检索结果-内蒙古大学图书馆

Deep learning at the service of metaheuristics for solving numerical optimization problems

Neural computing and Applications 2025年 1-36页

作者： Oyelade, Olaide N. Ezugwu, Absalom E. Saha, Apu K. Thieu, Nguyen V. Gandomi, Amir H. School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast Bangladesh Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 United States Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India Faculty of Computer Science Phenikaa University Yen Nghia Hanoi Ha Dong12116 Viet Nam Department of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Integrating deep learning methods into metaheuristic algorithms has gained attention for addressing design-related issues and enhancing performance. The primary objective is to improve solution quality and convergence speed within solution search spaces. This study investigates the use of deep learning methods as a generative model to learn historical content, including global best and worst solutions, solution sequences, function evaluation patterns, solution space characteristics, population modification trajectories, and movement between local and global search processes. An LSTM-based architecture is trained on dynamic optimization data collected during the metaheuristic optimization process. The trained model generates an initial solution space and is integrated into the optimization algorithms to intelligently monitor the search process during exploration and exploitation phases. The proposed deep learning-based methods are evaluated on 55 benchmark functions of varying complexities, including CEC 2017 and compared with 13 biology-based, evolution-based, and swarm-based metaheuristic algorithms. Experimental results demonstrate that all the deep learning-based optimization algorithms achieve high-quality solutions, faster convergence rates, and significant performance improvements. These findings highlight the critical role of deep learning in addressing design issues, enhancing solution quality, trajectory, and performance speed in metaheuristic algorithms. © The Author(s) 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A comparative study on graft copolymerization of MMA onto wood fiber under microwave and conventional heating

A comparative study on graft copolymerization of MMA onto wo...

引用

2022 International Conference on Material science, Mechanics and Technology, ICMMT 2022

作者： Ko, R.V.K. Soon, K.H. Siddique, B.M. Jayamani, E. Lee, X.Y. Palanisamy, S. Faculty of Engineering Computing and Science Swinburne University of Technology Sarawak Campus Sarawak Malaysia Department of Materials Engineering Faculty of Engineering and Technology Tunku Abdul Rahman University College Kuala Lumpur Malaysia School of Engineering Swinburne University of Technology Hawthorn Australia

Wood polymer composites (WPC) are gaining popularity and widespread usage due to an increased awareness of human population towards the importance of environmental effects and green eco-friendly materials. Mechanical properties of WPC could be improved through graft copolymerization of monomer onto wood fiber to improve interfacial bonding. In this study, a comparison of free radical graft copolymerization using microwave-assisted and conventional heating method was performed. Methyl methacrylate (MMA) monomer is used in graft copolymerization of Meranti wood using a free radical initiator system consisting of ferrous sulfate and hydrogen peroxide. Grafting reaction time was varied while other graft parameters were kept constant including monomer concentration, initiator molar ratio, reaction temperature and solvent volume. Maximum graft yield of 11.75% and 10.17% were obtained for water bath heated and microwave-assisted method respectively. The presence of grafted monomer was proven by FTIR spectra analysis. Thermogravimetric analysis performed on grafted wood fibers showed improved thermal resistance compared to ungrafted wood fiber. © Published under licence by IOP Publishing Ltd.

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Dipper Throated Algorithm for Feature Selection and Classification in Electrocardiogram

引用

Computer Systems science & engineering 2023年第5期45卷 1469-1482页

作者： Doaa Sami Khafaga Amel Ali Alhussan Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Mohamed Saber El-Sayed M.El-kenawy Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Electronics and Communications Engineering Department Faculty of EngineeringDelta University for Science and TechnologyMansouraEgypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt

Arrhythmia has been classified using a variety of *** of the dynamic nature of electrocardiogram(ECG)data,traditional handcrafted approaches are difficult to execute,making the machine learning(ML)solutions more *** with cardiac arrhythmias can benefit from competent monitoring to save their *** arrhythmia classification and prediction have greatly improved in recent *** are a category of conditions in which the heart's electrical activity is abnormally rapid or *** year,it is one of the main reasons of mortality for both men and women,*** the classification of arrhythmias,this work proposes a novel technique based on optimized feature selection and optimized K-nearest neighbors(KNN)*** proposed method makes advantage of the UCI repository,which has a 279-attribute high-dimensional cardiac arrhythmia *** proposed approach is based on dividing cardiac arrhythmia patients into 16 groups based on the electrocardiography dataset’s *** purpose is to design an efficient intelligent system employing the dipper throated optimization method to categorize cardiac arrhythmia *** method of comprehensive arrhythmia classification outperforms earlier methods presented in the *** achieved classification accuracy using the proposed approach is 99.8%.

