Search results

1 – 10 of over 10000
Open Access
Article
Publication date: 3 August 2020

Rajashree Dash, Rasmita Rautray and Rasmita Dash

Since the last few decades, Artificial Neural Networks have been the center of attraction of a large number of researchers for solving diversified problem domains. Due to…

Abstract

Since the last few decades, Artificial Neural Networks have been the center of attraction of a large number of researchers for solving diversified problem domains. Due to its distinguishing features such as generalization ability, robustness and strong ability to tackle nonlinear problems, it appears to be more popular in financial time series modeling and prediction. In this paper, a Pi-Sigma Neural Network is designed for foretelling the future currency exchange rates in different prediction horizon. The unrevealed parameters of the network are interpreted by a hybrid learning algorithm termed as Shuffled Differential Evolution (SDE). The main motivation of this study is to integrate the partitioning and random shuffling scheme of Shuffled Frog Leaping algorithm with evolutionary steps of a Differential Evolution technique to obtain an optimal solution with an accelerated convergence rate. The efficiency of the proposed predictor model is actualized by predicting the exchange rate price of a US dollar against Swiss France (CHF) and Japanese Yen (JPY) accumulated within the same period of time.

Details

Applied Computing and Informatics, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2634-1964

Keywords

Click here to view access options
Article
Publication date: 3 June 2020

Adam Basílio, Fran Sérgio Lobato and Fábio de Oliveira Arouca

The study of heat transfer mechanisms is an area of great interest because of various applications that can be developed. Mathematically, these phenomena are usually…

Abstract

Purpose

The study of heat transfer mechanisms is an area of great interest because of various applications that can be developed. Mathematically, these phenomena are usually represented by partial differential equations associated with initial and boundary conditions. In general, the resolution of these problems requires using numerical techniques through discretization of boundary and internal points of the domain considered, implying a high computational cost. As an alternative to reducing computational costs, various approaches based on meshless (or meshfree) methods have been evaluated in the literature. In this contribution, the purpose of this paper is to formulate and solve direct and inverse problems applied to Laplace’s equation (steady state and bi-dimensional) considering different geometries and regularization techniques. For this purpose, the method of fundamental solutions is associated to Tikhonov regularization or the singular value decomposition method for solving the direct problem and the differential Evolution algorithm is considered as an optimization tool for solving the inverse problem. From the obtained results, it was observed that using a regularization technique is very important for obtaining a reliable solution. Concerning the inverse problem, it was concluded that the results obtained by the proposed methodology were considered satisfactory, as even with different levels of noise, good estimates for design variables in proposed inverse problems were obtained.

Design/methodology/approach

In this contribution, the method of fundamental solution is used to solve inverse problems considering the Laplace equation.

Findings

In general, the proposed methodology was able to solve inverse problems considering different geometries.

Originality/value

The association between the differential evolution algorithm and the method of fundamental solutions is the major contribution.

Click here to view access options
Article
Publication date: 17 March 2021

Eslam Mohammed Abdelkader

Cracks on surface are often identified as one of the early indications of damage and possible future catastrophic structural failure. Thus, detection of cracks is vital…

Abstract

Purpose

Cracks on surface are often identified as one of the early indications of damage and possible future catastrophic structural failure. Thus, detection of cracks is vital for the timely inspection, health diagnosis and maintenance of infrastructures. However, conventional visual inspection-based methods are criticized for being subjective, greatly affected by inspector's expertise, labor-intensive and time-consuming.

Design/methodology/approach

This paper proposes a novel self-adaptive-based method for automated and semantic crack detection and recognition in various infrastructures using computer vision technologies. The developed method is envisioned on three main models that are structured to circumvent the shortcomings of visual inspection in detection of cracks in walls, pavement and deck. The first model deploys modified visual geometry group network (VGG19) for extraction of global contextual and local deep learning features in an attempt to alleviate the drawbacks of hand-crafted features. The second model is conceptualized on the integration of K-nearest neighbors (KNN) and differential evolution (DE) algorithm for the automated optimization of its structure. The third model is designated for validating the developed method through an extensive four layers of performance evaluation and statistical comparisons.

Findings

It was observed that the developed method significantly outperformed other crack and detection models. For instance, the developed wall crack detection method accomplished overall accuracy, F-measure, Kappa coefficient, area under the curve, balanced accuracy, Matthew's correlation coefficient and Youden's index of 99.62%, 99.16%, 0.998, 0.998, 99.17%, 0.989 and 0.983, respectively.

