检索结果-内蒙古大学图书馆

Feature Selection for Classification through Population Random Search with Memory

AUTOMATION AND REMOTE CONTROL 2019年第2期80卷 324-333页

作者： Hodashinsky, I. A. Sarin, K. S. Tomsk Univ Control Syst & Radioelect Tomsk Russia

We propose a new approach for feature selection. The proposed approach is based on a combination of random and heuristic search strategies. The solution is represented as a binary vector whose dimension is determined by the number of features in the dataset. New solutions are generated at random using a normal and uniform distribution. The heuristic underlying the proposed approach can be formulated as follows: the chance of a feature to get into the next generation is proportional to the frequency of this feature appearing in previous best solutions. The proposed approach has been tested on several datasets from the KEEL repository. We also show an experimental comparison with other methods.

关键词： feature selection fuzzy classifier binary optimization metaheuristics random search with memory

来源：评论

学校读者我要写书评

暂无评论

A novel binary artificial bee colony algorithm based on genetic operators

引用

INFORMATION SCIENCES 2015年 297卷 154-170页

作者： Ozturk, Celal Hancer, Emrah Karaboga, Dervis Erciyes Univ Fac Engn Dept Comp Engn Kayseri Turkey

This study proposes a novel binary version of the artificial bee colony algorithm based on genetic operators (GB-ABC) such as crossover and swap to solve binary optimization problems. Integrated to the neighbourhood searching mechanism of the basic ABC algorithm, the modification comprises four stages: (1) In neighbourhood of a (current) food source, randomly select two food sources from population and generate a solution including zeros (Zero) outside the population;(2) apply two-point crossover operator between the current, two neighbourhood, global best and Zero food sources to create children food sources;(3) apply swap operator to the children food sources to generate grandchildren food sources;and (4) select the best food source as a neighbourhood food source of the current solution among the children and grandchildren food sources. In this way, the global-local search ability of the basic ABC algorithm is improved in binary domain. The effectiveness of the proposed algorithm GB-ABC is tested on two well-known binary optimization problems: dynamic image clustering and 0-1 knapsack problems. The obtained results clearly indicate that GB-ABC is the most suitable algorithm in binary optimization when compared with the other well-known existing binary optimization algorithms. In addition, the achievement of the proposed algorithm is supported by applying it to the CEC2005 benchmark numerical problems. (C) 2014 Elsevier Inc. All rights reserved.

关键词： binary optimization Dynamic clustering Knapsack problem Artificial bee colony Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

EEG Channel Selection for Person Identification Using binary Grey Wolf Optimizer

引用

IEEE ACCESS 2022年 10卷 10500-10513页

作者： Alyasseri, Zaid Abdi Alkareem Alomari, Osama Ahmad Makhadmeh, Sharif Naser Mirjalili, Seyedali Al-Betar, Mohammed Azmi Abdullah, Salwani Ali, Nabeel Salih Papa, Joao P. Rodrigues, Douglas Abasi, Ammar Kamal Univ Kebangsaan Malaysia Fac Informat Sci & Technol Ctr Artificial Intelligence Bangi 43600 Selangor Malaysia Univ Kufa Informat Technol Res & Dev Ctr ITRDC Kufa 540011 Najaf Iraq Univ Sharjah MLALP Res Grp Sharjah U Arab Emirates Ajman Univ Coll Engn & Informat Technol Artificial Intelligence Res Ctr AIRC Ajman U Arab Emirates Torrens Univ Australia Ctr Artificial Intelligence Res & Optimisat Brisbane Qld 4006 Australia Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea Al Balqa Appl Univ Al Huson Univ Coll Dept Informat Technol Irbid 19117 Jordan Univ Kufa ITRDC Kufa 540011 Najaf Iraq Sao Paulo State Univ Dept Comp BR-17033360 Bauru SP Brazil

Electroencephalogram signals (EEG) have provided biometric identification systems with great capabilities. Several studies have shown that EEG introduces unique and universal features besides specific strength against spoofing attacks. Essentially, EEG is a graphic recording of the brain's electrical activity calculated by sensors (electrodes) on the scalp at different spots, but their best locations are uncertain. In this paper, the EEG channel selection problem is formulated as a binary optimization problem, where a binary version of the Grey Wolf Optimizer (BGWO) is used to find an optimal solution for such an NP-hard optimization problem. Further, a Support Vector Machine classifier with a Radial Basis Function kernel (SVM-RBF) is then considered for EEG-based biometric person identification. For feature extraction purposes, we examine three different auto-regressive coefficients. A standard EEG motor imagery dataset is employed to evaluate the proposed method, including four criteria: (i) Accuracy, (ii) F-Score, (iii) Recall, and (v) Specificity. In the experimental results, the proposed method (named BGWO-SVM) obtained 94.13% accuracy using only 23 sensors with 5 auto-regressive coefficients. Besides, BGWO-SVM finds electrodes not too close to each other to capture relevant information all over the head. As concluding remarks, BGWO-SVM achieved the best results concerning the number of selected channels and competitive classification accuracies against other meta-heuristics algorithms.