关键词： Feature selection electrocardiogram metaheuristics dipper throated algorithm

来源：评论

学校读者我要写书评

暂无评论

Organising unstructured data using Double Net Self-Organising Map (DNSOM) model

引用

Soft computing 2025年第7期29卷 3533-3554页

作者： You, Cheng Chun Lim, Seng Poh Lee, Chen Kang Tan, Joi San Lim, Seng Chee Department of Computer Science Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Jalan University Bandar Barat Perak Kampar31900 Malaysia Department of Computing Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Jalan Sungai Long Bandar Sungai Long Cheras Selangor Kajang43000 Malaysia School of Computing and Informatics ViTrox College 746 Persiaran Cassia Selatan 3 Batu Kawan Industrial Park Penang Bandar Cassia14110 Malaysia

Surface reconstruction is the process of representing surfaces using the data obtained from scanning devices. When the data obtained is unstructured during data collection, it can cause problems in presenting the surface due to the lack of connectivity information for the data. It shows that data collection is a crucial task in surface reconstruction. Previous works have proved that Self-Organising Map (SOM) models can be used to organise unstructured data. However, the 2-D SOM model will generate a surface with holes for the closed surfaces. Besides, the 3-D SOM model will generate an incorrect surface due to the connectivity of the internal neurons. In addition, the Cube Kohonen SOM (CKSOM) model is limited to the same grid size. Hence, a SOM model known as Double Net SOM (DNSOM) is proposed via the merging of two 2-D SOMs to overcome the issues. Three data sets (cube, sphere, and talus bone) with different grid sizes are applied to test the models. When the grid size of all the models increases, the surface becomes smoother. The DNSOM contains a lower quantisation error than the 2-D SOM and the lowest topographic error among the other SOM models. It performs faster than the 3-D SOM and CKSOM. It presents the correct closed surface with a smaller number of neurons and different grid sizes. Microsoft Visual Studio 2022 with the C++ programming language is used to develop the models, while GNUPlot is used to visualise the results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Local search yields a PTAS for fixed-dimensional k-means problem with penalties

引用

Journal of the Operations Research Society of China 2024年第2期12卷 351-362页

作者： Fan Yuan Da-Chuan Xu Dong-Lei Du Dong-Mei Zhang Beijing Institute for Scientific and Engineering Computing Beijing University of TechnologyBeijing 100124China Faculty of Management University of New BrunswickFrederictonNB E3B 9Y2Canada School of Computer Science and Technology Shandong Jianzhu UniversityJinan 250101ShandongChina

We study a problem called the k-means problem with penalties(k-MPWP),which is a natural generalization of the typical k-means *** this problem,we have a set D of client points in R^(d),a set F of possible centers in R^(d),and a penalty cost Pj>O for each point j∈*** are also given an integer k which is the size of the center point *** want to find a center point set S■F with size k,choose a penalized subset of clients P■D,and assign every client in D\P to its open *** goal is to minimize the sum of the squared distances between every point in D\P to its assigned centre point and the sum of the penalty costs for all clients in *** using the multi-swap local search technique and under the fixed-dimensional Euclidean space setting,we present a polynomial-time approximation scheme(PTAS)for the k-MPWP.

关键词： Approximation algorithm k-means Local search Penalty

来源：评论

学校读者我要写书评

暂无评论

FL@FM-TheWebConf’24: International Workshop on Federated Foundation Models for the Web 24

FL@FM-TheWebConf’24: International Workshop on Federated Fo...

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： King, Irwin Long, Guodong Xu, Zenglin Yu, Han Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Faculty of Engineering and IT University of Technology Sydney Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400701726

In the evolving landscape of machine learning research, two significant developments have emerged to prominence: foundation models and federated learning. The FL@FM-TheWebConf’24 workshop provides an exciting forum for researchers and practitioners to discuss promising works and chart potential trajectories forward for this emerging field. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Genetic Car Designer: A Large-Scale User Study of a Mixed-Initiative Design Tool (A Work in Progress)

Genetic Car Designer: A Large-Scale User Study of a Mixed-In...

引用

2023 Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour, AISB 2023

作者： Walton, Sean P. Vincalek, Jakub Rahat, Alma A.M. Stovold, James Evans, Ben J. Computational Foundry Faculty of Science and Engineering Swansea University Wales United Kingdom School of Computing and Communications Lancaster University Leipzig Nikolaistraße 10 Leipzig04109 Germany Department of Aerospace Faculty of Science and Engineering Swansea University Wales United Kingdom

ISBN: (纸本)9781713879466

This work-in-progress paper presents the initial results from a large-scale user study of a mixed-initiative design tool. A simple mixed-initiative design tool using a mutant shopping approach, coupled with MAP-Elites was created and made available to the public. In the tool participants were tasked with designing a simple car;the computer then presented sets of suggestions to participants to use and/or edit. Three out of four of these sets were generated using MAP-Elites and the forth was simply a control set of random designs. A total of 808 sessions were recorded and we found that participants who interacted with the algorithm produced better quality designs than the algorithm working alone. We also found that participants were statistically more likely to use suggestions from views which contained designs generated using a MAP-Elites algorithm compared to a randomised control. © AISB Convention *** rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Role of ERNIE Model in Analyzing Hotel Reviews using Chinese Sentiment Analysis

The Role of ERNIE Model in Analyzing Hotel Reviews using Chi...

