method is implemented to handle complex nonlinear constraints of the problem. To Show the applicability and efficiency of the proposed Robust Stochastic Fractal Search, an experimental example is solved and compared to the results of the previous researches in the literature as well as two novel algorithm MPEDE and HCLPSO. The results revealed that the Robust Stochastic Fractal Search provides very competitive solutions and outperforms other solution methods.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.008
      Issue No: Vol. 38 (2017)
  • A multi-objective evolutionary artificial bee colony algorithm for
           optimizing network topology design
    • Authors: Amani Saad; Salman A. Khan; Amjad Mahmood
      Pages: 187 - 201
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Amani Saad, Salman A. Khan, Amjad Mahmood
      The topological design of a computer communication network is a well-known NP-hard problem. The problem complexity is further magnified by the presence of multiple design objectives and numerous design constraints. This paper presents a goal programming-based multi-objective artificial bee colony optimization (MOABC) algorithm to solve the problem of topological design of distributed local area networks (DLANs). Five design objectives are considered herein, namely, network reliability, network availability, average link utilization, monetary cost, and network delay. Goal programming (GP) is incorporated to aggregate the multiple design objectives into a single objective function. A modified version of MOABC, named as evolutionary multi-objective ABC (EMOABC) is also proposed which incorporates the characteristics of simulated evolution (SE) algorithm for improved local search. The effect of control parameters of MOABC is investigated. Comparison of EMOABC with MOABC and the standard ABC (SABC) shows better performance of EMOABC. Furthermore, a comparative analysis is also done with non-dominated sorting genetic algorithm II (NSGA-II), Pareto-dominance particle swarm optimization (PDPSO) algorithm and two recent variants of decomposition based multi-objective evolutionary algorithms, namely, MOEA/D-1 and MOEA/D-2. Results indicate that EMOABC demonstrated superior performance than all the other algorithms.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.010
      Issue No: Vol. 38 (2017)
  • On maximizing reliability of grid transaction processing system
           considering balanced task allocation using social spider optimization
    • Authors: Dharmendra Prasad Mahato; Ravi Shankar Singh
      Pages: 202 - 217
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Dharmendra Prasad Mahato, Ravi Shankar Singh
      This paper deals with the problem of task allocation in the grid transaction processing system. There has been quite some research on the development of tools and techniques for grid computing systems, yet some important issues, e.g., service reliability with load balanced transaction allocation in grid computing system, have not been sufficiently studied. Load balanced transaction allocation becomes a challenging job in such a complex and dynamic environment as both the application and computational resources are heterogeneous. The problem is further complicated by the fact that these resources may fail at any point of time. The problem of finding an optimal task allocation solution is known to be an NP-hard. We propose grid transaction allocation based on social spider optimization (LBGTA_SSO) method for this problem. The LBGTA_SSO is based on the cooperative behavior of social spiders to find a collection of task allocation solutions. We also derive reliability formulae for grid transactions considering resource availability. For comparison we modify some existing algorithms to obtain the task allocation algorithms. The results show that our algorithm works better than the modified existing algorithms.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.07.011
      Issue No: Vol. 38 (2017)
  • Global-best brain storm optimization algorithm
    • Authors: Mohammed El-Abd
      Pages: 27 - 44
      Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37
      Author(s): Mohammed El-Abd
      Brain storm optimization (BSO) is a population-based metaheuristic algorithm that was recently developed to mimic the brainstorming process in humans. It has been successfully applied to many real-world engineering applications involving non-linear continuous optimization. In this work, we propose improving the performance of BSO by introducing a global-best version combined with per-variable updates and fitness-based grouping. In addition, the proposed algorithm incorporates a re-initialization scheme that is triggered by the current state of the population. The introduced Global-best BSO (GBSO) is compared against other BSO variants on a wide range of benchmark functions. Comparisons are based on final solutions and convergence characteristics. In addition, GBSO is compared against global-best versions of other meta-heuristics on recent benchmark libraries. Results prove that the proposed GBSO outperform previous BSO variants on a wide range of classical functions and different problem sizes. Moreover, GBSO outperforms other global-best meta-heuristic algorithms on the well-known CEC05 and CEC14 benchmarks.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.05.001
      Issue No: Vol. 37 (2017)
  • Multiobjective evolutionary algorithm based on vector angle neighborhood
    • Authors: Roman Denysiuk; António Gaspar-Cunha
      Pages: 45 - 57
      Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37
      Author(s): Roman Denysiuk, António Gaspar-Cunha
      Selection is a major driving force behind evolution and is a key feature of multiobjective evolutionary algorithms. Selection aims at promoting the survival and reproduction of individuals that are most fitted to a given environment. In the presence of multiple objectives, major challenges faced by this operator come from the need to address both the population convergence and diversity, which are conflicting to a certain extent. This paper proposes a new selection scheme for evolutionary multiobjective optimization. Its distinctive feature is a similarity measure for estimating the population diversity, which is based on the angle between the objective vectors. The smaller the angle, the more similar individuals. The concept of similarity is exploited during the mating by defining the neighborhood and the replacement by determining the most crowded region where the worst individual is identified. The latter is performed on the basis of a convergence measure that plays a major role in guiding the population towards the Pareto optimal front. The proposed algorithm is intended to exploit strengths of decomposition-based approaches in promoting diversity among the population while reducing the user's burden of specifying weight vectors before the search. The proposed approach is validated by computational experiments with state-of-the-art algorithms on problems with different characteristics. The obtained results indicate a highly competitive performance of the proposed approach. Significant advantages are revealed when dealing with problems posing substantial difficulties in keeping diversity, including many-objective problems. The relevance of the suggested similarity and convergence measures are shown. The validity of the approach is also demonstrated on engineering problems.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.05.005
      Issue No: Vol. 37 (2017)
  • Jaya, harmony search and water cycle algorithms for solving large-scale
           real-life urban traffic light scheduling problem
    • Authors: Kaizhou Gao; Yicheng Zhang; Ali Sadollah; Antonios Lentzakis; Rong Su
      Pages: 58 - 72
      Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37
      Author(s): Kaizhou Gao, Yicheng Zhang, Ali Sadollah, Antonios Lentzakis, Rong Su
      This paper studies a large-scale urban traffic light scheduling problem (LUTLSP). A centralized model is developed to describe the LUTLSP, where each outgoing flow rate is described as a nonlinear mixed logical switching function over the source link’s density, the destination link’s density and capacity, and the driver’s potential psychological response to the past traffic light signals. The objective is to minimize the total network-wise delay time of all vehicles in a time window. Three metaheuristic optimization algorithms, named as Jaya algorithm, harmony search (HS) and water cycle algorithm (WCA) are implemented to solve the LUTLSP. Since we adopt a discrete-time formulation of LUTLSP, we firstly develop a discrete version of Jaya and WCA. Secondly, some improvement strategies are proposed to speed up the convergence of applied optimizers. Thirdly, a feature based search operator is utilized to improve the search performance of reported optimization methods. Finally, experiments are carried out based on the real traffic data in Singapore. The HS, WCA, Jaya, and their variants are evaluated by solving 11 cases of traffic networks. The comparisons and discussions verify that the considered metaheuristic optimization methods can effectively solve the LUTLSP considerably surpassing the existing traffic light control strategy.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.05.002
      Issue No: Vol. 37 (2017)
  • Modified cuckoo search algorithm for multiobjective short-term
           hydrothermal scheduling
    • Authors: Thang Trung Nguyen; Dieu Ngoc Vo
      Pages: 73 - 89
      Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37
      Author(s): Thang Trung Nguyen, Dieu Ngoc Vo
      This paper proposes a modified cuckoo search algorithm (MCSA) for solving multi-objective short-term fixed head hydrothermal scheduling (HTS) problem. The main objective of the multiobjective HTS problem is to minimize both total power generation cost and emission of thermal generators over a scheduling period while satisfying power balance, hydraulic, and generator operating limit constraints. The proposed MCSA method is developed for the problem based on improvements from the conventional CSA method which is a new metaheuristic algorithm inspired from the behavior of some cuckoo species laying their egg into the nest of other species to improve the optimal solution and speed up the computational process. In the MCSA method, the nests are evaluated and classified into two groups including the top group with better quality eggs and the abandoned group with worse quality eggs. Two effective strategies via Lévy flights for producing new solutions are applied to the abandoned and top groups. To validate the efficiency of the MCSA method, several test systems have been tested and the result comparisons from the test systems have indicated that the proposed method can obtain higher quality solution and shorter computational time than many other methods. Therefore, the proposed MCSA method can be new efficient method for solving multiobjective short-term fixed-head HTS problems.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.05.006
      Issue No: Vol. 37 (2017)
  • Sizing and topology optimization of truss structures using genetic
    • Authors: Hirad Assimi; Ali Jamali; Nader Nariman-zadeh
      Pages: 90 - 103
      Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37
      Author(s): Hirad Assimi, Ali Jamali, Nader Nariman-zadeh
      This paper presents a genetic programming approach for simultaneous optimization of sizing and topology of truss structures. It aims to find the optimal cross-sectional areas and connectivities of the joints to achieve minimum weight in the search space. The structural optimization problem is subjected to kinematic stability, maximum allowable stress and deflection. This approach uses the variable-length representation of potential solutions in the shape of computer programs and evolves to the optimum solution. This method has the capability to identify redundant truss elements and joints in the design space. The obtained results are compared with existing popular and competent techniques in literature and its competence as a tool in the optimization problem are demonstrated in solving some benchmark examples, the proposed approach provided lighter truss structures than the available solutions reported in the literature.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.05.009
      Issue No: Vol. 37 (2017)
  • Multi-criteria algorithms for portfolio optimization under practical
    • Authors: Suraj S. Meghwani; Manoj Thakur
      Pages: 104 - 125
      Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37
      Author(s): Suraj S. Meghwani, Manoj Thakur
      Selection of promising assets and allocating capital among them is a crucial part of the financial decision-making process. Modern portfolio theory formulated it as a quadratic optimization problem of maximizing expected returns and minimizing the risk of the portfolio. This problem was modified to incorporate investor's preferences resulting in discrete non-linear search space which cannot be handled by traditional quadratic programming approaches. Relevant literature shows the success of evolutionary algorithms in modelling some of these preferences Multi-criteria algorithms for portfolio optimization under practical constraintsin a constrained optimization problem. This study proposes a candidate generation procedure and a repair mechanism for practical portfolio optimization model in multi-objective evolutionary algorithm (MOEA) settings. Both these methods together can handle a larger class of constraints namely cardinality, pre-assignment, budget, quantity (floor and ceiling) and round-lot constraints. Proposed methods can easily be incorporated into existing evolutionary algorithms. To evaluate their effectiveness, four MOEAs namely Non-dominated Sorting Genetic Algorithm-II (NSGA-II), Strength Pareto Evolutionary Algorithm 2 (SPEA2), Global Weighting Achievement Scalarizing Function Genetic Algorithm (GWASFGA) and Pareto Envelope-based Selection Algorithm-II (PESA-II) have been adapted and their capability of approximating unconstrained efficient frontier are discussed. For empirical testing, seven datasets involving maximum up to 1290 assets are used. All the adapted algorithms are compared and evaluated on the basis of five well-known performance metrics for MOEAs. The potential of our adapted algorithms is presented in comparison with existing MOEAs for the identical problems.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.06.005
      Issue No: Vol. 37 (2017)
  • Weibull-based scaled-differences schema for Differential Evolution
    • Authors: Miguel
      Abstract: Publication date: February 2018
      Source:Swarm and Evolutionary Computation, Volume 38
      Author(s): Miguel Cárdenas-Montes
      Differential Evolution is one of the most efficient real-parameter optimization algorithm. It is based on the application of the scaled difference of a pair of population members to another population member, all of them distinct. Diverse variants have been proposed within this schema. In this work, the statistical distribution of these differences of high-performance variants of Differential Evolution is modelled through a Weibull probability distribution. From the application of this model to diverse Differential Evolution variants and benchmark functions, a pattern for the most efficient variants can be drawn. As a consequence, a variant where the scaled differences are replaced by random numbers generated from a Weibull distribution is proposed and evaluated.