关键词： Electroencephalography Electrodes Sensors Support vector machines Iris recognition Authentication Visualization EEG biometric channels selection Grey Wolf Optimizer identification binary optimization

来源：评论

学校读者我要写书评

暂无评论

An improved binary sparrow search algorithm for feature selection in data classification

引用

NEURAL COMPUTING & APPLICATIONS 2022年第18期34卷 15705-15752页

作者： Gad, Ahmed G. Sallam, Karam M. Chakrabortty, Ripon K. Ryan, Michael J. Abohany, Amr A. Kafrelsheikh Univ Fac Comp & Informat Kafrelsheikh Egypt Zagazig Univ Fac Comp & Informat Zagazig Egypt Univ Canberra Fac Sci & Technol Sch IT & Syst Canberra ACT 2601 Australia UNSW Canberra ADFA Sch Engn & IT Capabil Syst Ctr Canberra ACT Australia Capabil Associates Canberra Canberra ACT Australia

Feature Selection (FS) is an important preprocessing step that is involved in machine learning and data mining tasks for preparing data (especially high-dimensional data) by eliminating irrelevant and redundant features, thus reducing the potential curse of dimensionality of a given large dataset. Consequently, FS is arguably a combinatorial NP-hard problem in which the computational time increases exponentially with an increase in problem complexity. To tackle such a problem type, metaheuristic techniques have been opted by an increasing number of scholars. Herein, a novel meta-heuristic algorithm, called Sparrow Search Algorithm (SSA), is presented. The SSA still performs poorly on exploratory behavior and exploration-exploitation trade-off because it does not duly stimulate the search within feasible regions, and the exploitation process suffers noticeable stagnation. Therefore, we improve SSA by adopting: i) a strategy for Random Re-positioning of Roaming Agents (3RA);and ii) a novel Local Search Algorithm (LSA), which are algorithmically incorporated into the original SSA structure. To the FS problem, SSA is improved and cloned as a binary variant, namely, the improved binary SSA (iBSSA), which would strive to select the optimal or near-optimal features from a given dataset while keeping the classification accuracy maximized For binary conversion, the iBSSA was primarily validated against nine common S-shaped and V-shaped Transfer Functions (TFs), thus producing nine iBSSA variants. To verify the robustness of these variants, three well-known classification techniques, including k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest (RF) were adopted as fitness evaluators with the proposed iBSSA approach and many other competing algorithms, on 18 multifaceted, multi-scale benchmark datasets from the University of California Irvine (UCI) data repository. Then, the overall best-performing iBSSA variant for each of the three classifiers was com

关键词： Machine learning Classification Feature selection Meta-heuristics Sparrow search algorithm Combinatorial optimization Swarm-based optimization Pattern recognition Data mining binary optimization

来源：评论

学校读者我要写书评

暂无评论

A binary differential search algorithm for the 0-1 multidimensional knapsack problem

引用

APPLIED MATHEMATICAL MODELLING 2016年第23-24期40卷 9788-9805页

作者： Liu, Jianjun Wu, Changzhi Cao, Jiang Wang, Xiangyu Teo, Kok Lay China Univ Petr Coll Sci Beijing 102249 Peoples R China Curtin Univ Sch Built Environm Australasian Joint Res Ctr Bldg Informat Modellin Perth WA 6845 Australia Kyung Hee Univ Dept Housing & Interior Design Seoul South Korea Curtin Univ Dept Math & Stat Perth WA 6845 Australia

The multidimensional knapsack problem (MKP) is known to be NP-hard in operations research and it has a wide range of applications in engineering and management. In this study, we propose a binary differential search method to solve 0-1 MKPs where the stochastic search is guided by a Brownian motion-like random walk. Our proposed method comprises two main operations: discrete solution generation and feasible solution production. Discrete solutions are generated by integrating Brownian motion-like random search with an integer-rounding operation. However, the rounded discrete variables may violate the constraints. Thus, a feasible solution production strategy is used to maintain the feasibility of the rounded discrete variables. To demonstrate the efficiency of our proposed algorithm, we solved various 0-1 MKPs using our proposed algorithm as well as some existing meta-heuristic methods. The numerical results obtained demonstrated that our algorithm performs better than existing meta-heuristic methods. Furthermore, our algorithm has the capacity to solve large-scale 0-1 MKPs. (C) 2016 Elsevier Inc. All rights reserved.