Originality/value

Literature review lacks an efficient method which can look at crack detection and recognition of an ensemble of infrastructures. Furthermore, there is absence of systematic and detailed comparisons between crack detection and recognition models.

Details

Smart and Sustainable Built Environment, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2046-6099

Keywords

Click here to view access options
Article
Publication date: 18 May 2020

Abhishek Dixit, Ashish Mani and Rohit Bansal

Feature selection is an important step for data pre-processing specially in the case of high dimensional data set. Performance of the data model is reduced if the model is…

Abstract

Purpose

Feature selection is an important step for data pre-processing specially in the case of high dimensional data set. Performance of the data model is reduced if the model is trained with high dimensional data set, and it results in poor classification accuracy. Therefore, before training the model an important step to apply is the feature selection on the dataset to improve the performance and classification accuracy.

Design/methodology/approach

A novel optimization approach that hybridizes binary particle swarm optimization (BPSO) and differential evolution (DE) for fine tuning of SVM classifier is presented. The name of the implemented classifier is given as DEPSOSVM.

Findings

This approach is evaluated using 20 UCI benchmark text data classification data set. Further, the performance of the proposed technique is also evaluated on UCI benchmark image data set of cancer images. From the results, it can be observed that the proposed DEPSOSVM techniques have significant improvement in performance over other algorithms in the literature for feature selection. The proposed technique shows better classification accuracy as well.

Originality/value

The proposed approach is different from the previous work, as in all the previous work DE/(rand/1) mutation strategy is used whereas in this study DE/(rand/2) is used and the mutation strategy with BPSO is updated. Another difference is on the crossover approach in our case as we have used a novel approach of comparing best particle with sigmoid function. The core contribution of this paper is to hybridize DE with BPSO combined with SVM classifier (DEPSOSVM) to handle the feature selection problems.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 13 no. 2
Type: Research Article
ISSN: 1756-378X

Keywords

Click here to view access options
Article
Publication date: 9 December 2020

Tintu Mary John and Shanty Chacko

This paper aims to concentrate on an efficient finite impulse response (FIR) filter architecture in combination with the differential evolution ant colony algorithm…

Abstract

Purpose

This paper aims to concentrate on an efficient finite impulse response (FIR) filter architecture in combination with the differential evolution ant colony algorithm (DE-ACO). For the design of FIR filter, the evolutionary algorithm (EA) is found to be very efficient because of its non-conventional, nonlinear, multi-modal and non-differentiable nature. While focusing with frequency domain specifications, most of the EA techniques described with the existing systems diverge from the power related matters.

Design/methodology/approach

The FIR filters are extensively used for many low power, low complexities, less area and high speed digital signal processing applications. In the existing systems, various FIR filters have been proposed to focus on the above criterion.

Findings

In the proposed method, a novel DE-ACO is used to design the FIR filter. It focuses on satisfying the economic power utilization and also the specifications in the frequency domain.

Originality/value

The proposed DE-ACO gives outstanding performance with a strong ability to find optimal solution, and it has got quick convergence speed. The proposed method also uses the Software integrated synthesis environment (ISE) project navigator (p.28xd) for the simulation of FIR filter based on DE-ACO techniques.

Details

Circuit World, vol. 47 no. 3
Type: Research Article
ISSN: 0305-6120

Keywords

Click here to view access options
Article
Publication date: 6 July 2015

Ismaila Bayo Tijani, Rini Akmeliawati, Ari Legowo and Agus Budiyono

– The purpose of this paper is to develop a multiobjective differential evolution (MODE)-based extended H-infinity controller for autonomous helicopter control.

Abstract

Purpose

The purpose of this paper is to develop a multiobjective differential evolution (MODE)-based extended H-infinity controller for autonomous helicopter control.

Design/methodology/approach

Development of a MATLAB-based MODE suitable for controller synthesis. Formulate the H-infinity control scheme as an extended H-infinity loop shaping design procedure (H -LSDP) with incorporation of v-gap metric for robustness to parametric variation. Then apply the MODE-based algorithm to optimize the weighting function of the control problem formulation for optimal performance.

