Fate Agent EAs form a novel flavour or subclass in EC. The idea is to decompose the main loop of traditional evolutionary algorithms into three independently acting forces, implemented by the so-called Fate Agents, an...
详细信息
ISBN:
(纸本)9781450328814
Fate Agent EAs form a novel flavour or subclass in EC. The idea is to decompose the main loop of traditional evolutionary algorithms into three independently acting forces, implemented by the so-called Fate Agents, and create an evolutionary process by injecting these agents into a population of candidate solutions. This paper introduces an extension to the original concept, adding a mechanism to self-adapt the mutation of the Breeder Agents. The method improves the behaviour of the original Fate Agent EA on dynamically changing fitness landscapes.
Multi objective optimization evolutionary algorithms (MOEAs) play a crucial role in addressing multi-objective optimization problems (MOPs) in the field of artificial intelligence. However, MOEAs often struggle to sim...
详细信息
Many-objective Optimization problems (MaOPs), with four or more objectives are difficult to solve, is a kind of common optimization problems in actual industrial production. In recent years, a large number of many-obj...
详细信息
Solving bilevel multi-objective programming problems is one of the hardest tasks facing researchers in the optimization community. Bilevel multi-objective programming problems is an optimization problem consists of tw...
详细信息
Solving bilevel multi-objective programming problems is one of the hardest tasks facing researchers in the optimization community. Bilevel multi-objective programming problems is an optimization problem consists of two interconnected hierarchical multi-objective programming problems: upper-level problem and lower-level problem. Difficulty in solving bilevel multi objective programming problems is the need to solve lower-level multi-objective programming problem to know the feasible space of the upper-level problem. The proposed algorithm consists of two nested artificial multi-objective algorithms. One algorithm is for the upper-level problem and the other is for the lower-level problem. Also, the proposed algorithm is enriched with a k means cluster scheme in two phases. The first phase is before starting two nested algorithms to help the algorithm to start with more appropriates solutions to the bi-level problem. The second phase is within the two nested algorithms to guide the algorithm to the most preferred solutions to the upper-level decision-maker. The performance of the proposed algorithm has been evaluated on different test problems including low dimension and high dimension test problems. The experimental results show that the proposed algorithm is a feasible and efficient method for solving the bilevel multi-objective programming problem. (c) 2021 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University.
The El Ni & ntilde;o-Southern Oscillation (ENSO) is a complex and influential climate phenomenon critical to understanding global climate systems and enhancing climate predictions. Despite extensive research utili...
详细信息
The El Ni & ntilde;o-Southern Oscillation (ENSO) is a complex and influential climate phenomenon critical to understanding global climate systems and enhancing climate predictions. Despite extensive research utilizing both statistical methods and numerical models for accurate ENSO forecasting, significant gaps remain in practical applications. Therefore, we proposed a novel memory kernel function-based approach to solve the inverse problem of ENSO time-varying systems. This method involves constructing differential equations through memory vectors composed of multiple initial values, effectively capturing the system's evolutionary and trends. Unlike traditional inverse problem-solving methods, our research delved into the inherent properties exhibited by ENSO, such as memory and periodicity, and embedded these properties as specific targets in differential equations. By leveraging the flexibility of evolutionary algorithms to solve mathematical problems, we achieved a model targeted at ENSO and predicted at lead times up to 26 months. The results demonstrate that this scheme overcomes the limitations of traditional differential equations with a single initial value and extends these equations to memory vector equations based on multiple initial values. This not only enhances our ability to describe the evolutionary laws of complex systems but also improves the timeliness and reliability of ENSO predictions, achieving encouraging results.
Real world problems in various domains demonstrate different characteristics of changes over time. This is why several researchers have been interested in dynamic optimisation for the last two decades. Since changes o...
详细信息
Real world problems in various domains demonstrate different characteristics of changes over time. This is why several researchers have been interested in dynamic optimisation for the last two decades. Since changes occur over time in a dynamic optimisation problem, the goal of a related algorithm becomes tracking the changing optima over time. evolutionary algorithms and various swarm intelligence techniques have been adapted in the literature to solve dynamic optimisation problems. The Fireworks Algorithm (FWA) is a recently proposed swarm intelligence algorithm for global optimisation of complex static functions that simulates the explosion process of fireworks. Although a set of improvements over the conventional FWA are presented in the literature for the static optimisation problems, the most evident extension is the Enhanced Fireworks Algorithm (EFWA). In this paper, cost effective extensions of the EFWA are proposed for solving dynamic optimisation problems in continuous space. The performance evaluation of our EFWA-based algorithms is validated with the Moving Peaks Benchmark. Empirical studies on different benchmark instances clearly show the applicability of our extensions. Our EFWA-based extensions outperform the related work in terms of both quality of solution and computational cost for a large set of test instances of the benchmark.
