Image segmentation consists of separating an image into regions that are entirely different from each other, and multilevel thresholding is a method used to perform this task. This article proposes an estimation of Di...
详细信息
Image segmentation consists of separating an image into regions that are entirely different from each other, and multilevel thresholding is a method used to perform this task. This article proposes an estimation of distribution algorithms (EDA) combined with a Differential Evolution (DE) operator as a metaheuristic to solve the multilevel thresholding problem. The proposal is called the Differential Mutation estimation of distribution algorithm (DMEDA), where the inclusion of the Differential Mutation increases the standard EDA's exploration capacity. The performance of the DMEDA for image segmentation is tested using Otsu's between-class variance and Kapur's entropy as objective functions applied separately over the Berkeley Segmentation Data Set 300 (BSDS300). Besides, a comparative study includes eight well-known algorithms in the literature. In this sense, statistical and non-parametric tests are performed to verify the efficiency of the DMEDA in solving the image segmentation problem from an optimization perspective. In terms of segmentation, different metrics are employed to verify the capabilities of the DMEDA to segment digital images properly. Regarding the two objective functions, the proposed DMEDA obtains better results in 97% of the experiments for Otsu's between-class variance and 85% for Kapur's entropy.
Distributed assembly permutation flow shop scheduling problem is the hot spot of distributed pipeline scheduling research;however, parallel assembly machines are often in the assembly stage. Therefore, we propose and ...
详细信息
Distributed assembly permutation flow shop scheduling problem is the hot spot of distributed pipeline scheduling research;however, parallel assembly machines are often in the assembly stage. Therefore, we propose and study distributed parallel assembly permutation flow shop scheduling problem (DPAPFSP). This aims to enhance the efficiency of multi-factory collaborative production in a networked environment. Initially, a corresponding mathematical model was established. Then, an improved hybrid distributionestimationalgorithm was proposed to minimize the makespan. The algorithm adopts a single-layer permutation encoding and decoding strategy based on the rule of the Earliest Finished Time. A local neighbourhood search based on critical paths is performed for the optimal solution using five types of neighborhood design. A dual sampling strategy based on repetition rates was introduced to ensure the diversity of the population in the later periods of iteration. Simulated annealing searching was applied to accelerate the decline of optimal value. Finally, we conduct simulation experiments using 900 arithmetic cases and compare the simulation experimental data of this algorithm with the other four existing algorithms. The analysis results demonstrate this improved algorithm is very effective and competitive in solving the considered DPAPFSP. The authors introduce the distributed parallel assembly permutation flow shop scheduling problem, aiming to enhance collaborative production efficiency among multiple factories in a networked environment. A mathematical model is established and an improved hybrid distributionestimationalgorithm is proposed to minimise the makespan. image
As a key production process in the steel industry, excellent scheduling of Steelmaking-refining-Continuous Casting (SCC) manufacturing process can improve production efficiency, shorten the steel production cycle, and...
详细信息
As a key production process in the steel industry, excellent scheduling of Steelmaking-refining-Continuous Casting (SCC) manufacturing process can improve production efficiency, shorten the steel production cycle, and reduce the production cost for steel enterprises. This paper presents a Characteristics-based estimation of distribution algorithm (CEDA) for the SCC scheduling problem in the real-world steel plants. Considering the processing characteristics of the continuous casting machine, a novel caster-based encoding scheme and an improved decoding scheme are proposed. Also, a distance concept is introduced to mitigate the impact of similar individuals on the probability model, and an importance-based probability model updating mechanism is designed to increase the impact of excellent individual on the probability model. Furthermore, an individual sampling scheme with enhanced probability is constructed to ensure continuous processing of the continuous casting machine as much as possible. Finally, this paper designs a limited insertion operation in the local search to address the exploitation of the proposed algorithm. Extensive numerical simulations demonstrate that the proposed CEDA for the SCC scheduling process is more efficient than some state-of-the-art algorithms in the literature.
Efficient allocating and scheduling emergency rescue tasks are a primary issue for emergency management. This paper considers emergency scheduling of rescue tasks under stochastic deterioration of the injured. First, ...
详细信息
Efficient allocating and scheduling emergency rescue tasks are a primary issue for emergency management. This paper considers emergency scheduling of rescue tasks under stochastic deterioration of the injured. First, a mathematical model is established to minimize the average mathematical expectation of all tasks' completion time and casualty loss. Second, an improved multi-objective estimation of distribution algorithm (IMEDA) is proposed to solve this problem. In the IMDEA, an effective initialization strategy is designed for obtaining a superior population. Then, three statistical models are constructed, which include two tasks existing in the same rescue team, the probability of first task being processed by a rescue team, and the adjacency between two tasks. Afterward, an improved sampling method based on referenced sequence is employed to efficiently generate offspring population. Three multi-objective local search methods are presented to improve the exploitation in promising areas around elite individuals. Furthermore, the parameter calibration and effectiveness of components of IMEDA are tested through experiments. Finally, the comprehensive comparison with state-of-the-art multi-objective algorithms demonstrates that IMEDA is a high-performing approach for the considered problem.
In this study, a flexible job shop scheduling problem with time-of-use electricity price constraint is considered. The problem includes machine processing speed, setup time, idle time, and the transportation time betw...