      PubDate: 2017-12-27T13:32:09Z
  • Optimal placement of TCSC and SVC for reactive power planning using Whale
           optimization algorithm
    • Authors: Saurav Raj; Biplab Bhattacharyya
      Abstract: Publication date: Available online 23 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Saurav Raj, Biplab Bhattacharyya
      In the present work, Whale optimization algorithm (WOA), Differential evolution (DE), Grey wolf optimization (GWO), Quasi-opposition based Differential Evolution (QODE) and Quasi-opposition based Grey wolf optimization (QOGWO) algorithm has been applied for the solution of reactive power planning with FACTS devices i.e., Thyristor controlled series compensator (TCSC) and Static Var compensator (SVC). WOA is a recently developed nature-inspired meta-heuristic algorithm based on hunting behaviour of Humpback Whales; DE is a stochastic real-parameter optimization technique comprising of genetic parameters namely - mutation & cross-over; and GWO is a nature-inspired meta-heuristic algorithm based on hunting behaviour of Grey wolf. Standard IEEE 30 and IEEE 57 bus test system has been adopted for the testing purposes. Location of TCSC has been determined by the power flow analysis method and location of SVC has been determined by the voltage collapse proximity indication (VCPI) method. Further, WOA, GWO, DE, QODE and QOGWO algorithms have been applied to find the optimal setting of all control variables including TCSC, the series type and SVC, the shunt kind of FACTS device in the test system which minimizes active power loss and system operating cost while maintaining voltage profile within permissible limit. The superiority of the proposed WOA technique has been illustrated by comparing the results obtained with all other techniques discussed in the present problem. ANOVA test has also been conducted to show the statistical analysis between different techniques. The proposed approach shows lesser number of iterations which does not gets trapped in the local minima and offers promising convergence characteristics.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.12.008
  • Profit maximizing logistic model for customer churn prediction using
           genetic algorithms
    • Authors: Eugen Stripling; Seppe vanden Broucke; Katrien Antonio; Bart Baesens; Monique Snoeck
      Abstract: Publication date: Available online 21 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Eugen Stripling, Seppe vanden Broucke, Katrien Antonio, Bart Baesens, Monique Snoeck
      To detect churners in a vast customer base, as is the case with telephone service providers, companies heavily rely on predictive churn models to remain competitive in a saturated market. In previous work, the expected maximum profit measure for customer churn (EMPC) has been proposed in order to determine the most profitable churn model. However, profit concerns are not directly integrated into the model construction. Therefore, we present a classifier, named ProfLogit, that maximizes the EMPC in the training step using a genetic algorithm, where ProfLogit's interior model structure resembles a lasso-regularized logistic model. Additionally, we introduce threshold-independent recall and precision measures based on the expected profit maximizing fraction, which is derived from the EMPC framework. Our proposed technique aims to construct profitable churn models for retention campaigns to satisfy the business requirement of profit maximization. In a benchmark study with nine real-life data sets, ProfLogit exhibits the overall highest, out-of-sample EMPC performance as well as the overall best, profit-based precision and recall values. As a result of the lasso resemblance, ProfLogit also performs a profit-based feature selection in which features are selected that would otherwise be excluded with an accuracy-based measure, which is another noteworthy finding.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.10.010
  • Structural test data generation using a memetic ant colony optimization
           based on evolution strategies
    • Authors: Hossein Sharifipour; Mojtaba Shakeri; Hassan Haghighi
      Abstract: Publication date: Available online 20 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Hossein Sharifipour, Mojtaba Shakeri, Hassan Haghighi
      Test data generation is one of the key activities that has a significant impact on the efficiency and effectiveness of software testing. Since manual test data generation is quite inefficient and even impractical, automated test data generation has been realized to produce an appropriate subset of input data to carry out effective software testing in reasonable times. This paper presents a memetic ant colony optimization (ACO) algorithm for structural test data generation. The proposed approach incorporates (1+1)-evolution strategies (ES) to improve the search functionality of ants in local moves and enhance search exploitation. Moreover, we have introduced a novel definition of the pheromone functionality in the way that it discourages ants from choosing mostly covered paths of the program to reinforce search exploration. Given that branch coverage is considered as the coverage criterion, two fitness functions are used accordingly for our proposed algorithm. The first fitness function is a Boolean function which is particularly defined to maximize branch coverage. It outputs one if a given solution is successful in traversing at least a yet uncovered branch; otherwise, it returns zero. The second fitness function is formulated according to the complexity of branches covered. The value of the second fitness function is not taken into account for solutions whose Boolean function value equals one. For these solutions, the decision-making process of ants is merely carried out based on the first fitness function. The experimental results indicate the superiority of our memetic ACO algorithm relative to existing test data generation techniques in terms of both branch coverage and convergence speed.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.12.009
  • A novel discrete water wave optimization algorithm for blocking flow-shop
           scheduling problem with sequence-dependent setup times
    • Authors: Zhongshi Shao; Dechang Weishi Shao
      Abstract: Publication date: Available online 13 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Zhongshi Shao, Dechang Pi, Weishi Shao
      This paper considers n-job m-machines blocking flow-shop scheduling problem (BFSP) with sequence-dependent setup times (SDST), which has important ramifications in the modern industry. To solve this problem, two efficient heuristics are firstly presented according to the property of the problem. Then, a novel discrete water wave optimization (DWWO) algorithm is proposed. In the proposed DWWO, an initial population with high quality and diversity is constructed based on the presented heuristic and a perturbation procedure. A two-stage propagation is designed to direct the algorithm towards the good solutions. The path relinking technique is employed in refraction phase to help individuals escape from local optima. A variable neighborhood search is developed and embedded in breaking phase to enhance local exploitation capability. A new population updating scheme is applied to accelerate the convergence speed. Moreover, a speedup method is presented to reduce the computational efforts needed for evaluating insertion neighborhood. Finally, extensive numerical tests are carried out, and the results compared to some state-of-the-art metaheuristics demonstrate the effectiveness of the proposed DWWO in solving BFSP with SDST.