In this article, we survey the current research trends of enhancement and denoising of depth-based motion capture data (D-Mocap) and also discuss possible future research issues. We first present the commonly used pro...
详细信息
In this article, we survey the current research trends of enhancement and denoising of depth-based motion capture data (D-Mocap) and also discuss possible future research issues. We first present the commonly used problem formulation for human motion enhancement. We then review related work and cover a broad set of methodologies including filtering based, learning based, and evolutionary based approaches. In addition, we present some important experiments-related issues, such as data creation or collection, reference data generation, and the metrics used for performance evaluation. It is our intent to provide a comprehensive tutorial and survey on the recent efforts on D-Mocap improvement, both methodologically and experimentally. By comparing the state-of-the-art methods, we also propose future research needs that could make D-Mocap more useful and relevant for real-world clinical applications.
evolutionary computation is attracting attention in the energy domain as an alternative to tackle inherent mathematical complexity of some problems related to high-dimensionality, non-linearity, non-convexity, multimo...
详细信息
evolutionary computation is attracting attention in the energy domain as an alternative to tackle inherent mathematical complexity of some problems related to high-dimensionality, non-linearity, non-convexity, multimodality, or discontinuity of the search space. In this context, the research community launched the 2020 "Competition on evolutionary Computation in the Energy Domain: Smart Grid Applications" and an associated simulation framework to evaluate the performance of state-of-the-art evolutionary algorithms solving real-world problems. The competition includes two testbeds: (1) Day-ahead energy resource management problem in smart grids under uncertain environments;and (2) Bi-level optimization of end-users' bidding strategies in local energy markets. This paper describes the general framework of the competition, the two testbeds, and the evolutionary algorithms that participated. A special section is dedicated to the winner approach, CUMDANCauchy++, a cellular Estimation Distribution Algorithm (EDA). A thorough analysis of the results reveals that, led by CUMDANCauchy++, the top three algorithms form a block of approaches all based on cellular EDAs. Moreover, for testbed 2, in which CUMDANCauchy++ did not achieve the best performance, the winner approach is also based on EDAs. The outcomes of the competition show that CUMDANCauchy++ is an effective algorithm solving both testbeds, and EDAs emerge as an algorithm class with promising performance for solving smart grid applications. (C) 2022 Elsevier B.V. All rights reserved.
Generative Adversarial Networks (GANs) have gained popularity due to their ability to produce realistic examples from existing data without any supervision. However, they are dependent on their hyperparameters, the tu...
详细信息
ISBN:
(纸本)9798400701207
Generative Adversarial Networks (GANs) have gained popularity due to their ability to produce realistic examples from existing data without any supervision. However, they are dependent on their hyperparameters, the tuning of which is usually a manual task. Additionally, the computing resources required for such training are also extremely high. In this paper, ATLAS - a Cloud-based Co-evolutionary Framework for training such adversarial networks using evolutionary algorithms is proposed. ATLAS views the GAN components (generator and discriminator) as in a predator-prey relationship and involves co-evolution as a method to address the challenges of overfitting, exploding/vanishing gradients and tunes the hyperparameters of both the components of the GAN. The ATLAS framework is designed to be customizable, and resource flexible to allow for set-up and easy usage for training complex adversarial networks in both distributed and cloud environments. Experiments testing ATLAS capability for anomaly detection were performed and the results show that ATLAS can consistently evolve and produce high-performance GAN models.
Simulation-optimization (S-O) is a well-regarded method for solving groundwater (GW) management problems. Although S-O has significantly improved the decision support system for GW management, it still lacks practical...
详细信息
Simulation-optimization (S-O) is a well-regarded method for solving groundwater (GW) management problems. Although S-O has significantly improved the decision support system for GW management, it still lacks practical applicability. As a result, many researchers have been improving its components, leading to slightly or significantly better performance. To understand these challenges efficiently, this article delves into principal components of S-O that offer in-depth critical insights into GW's sustainability. The discussed segments are divided into simulation models, optimization methods, categories and conceptualization of management problems, and the formulation of real-world objective functions. This review also examines surrogate-assisted simulation models to reduce computational challenges. Methods to address model uncertainty and decision-making in applying S-O for sustained yield problems are addressed. The review outlays critical steps in S-O methodology and recommends potential research directions to aid researchers in further enhancing the practicality of S-O.
暂无评论