检索结果-内蒙古大学图书馆

Molecular Descriptor Subset Selection in Theoretical Peptide Quantitative Structure-Retention Relationship Model Development Using Nature-Inspired Optimization algorithms

引用

ANALYTICAL CHEMISTRY 2015年第19期87卷 9876-9883页

作者： Zuvela, Petar Liu, J. Jay Macur, Katarzyna Baczek, Tomasz Pukyong Natl Univ Dept Chem Engn Busan 608739 South Korea Univ Gdansk Intercollegiate Fac Biotechnol Lab Mass Spectrometry PL-80822 Gdansk Poland Med Univ Gdansk PL-80822 Gdansk Poland Med Univ Gdansk Dept Pharmaceut Chem PL-80416 Gdansk Poland

In this work, performance of five nature-inspired optimization algorithms, genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC), firefly algorithm (FA), and flower pollination algorithm (EPA), was compared in molecular descriptor selection for development of quantitative structure retention relationship (QSRR) models for 83 peptides that originate from eight model proteins. The matrix with 423 descriptors was used as input, and QSRR models based on selected descriptors were built using partial least squares (PLS), whereas root mean square error of prediction (RMSEP) was used as a fitness function for their selection. Three performance criteria, prediction accuracy, computational cost, and the number of selected descriptors, were used to evaluate the developed QSRR models. The results show that all five variable selection methods outperform interval PLS (iPLS), sparse PLS (sPLS), and the full PLS model, whereas GA is superior because of its lowest computational cost and higher accuracy (RMSEP of 5.534%) with a smaller number of variables (nine descriptors). The GA-QSRR model was validated initially through Y-randomization. In addition, it was successfully validated with an external testing set out of 102 peptides originating from Bacillus subtilis proteomes (RMSEP of 22.030%). Its applicability domain was defined, from which it was evident that the developed GA-QSRR exhibited strong robustness. All the sources of the model's error were identified, thus allowing for further application of the developed methodology in proteomics.

关键词： PEPTIDES RESEARCH GENETIC algorithms bees algorithm PARTICLE swarm optimization LEAST squares

来源：评论

学校读者我要写书评

暂无评论

Cloud remanufacturing: Remanufacturing enhanced through cloud technologies

引用

JOURNAL OF MANUFACTURING SYSTEMS 2022年 64卷 133-148页

作者： Caterino, Mario Fera, Marcello Macchiaroli, Roberto Pham, Duc Truong Univ Campania Luigi Vanvitelli Dept Engn Aversa Italy Univ Birmingham Dept Mech Engn Birmingham England

Remanufacturing represents one of the most promising strategies for promoting circular economy (CE) principles and achieving economic and environmental sustainability goals. The implementation of Industry 4.0 (I4.0) enabling technologies such as cloud computing and the Internet of Things in the classical remanufacturing process provides the opportunity to define a new approach called Cloud Remanufacturing, which realises a distributed system in which remanufacturing resources, located at different geographic sites, are shared and managed in a centralised environment. This paper aims to introduce the new concept of Cloud Remanufacturing by proposing a framework to explain its logic and characterise its main features. Furthermore, the mathematical relationships for evaluating the costs and the times for completing the remanufacturing process enhanced by I4.0 technologies will be developed, and, relying on them, the model will be tested for 2 scenarios involving different extended areas. In detail, the problem of activity scheduling in Cloud Remanufacturing will be addressed using two metaheuristic approaches. The results show the effectiveness and theoretical applicability of the model, even if a comparison with a real case study is not possible due to the lack of a real centrally managed remanufacturing distributed system.

关键词： Remanufacturing Circular economy Cloud technologies Makespan problem Tabu Search bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Inverse design of airfoils via an intelligent hybrid optimization technique

引用

ENGINEERING WITH COMPUTERS 2017年第3期33卷 361-374页

作者： Tandis, Emad Assareh, Ehsanolah Univ Jundi Shapor Dept Mech Engn Dezful Iran Islamic Azad Univ Dezful Branch Dept Mech Engn Dezful Iran

The solutions for inverse shape design (ISD) problems are provided in many cases using evolutionary algorithms linked up with CFD solvers. Among the optimization methods, evolutionary algorithms have many advantages, especially in stability, but they usually need a large number of function evaluations. This can be more important as evaluation of cost function requires flow solution which is usually a time-consuming process. This paper presents a new population-based hybrid algorithm called genetic-based bees algorithm (GBBA) as a solution to ISD problems. This method uses crossover and neighborhood searching operators derived from, respectively, genetic algorithm (GA) and bees algorithm (BA) to provide a method with good performance in accuracy and speed convergence. Three test cases have been used to compare the performance of the proposed hybrid algorithm with GA and BA. Here, both ideal and viscose flow solvers are involved to solve flow equations in the physical domain. PARSEC and Bezier are two shape definition methods used for surface modification in these cases. The results show that the final shape obtained by the proposed hybrid algorithm is more accurate compared to either BA or GA. Furthermore, speed convergence increases when GBBA is employed.

