Feature subset selection (FSS) employing a wrapper approach is fundamentally a combinatorial optimization problem maximizing the area under the receiver operating characteristic curve (AUC) of a classifier built on th...
详细信息
Feature subset selection (FSS) employing a wrapper approach is fundamentally a combinatorial optimization problem maximizing the area under the receiver operating characteristic curve (AUC) of a classifier built on this subset under single objective environment. To balance both the AUC and the cardinality of the selected feature subset, we propose a novel multiplicative fitness function that combines AUC and a decreasing function of cardinality. Although the differential evolution algorithm is robust, it is prone to premature convergence, which can result in entrapment in local optima. To address this challenge, we propose chaotic binary differential evolution coupled with feature-level elitism (CE-BDE), where the chaotic maps are introduced at the initialization and the crossover operator. We also introduce feature-level elitism to improve the exploitation capability. Feature-level elitism involves preserving those features, which are chosen based on their frequency of occurrence in the population in the evolution process. Dealing with big data entails computational complexity, which motivates us to propose an effective parallel/ distributed strategy island model. The results demonstrate that the parallel CE-BDE outperformed the rest of the algorithms in terms of mean AUC and cardinality. The speedup and computational gain yielded by the proposed parallel approach further accentuate its superiority. Overall, the topperforming algorithm with the multiplicative fitness function turned out to be statistically significant compared to that with the additive fitness function across 5 out of 6 datasets.
Current model-based methods for monitoring photovoltaic (PV) modules typically rely on the single-diode model (SDM) or its variants, assuming uniform operating conditions across the module. However, these ideal condit...
详细信息
Current model-based methods for monitoring photovoltaic (PV) modules typically rely on the single-diode model (SDM) or its variants, assuming uniform operating conditions across the module. However, these ideal conditions are difficult to realize in real-world applications due to partial shading, soiling, degradation, and other phenomena. This paper proposes a 7-parameter self-adapting Double SDM model (D-SDM) to enhance the accuracy and reliability of parameter identification in PV modules under real operating conditions. A robust methodology based on evolutionary algorithms is proposed to estimate the parameters of the D-SDM, directly from the I-V characteristic of a PV module, applicable in both uniform and mismatched scenarios. The proposed methodology also includes a robust fitting error calculation that only considers the section of the I-V curve where all the cells operate with positive voltage. The methodology is validated using experimental and simulated I-V curves across various mismatching patterns, demonstrating the superior stability and reliability of the proposed method, which can be used for PV system monitoring and diagnosis in complex conditions.
evolutionary algorithms (EA) usually carry out an efficient exploration of the search-space, but get often trapped in local minima and do not prove the optimality of the solution. Interval-based techniques, on the oth...
详细信息
ISBN:
(纸本)9783319116839;9783319116822
evolutionary algorithms (EA) usually carry out an efficient exploration of the search-space, but get often trapped in local minima and do not prove the optimality of the solution. Interval-based techniques, on the other hand, yield a numerical proof of optimality of the solution. However, they may fail to converge within a reasonable time due to their exponential complexity and their inability to quickly compute a good approximation of the global minimum. The contribution of this paper is a hybrid algorithm called Charibde in which a particular EA, Differential Evolution, cooperates with a branch and bound algorithm endowed with interval propagation techniques. It prevents premature convergence toward local optima and is highly competitive with both deterministic and stochastic existing approaches. We demonstrate its efficiency on a benchmark of highly multimodal problems, for which we provide previously unknown global minima and certification of optimality.
Increasing sediment yield is one of the important environmental challenges in river basins resulting from changing land *** current study develops an adaptive neuro fuzzy inference system(ANFIS)hy-bridized with evolut...
