检索结果-内蒙古大学图书馆

3D affine registration using teaching-learning based optimization

3D RESEARCH 2013年第3期4卷 2-2页

作者： Jani, Ashish Savsani, Vimal Pandya, Abhijit Florida Atlantic Univ Boca Raton FL 33431 USA Pandit Deendayal Petr Univ Gandhinagar Gujarat India

3D image registration is an emerging research field in the study of computer vision. In this paper, two effective global optimization methods are considered for the 3D registration of point clouds. Experiments were conducted by applying each algorithm and their performance was evaluated with respect to rigidity, similarity and affine transformations. Comparison of algorithms and its effectiveness was tested for the average performance to find the global solution for minimizing the error in the terms of distance between the model cloud and the data cloud. The parameters for the transformation matrix were considered as the design variables. Further comparisons of the considered methods were done for the computational effort, computational time and the convergence of the algorithm. The results reveal that the use of TLBO was outstanding for image processing application involving 3D registration.

关键词： optimization image registration teaching learning based optimization simulated annealing iterative closed point

来源：评论

学校读者我要写书评

暂无评论

Forgery Detection of Digital Images Using teaching-learning based optimization and Principal Component Analysis

引用

SENSING AND IMAGING 2023年第1期24卷 19-19页

作者： Uma, S. Sathya, P. D. Annamalai Univ Dept Elect & Commun Engn Chidambaram 608002 Tamil Nadu India

Present day image processing tools enable the user to modify the contents of digital images for improving the quality, colour balance, appearance, and so on. They can also be used for creating false evidence for insurance claim, law of court, medical diagnosis and treatment, thereby requiring authentication before using digital images as evidences. The interest point based forgery detection techniques are well-accepted as they are computationally better than block based approaches, still they fail to detect when the forged region is smooth with low gradients. This paper endeavours to use a limited number of interest points, detected by "Difference of Gaussian" and "Features from Accelerated Segment Test" techniques, and employ "Scale Invariant Features Transform" descriptors, besides applying "Principal Component Analysis" for feature reduction and "Random Sample Consensus" for elimination of false matches. It also employs "teaching-Leaning based optimization" for clustering the features with a view of obtaining the global best clusters. It studies the performances on 500 digital images and portrays the performances of the proposed method.

关键词： Forgery detection teaching learning based optimization SIFT RANSAC

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid Extreme learning Machine and teaching–learning-based optimization algorithm for skin cancer detection

引用

Healthcare Analytics 2023年 3卷 100161-100161页

作者： Priyadharshini, N. Selvanathan, N. Hemalatha, B. Sureshkumar, C. Department of Computer Science Sri GVG Visalakshi College for Women Udumalpet India Department of Information Technology Sona College of Technology Salem India Department of Information Technology KGiSL Institute of Technology Coimbatore India

Skin cancers, such as melanoma, can be difficult to spot in their early stages because they often resemble benign moles. Early detection of melanoma is crucial as it increases the chances of successful treatment and prevents cancer from spreading to other areas of the body. Machine learning algorithms and computer vision techniques are versatile techniques for detecting melanoma. However, current research has limitations, such as inaccurate detection and longer computation times. This paper proposes a novel hybrid Extreme learning Machine (ELM) and teaching–learning-based optimization (TLBO) algorithm as a versatile technique for detecting melanoma. ELM is a single-hidden layer feed-forward neural network that can be trained quickly and accurately, while TLBO is an optimization algorithm used to fine-tune the network's parameters for improved performance. Together, these techniques can classify skin lesions as benign or malignant images, potentially improving melanoma detection accuracy. © 2023 The Author(s)

关键词： Extreme learning classifier Improved weighted fuzzy C-Means algorithm Neural networks Segmentation Skin cancer teaching learning based optimization

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid teaching learning based multi-objective particle swarm optimization

引用

NEUROCOMPUTING 2017年 222卷 11-25页

作者： Cheng, Tingli Chen, Minyou Fleming, Peter J. Yang, Zhile Gan, Shaojun Chongqing Univ Sch Elect Engn Chongqing Peoples R China Univ Sheffield Dept Automat Control & Syst Engn Sheffield S10 2TN S Yorkshire England Queens Univ Belfast Sch Elect Elect Engn & Comp Sci Belfast BT7 1NN Antrim North Ireland

How to obtain a good convergence and well-spread optimal Pareto front is still a major challenge for most meta heuristic multi-objective optimization (MOO) methods. In this paper, a novel hybrid teaching learning based particle swarm optimization (HTL-PSO) with circular crowded sorting (CCS), named HTL-MOPSO, is proposed for solving MOO problems. Specifically, the new HTL-MOPSO combines the canonical PSO search with a teaching-learning-based optimization (TLBO) algorithm in order to promote the diversity and improve search ability. Also, CCS technique is developed to improve the diversity and spread of solutions when truncating the external elitism archive. The performance of HTL-MOPSO algorithm was tested on several well-known benchmarks problems and compared with other state-of-the-art MOO algorithms in respect of convergence and spread of final solutions to the true Pareto front. Also, the individual contributions made by the strategies of HTL-PSO and CCS are analyzed. Experimental results validate the effectiveness of HTL-MOPSO and demonstrate its superior ability to find solutions of better spread and diversity, while assuring a good convergence.