      PubDate: 2017-12-27T13:32:09Z
  • Improved Raven Roosting Optimization algorithm (IRRO)
    • Authors: Shadi Torabi; Faramarz Safi-Esfahani
      Abstract: Publication date: Available online 12 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Shadi Torabi, Faramarz Safi-Esfahani
      Optimization means finding the best solution from among an infinite number of possible solutions to a complex problem. Several methods are generally used for solving complex problems, such as meta-heuristic algorithms that are inspired from living organisms. Raven Roosting Optimization (RRO) is an algorithm inspired by the mimicking behavior of ravens but it has the problem of premature convergence. This paper provides an expansion of RRO algorithm namely IRRO to resolve the problem. It focuses on a population that follows the leader and divides the population into groups of weak ravens and greedy ravens. It also uses a parameter to control the amount of food remaining for the ravens. This is then extended by comparison of the proposed algorithm to RRO, Particle Swarm Optimization (PSO) approach Bat algorithm (BA), Chicken Swarm Optimization (CSO), Gray Wolf Optimization (GWO), Whale Optimization Algorithm (WOA). The experimental results on 30 standard benchmark functions how the improvement of the proposed algorithm compared to RRO, PSO, BA, CSO, GWO and WOA algorithms.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.11.006
  • Application and benchmarking of multi-objective evolutionary algorithms on
           high-dose-rate brachytherapy planning for prostate cancer treatment
    • Authors: Ngoc Hoang Luong; Tanja Alderliesten; Arjan Bel; Yury Niatsetski; Peter A.N. Bosman
      Abstract: Publication date: Available online 9 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Ngoc Hoang Luong, Tanja Alderliesten, Arjan Bel, Yury Niatsetski, Peter A.N. Bosman
      High-Dose-Rate (HDR) brachytherapy (BT) treatment planning involves determining an appropriate schedule of a radiation source moving through a patient's body such that target volumes are irradiated with the planning-aim dose as much as possible while healthy tissues (i.e., organs at risk) should not be irradiated more than certain thresholds. Such movement of a radiation source can be defined by so-called dwell times at hundreds of potential dwell positions, which must be configured to satisfy a clinical protocol of multiple different treatment criteria within a strictly-limited time frame of not more than one hour. In this article, we propose a bi-objective optimization model that intuitively encapsulates in two objectives the complicated high-dimensional multi-criteria nature of the BT treatment planning problem. The resulting Pareto-optimal fronts exhibit possible trade-offs between the coverage of target volumes and the sparing of organs at risk, thereby intuitively facilitating the decision-making process of treatment planners when creating a clinically-acceptable plan. We employ real medical data for conducting experiments and benchmark four different Multi-Objective Evolutionary Algorithms (MOEAs) on solving our problem: the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), the Multi-objective Adapted Maximum-Likelihood Gaussian Model Iterated Density-Estimation Evolutionary Algorithm (MAMaLGaM), and the recently-introduced Multi-Objective Real-Valued Gene-pool Optimal Mixing Evolutionary Algorithm (MO-RV-GOMEA). The variation operator that is specific to MO-RV-GOMEA enables performing partial evaluations to efficiently calculate objective values of offspring solutions without incurring the cost of fully recomputing the radiation dose distributions for new treatment plans. Experimental results show that MO-RV-GOMEA is the best performing MOEA that effectively exploits dependencies between decision variables to efficiently solve the multi-objective BT treatment planning problem.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.12.003
  • Lifecycle Coevolution Framework for many evolutionary and swarm
           intelligence algorithms fusion in solving complex optimization problems
    • Authors: Maowei He; Hanning Chen; Liling Sun; Weixing Su; Fang Liu; Xiaodan Liang; Lianbo Ma
      Abstract: Publication date: Available online 7 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Maowei He, Hanning Chen, Liling Sun, Weixing Su, Fang Liu, Xiaodan Liang, Lianbo Ma
      In last few decades, many different evolutionary and swarm intelligence (EA and SI) algorithms have been delicately developed for solving complex optimization problems. However, according to no free lunch theorem (NFL), a general-purpose universal EA or SI algorithm that is efficient for various types of optimization problems is theoretically impossible. The main focus in this research is to prove that there are potential free lunches in coevolutionary optimization mode. The significant improvements in the generality and effectiveness of EA and SI search ability can be achieved by fusing unlimited number of optimization algorithms based on the new concept of Lifecycle Coevolution Framework (LCF). The main innovation of LCF is to run the different SI algorithms simultaneously, in which individuals of each optimizer dynamically shift their states of birth, searching, learning, reproduction, and death throughout the whole colony life cycle. Based on LCF, we instantiate a novel coevolutionary optimization algorithm called a Lifecycle Framework of Multiple Evolution Algorithms (LCFMEAs). For purposes of examining the success of LCFMEAs in solving complex optimization problems, 50 benchmark functions with different specifications are employed. The results show that LCFMEAs provide extremely competitive performance when it is compared with six widely used evolutionary and swarm intelligence algorithms.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.12.002
  • A novel orthogonal PSO algorithm based on orthogonal diagonalization
    • Authors: Loau Tawfak Al-Bahrani; Jagdish C. Patra
      Abstract: Publication date: Available online 6 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Loau Tawfak Al-Bahrani, Jagdish C. Patra
      One of the major drawbacks of the global particle swarm optimization (GPSO) algorithm is zigzagging of the direction of search that leads to premature convergence by falling into local minima. In this paper, a new algorithm named orthogonal PSO (OPSO) algorithm is proposed that not only alleviates the associated problems in GPSO algorithm but also achieves better performance. In OPSO algorithm, the m particles of the swarm are divided into two groups: one active group of best personal experience of d particles and a passive group of personal experience of remaining (m ‒ d) particles. The purpose of creating two groups is to enhance the diversity in the swarm's population. In each iteration, the d active group particles undergo an orthogonal diagonalization process and are updated in such way that their position vectors are orthogonally diagonalized. The passive group particles are not updated as their contribution in finding correct direction is not significant. In the proposed algorithm, the particles are updated using only one guide, thus avoiding the conflict between the two guides that occurs in the GPSO algorithm. We tested the OPSO algorithm with thirty unimodal and multimodal high-dimensional benchmark functions and compared its performance with GPSO and several competing evolutionary techniques. With extensive simulated experiments, we have shown superiority of the proposed algorithm in terms of convergence, accuracy, consistency, robustness and reliability over other algorithms. The proposed algorithm is found to be successful in achieving optimal solution in all the thirty benchmark functions.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.12.004
  • An Enhanced Imperialist Competitive Algorithm for optimum design of
           skeletal structures
    • Authors: Mahmoud R. Maheri; M. Talezadeh
      Abstract: Publication date: Available online 6 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Mahmoud R. Maheri, M. Talezadeh
      An Enhanced Imperialist Competitive Algorithm (EICA) is proposed aimed at enabling the ICA algorithm to escape from local optima faster, thus enabling faster convergence of the basic ICA algorithm. To this end, the imperialistic competition phase of the algorithm is enhanced by giving added value to a slightly unfeasible solution, based on its distance from the relative imperialist. The performance of the proposed EICA algorithm is investigated through design optimizations of four benchmark side-sway frames. Results indicate that, in terms of both the design quality and the solution speed, EICA compares significantly favourable with a number of other meta-heuristic optimizers, including the basic ICA.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.12.001
  • BIM2RT: BWAS-immune mechanism based multipath reliable transmission with
           fault tolerance in wireless sensor networks
    • Authors: Hongbing Li; Qiang Chen; Yong Ran; Xiaowei Niu; Liwan Chen; Huafeng Qin
      Abstract: Publication date: Available online 2 December 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Hongbing Li, Qiang Chen, Yong Ran, Xiaowei Niu, Liwan Chen, Huafeng Qin
      Transmission reliability is one of the most important metrics to evaluate the performance of wireless sensor networks. However, fault nodes or links always affect transmission reliability and comprehensive performance of network due to the characteristics of network itself and working scenario. Intelligent computing, BWAS (Best Worst Ant System) and immune mechanism, provide new ideas and methods to the collaborative optimization in reliable transmission in wireless sensor networks. BWAS-Immune Mechanism based Multipath Reliable Transmission algorithm (BIM2RT) with fault tolerance is presented which includes BWAS based Multipath Established algorithm (BME) and Immune based Multipath Transmission algorithm (IMT). BME establishes all possible transmission paths from the source node to the destination node quickly by the guidance of pheromone information generated by artificial ants. These multipaths are the input and constitute the initial variation population for the next IMT which executes the mutation on the initial variation antibody population. IMT establishes optimum transmission paths with good convergence due to initial optimal solution by BME and avoids to get local optima. It converts the issue of multipath establishment into multi-objective optimization which not only gives the consideration to the factors of transmission delay and energy consumption but also the hops/distance. Combining with load balance mechanism, fault tolerance of multipath transmission is proved by the redundant routing and transmission. Mathematical model is established to analyze the comprehensive performance of multipath transmission through the metrics of data receiving rate, efficiency of energy consumption and transmission delay. Simulation result shows good performance of data transmission reliability and fault tolerance.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.11.005
  • A decomposition-based multi-objective evolutionary algorithm with quality
    • Authors: Jianping Luo; Yun Yang; Xia Li; Qiqi Liu; Minrong Chen; Kaizhou Gao
      Abstract: Publication date: Available online 21 November 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Jianping Luo, Yun Yang, Xia Li, Qiqi Liu, Minrong Chen, Kaizhou Gao
      The issue of integrating preference information into multi-objective optimization is considered, and a multi-objective framework based on decomposition and preference information, called indicator-based MOEA/D (IBMOEA/D), is presented in this study to handle the multi-objective optimization problems more effectively. The proposed algorithm uses a decomposition-based strategy for evolving its working population, where each individual represents a subproblem, and utilizes a binary quality indicator-based selection for maintaining the external population. Information obtained from the quality improvement of individuals is used to determine which subproblem should be invested at each generation by a power law distribution probability. Thus, the indicator-based selection and the decomposition strategy can complement each other. Through the experimental tests on seven many-objective optimization problems and one discrete combinatorial optimization problem, the proposed algorithm is revealed to perform better than several state-of-the-art multi-objective evolutionary algorithms. The effectiveness of the proposed algorithm is also analyzed in detail.