关键词： Inverse shape design Genetic algorithms bees algorithm Airfoil optimization Hybrid algorithm

来源：评论

学校读者我要写书评

暂无评论

A comparison of nature inspired algorithms for the quadratic assignment problem

引用

BULLETIN OF THE POLISH ACADEMY OF SCIENCES-TECHNICAL SCIENCES 2017年第4期65卷 513-522页

作者： Chmiel, W. Kadluczka, P. Kwiecien, J. Filipowicz, B. AGH Univ Sci & Technol 30 Mickiewicza Ave PL-30059 Krakow Poland

This paper presents an application of the ant algorithm and bees algorithm in optimization of QAP problem as an example of NP-hard optimization problem. The experiments with two types of algorithms: the bees algorithm and the ant algorithm were performed for the test instances of the quadratic assignment problem from QAPLIB, designed by Burkard, Karisch and Rendl. On the basis of the experiments results, an influence of particular elements of algorithms, including neighbourhood size and neighbourhood search method, will be determined.

关键词： permutation problem quadratic assignment problem ant algorithm bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of Smartphone and Model Updating Technique in Structural Health Monitoring

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2019年第5期44卷 4819-4828页

作者： Dey, Palash Akhil, V Laskar, A., I Natl Inst Technol Silchar Dept Civil Engn Silchar 788010 Assam India

The present study outlines the application of smartphone and model updating in structural health monitoring by using vibration response data. The application of the approach has been shown for simply supported beams with uncracked and different crack configurations. Crack has been artificially generated at the time of casting using thin steel plate of 1.5 mm thickness. Finite element analyses have been carried out for uncracked and cracked beams. Laboratory tests were conducted using smartphone to obtain the natural frequencies of both damaged and undamaged beams with the help of accelerometer application software. Acceleration in the vertical direction of the cracked and uncracked beams was measured using this mobile application and thereafter, frequency response function curves have been obtained from this. At last, the model has been updated using bees algorithm to get more accurate results.

关键词： Model updating Structural health monitoring bees algorithm Noise contamination and smartphone

来源：评论

学校读者我要写书评

暂无评论

Reducing the Overfitting in Convolutional Neural Network using Nature-Inspired algorithm: A Novel Hybrid Approach

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2024年第9期49卷 13099-13114页

作者： Alamri, Nawaf Mohammad King Abdulaziz Univ Dept Ind Engn Jeddah Saudi Arabia

Convolutional neural network (CNN) is one of the well-known deep learning algorithms that uses convolutional filters to extract the features in the images. The most important issue when training CNN is the overfitting which prevents the model from generalization to unseen data. This paper addressed this issue by proposing a novel hybrid approach that uses bees algorithm (BA) to optimize the regularization parameter and weight regularization factor to adjust the regularization value in each convolutional layer and fully connected layer resulting in a hybrid algorithm called bees algorithm regularized convolutional neural network (BA-RCNN). It was applied to three different datasets for classification or predictions purposes and showed an improvement in the validation and testing accuracy leading to a lower difference with the training accuracy which means the overfitting is reduced comparing to the original CNN. Applying the BA-RCNN algorithm to 'Cifar10DataDir' improved the validation accuracy from 80.34% for the original CNN to 82.80% for the hybrid BA-RCNN algorithm, in the electrocardiogram the improvement was from 87.80 to 90.47% and both datasets were used for classification. Furthermore, the hybrid BA-RCNN algorithm was applied to predict the porosity percentage based on artificial porosity images and the results showed that the validation accuracy was improved from 81.67% for the original CNN to 87.33% for the hybrid BA-RCNN algorithm.

关键词： Deep learning Convolutional neural network bees algorithm Overfitting bees algorithm regularized convolutional neural network (BA-RCNN)

来源：评论

学校读者我要写书评

暂无评论

Optimal design of frequency selective surfaces with fractal motifs

引用

IET MICROWAVES ANTENNAS & PROPAGATION 2014年第9期8卷 627-631页

作者： da Silva, Marcelo Ribeiro Nobrega, Clarissa de Lucena Silva, Paulo Henrique da F. D'Assuncao, Adaildo Gomes Univ Fed Rio Grande do Norte UFRN CT DCO BR-59078970 Natal RN Brazil Fed Inst Educ Sci & Technol Paraiba IFPB BR-58015430 Joao Pessoa Paraiba Brazil

An alternative electromagnetic (EM) optimisation technique for the optimal design of frequency selective surfaces (FSSs) with fractal motifs is described. Based on computational intelligence tools, the proposed technique overcomes the high computational cost associated with FSS parametric full-wave analysis. In an application example, a fast and accurate multilayer perceptrons model of a FSS band-stop spatial filter with a Vicsek fractal motif is developed. This neural network model is used for repetitive cost function computations in population-based search algorithm simulations. A bees algorithm, continuous genetic algorithm and particle swarm optimisation are used for FSS optimisation with specific resonant frequency and bandwidth. The performance of these algorithms is compared in terms of numerical convergence. Consistent results are presented for a second-pass of designed FSS prototype with Vicsek fractal elements.

