查看更多>>摘要：Multimodal multi-objective optimization (MMO) can offer more elegant solutions and provide diverse decisions to decision-makers in real world optimization problems. Many multimodal evolutionary mechanisms have been proposed to explore and exploit two solution spaces (i.e. decision space and objective space) in recent years. However, most existing methods only use single evolutionary operator to generate offsprings and ignore the advantage of using hybrid evolutionary algorithm. Moreover, it is still a great challenge to balance the effectiveness and efficiency simultaneously in the evolutionary process of MMO. In view of this, an efficient Two-Archive model based multimodal evolutionary algorithm is proposed in this paper. Two parallel offspring generation mechanisms based on competitive particle swarm optimizer and differential evolution are applied to expand two solution spaces with different evolutionary requirements. Moreover, niching local search scheme and reverse vector mutation strategy play roles in achieving better convergence and diversity. Finally, 22 MMO test problems are used to validate the superiority of the proposed method by comparing it with 5 state-of-the-art MMO algorithms. The proposed method is also expanded to solve 9 feature selection problems for validating the effectiveness of the proposed method on real world applications. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：The main role of the optimal Generator Maintenance Scheduling (GMS) problem in power systems is to develop an optimal preventive maintenance scheduling of the generation part units. An optimal GMS provides power systems with higher operational reliability, extends the generators lifetime and reduces the cost of generators maintenance. The GMS problem is formulated as an optimisation problem. This problem should satisfy both load's power demand and workforce constraints with ensuring the reliability of power systems at economical operation cost. The GMS problem has been studied for many years when exact mathematical methods have been used in the past to reach exact solutions for small-scale problems. However, these conventional mathematical approaches have many limitations and they suffer from unreasonable computational efforts as system dimension increases. Traditional approximate methods have been adopted to overcome the limitations of exact methods for medium-scale power systems. However, they provide approximate solutions and they require a large computational effort for wide-area systems of big dimensions. Recently, modern methods based on metaheuristics optimisation have taken a long part to solve the GMS problem and to overcome the limitations of approximate methods. In this paper, a proposed Discrete Chaotic Jaya Optimisation (DCJO) algorithm is employed to perform the preventive maintenance scheduling of electric power systems generators. The proposed algorithm is based on a cooperation between the discrete Jaya optimisation algorithm and a proposed move rule based on Chaotic Local Search (CLS) technique to improve both exploration and exploitation phases. The GMS problem is modelled based on the reliability criterion of an objective function of a sum of the squares of the reserves of generation. The optimisation process is performed through minimising an evaluation function of a weighted sum of the objective function and the penalty function for violations of the constraints. The proposed approach has been tested in a 21-unit test system over a planned horizon of 52 weeks in which the peak load is 4739 MW and the maximum generation is 5688 MW and there is a total number of 35 workforce available per week to perform the maintenance tasks. The proposed method has been compared through several statistical tests with recent algorithms of the related works. The obtained results show the effectiveness of the proposed algorithm for solving the GMS problem as compared to other recent algorithms. This approach can be relied at the present upon to solve maintenance scheduling problems of generation units in power systems. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：The Coronavirus disease 2019 (COVID19) pandemic has led to a dramatic loss of human life worldwide and caused a tremendous challenge to public health. Immediate detection and diagnosis of COVID19 have lifesaving importance for both patients and doctors. The availability of COVID19 tests increased significantly in many countries, thereby provisioning a limited availability of laboratory test kits Additionally, the Reverse Transcription-Polymerase Chain Reaction (RT-PCR) test for the diagnosis of COVID 19 is costly and time-consuming. X-ray imaging is widely used for the diagnosis of COVID19. The detection of COVID19 based on the manual investigation of X-ray images is a tedious process. Therefore, computer-aided diagnosis (CAD) systems are needed for the automated detection of COVID19 disease. This paper proposes a novel approach for the automated detection of COVID19 using chest X-ray images. The Fixed Boundary-based Two-Dimensional Empirical Wavelet Transform (FB2DEWT) is used to extract modes from the X-ray images. In our study, a single X-ray image is decomposed into seven modes. The evaluated modes are used as input to the multiscale deep Convolutional Neural Network (CNN) to classify X-ray images into no-finding, pneumonia, and COVID19 classes. The proposed deep learning model is evaluated using the X-ray images from two different publicly available databases, where database A consists of 1225 images and database B consists of 9000 images. The results show that the proposed approach has obtained a maximum accuracy of 96% and 100% for the multiclass and binary classification schemes using X-ray images from dataset A with 5-fold cross validation (CV) strategy. For dataset B, the accuracy values of 97.17% and 96.06% are achieved using multiscale deep CNN for multiclass and binary classification schemes with 5-fold CV. The proposed multiscale deep learning model has demonstrated a higher classification performance than the existing approaches for detecting COVID19 using X-ray images. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：In this paper we present a model based on computational intelligence and natural language generation for the automatic generation of textual summaries from numerical data series, aiming to provide insights which help users to understand the relevant information hidden in the data. Our model includes a fuzzy temporal ontology with temporal references which addresses the problem of managing imprecise temporal knowledge, which is relevant in data series. We fully describe a real use case of application in the environmental information systems field, providing linguistic descriptions about the air quality index (AQI), which is a very well-known indicator provided by all meteorological agencies worldwide. We consider two different data sources of real AQI data provided by the official Galician (NW Spain) Meteorology Agency: (i) AQI distribution in the stations of the meteorological observation network and (ii) time series which describe the state and evolution of the AQI in each meteorological station. Both application models were evaluated following the current standards and good practices of manual human expert evaluation of the Natural Language Generation field. Assessment results by two experts meteorologists were very satisfactory, which empirically confirm that the proposed textual descriptions fit this type of data and service both in content and layout. (c) 2022 The Authors. Published by Elsevier B.V.This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by- nc- nd/4.0/).