Findings

The proposed optimized H-infinity control was able to yield set of Pareto-controller candidates with optimal compromise between conflicting stability and time-domain performances required in autonomous helicopter deployment. The result of performance evaluation shows robustness to parameter variation of up to 20 per cent variation in nominal values, and in addition provides satisfactory disturbance rejection to wind disturbance in all the three axes.

Research limitations/implications

The formulated H-infinity controller is limited to hovering and low speed flight envelope. The optimization is focused on weighting function parameters for a given fixed weighting function structure. This thus requires a priori selection of weighting structures.

Practical implications

The proposed MODE-infinity controller algorithm is expected to ease the design and deployment of the robust controller in autonomous helicopter application especially for practicing engineer with little experience in advance control parameters tuning. Also, it is expected to reduce the design cycle involved in autonomous helicopter development. In addition, the synthesized robust controller will provide effective hovering/low speed autonomous helicopter flight control required in many civilian unmanned aerial vehicle (UAV) applications.

Social implications

The research will facilitate the deployment of low-cost, small-scale autonomous helicopter in various civilian applications.

Originality/value

The research addresses the challenges involved in selection of weighting function parameters for H-infinity control synthesis to satisfy conflicting stability and time-domain objectives. The problem of population initialization and objectives function computation in the conventional MODE algorithm are addressed to ensure suitability of the optimization algorithm in the formulated H-infinity controller synthesis.

Details

Aircraft Engineering and Aerospace Technology: An International Journal, vol. 87 no. 4
Type: Research Article
ISSN: 0002-2667

Keywords

Click here to view access options
Article
Publication date: 13 September 2021

Manik Chandra and Rajdeep Niyogi

This paper aims to solve the web service selection problem using an efficient meta-heuristic algorithm. The problem of selecting a set of web services from a large-scale…

Abstract

Purpose

This paper aims to solve the web service selection problem using an efficient meta-heuristic algorithm. The problem of selecting a set of web services from a large-scale service environment (web service repository) while maintaining Quality-of-Service (QoS), is referred to as web service selection (WSS). With the explosive growth of internet services, managing and selecting the proper services (or say web service) has become a pertinent research issue.

Design/methodology/approach

In this paper, to address WSS problem, the authors propose a new modified fruit fly optimization approach, called orthogonal array-based learning in fruit fly optimizer (OL-FOA). In OL-FOA, they adopt a chaotic map to initialize the population; they add the adaptive DE/best/2mutation operator to improve the exploration capability of the fruit fly approach; and finally, to improve the efficiency of the search process (by reducing the search space), the authors use the orthogonal learning mechanism.

Findings

To test the efficiency of the proposed approach, a test suite of 2500 web services is chosen from the public repository. To establish the competitiveness of the proposed approach, it compared against four other meta-heuristic approaches (including classical as well as state-of-the-art), namely, fruit fly optimization (FOA), differential evolution (DE), modified artificial bee colony algorithm (mABC) and global-best ABC (GABC). The empirical results show that the proposed approach outperforms its counterparts in terms of response time, latency, availability and reliability.

Originality/value

In this paper, the authors have developed a population-based novel approach (OL-FOA) for the QoS aware web services selection (WSS). To justify the results, the authors compared against four other meta-heuristic approaches (including classical as well as state-of-the-art), namely, fruit fly optimization (FOA), differential evolution (DE), modified artificial bee colony algorithm (mABC) and global-best ABC (GABC) over the four QoS parameter response time, latency, availability and reliability. The authors found that the approach outperforms overall competitive approaches. To satisfy all objective simultaneously, the authors would like to extend this approach in the frame of multi-objective WSS optimization problem. Further, this is declared that this paper is not submitted to any other journal or under review.

Details

International Journal of Pervasive Computing and Communications, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1742-7371

Keywords

Open Access
Article
Publication date: 14 October 2019

Zhouxia Li, Zhiwen Pan, Xiaoni Wang, Wen Ji and Feng Yang

Intelligence level of a crowd network is defined as the expected reward of the network when completing the latest tasks (e.g. last N tasks). The purpose of this paper is…

Abstract

Purpose

Intelligence level of a crowd network is defined as the expected reward of the network when completing the latest tasks (e.g. last N tasks). The purpose of this paper is to improve the intelligence level of a crowd network by optimizing the profession distribution of the crowd network.