关键词： binary optimization Differential search MKP

来源：评论

学校读者我要写书评

暂无评论

Optimal patterning of heterogeneous surface charge for improved electrokinetic micromixing

引用

COMPUTERS & CHEMICAL ENGINEERING 2013年 49卷 18-24页

作者： Jain, Mranal Nandakumar, K. Louisiana State Univ Cain Dept Chem Engn Baton Rouge LA 70803 USA

Micromixing is a key step in realizing fast analysis time in many bio-chemical, biological and detection applications of lab-on-a-chip (LOC) devices. The conventional T-mixer design requires longer channel lengths and times to achieve complete mixing owing to its dependence on transverse diffusion. As the surface properties of the microchannel govern the electro-osmotic flow characteristics, surface heterogeneity (non-uniform zeta potentials) can be exploited to generate vortices or specific flow structures to improve the mixing performance. Previous studies have shown that localized circulations or non-axial flow induced due to the presence of heterogeneity augment micromixing performance. However, the effect of heterogeneous charge patterns on mixing performance has not been studied systematically. In this computational study, a binary numerical optimization problem is formulated to achieve best mixing performance by identifying the optimal heterogeneous charge pattern. The resulting optimal design generates the most favorable transverse flow structure to provide optimal mixing performance. Various other configurations (staggered, herringbone, etc.) are examined over a range of operating conditions. The optimal design is found to be superior for all operating conditions with over 3-fold improvement in mixing performance with respect to homogeneous T-mixer. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Micromixing Electrokinetics binary optimization

来源：评论

学校读者我要写书评

暂无评论

Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems

引用

NEURAL COMPUTING & APPLICATIONS 2016年第4期27卷 1053-1073页

作者： Mirjalili, Seyedali Griffith Univ Sch Informat & Commun Technol Nathan Campus Nathan Qld 4111 Australia Queensland Inst Business & Technol Mt Gravatt Qld 4122 Australia

A novel swarm intelligence optimization technique is proposed called dragonfly algorithm (DA). The main inspiration of the DA algorithm originates from the static and dynamic swarming behaviours of dragonflies in nature. Two essential phases of optimization, exploration and exploitation, are designed by modelling the social interaction of dragonflies in navigating, searching for foods, and avoiding enemies when swarming dynamically or statistically. The paper also considers the proposal of binary and multi-objective versions of DA called binary DA (BDA) and multi-objective DA (MODA), respectively. The proposed algorithms are benchmarked by several mathematical test functions and one real case study qualitatively and quantitatively. The results of DA and BDA prove that the proposed algorithms are able to improve the initial random population for a given problem, converge towards the global optimum, and provide very competitive results compared to other well-known algorithms in the literature. The results of MODA also show that this algorithm tends to find very accurate approximations of Pareto optimal solutions with high uniform distribution for multi-objective problems. The set of designs obtained for the submarine propeller design problem demonstrate the merits of MODA in solving challenging real problems with unknown true Pareto optimal front as well. Note that the source codes of the DA, BDA, and MODA algorithms are publicly available at//***/***.

关键词： optimization Multi-objective optimization Constrained optimization binary optimization Benchmark Swarm intelligence Evolutionary algorithms Particle swarm optimization Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

KRR-CNN: kernels redundancy reduction in convolutional neural networks

引用

NEURAL COMPUTING & APPLICATIONS 2022年第3期34卷 2443-2454页

作者： Hssayni, El Houssaine Joudar, Nour-Eddine Ettaouil, Mohamed Sidi Mohamed Ben Abdellah Univ Fac Sci & Technol Fez Dept Math Modelling & Math Struct Lab Fes Morocco Mohammed V Univ Rabat ENSAM Dept Appl Math & Informat M2CSRes Ctr STIS Rabat Morocco

Convolutional neural networks (CNNs) are a promising tool for solving real-world problems. However, successful CNNs often require a large number of parameters, which leads to a significant amount of memory and a higher computational cost. This may produce some undesirable phenomena, notably the overfitting. Indeed, in CNNs, many kernels are usually redundant and can be eliminated from the network while preserving the performance. In this work, we propose a new optimization model for kernels redundancy reduction in CNN named KRR-CNN. It consists of minimization and optimization phases. In the first one, a dataset is used to train a specific CNN generating a learned CNN with optimal parameters. These later are combined with a decision optimization model to reduce kernels that have not contributed to the first task. The optimization phase is carried out by the evolutionary genetic algorithm. Efficiency of KRR-CNN has been demonstrated by several experiments. In fact, the suggested model allows reducing the kernels redundancy and improving the classification performance comparable to the state-of-the-art CNNs.