关键词： Multi-objective optimization Particle swarm optimization teaching learning based optimization Crowded sorting

来源：评论

学校读者我要写书评

暂无评论

Design of TMLAA for the Utilization of Radiated Harmonic Beam Over Digital Modulation Schemes

引用

MICROWAVE AND OPTICAL TECHNOLOGY LETTERS 2025年第1期67卷

作者： Varma, D. Suneel Ram, Gopi Kumar, G. Arun Astra Microwave Pvt Ltd Hyderabad India Natl Inst Technol Dept ECE Warangal India

This work presents the effective steering of multi-harmonic beams of a time-modulated linear antenna array (TMLAA) for multi-channel communication. A classroom learning-inspired teaching learning based optimization (TLBO) is utilized for active duration optimization of the 16-element TMLAA for harmonic steering. The simulation study employing the optimization technique effectively steered the first two harmonic beams with enhanced radiated power and considerable Sidelobe level (SLL) below - 20 dB $-20\,\mathrm{dB}$. Further, for practical validation, the measurement of the fabricated prototype is presented for one scenario. Finally, the use of harmonic beams for the communication links is validated by measuring the bit error rate (BER) of the considered digitally modulated scheme.

关键词： beam steering bit error rate harmonic beam steering phase shift keying teaching learning based optimization

来源：评论

学校读者我要写书评

暂无评论

Estimating the non-uniform air velocity distribution for the optimal design of a heat exchanger

引用

APPLIED THERMAL ENGINEERING 2019年 153卷 704-714页

作者： Hajabdollahi, Zahra Hajabdollahi, Hassan Kim, Kyung Chun Pusan Natl Univ Sch Mech Engn Busan 609735 South Korea Vali E Asr Univ Rafsanjan Dept Mech Engn Rafsanjan *** Iran

The maldistribution of flow in a heat exchanger usually has negative effects on the heat exchanger specifications such as the effectiveness, annual cost, and pressure drop. This paper examines the issue to improve the thermoeconomic performance. For this purpose, a plate-fin heat exchanger was selected and optimized by considering both the effectiveness and total annual cost as objective functions. The design parameters were the parameters of the heat exchanger and fin, as well as the non-uniform inlet flow profiles for both sides of the hot and cold streams. To generalize the results, the optimization was applied at different mass flow rates. The optimum results of the non-uniform profile were compared with those obtained with a uniform profile of the inlet flow. The optimum results reveal that thermoeconomic improvement occurred in the case of non-uniform flow compared with the case of uniform flow. For example, a 12.7% reduction for the total annual cost was found in the case of non-uniform flow in comparison to the uniform flow for a fixed effectiveness of 0.92. At low effectiveness, no significant improvement was found in the case of non-uniform flow. Nevertheless, the suggested profiles could be considered as an alternative to uniform inlet profiles.

关键词： teaching learning based optimization Plate-fin heat exchanger Flow maldistribution Uniform flow Optimum inlet flow profile

来源：评论

学校读者我要写书评

暂无评论

Thermo-hydraulic performance of roughened solar air heater by design of experiment and meta-heuristic approach

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2019年 10卷 92-102页

作者： Kumar, Anup Layek, Apurba NIT Durgapur Mech Engn Dept Durgapur 713209 India

The present investigation is undertaken with an objective to maximize thermo-hydraulic performance of solar air heater providing with twisted rib roughness. The optimization of various roughness parameters is done by implementing design of experiment (response surface methodology) and meta-heuristic (particle swarm optimization, teaching learning based optimization) approach for determining optimal thermo-hydraulic performance. The experimental work is conducted using Box Behnken design for 2nd order quadratic model. A mathematical model is developed for thermo-hydraulic performance in terms of roughness parameters e.g. pitch-height ratio (P/e), rib orientation (a), twist ratio (y/e) and Reynolds number (Re). The exorbitantly responsibility of rib roughness parameters on thermo-hydraulic performance is also discussed. The final optimum set of result for roughness parameters obtained by response surface methodology, particle swarm optimization, teaching learning based optimization technique are tested with experimental result to validate its robustness, flexibility and authenticity. The simulated optimized results obtained from teaching learning based optimization approaches exhibits quite satisfying with experimental data as far as competence, execution, reliability and global convergence.