详细信息
Increasing sediment yield is one of the important environmental challenges in river basins resulting from changing land *** current study develops an adaptive neuro fuzzy inference system(ANFIS)hy-bridized with evolutionary algorithms to predict annual sediment yield at the catchment scale consid-ering some key factors affecting the alteration of the sediment *** key factors consist of the area of the sub-catchments,average slope of the sub-catchments,rainfall,and forest index,and the output of the model is sediment *** indices such as the Nash-Sutcliffe efficiency(NSE),root mean square error and vulnerability index(Ⅵ)were applied to evaluate the performance of the ***,hybrid models were compared in terms of complexities to select the best *** on the results in Talar River basin in Iran,several hybrid models in which particle swarm optimization(PSO),genetic algorithm,invasive weed optimization,biogeography-based optimization,and shuffled complex evolu-tion used to train the neuro fuzzy network are able to generate reliable sediment yield *** NSE of all previously listed models is more than 0.8 which means they are robust for assessing sediment yield resulting from land use change with a focus on *** proposed models are fairly similar in terms of computational complexities which implies no priority for selecting the best ***,PSO-ANFIS performed slightly better than the other models especially in terms of accuracy of the outputs due to a high NSE(0.92)and a low Ⅵ(1.9 Mg/ha).Using the proposed models is recommended due to the lower required time and data compared to a physically based models such as the The Soil and Water Assessment ***,some drawbacks restrict the application of the proposed *** example,the proposed models cannot be used for small temporal scales.
This paper concerns methodology for exploiting the multi-objective Extremal Optimization for load-balancing algorithms in high-performance distributed systems. In clusters and data centers, there has always been a tra...
详细信息
This paper concerns methodology for exploiting the multi-objective Extremal Optimization for load-balancing algorithms in high-performance distributed systems. In clusters and data centers, there has always been a tradeoff between contradictory goals such as obtaining high performance, reducing inter-node communication, task or virtual machine migration, and energy savings. Thus, a multi-objective optimization strategy should be provided based on task migration to achieve an efficient processor load balance in the executive distributed environment, which is an NP-hard computational problem. The paper proposes anew selection scheme for the final load-balanced solution in the Pareto front. In this gradient-supported scheme, we examine lexicographic solutions relaxed by a margin of allowable loss, provided that the remaining optimization criteria are improved. This has been achieved by calculating the gradients of the tangent lines connecting the analyzed lexicographic solutions and the subsequent Pareto front points. The algorithm has been evaluated by comparative simulation experiments with application program graphs run in distributed systems. The evaluation, which included a comparison with a genetic algorithm, confirmed the very good performance of the proposed gradient-based Pareto front selection method.
Multi-objective evolutionary algorithms suffer from performance degradation when solving dynamic multi- objective optimization problems (DMOPs) with a new conditional configuration from scratch, which motivates the re...
详细信息
Multi-objective evolutionary algorithms suffer from performance degradation when solving dynamic multi- objective optimization problems (DMOPs) with a new conditional configuration from scratch, which motivates the research on knowledge extraction. However, most knowledge extraction strategies only focus on obtaining effective information from a single knowledge source, while ignoring the useful information from other knowledge sources with similar properties. Motivated by this, a weighted multi-source knowledge extraction strategy-based dynamic multiobjective evolutionary algorithm is proposed. First, a similarity criterion based on angle information is constructed to quantify similarity between different source domains and the target domain. Second, a knowledge extraction technique is developed to select a specific number of individuals from each source domain using a distance metric. Third, a generation strategy based on dynamic weighting mechanism is proposed, which generates a certain number of individuals and merges these individuals into the initial population within the new environment. Finally, the comprehensive experiments are conducted on public DMOP benchmarks and demonstrate the devised method significantly outperforms the state-of-the-art competing algorithms.
Hyperparameter optimization (HPO) and neural architecture search (NAS) have developed dramatically with the evolution of deep neural networks (DNNs). HPO and NAS require DNN training when evaluating a set of hyperpara...