查看更多>>摘要：With the increase in the volume of greenhouse gases and pollutants, supply chain managers have sought to design and set up networks that pay special attention to environmental factors besides the economic aspects. In this research, a three-level supply chain network is considered including one manufacturer, several retailers and several customers. Greenhouse gas emissions as an environmental issue, the dependence of demand on the selling price of products and cooperative advertising have been examined to design this network. Also, several transportation systems and production methods with different environmental effects and different costs have been considered. The problem has been modeled by both the general and advertising cost classification approaches. Each model has been linearized by McCormick and sequential linear programming methods, and in each approach, Stackelberg, Nash and cooperative games have been used to determine the relationship between members of the supply chain. Finally, an algorithm has been proposed from a combination of variable neighborhood search algorithm and mathematical modeling and after adjusting its parameters by Taguchi statistical method, Stackelberg, Nash and cooperative games have been implemented on it. The results of linearization methods and the meta-heuristic algorithm show that the profit of the manufacturers, retailers and the whole supply chain depends on the type of the game selected. The profit of the whole supply chain is greater in cooperative conditions than in non-cooperative conditions, and in non-cooperative games, the final profit of the manufacturer will be greater in Stackelberg game. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
查看更多>>摘要：This article presents the application of a learning-based optimization method to solve the Bus Synchronization Problem, a relevant problem in public transportation systems. The problem consists in synchronizing the timetable of buses to optimize the transfer of passengers between bus lines. A new problem model is proposed, extending previous formulations in the literature, and solved using Virtual Savant. Virtual Savant is a novel soft computing method inspired by the Savant Syndrome that combines machine learning and optimization to solve complex real-world problems in a massively parallel way. The proposed methodology is validated and evaluated over a set of synthetic and realistic instances based on the public transportation system of Montevideo, Uruguay, and compared against a reference evolutionary algorithm and the current solution defined by the city authorities. The main results indicate that Virtual Savant is able to compute accurate solutions and outperform baseline results in eleven out of fifteen realistic instances. This is the first reported research applying Virtual Savant to a problem with a high synergy between its decision variables. The obtained results suggest that it is a suitable tool for solving this kind of optimization problems. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
Yilmaz, Mustafa K.Kusakci, Ali OsmanAksoy, MineHacioglu, Umit...
16页
查看更多>>摘要：The demand for air transport services has significantly increased around the globe, which has brought new investments in airports, which, in turn, requires in-depth efficiency analysis of these capital intensive endeavors. This study examines the operational efficiencies of 46 Turkish civil airports from 2015 to 2018. We employ a novel hybrid methodology that combines Spherical Fuzzy Sets based Analytic Hierarchy Process (SFS-AHP) and Data Envelopment Analysis (DEA), which provides a solid basis for efficiency analysis. To this end, it can handle the hesitancy and uncertainty that the subjective evaluation process of input and output factors possess. Then, we use Self Organizing Maps (SOM), a machine learning method for clustering, to examine the effect of outlier airports on the efficiency scores. Finally, a posthoc analysis is conducted with Tobit regression model to assess the explanatory power of external factors on the efficiency scores, i.e., tourism potential, number of international flights, distance to the city center, population, public/private ownership, and age of airport. The findings show that 67.2% of the Turkish airports operate below the optimal efficiency level, and 93.5% of them should make considerable efforts to refine their operations by implementing managerial and structural changes to reduce input factors. The results also suggest that the airports located in high density touristic areas achieve higher efficiency levels. Those relatively closer to the city center lead to more airport traffic, generating more revenues. Thus, both factors have a significant impact on efficiency scores. The study provides a novel efficiency analysis framework for airport operators and policy makers that helps them make informed decisions. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
NSTL
Elsevier