      PubDate: 2017-12-27T13:32:09Z
      DOI: 10.1016/j.swevo.2017.11.004
  • Inside Front Cover - Editorial Board Page/Cover image legend if applicable
    • Abstract: Publication date: December 2017
      Source:Swarm and Evolutionary Computation, Volume 37

      PubDate: 2017-11-18T15:54:35Z
  • A semi-supervised Genetic Programming method for dealing with noisy labels
           and hidden overfitting
    • Authors: Sara Silva; Leonardo Vanneschi; Ana I.R. Cabral; Maria J. Vasconcelos
      Abstract: Publication date: Available online 15 November 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Sara Silva, Leonardo Vanneschi, Ana I.R. Cabral, Maria J. Vasconcelos
      Data gathered in the real world normally contains noise, either stemming from inaccurate experimental measurements or introduced by human errors. Our work deals with classification data where the attribute values were accurately measured, but the categories may have been mislabeled by the human in several sample points, resulting in unreliable training data. Genetic Programming (GP) compares favorably with the Classification and Regression Trees (CART) method, but it is still highly affected by these errors. Despite consistently achieving high accuracy in both training and test sets, many classification errors are found in a later validation phase, revealing a previously hidden overfitting to the erroneous data. Furthermore, the evolved models frequently output raw values that are far from the expected range. To improve the behavior of the evolved models, we extend the original training set with additional sample points where the class label is unknown, and devise a simple way for GP to use this additional information and learn in a semi-supervised manner. The results are surprisingly good. In the presence of the exact same mislabeling errors, the additional unlabeled data allowed GP to evolve models that achieved high accuracy also in the validation phase. This is a brand new approach to semi-supervised learning that opens an array of possibilities for making the most of the abundance of unlabeled data available today, in a simple and inexpensive way.