详细信息
In this study, a flexible job shop scheduling problem with time-of-use electricity price constraint is considered. The problem includes machine processing speed, setup time, idle time, and the transportation time between machines. Both maximum completion time and total electricity price are optimized simultaneously. A hybrid multi-objective optimization algorithm of estimation of distribution algorithm and deep Q-network is proposed to solve this. The processing sequence, machine assignment, and processing speed assignment are all described using a three-dimensional solution representation. Two knowledge-based initialization strategies are designed for better performance. In the estimation of distribution algorithm component, three probability matrices corresponding to solution representation are provided. In the deep Q-network component, 34 state features are selected to describe the scheduling situation, while nine knowledge-based actions are defined to refine the scheduling solution, and the reward based on the two objectives is designed. As the knowledge for initialization and optimization strategies, five properties of the considered problem are proposed. The proposed mixed integer linear programming model of the problem is validated by exact solver CPLEX. The results of the numerical testing on wide-range scale instances show that the proposed hybrid algorithm is efficient and effective at solving the integrated flexible job shop scheduling problem.
With the enormous increase in energy usage by cloud data centers for handling various workflow applications, the energy-aware cloud workflow scheduling has become a hot issue. However, there is still a need and room f...
详细信息
With the enormous increase in energy usage by cloud data centers for handling various workflow applications, the energy-aware cloud workflow scheduling has become a hot issue. However, there is still a need and room for improvement in both the model for estimating workflow energy consumption and the algorithm for energy-aware cloud workflow scheduling. To fill these gaps, a new model for estimating the energy consumption of the cloud workflow execution and a novel Two-Stage estimation of distribution algorithm with heuristics (TSEDA) for energy-aware cloud workflow scheduling are proposed based on the relationships among scheduling scheme, host load and power. In particular, in the proposed TSEDA, a new probability model and its updating mechanism are presented, and a two-stage coevolution strategy with some novel heuristic methods for individual generation, decoding and improvement is designed. Extensive experiments are conducted on workflow applications with various sizes and types, and the results show that the proposed TSEDA outperforms conventional algorithms.
The estimation of distribution algorithm (EDA) has recently emerged as a promising alternative to the traditional evolutionary algorithms for solving combinatorial optimization problems. In this paper, an estimation o...
详细信息
The estimation of distribution algorithm (EDA) has recently emerged as a promising alternative to the traditional evolutionary algorithms for solving combinatorial optimization problems. In this paper, an estimation of distribution algorithm with multiple intensification strategies (EDA-MIS) is proposed to solve a typical kind of hybrid flow-shop scheduling problem. The two-stage heterogeneous hybrid flow-shop scheduling problem is investigated. The sequence-dependent setup time at the first stage is also considered. In the proposed EDA-MIS, the initial population is constructed through the heuristic method and random strategy. An order matrix is established to estimate the probabilistic model of promising solutions. Then the solutions of the algorithm are evolved through the processes of selection, recombination, sampling, and local search. The obtained results indicate that the EDA-MIS provides good solutions in the aspects of solution quality and computational efficiency.
The canonical estimation of distribution algorithm (EDA) easily falls into a local optimum with an ill-shaped population distribution, which leads to weak convergence performance and less stability when solving global...
详细信息
The canonical estimation of distribution algorithm (EDA) easily falls into a local optimum with an ill-shaped population distribution, which leads to weak convergence performance and less stability when solving global optimization problems. To overcome this defect, we explore a novel EDA variant with an ensemble of three distribution modification strategies, i.e., archive-based population updating (APU), multileader-based search diversification (MSD), and the triggered distribution shrinkage (TDS) strategy, named E-3-EDA. The APU strategy utilizes historical population information to rebuild the search scope and avoid ill-shaped distributions. Moreover, it continuously updates the archive to avoid overfitting the distribution model. The MSD makes full use of the location differences among populations to evolve the sampling toward promising regions. TDS is triggered when the search stagnates, shrinking the distribution scope to achieve local exploitation. Additionally, the E-3-EDA performance is evaluated using the CEC 2014 and CEC 2018 test suites on 10-dimensional, 30-dimensional, 50-dimensional and 100-dimensional problems. Moreover, several prominent EDA variants and other top methods from CEC competitions are comprehensively compared with the proposed method. The competitive performance of E-3-EDA in solving complex problems is supported by the nonparametric test results.
The complex optimization problems have been investigated deeply by researchers in the optimization community. The estimation of distribution algorithm (EDA) and the monarch butterfly optimization algorithm (MBO) are m...
详细信息
ISBN:
(纸本)9798350349184;9798350349191
The complex optimization problems have been investigated deeply by researchers in the optimization community. The estimation of distribution algorithm (EDA) and the monarch butterfly optimization algorithm (MBO) are meta-heuristic algorithms that attracted wide attention. In this study, an improved algorithm based on estimation of distribution of algorithm combined with Monarch Butterfly Optimization algorithm named EDMBO is proposed. The weighted average of candidate solutions is embedded to estimate the mean value. A linear search strategy is introduced to enhance the exploitation of the algorithm. The CEC 2017 benchmark test suite is adopted to verify the performance of the algorithm. The experimental results show that the EDMBO is competitive.
The energy-efficient distributed heterogeneous flexible job shop scheduling problem (DHFJSP), incorporating green objectives and multi-factory production models, is a widespread but challenging problem in the manufact...
详细信息
ISBN:
(纸本)9789819755776;9789819755783
The energy-efficient distributed heterogeneous flexible job shop scheduling problem (DHFJSP), incorporating green objectives and multi-factory production models, is a widespread but challenging problem in the manufacturing industry. A reinforcement learning-based estimation of distribution algorithm (RLEDA) is proposed to solve the energy-efficient DHFJSP while minimizing the makespan and total energy consumption (TEC). A hybrid heuristic initialization method is devised to obtain a high-quality population. Two probabilistic models are employed to generate new solutions based on the characteristics of the sub-problems to avoid premature convergence. The Q-learning-based population learning rate adaptive mechanism adjusts the degree of learning information from dominant individuals to improve the distribution of the population. Thirty instances of different scales are utilized to evaluate the effectiveness of the RLEDA. The experimental results show that the RLEDA outperforms the comparison algorithms in solving energy-efficient DHFJSP.
暂无评论