Design/methodology/approach

Based on the concept of information entropy, this paper introduces the concept of business entropy and puts forward several factors affecting business entropy to analyze the relationship between the intelligence level and the profession distribution of the crowd network. This paper introduced Profession Distribution Deviation and Subject Interaction Pattern as the two factors which affect business entropy. By quantifying and combining the two factors, a Multi-Factor Business Entropy Quantitative (MFBEQ) model is proposed to calculate the business entropy of a crowd network. Finally, the differential evolution model and k-means clustering are applied to crowd intelligence network, and the species distribution of intelligent subjects is found, so as to achieve quantitative analysis of business entropy.

Findings

By establishing the MFBEQ model, this paper found that when the profession distribution of a crowd network is deviate less to the expected distribution, the intelligence level of a crowd network will be higher. Moreover, when subjects within the crowd network interact with each other more actively, the intelligence level of a crowd network becomes higher.

Originality/value

This paper aims to build the MFBEQ model according to factors that are related to business entropy and then uses the model to evaluate the intelligence level of a number of crowd networks.

Details

International Journal of Crowd Science, vol. 3 no. 3
Type: Research Article
ISSN: 2398-7294

Keywords

Click here to view access options
Article
Publication date: 1 March 2004

J.K. Sykulski

Design and optimisation of many practical electromechanical devices involve intensive field simulation studies and repetitive usage of time‐consuming software such as…

Abstract

Design and optimisation of many practical electromechanical devices involve intensive field simulation studies and repetitive usage of time‐consuming software such as finite elements (FEs), finite differences of boundary elements. This is a costly, but unavoidable process and thus a lot of research is currently directed towards finding ways by which the number of necessary function calls could be reduced. New algorithms are being proposed based either on stochastic or deterministic techniques where a compromise is achieved between accuracy and speed of computation. Four different approaches appear to be particularly promising and are summarised in this review paper. The first uses a deterministic algorithm, known as minimal function calls approach, introduces online learning and dynamic weighting. The second technique introduced as ES/DE/MQ – as it combines evolution strategy, differential evolution and multiquadrics interpolation – offers all the advantages of a stochastic method, but with much reduced number of function calls. The third recent method uses neuro‐fuzzy modelling and leads to even further economy of computation, although with slightly reduced accuracy of computation. Finally, a combined FE/neural network approach offers a novel approach to optimisation if a conventional magnetic circuit model could also be used.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, vol. 23 no. 1
Type: Research Article
ISSN: 0332-1649

Keywords

Click here to view access options
Article
Publication date: 31 January 2020

Nebojsa B. Raicevic, Slavoljub R. Aleksic, Ilona Iatcheva and Marinko Barukcic

This paper aims to present a new approach to the numerical solution of skin effect integral equations in cylindrical conductors. An approximate, but very simple and…

Abstract

Purpose

This paper aims to present a new approach to the numerical solution of skin effect integral equations in cylindrical conductors. An approximate, but very simple and accurate method for calculating the current density distribution, skin-effect resistance and inductance, in pulse regime of cylindrical conductor, having a circular or rectangular cross-section, is considered. The differential evolution method is applied for minimization of error functional. Because of its application in the practice, the lightning impulse is observed. Direct and inverse fast Fourier transform is applied.

Design/methodology/approach

This method contributes to increasing of correctness and much faster convergence. As the electromagnetic field components depend on the current density derivation, the proposed method gives a very accurate solution not only for current density distribution and resistance but also for field components and for internal inductance coefficients. Distribution of current and electromagnetic field in bus-bars can be successfully determined if the proximity effect is included together with the skin effect in calculations.

Findings

The study shows the strong influence of direct lightning strikes on the distribution of electrical current in cables used in lightning protection systems. The current impulse causes an increase in the current density at all points of the cross-section of the conductor, and in particular the skin effect on the external periphery. Based on the data calculated by using the proposed method, it is possible to calculate the minimum dimensions of the conductors to prevent system failures.

Research limitations/implications

There are a number of approximations of lightning strike impulse in the literature. This is a limiting factor that affects the reliability and agreement between measured data with calculated values.

Originality/value

In contrast with other methods, the current density function is approximated by finite functional series, which automatically satisfy wave equation and existing boundary conditions. It is necessary to minimize the functional. This approach leads to a very accurate solution, even in the case when only two terms in current approximation are adopted.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering , vol. 39 no. 3
Type: Research Article
ISSN: 0332-1649

Keywords

1 – 10 of over 10000