关键词： Convolutional neural networks Convolution kernel binary optimization Genetic algorithm Image classification

来源：评论

学校读者我要写书评

暂无评论

Demand side management of plug-in electric vehicles and coordinated unit commitment: A novel parallel competitive swarm optimization method

引用

ENERGY CONVERSION AND MANAGEMENT 2019年 196卷 935-949页

作者： Wang, Ying Yang, Zhile Mourshed, Monjur Guo, Yuanjun Niu, Qun Zhu, Xiaodong Zhengzhou Univ Zhengzhou 450001 Henan Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Guangdong Peoples R China Cardiff Univ Sch Engn Cardiff CF24 3AA S Glam Wales Shanghai Univ Sch Mechatron & Automat Shanghai Peoples R China

Decreasing initial costs, the increased availability of charging infrastructure and favorable policy measures have resulted in the recent surge in plug-in electric vehicle (PEV) ownerships. PEV adoption increases electricity consumption from the grid that could either exacerbate electricity supply shortages or smooth demand curves. The optimal coordination and commitment of power generation units while ensuring wider access of PEVs to the grid are, therefore, important to reduce the cost and environmental pollution from thermal power generation systems, and to transition to a smarter grid. However, flexible demand side management (DSM) considering the stochastic charging behavior of PEVs adds new challenges to the complex power system optimization, and makes existing mathematical approaches ineffective. In this research, a novel parallel competitive swarm optimization algorithm is developed for solving large-scale unit commitment (UC) problems with mixed-integer variables and multiple constraints - typically found in PEV integrated grids. The parallel optimization framework combines binary and real-valued competitive swarm optimizers for solving the UC problem and demand side management of PEVs simultaneously. Numerical case studies have been conducted with multiple scales of unit numbers and various demand side management strategies of plug-in electric vehicles. The results show superior performance of proposed parallel competitive swarm optimization based method in successfully solving the proposed complex optimization problem. The flexible demand side management strategies of plug-in electric vehicles have shown large potentials in bringing considerable economic benefit.

关键词： Unit commitment Demand side management Plug-in electric vehicles Competitive swarm optimization binary optimization

来源：评论

学校读者我要写书评

暂无评论

Two phased Yarn scheduling with novel binary hypergraphed PSO

引用

JOURNAL OF SUPERCOMPUTING 2023年第18期79卷 20712-20746页

作者： Sharma, Sonia Bharti, Rajendra Kumar Seth Jai Parkash Mukand Lal Inst Engn & Technol JM Dept Comp Sci Yamunanagar India Uttarakhand Tech Univ Dehra Dun India Bipin Tripathi Kumaon Inst Technol CSE Dwarahat Uttaranchal India

Big Data Analytics has been spiralling as one of the eminent technologies in realising agile, secure and efficient operability in practically almost everything being done contemporarily. Hadoop is one of the efficient and highly scalable open-source frameworks that use commodity hardware for the processing of big data in a distributed environment entailing just candid programming strategies. But finding the optimal utility for a collection of autonomous, disparate distributed computing systems presents myriad perplexities. The focus of this study is mostly pivoted on finding ways to improve the scheduling procedures. This paper presented a novel scheduling algorithm binary Hypergraphed Particle Swarm Optimisation (BHGPSO) that strives to allocate resources fairly and reduces execution time by making maximum use of available resources. It is also eligible in achieving a higher data locality rate by presenting the tasks and nodes as hypergraphs and using an enhanced eigen-trick-induced spectral clustering to group the nodes to obtain the locality weights. The experimental results demonstrate that the proposed algorithm significantly improves the degree of imbalance, makespan, execution time, and efficiency. It is also worth noting that it outperformed the execution time estimation schemes and the greedy resource allocation approach. The proposed scheduler increased data locality by up to 39.81% while decreasing execution time by 18.3%. The BHGPSO is a policy that can be plugged into the Hadoop architecture. It does escalate the scalability of Hadoop, making it more user-friendly.

关键词： Big data Hadoop Yarn scheduling Hypergraph binary optimization

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：