The theory of evolutionary computation for discrete search spaces has made significant progress in the last ten years. This survey summarizes some of the most important recent results in this research area. It discuss...
详细信息
Health technology research brings together complementary interdisciplinary research skills in the development of innovative health technology applications. Recent research indicates that artificial intelligence can he...
详细信息
Health technology research brings together complementary interdisciplinary research skills in the development of innovative health technology applications. Recent research indicates that artificial intelligence can help achieve outstanding performance for particular types of health technology applications. An evolutionary algorithm is one of the subfields of artificial intelligence, and is an effective algorithm for global optimization inspired by biological evolution. With the rapidly growing complexity of design issues, methodologies and a higher demand for quality health technology applications, the development of evolutionary computation algorithms for health has become timely and of high relevance. This Special Issue intends to bring together researchers to report the recent findings in evolutionary algorithms in health technology.
In this paper, we introduce polygene-based evolution, a novel framework for evolutionary algorithms (EAs) that features distinctive operations in the evolutionary process. In traditional EAs, the primitive evolution...
详细信息
In this paper, we introduce polygene-based evolution, a novel framework for evolutionary algorithms (EAs) that features distinctive operations in the evolutionary process. In traditional EAs, the primitive evolution unit is a gene, wherein genes are independent components during evolution. In polygene-based evolutionary algorithms (PGEAs), the evolution unit is a polygene, i.e., a set of co-regulated genes. Discovering and maintaining quality polygenes can play an effective role in evolving quality individuals. Polygenes generalize genes, and PGEAs generalize EAs. Implementing the PGEA framework involves three phases: (Ⅰ) polygene discovery, (Ⅱ) polygene planting, and (Ⅲ) polygene-compatible evolution. For Phase I, we adopt an associative classificationbased approach to discover quality polygenes. For Phase Ⅱ, we perform probabilistic planting to maintain the diversity of individuals. For Phase Ⅲ, we incorporate polygenecompatible crossover and mutation in producing the next generation of individuals. Extensive experiments on function optimization benchmarks in comparison with the conventional and state-of-the-art EAs demonstrate the potential of the approach in terms of accuracy and efficiency improvement.
evolutionary bilevel algorithms are used for approximating the running resistance on the basis of the long-term fuel consumption data of a diesel passenger train in different routes. The input data comprises the geome...
详细信息
evolutionary bilevel algorithms are used for approximating the running resistance on the basis of the long-term fuel consumption data of a diesel passenger train in different routes. The input data comprises the geometry of these routes, speed and acceleration limits and certain engine properties. A running resistance is found for which the consumptions predicted by the model are equal to the logged consumptions of the vehicle for each of the routes in the training set. The model has been validated with simulated data with known properties and also with a diesel-hydraulic railcar operating on a 94 km route in northern Spain. The error in the running resistance estimation using evolutionary algorithms with respect to the measurement with a coasting test was less than 4%.
Due to the complexity of underlying data in a color image, retrieval of specific object features and relevant information becomes a complex task. Colour images have different color components and a variety of colour i...
详细信息
Due to the complexity of underlying data in a color image, retrieval of specific object features and relevant information becomes a complex task. Colour images have different color components and a variety of colour intensity which makes segmentation very challenging. In this paper we suggest a fitness function based on pixel-by-pixel values and optimize these values through evolutionary algorithms like differential evolution (DE), particle swarm optimization (PSO) and genetic algorithms (GA). The corresponding variants are termed GA-SA, PSO-SA and DE-SA;where SA stands for Segmentation Algorithm. Experimental results show that DE performed better in comparison of PSO and GA on the basis of computational time and quality of segmented image.
A correct thermal building design is a key issue on the viewpoint of energy-efficiency targets established by the United Nations Framework Convention on Climate Change. Dynamic energy simulation tools are often used t...
详细信息
A correct thermal building design is a key issue on the viewpoint of energy-efficiency targets established by the United Nations Framework Convention on Climate Change. Dynamic energy simulation tools are often used to predict the thermal performance of new buildings or to recommend energy retrofit packages for refurbishment. To reduce uncertainties in model input definition, the dynamic calibration models assumes a crucial role in the accuracy of energy modelling. Thus, the research goal consists in the development of a calibration approach to reduce the differences between building simulation and real monitored data (performance gap) using a hybrid evolutionary algorithm in dynamic building simulation. A University building has been monitored over one year and the registered data was used to calibrate the numerical model and to validate the calibration methodology proposed. The results attained reveal agreement between predicted and real data with a CV RMSE index attained between 4.5 and 5.4.
This article examines the effect of different configuration issues of the Multiobjective evolutionary algorithms on the efficient frontier formulation for the constrained portfolio optimization problem. We present the...