      PubDate: 2017-11-18T15:54:35Z
      DOI: 10.1016/j.swevo.2017.11.003
  • A tissue P system based evolutionary algorithm for multi-objective VRPTW
    • Authors: Wenbo Dong; Kang Zhou; Huaqing Qi; Cheng He; Jun Zhang
      Abstract: Publication date: Available online 8 November 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Wenbo Dong, Kang Zhou, Huaqing Qi, Cheng He, Jun Zhang
      Multi-objective vehicle routing problem with time windows (VRPTW) has important applications in engineering and computer science, and it is a NP-hard problem. In the last decade, numerous new methods for multi-objective VRPTW have sprung up. However, the calculation speed of most algorithms is not fast enough, and on the other hand, these algorithms did not give a complete Pareto optimal front, although their results are excellent. Hence, in this paper, a tissue P system with three cells based MOEA, termed PDVA, is proposed to solve the multi-objective VRPTW. In PDVA, two mechanisms, the discrete glowworm evolution mechanism (DGEM) and the variable neighborhood evolution mechanism (VNEM), are used as sub-algorithms in two cells respectively to balance the exploration and exploitation reasonably. Simultaneously, some special strategies are used to enhance the performance of the proposed algorithm. The following experiments are presented to test the proposed algorithm. First, the influence of the parameters on the performance of the algorithm is investigated. Second, the validity of the algorithm is highlighted when compared to the DGEM-VNEM algorithm. Third, the quality and diversity of the solutions are improved when compared to the other popular algorithms. These results and comparisons on test instances demonstrate the competitiveness of PDVA in solving multi-objective VRPTW in terms of both quantity and speed.

      PubDate: 2017-11-10T14:39:12Z
      DOI: 10.1016/j.swevo.2017.11.001
  • Population topologies for particle swarm optimization and differential
    • Authors: Nandar Lynn; Mostafa Z. Ali; Ponnuthurai Nagaratnam Suganthan
      Abstract: Publication date: Available online 6 November 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Nandar Lynn, Mostafa Z. Ali, Ponnuthurai Nagaratnam Suganthan
      Over the last few decades, many population-based swarm and evolutionary algorithms were introduced in the literature. It is well known that population topology or sociometry plays an important role in improving the performance of population-based optimization algorithms by enhancing population diversity when solving multiobjective and multimodal problems. Many population structures and population topologies were developed for particle swarm optimization and differential evolutionary algorithms. Therefore, a comprehensive review of population topologies developed for PSO and DE is carried out in this paper. We anticipate that this survey will inspire researchers to integrate the population topologies into other nature inspired algorithms and to develop novel population topologies for improving the performances of population-based optimization algorithms for solving single objective optimization, multiobjective optimization and other classes of optimization problems.

      PubDate: 2017-11-10T14:39:12Z
      DOI: 10.1016/j.swevo.2017.11.002
  • Handling time-varying constraints and objectives in dynamic evolutionary
           multi-objective optimization
    • Authors: Radhia Azzouz; Slim Bechikh; Lamjed Ben Said; Walid Trabelsi
      Abstract: Publication date: Available online 4 November 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Radhia Azzouz, Slim Bechikh, Lamjed Ben Said, Walid Trabelsi
      Recently, several researchers within the evolutionary and swarm computing community have been interested in solving dynamic multi-objective problems where the objective functions, the problem's parameters, and/or the constraints may change over time. According to the related literature, most works have focused on the dynamicity of objective functions, which is insufficient since also constraints may change over time along with the objectives. For instance, a feasible solution could become infeasible after a change occurrence, and vice versa. Besides, a non-dominated solution may become dominated, and vice versa. Motivated by these observations, we devote this paper to focus on the dynamicity of both: (1) problem's constraints and (2) objective functions. To achieve our goal, we propose a new self-adaptive penalty function and a new feasibility driven strategy that are embedded within the NSGA-II and that are applied whenever a change is detected. The feasibility driven strategy is able to guide the search towards the new feasible directions according to the environment changes. The empirical results have shown that our proposal is able to handle various challenges raised by the problematic of dynamic constrained multi-objective optimization. Moreover, we have compared our new dynamic constrained NSGA-II version, denoted as DC-MOEA, against two existent dynamic constrained evolutionary algorithms. The obtained results have demonstrated the competitiveness and the superiority of our algorithm on both aspects of convergence and diversity.

      PubDate: 2017-11-10T14:39:12Z
      DOI: 10.1016/j.swevo.2017.10.005
  • A multi-objective particle swarm optimization algorithm for community
           detection in complex networks
    • Authors: Shadi Rahimi; Alireza Abdollahpouri; Parham Moradi
      Abstract: Publication date: Available online 31 October 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Shadi Rahimi, Alireza Abdollahpouri, Parham Moradi
      Community structure is an interesting feature of complex networks. The problem of community detection has attracted many research efforts in recent years. Most of the algorithms developed for this purpose take advantage of single-objective optimization methods which may be ineffective for complex networks. In this article, a novel multi-objective community detection method based on a modified version of particle swarm optimization, named MOPSO-Net is proposed. Kernel k-means (KKM) and ratio cut (RC) are employed as objective criteria to be minimized. Our innovation in PSO algorithm is changing the moving strategy of particles. Experiments on synthetic and real-world networks confirm a significant improvement in terms of normalized mutual information (NMI) and modularity in comparison with recent similar approaches.