关键词： Solar air heater Twisted rib roughness Response surface methodology Particle swarm optimization teaching learning based optimization

来源：评论

学校读者我要写书评

暂无评论

Group learning algorithm: a new metaheuristic algorithm

引用

NEURAL COMPUTING & APPLICATIONS 2023年第19期35卷 14013-14028页

作者： Rahman, Chnoor M. Charmo Univ Coll Sci Comp Dept Sulaymaniyah Iraq Amer Univ Iraq Sulaimani Informat Technol Dept Sulaymaniyah Iraq

Metaheuristics are intelligent optimization techniques that lead the searching procedure through utilizing exploitation and exploration. Increasing the number of hard problems with big data sets has encouraged researchers to implement novel metaheuristics and hybrid the existing ones to improve their performance. Hence, in this work, a novel metaheuristic called group learning algorithm is proposed. The main inspiration of the algorithm emerged from the way individuals inside a group affect each other, and the effect of group leader on group members. The two main steps of optimization, exploration and exploitation are outlined through integrating the behaviors of group members and the group leader to complete the assigned task. The proposed work is evaluated against a number of benchmarks. The produced results of classical benchmarks are compared against PSO, GWO, TLBO, BA, ALO, and SSA. In general, compared to other participated algorithms, out of 19 classical benchmarks, the proposed work showed better results in 11. However, the second best algorithm which is SSA performed better in 4 out of 19 benchmarks. To further evaluate the ability of the algorithm to optimize large scale optimization problems CEC-C06 2019 benchmarks are utilized. In comparison to other participated algorithms, the proposed work produced better results in most of the cases. Additionally, the statistical tests confirmed the significance of the produced results. The results are evidence that the proposed algorithm has the ability to optimize various types of problems including large scale optimization problems.

关键词： optimization Single objective optimization Benchmark Particle swarm optimization Grey wolf optimization algorithm teaching learning based optimization Population based algorithm Evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Cyber-Resilient Trading for Sustainable Energy Management: A Three-Phase Demand-Side Management Solution with Integrated Deep learning-based Renewable Energy Forecasting

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2024年第2期60卷 2532-2541页

作者： Pati, Uttamarani Mistry, Khyati D. Sardar Vallabhbhai Natl Inst Technol Elect Engn Dept Surat 395007 India

Rising technological advancement has resulted in increased demand for power. As a result of this tendency, conventional fuel stocks have been severely exhausted. Energy suppliers are concerned about the sustainability of their grid's electricity dependability as fuel sources dwindle. Also, to reduce carbon footprints, governments throughout the world are exerting pressure on the energy sector to convert to cleaner energy sources. In order to lower the system's dependence on traditional fuel reserves during peak demand hours and progress towards introducing greener energy into the network with no discernible generation intermittency, an efficient scheduling model has been developed in this article to regulate end-user load as well as solar generation. The scheduling model is built with a long-short term memory (LSTM) network-based solar energy prediction approach integrated with a load and solar energy scheduling model based on teaching-learning optimization (TLBO). In addition to effective scheduling, a secure trade platform based on blockchain technology is being developed for utility and prosumer interaction in a cyber-secured environment. The suggested technique is intended for three-phased distribution networks, and its effectiveness is demonstrated using a 906-bus low voltage European distribution network. The proposed methodology is developed using MATLAB and Remix IDE interface. The effectiveness of the considered optimization in the proposed scheduling model is tested against another population-based optimization based identical scheduling model.

关键词： optimization Load modeling Job shop scheduling Renewable energy sources Mathematical models Costs Solar energy Blockchain based decentralized application load scheduling long-short term memory solar energy supply scheduling teaching learning based optimization

来源：评论

学校读者我要写书评

暂无评论

An efficient multi-unit production planning strategy based on continuous variables

引用

APPLIED SOFT COMPUTING 2018年 68卷 458-477页

作者： Chauhan, Sandeep Singh Kotecha, Prakash Indian Inst Technol Guwahati Dept Chem Engn Gauhati 781039 Assam India

Production planning can significantly enhance the competitiveness and hence plays a crucial role in manufacturing industries. In the production planning problem discussed in this article, a set of processes are available which can be operated at various capacity levels with the production and investment costs being proportional to the production of the processes. The determination of the optimal production plan, in terms of the selection of product to be manufactured, the selection and operating capacity of the manufacturing processes in the presence of multiple resource constraints so as to obtain maximum profit is a combinatorial optimization problem. In this article, we state the limitations of the formulation/strategies employed in literature and propose a multi-unit strategy which utilizes only continuous variables to overcome them. The proposed strategy is generic and demonstrated in the context of production planning in a petrochemical industry that has been previously used to potentially guide the petrochemical industries. The proposed strategy is demonstrated with multiple computational intelligence algorithms viz., artificial bee colony, dynamic neighbourhood learning particle swarm optimizer, multi-population ensemble differential evolution, and teaching -learning-based optimization. For the cases discussed in literature, the proposed strategy shows an improvement of up to 12.1% in the profit. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Production planning Artificial bee colony teaching learning based optimization Dynamic neighborhood learning particle swarm optimizer Multi-Population Ensemble Differential Evolution

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：