关键词： electrical engineering computing frequency selective surfaces genetic algorithms multilayer perceptrons particle swarm optimisation search problems spatial filters frequency selective surfaces optimal design alternative electromagnetic optimisation technique computational intelligence tools FSS parametric full-wave analysis multilayer perceptrons FSS band-stop spatial fllter Vicsek fractal motif neural network model repetitive cost function computations population-based search algorithm simulations particle swarm optimisation continuous genetic algorithm bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Crack detection in circular cylindrical shells using differential quadrature method

引用

INTERNATIONAL JOURNAL OF PRESSURE VESSELS AND PIPING 2013年 111卷 209-216页

作者： Moradi, S. Tavaf, V. Shahid Chamran Univ Dept Mech Engn Ahvaz 61355 Iran

The differential quadrature method combined with an evolutionary optimization algorithm has been proposed for crack detection in cylindrical shell structures. The circumferential crack, which is assumed to be open, is modeled by the extended rotational spring. A crack with finite length divides the shell into four segments. The governing differential equations of motion of the shell are formulated based on Flugge's shell theory. Applying differential quadrature to the differential equations of each segment and the corresponding boundary and continuity conditions results in an algebraic system of equations. Then, an eigenvalue analysis is performed to obtain the natural frequencies of the cracked shell. To identify the crack parameters, an optimization problem is defined and minimized by bees algorithm, a swarm-based evolutionary optimization technique. The integrity and applicability of the proposed method is confirmed by some experimental case studies. The results show that the crack statuses are predicted well. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Crack detection Differential quadrature Shell Experimental modal analysis bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Trivariate non-Gaussian copulas to analyze the spatial behavior of rat sightings

引用

STATISTICA NEERLANDICA 2019年第2期73卷 256-273页

作者： Ayyad, C. Mateu, J. Omidi, M. Tamayo-Uria, I. Mohammadzadeh, M. Jaume I Univ Dept Math E-12071 Castellon De La Plana Spain Ilam Univ Dept Math Ilam Iran Ctr Res Environm Epidemiol CREAL Barcelona Spain Tarbiat Modares Univ Dept Stat Tehran Iran

The brown rat lives with man in a wide variety of environmental contexts and adversely affects public health by transmission of diseases, bites, and allergies. Understanding behavioral and spatial correlation aspects of pest species can contribute to their effective management and control. Rat sightings can be described by spatial coordinates in a particular region of interest defining a spatial point pattern. In this paper, we investigate the spatial structure of rat sightings in the Latina district of Madrid (Spain) and its relation to a number of distance-based covariates that relate to the proliferation of rats. Given a number of locations, biologically considered as attractor points, the spatial dependence is modeled by distance-based covariates and angular orientations through copula functions. We build a particular spatial trivariate distribution using univariate margins coming from the covariate information and provide predictive distributions for such distances and angular orientations.

关键词： bees algorithm copula functions multivariate copulas rat sightings spatial copula spatial point patterns Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Nature-inspired metaheuristic techniques for automatic clustering: a survey and performance study

引用

SN APPLIED SCIENCES 2020年第2期2卷 273页

作者： Ezugwu, Absalom E. Univ KwaZulu Natal Sch Comp Sci King Edward RdPietermaritzburg Campus ZA-3201 Pietermaritzburg Kwazulu Natal South Africa

The application of several swarm intelligence and evolutionary metaheuristic algorithms in data clustering problems has in the past few decades gained wide popularity and acceptance due to their success in solving and finding good quality solutions to a variety of complex real-world optimization problems. Clustering is considered one of the most important data analysis techniques in the domain of data mining. A clustering problem refers to the partitioning of unlabeled data objects into a certain number of clusters based on their attribute values or features, with the objective of maximizing intra-clusters homogeneity and inter-cluster heterogeneity. This paper presents an up-to-date survey of major nature-inspired metaheuristic algorithms that have been employed to solve automatic clustering problems. Further, a comparative study of several modified well-known global metaheuristic algorithms is carried out to solve automatic clustering problems. Also, three hybrid swarm intelligence and evolutionary algorithms, namely, particle swarm differential evolution algorithm, firefly differential evolution algorithm and invasive weed optimization differential evolution algorithm, are proposed to deal with the task of automatic data clustering. In contrast to many of the existing traditional and evolutionary computational clustering techniques, the clustering algorithms presented in this paper do not require any predetermined information or prior-knowledge of the dataset that is to be classified, but rather they are capable of spontaneously identifying the optimal number of partitions of the data points during the course of program execution. Forty-one benchmarked datasets that comprise eleven artificial and thirty real world datasets are collated and utilized to evaluate the performances of the representative nature-inspired clustering algorithms. According to the extensive experimental results, comparisons and statistical significance, the firefly algorithm appeared to be

关键词： Automatic clustering Clustering analysis Differential evolution Particle swarm optimization Firefly algorithm Invasive weed optimization Artificial bee colony bees algorithm Biogeography-based optimization Harmony search Symbiotic organisms search Teaching-learning-based optimization DB validity index CS validity index

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：