      PubDate: 2017-11-03T14:04:14Z
      DOI: 10.1016/j.swevo.2017.10.009
  • Rank Fusion and Semantic Genetic Notion Based Automatic Query Expansion
    • Authors: Jagendra Singh; Aditi Sharan
      Abstract: Publication date: Available online 13 September 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Jagendra Singh, Aditi Sharan
      Query expansion term selection methods are really very important for improving the accuracy and efficiency of pseudo-relevance feedback based automatic query expansion for information retrieval system by removing irrelevant and redundant terms from the top retrieved feedback documents corpus with respect to user query. Individual query expansion term selection methods have been widely investigated for improving its performance. However, it is always a challenging task to find an individual query expansion term selection method that would outperform other individual query expansion term selection methods in most cases. In this paper, first we explore the possibility of improving the overall performance using individual query expansion term selection methods. Second, we propose a model for combining multiple query expansion term selection methods by using rank combination approach, called multiple ranks combination based query expansion. Third, semantic filtering is used to filter semantically irrelevant term obtained after combining multiple query expansion term selection methods, called ranks combination and semantic filtering based query expansion. Fourth, the genetic algorithm is used to make an optimal combination of query terms and candidate term obtained after rank combination and semantic filtering approach, called semantic genetic filtering and rank combination based query expansion. Our experimental results demonstrated that our proposed approaches achieved significant improvement over each individual query expansion term selection method and related state-of-the-art approaches.

      PubDate: 2017-09-16T13:42:43Z
      DOI: 10.1016/j.swevo.2017.09.007
  • Image contrast enhancement using an artificial bee colony algorithm
    • Authors: Jia Chen; Weiyu Yu; Jing Tian; Li Chen; Zhili Zhou
      Abstract: Publication date: Available online 9 September 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Jia Chen, Weiyu Yu, Jing Tian, Li Chen, Zhili Zhou
      The objective of image contrast enhancement is to improve the contrast level of images, which are degraded during image acquisition. Image contrast enhancement is considered as an optimization problem in this paper and the artificial bee colony (ABC) algorithm is utilized to find the optimal solution for this optimization problem. The contribution of the proposed approach is two-fold. First, in view of that the fitness function is indispensable to evaluate the quality of the enhanced image, a new objective fitness function is proposed in this paper. Second, the image transformation function is critical to generate new pixel intensities for the enhanced image from the original input image; more importantly, it guides the searching movements of the artificial bees. For that, a parametric image transformation function is utilized in this paper so that only the optimal parameters used in the transformation function need to be searched by the ABC algorithm. This is in contrast to that the whole space of image intensity levels is used in the conventional ABC-based image enhancement approaches. Extensive experiments are conducted to demonstrate that the proposed approach outperforms conventional image contrast enhancement approaches to achieve both better visual image quality and higher objective performance measures.

      PubDate: 2017-09-10T09:28:23Z
      DOI: 10.1016/j.swevo.2017.09.002
  • Binary Grey Wolf Optimizer for large scale unit commitment problem
    • Authors: Lokesh Kumar Panwar; Srikanth Reddy K; Ashu Verma; B.K. Panigrahi; Rajesh Kumar
      Abstract: Publication date: Available online 24 August 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Lokesh Kumar Panwar, Srikanth Reddy K, Ashu Verma, B.K. Panigrahi, Rajesh Kumar
      The unit commitment problem belongs to the class of complex large scale, hard bound and constrained optimization problem involving operational planning of power system generation assets. This paper presents a heuristic binary approach to solve unit commitment problem (UC). The proposed approach applies Binary Grey Wolf Optimizer (BGWO) to determine the commitment schedule of UC problem. The grey wolf optimizer belongs to the class of bio-inspired heuristic optimization approaches and mimics the hierarchical and hunting principles of grey wolves. The binarization of GWO is owing to the UC problem characteristic binary/discrete search space. The binary string representation of BGWO is analogous to the commitment and de-committed status of thermal units constrained by minimum up/down times. Two models of Binary Grey Wolf Optimizer are presented to solve UC problem. The first approach includes upfront binarization of wolf update process towards the global best solution (s) followed by crossover operation. While, the second approach estimates continuous valued update of wolves towards global best solution(s) followed by sigmoid transformation. The Lambda-Iteration method to solve the convex economic load dispatch (ELD) problem. The constraint handling is carried out using the heuristic adjustment procedure. The BGWO models are experimented extensively using various well known illustrations from literature. In addition, the numerical experiments are also carried out for different circumstances of power system operation. The solution quality of BGWO are compared to existing classical as well as heuristic approaches to solve UC problem. The simulation results demonstrate the superior performance of BGWO in solving UC problem for small, medium and large scale systems successfully compared to other well established heuristic and binary approaches.

      PubDate: 2017-09-03T21:03:58Z
      DOI: 10.1016/j.swevo.2017.08.002
  • Computing budget allocation in multi-objective evolutionary algorithms for
           stochastic problems
    • Authors: Mengmei Liu; Aaron M. Cramer
      Abstract: Publication date: Available online 24 August 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Mengmei Liu, Aaron M. Cramer
      Multi-objective stochastic problems are important problems in practice and are often solved through multi-objective evolutionary algorithms. Researchers have developed different noise handling techniques to improve the efficiency and accuracy of such algorithms, primarily by integrating these methods into the evaluation or environmental selection steps of the algorithms. In this work, a combination of studies that compare integration of different computing budget allocation methods into either the evaluation or the environmental selection steps are conducted. These comparisons are performed on stochastic problems derived from benchmark multi-objective optimization problems and consider varying levels of noise. The algorithms are compared in terms of both proximity to and coverage of the true Pareto-optimal front and sufficient studies are performed to allow statistically significant conclusions to be drawn. It is shown that integrating computing budget allocation methods into the environmental selection step is better than integration within the evaluation step.