详细信息
Hyperparameter optimization (HPO) and neural architecture search (NAS) have developed dramatically with the evolution of deep neural networks (DNNs). HPO and NAS require DNN training when evaluating a set of hyperparameters and a network architecture, respectively. Therefore, these tasks impose expensive computational time because the objective function is repeatedly evaluated during the search process. To expedite this process, multi-fidelity optimization algorithms have been developed for efficient optimization by exploiting a cheap-to-evaluate low-fidelity objective function. Furthermore, population-based algorithms, such as genetic algorithms and evolution strategies, that leverage parallel processing are also employed to hasten optimization. In this paper, we propose anew algorithm, referred to as parameter-free dynamic fidelity selection (PF-DFS), for efficiently performing HPO and NAS when using the ranking-based evolutionary algorithms. We present an evaluation of the effectiveness of PF-DFS with two prominent ranking-based evolutionary algorithms on 38 multi-fidelity optimization problems of HPO and NAS. Our experimental results demonstrate that PF-DFS accelerates the search speed by 2.5%-24.9% while maintaining the quality of the obtained solutions, as compared to the optimizers without PF-DFS. Furthermore, we demonstrate that CMA-ES with PF-DFS outperforms Hyperband and DEHB (combining differential evolution with Hyperband), widelyused/state-of-the-art multi-fidelity optimization algorithms, in HPO for classification and segmentation tasks of real-world scenarios.
The increasing global demand for sustainable and cleaner transportation has led to extensive research on alternative fuels for Internal Combustion (IC) engines. One promising option is the utilization of methane/hydro...
详细信息
The increasing global demand for sustainable and cleaner transportation has led to extensive research on alternative fuels for Internal Combustion (IC) engines. One promising option is the utilization of methane/hydrogen blends in Spark-Ignition (SI) engines due to their potential to reduce Green House Gas (GHG) emissions and improve engine performance. However, the optimal operation of such an engine is challenging due to the interdependence of multiple conflicting objectives, including Brake Mean Effective Pressure (BMEP), Brake Specific Fuel Consumption (BSFC), and nitrogen oxide (NOx) emissions. This paper proposes an evolutionary optimization algorithm that employs a surrogate model as a fitness function to optimize methane/hydrogen SI engine performance and emissions. To create the surrogate model, we propose a novel ensemble learning algorithm that consists of several base learners. This paper employs ten different learning algorithms diversified via the Wagging method to create a pool of base-learner algorithms. This paper proposes a combinatorial evolutionary pruning algorithm to select an optimal subset of learning algorithms from a pool of base learners for the final ensemble algorithm. Once the base learners are designed, they are incorporated into an ensemble, where their outputs are aggregated using a weighted voting scheme. The weights of these base learners are optimized through a gradient descent algorithm. However, when optimizing a problem using surrogate models, the fitness function is subject to approximation uncertainty. To address this issue, this paper introduces an uncertainty reduction algorithm that performs averaging within a sphere around each solution. Experiments are performed to compare the proposed ensemble learning algorithm to the classical learning algorithms and state-of-the-art ensemble algorithms. Also, the proposed smoothing algorithm is compared with the state-ofthe-art evolutionary algorithms. Experimental studies suggest th
This paper puts forward a proposal for combining multi-operator evolutionary algorithms (EAs), in which three EAs, each with multiple search operators, are used. During the evolution process, the algorithm gradually e...
详细信息
ISBN:
(纸本)9781479914883
This paper puts forward a proposal for combining multi-operator evolutionary algorithms (EAs), in which three EAs, each with multiple search operators, are used. During the evolution process, the algorithm gradually emphasizes on the best performing multi-operator EA, as well as the search operator. The proposed algorithm is tested on the CEC2014 single objective real-parameter competition. The results show that the proposed algorithm has the ability to reach good solutions.
In this paper, we present a cosimulation environment that seamlessly integrates design and simulation tools used for mechanical parts design and optimization. The proposed environment enables use of tools from differe...
详细信息
ISBN:
(纸本)9781479928064
In this paper, we present a cosimulation environment that seamlessly integrates design and simulation tools used for mechanical parts design and optimization. The proposed environment enables use of tools from different vendors in addition to the developer's own developed tools. This way, the individual parts or components of the mechanical assembly no longer need to be designed, simulated, and optimized apart from each other. Furthermore, integrated cosimulation facilitates developing the integration methodology for the design, test and parameter optimization of these components. Within the presented environment, an evolutionary optimization method is applied to a novel four bar steering mechanism. It is used to evolve its morphology that requires minimal steering forces. A precise cosimulation is used to dynamically model the assembly, all constraints, and to evaluate each morphology by analyzing the required forces for accomplishing a desired steering maneuver.
暂无评论