详细信息
This article examines the effect of different configuration issues of the Multiobjective evolutionary algorithms on the efficient frontier formulation for the constrained portfolio optimization problem. We present the most popular techniques for dealing with the complexities of the constrained portfolio optimization problem and experimentally analyse their strengths and weaknesses. In particular, we examine the efficient incorporation of complex real world constraints into the Multiobjective evolutionary algorithms and their corresponding effect on the efficient frontier formulation for the portfolio optimization problem. Moreover, we examine various constraint-handling approaches for the constrained portfolio optimization problem such as penalty functions and reparation operators and we draw conclusions about the efficacy of the examined approaches. We also examine the effect on the efficient frontier formulation by the application of different genetic operators and the relevant results are analysed. Finally, we address issues related with the various performance metrics that are applied for the evaluation of the derived solutions.
In this study, a single autonomous underwater vehicle (AUV) aims to rendezvous with a submerged leader recovery vehicle through a cluttered and variable operating field. The rendezvous problem is transformed into a No...
详细信息
In this study, a single autonomous underwater vehicle (AUV) aims to rendezvous with a submerged leader recovery vehicle through a cluttered and variable operating field. The rendezvous problem is transformed into a Nonlinear Optimal Control Problem (NOCP) and then numerical solutions are provided. A penalty function method is utilized to combine the boundary conditions, vehicular and environmental constraints with the performance index that is final rendezvous time. Four evolutionary based path planning methods namely Particle Swarm Optimization (PSO), Biogeography-Based Optimization (BBO), Differential Evolution (DE), and Firefly Algorithm (FA) are employed to establish a reactive planner module and provide a numerical solution for the proposed NOCP. The objective is to synthesize and analyze the performance and capability of the mentioned methods for guiding an AUV from an initial loitering point toward the rendezvous through a comprehensive simulation study. The proposed planner module entails a heuristic for refining the path considering situational awareness of environment, encompassing static and dynamic obstacles within a spatiotemporal current fields. The planner thus needs to accommodate the unforeseen changes in the operating field such as emergence of unpredicted obstacles or variability of current field and turbulent regions. The simulation results demonstrate the inherent robustness and efficiency of the proposed planner for enhancing a vehicle's autonomy so as to enable it to reach the desired rendezvous. The advantages and shortcoming of all utilized methods are also presented based on the obtained results. (C) 2017 Elsevier B.V. All rights reserved.
Selection functions enable evolutionary algorithms (EAs) to apply selection pressure to a population of individuals, by regulating the probability that an individual's genes survive, typically based on fitness. Va...
详细信息
Selection functions enable evolutionary algorithms (EAs) to apply selection pressure to a population of individuals, by regulating the probability that an individual's genes survive, typically based on fitness. Various conventional fitness based selection functions exist, each providing a unique method of selecting individuals based on their fitness, fitness ranking within the population, and/or various other factors. However, the full space of selection algorithms is only limited by max algorithm size, and each possible selection algorithm is optimal for some EA configuration applied to a particular problem class. Therefore, improved performance is likely to be obtained by tuning an EA's selection algorithm to the problem at hand, rather than employing a conventional selection function. This thesis details an investigation of the extent to which performance can be improved by tuning the selection algorithm. We do this by employing a Hyper-heuristic to explore the space of algorithms which determine the methods used to select individuals from the population. We show, with both a conventional EA and a Covariance Matrix Adaptation evolutionary Strategy, the increase in performance obtained with a tuned selection algorithm, versus conventional selection functions. Specifically, we measure performance on instances from several benchmark problem classes, including separate testing instances to show generalization of the improved performance. This thesis consists of work that was presented at the Genetic and evolutionary Computation Conference (GECCO) in 2018, as well as work that will be submitted to GECCO in 2019.
During millions of years, nature has developed patterns and processes with interesting characteristics. They have been used as inspiration for a significant number of innovative models that can be extended to solve co...
详细信息
During millions of years, nature has developed patterns and processes with interesting characteristics. They have been used as inspiration for a significant number of innovative models that can be extended to solve complex engineering and mathematical problems. One of the most famous patterns present in nature is the Golden Section (GS). It defines an especial proportion that allows the adequate formation, selection, partition, and replication in several natural phenomena. On the other hand, evolutionary algorithms (EAs) are stochastic optimization methods based on the model of natural evolution. One important process in these schemes is the operation of selection which exerts a strong influence on the performance of their search strategy. Different selection methods have been reported in the literature. However, all of them present an unsatisfactory performance as a consequence of the deficient relations between elitism and diversity of their selection procedures. In this paper, a new selection method for evolutionary computation algorithms is introduced. In the proposed approach, the population is segmented into several groups. Each group involves a certain number of individuals and a probability to be selected, which are determined according to the GS proportion. Therefore, the individuals are divided into categories where each group contains individual with similar quality regarding their fitness values. Since the possibility to choose an element inside the group is the same, the probability of selecting an individual depends exclusively on the group from which it belongs. Under these conditions, the proposed approach defines a better balance between elitism and diversity of the selection strategy. Numerical simulations show that the proposed method achieves the best performance over other selection algorithms, in terms of its solution quality and convergence speed. (C) 2018 Elsevier Ltd. All rights reserved.
暂无评论