      PubDate: 2017-09-03T21:03:58Z
      DOI: 10.1016/j.swevo.2017.08.004
  • A distributed evolutionary multivariate discretizer for Big Data
           processing on Apache Spark
    • Authors: S. Ramírez-Gallego; S. García; J.M. Benítez; F. Herrera
      Abstract: Publication date: Available online 23 August 2017
      Source:Swarm and Evolutionary Computation
      Author(s): S. Ramírez-Gallego, S. García, J.M. Benítez, F. Herrera
      Nowadays the phenomenon of Big Data is overwhelming our capacity to extract relevant knowledge through classical machine learning techniques. Discretization (as part of data reduction) is presented as a real solution to reduce this complexity. However, standard discretizers are not designed to perform well with such amounts of data. This paper proposes a distributed discretization algorithm for Big Data analytics based on evolutionary optimization. After comparing with a distributed discretizer based on the Minimum Description Length Principle, we have found that our solution yields more accurate and simpler solutions in reasonable time.

      PubDate: 2017-09-03T21:03:58Z
      DOI: 10.1016/j.swevo.2017.08.005
  • LONSA: A labeling-oriented non-dominated sorting algorithm for
           evolutionary many-objective optimization
    • Authors: R.F. Alexandre; C.H.N.R. Barbosa; J.A. Vasconcelos
      Abstract: Publication date: Available online 18 August 2017
      Source:Swarm and Evolutionary Computation
      Author(s): R.F. Alexandre, C.H.N.R. Barbosa, J.A. Vasconcelos
      Multiobjective algorithms are powerful in tackling complex optmization problems mathematically represented by two or more conflicting objective functions and their constraints. Sorting a set of current solutions across non-dominated fronts is the key step for the searching process to finally identify which ones are the best solutions. To perform that step, a high computational effort is demanded, especially if the size of the solution set is huge or the mathematical model corresponds to a many-objective problem. In order to overcome this, a new labeling-oriented algorithm is proposed in this paper to speed up the solution-to-front assignment by avoiding usual dominance tests. Along with this algorithm, called Labeling-Oriented Non-dominated Sorting Algorithm (LONSA), the associated methodology is carefully detailed to clearly explain how the classification of the solution set is successfully achieved. This work presents a comparison between LONSA and other well-known algorithms usually found in the literature. The simulation results have shown a better performance of the proposed algorithm against nine chosen strategies in terms of computational time as well as number of comparisons.

      PubDate: 2017-09-03T21:03:58Z
      DOI: 10.1016/j.swevo.2017.08.003
  • Improved gene expression programming to solve the inverse problem for
           ordinary differential equations
    • Authors: Kangshun Li; Yan Chen; Wei Li; Jun He; Yu Xue
      Abstract: Publication date: Available online 12 August 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Kangshun Li, Yan Chen, Wei Li, Jun He, Yu Xue
      Many complex systems in the real world evolve with time. These dynamic systems are often modeled by ordinary differential equations in mathematics. The inverse problem of ordinary differential equations is to convert the observed data of a physical system into a mathematical model in terms of ordinary differential equations. Then the model may be used to predict the future behavior of the physical system being modeled. Genetic programming has been taken as a solver of this inverse problem. Similar to genetic programming, gene expression programming could do the same job since it has a similar ability of establishing the model of ordinary differential systems. Nevertheless, such research is seldom studied before. This paper is one of the first attempts to apply gene expression programming for solving the inverse problem of ordinary differential equations. Based on a statistic observation of traditional gene expression programming, an improvement is made in our algorithm, that is, genetic operators should act more often on the dominant part of genes than on the recessive part. This may help maintain population diversity and also speed up the convergence of the algorithm. Experiments show that this improved algorithm performs much better than genetic programming and traditional gene expression programming in terms of running time and prediction precision.

      PubDate: 2017-09-03T21:03:58Z
      DOI: 10.1016/j.swevo.2017.07.005
  • An investigation into many-objective optimization on combinatorial
           problems: analyzing the pickup and delivery problem
    • Authors: Abel García-Nájera; Antonio López-Jaimes
      Abstract: Publication date: Available online 4 August 2017
      Source:Swarm and Evolutionary Computation
      Author(s): Abel García-Nájera, Antonio López-Jaimes
      Many-objective optimization focuses on solving optimization problems with four or more objectives. Effort has been made mainly on studying continuous problems, with interesting results and for which several proposals have appeared. An important result states that the problem does not necessarily becomes more difficult while more objectives are considered. Nevertheless, combinatorial problems have not received an appropriate attention, making this an open research area. This investigation takes this subject on by studying a many-objective combinatorial problem, particularly, the pickup and delivery problem (PDP), which is an important combinatorial optimization problem in the transportation industry and consists of finding a collection of routes with minimum cost. Traditionally, cost has been associated with the number of routes and the total travel distance, however, in many applications, some other objectives emerge, for example, travel time, workload imbalance, and uncollected profit. If we consider all these objectives equally important, PDP can be tackled as a many-objective problem. This study is concerned with the study of: (i) the performance of four representative multi-objective evolutionary algorithms on PDP varying the number of objectives, (ii) the properties of the many-objective PDP regarding scalability, i.e. the conflict between each pair of objectives and the proportion of non-dominated solutions as the number of objectives is varied, and finally (iii) the change of PDP's difficulty when the number of objectives is increased. Results show that the regarded objectives are actually in conflict and that the problem is more difficult to solve while more objectives are considered.

      PubDate: 2017-08-04T18:36:10Z
      DOI: 10.1016/j.swevo.2017.08.001
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-