引用

2023 International Conference on Computer Communication and Informatics, ICCCI 2023

作者： Jie, Lee Hao Ayyasamy, Ramesh Kumar Sangodiah, Anbuselvan Jalil, Norazira Binti A Krishnan, Kesavan Chinnasamy, P. University Tunku Abdul RahmanKampar Faculty of Information and Communication Technology Malaysia Faculty of Computing and Engineering Quest International University Ipoh Malaysia Universiti Malaya Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia MLR Institute of Technology Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350348217

This research aims to find the best deep learning model to do Chinese sentimental analysis. BERT's model may work well in the English language but not work in the Chinese language. English is easier to encode in embedding space, and words are separated by space characters, unlike Chinese words, which do not exist separate by the area. BERT Chinese model work on character level encoding is not enough to make the BERT model adapt to Chinese NLP tasks. The BERT Model and ERNIE models are the current state of art pre-training language models. Word level embeddings and input is needed to improve the BERT model to perform in Chinese Sentiment Analysis. With the motivation to improve the Chinese Sentiment Analysis, this study will explore the role of different models to propose a better version of the ERNIE model. This study will limit the scope to improve Chinese sentiment analysis among different NLP tasks. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Improved Transportation Model with Internet of Things Using Artificial Intelligence Algorithm

引用

Computers, Materials & Continua 2023年第8期76卷 2261-2279页

作者： Ayman Khallel Al-Ani Shams Ul Arfeen Laghari Hariprasath Manoharan Shitharth Selvarajan Mueen Uddin Cybersecurity Research Group Faculty of Computing and InformaticsUniversity Malaysia SabahJalan UMSKota KinabaluSabah88400Malaysia National Advanced IPv6 Centre(NAv6) Universiti Sains MalaysiaGelugorPenang11800Malaysia Department of Electronics and Communication Engineering Panimalar Engineering CollegePoonamalleeChennai600123TamilnaduIndia Department of Computer Science&Engineering Kebri Dehar UniversityKebri Dehar250Ethiopia College of Computing and Information Technology University of Doha for Science and TechnologyDoha24449Qatar

In this paper,the application of transportation systems in realtime traffic conditions is evaluated with data handling *** proposed method is designed in such a way as to detect the number of loads that are present in a vehicle where functionality tasks are computed in the *** to the existing approach,the design model in the proposed method is made by dividing the computing areas into several cluster regions,thereby reducing the complex monitoring system where control errors are ***,a route management technique is combined with Artificial Intelligence(AI)algorithm to transmit the data to appropriate central ***,the combined objective case studies are examined as minimization and maximization criteria,thus increasing the efficiency of the proposed ***,four scenarios are chosen to investigate the projected design’s *** all simulated metrics,the proposed approach provides better operational outcomes for an average percentage of 97,thereby reducing the amount of traffic in real-time conditions.

关键词： Transportation Artificial Intelligence(AI) data-driven Internet of Things(IoT)

来源：评论

学校读者我要写书评

暂无评论

A novel medical steganography technique based on Adversarial Neural Cryptography and digital signature using least significant bit replacement

引用

International Journal of Cognitive computing in engineering 2024年第1期5卷 379-397页

作者： Hameed, Mohamed Abdel Hassaballah, M. Abdelazim, Riem Sahu, Aditya Kumar Department of Computer Science Faculty of Computers and Information Luxor University Luxor85951 Egypt Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University AlKharj16278 Saudi Arabia Department of Computer Science Faculty of Computers and Information South Valley University Qena Egypt Department of Information Systems College of Information Technology Misr University for Science and Technology Giza Egypt Amrita School of Computing Amrita Vishwa Vidyapeetham Andhra Pradesh Amaravati522503 India

With recent advances in technology protecting sensitive healthcare data is challenging. Particularly, one of the most serious issues with medical information security is protecting of medical content, such as the privacy of patients. As medical information becomes more widely available, security measures must be established to protect confidentiality, integrity, and availability. Image steganography was recently proposed as an extra data protection mechanism for medical records. This paper describes a data-hiding approach for DICOM medical pictures. To ensure secrecy, we use Adversarial Neural Cryptography with SHA-256 (ANC-SHA-256) to encrypt and conceal the RGB patient picture within the medical image's Region of Non-Interest (RONI). To ensure anonymity, we use ANC-SHA-256 to encrypt the RGB patient image before embedding. We employ a secure hash method with 256bit (SHA-256) to produce a digital signature from the information linked to the DICOM file to validate the authenticity and integrity of medical pictures. Many tests were conducted to assess visual quality using diverse medical datasets, including MRI, CT, X-ray, and ultrasound cover pictures. The LFW dataset was chosen as a patient hidden picture. The proposed method performs well in visual quality measures including the PSNR average of 67.55, the NCC average of 0.9959, the SSIM average of 0.9887, the UQI average of 0.9859, and the APE average of 3.83. It outperforms the most current techniques in these visual quality measures (PSNR, MSE, and SSIM) across six medical assessment categories. Furthermore, the proposed method offers great visual quality while being resilient to physical adjustments, histogram analysis, and other geometrical threats such as cropping, rotation, and scaling. Finally, it is particularly efficient in telemedicine applications with high achieving security with a ratio of 99% during remote transmission of Electronic Patient Records (EPR) over the Internet, which safeguards the patien

关键词： Steganography

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：