检索结果-内蒙古大学图书馆

A Comprehensive Survey on Intelligent Reflecting Surfaces and Unmanned Aerial Vehicles Integration for Enhanced Communication in Massive Networks 11

A Comprehensive Survey on Intelligent Reflecting Surfaces an...

引用

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Attar, Hani Ababneh, Jafar Hafez, Mohamed Rachini, Ali Solyman, Ahmed Bahy, Ramy M. Zarqa University Faculty of Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia Zarqa University Faculty of Information Technology Cyber Security Department Zarqa Jordan INTI-IU-University Nilai Faculty of Engineering Feqs Malaysia Department of Computer Science and Information Technology Jounieh Lebanon School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom Technical Research Center Cairo Egypt

ISBN: (纸本)9798331509293

Intelligent Reflecting Surfaces (IRSs) offer a revolutionary approach to wireless communication by dynamically controlling the properties of electromagnetic waves. By manipulating wavefronts without requiring radio frequency links, IRSs can enhance spectrum and energy efficiency, reduce costs, and improve overall system performance. Unmanned Aerial Vehicles (UAVs) have garnered significant attention due to their mobility and adaptability. However, real-time data transmission between UAVs can be hindered by obstacles and security risks. By combining IRSs and UAVs, we can create unparalleled opportunities in demanding environments. Through coordinated movements and intelligent wave reflection, both systems can optimize wireless signal propagation. This paper provides a comprehensive review of IRS-assisted UAV communications. We explore existing research, introduce novel technologies and applications, and highlight potential research directions for developing low-cost and energy-efficient wireless systems. Additionally, we address current challenges and outline promising areas for future study. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis and Evaluation of Well-being Activity-Infused Fine-Tuned Language Models with Benchmark Models

Comparative Analysis and Evaluation of Well-being Activity-I...

引用

2025 IEEE Symposium on Computational Intelligence in Health and Medicine, CIHM 2025

作者： Mohammed, Hamza Haruna Kiss, Gabriel Serrano, J. Artur Lindseth, Frank Department of Computer Science Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim Norway Department of Neuromedicine and Movement Science Faculty of Medicine and Health Sciences Norwegian University of Science and Technology Trondheim Norway

ISBN: (纸本)9798331508333

Large language models (LLMs) have significantly impacted natural language processing (NLP), healthcare, and beyond fields. LLMs have demonstrated unprecedented abilities to understand and generate human-like text, making them highly valuable for various tasks, including information retrieval, question-answering, and conversational AI. However, as these models are integrated into real-world applications, especially in sensitive domains such as healthcare, it becomes essential to evaluate their performance comprehensively. We present a process for fine-tuning LLMs to incorporate cardiac exercise and corpus of well-being activity, aiming to promote activity health support through NLP-driven applications. Using QLoRA, you can ensure that the model size remains small and reduce overhead while maintaining the high performance of the fine-tuned model. Subsequently, this paper presents a comparative analysis benchmark pipeline to evaluate fine-tuned models with base models on standard benchmark datasets from the healthcare domain. The aim is to evaluate the performance, robustness and accuracy of these models, showing that the fine-tuning process does not degrade the model performance, but improves the performance to some extent in some benchmarks. © 2025 IEEE.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Wind Power Forecasting Using Enhanced Multilayer Perceptron

引用

computers, Materials & Continua 2025年第5期83卷 2287-2303页

作者： Ahmed A.Ewees Mohammed A.A.Al-Qaness Ali Alshahrani Mohamed Abd Elaziz Computer Science and Artificial Intelligence Department College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia Department of Computer Damietta UniversityDamietta34517Egypt College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China Department of Mathematics Faculty of ScienceZagazig UniversityZagazig44519Egypt

Wind power forecasting plays a crucial role in optimizing the integration of wind energy into the grid by predicting wind patterns and energy *** enhances the efficiency and reliability of renewable energy *** approaches inform energy management strategies,reduce reliance on fossil fuels,and support the broader transition to sustainable energy *** primary goal of this study is to introduce an effective methodology for estimating wind power through temporal data *** research advances an optimized Multilayer Perceptron(MLP)model using recently proposedmetaheuristic optimization algorithms,namely the FireHawk Optimizer(FHO)and the Non-Monopolize Search(NO).A modified version of FHO,termed FHONO,is developed by integrating NO as a local search mechanism to enhance the exploration capability and address the shortcomings of the original *** developed FHONO is then employed to optimize the MLP for enhanced wind power *** effectiveness of the proposed FHONO-MLP model is validated using renowned datasets from wind turbines in *** results of the comparative analysis between FHONO-MLP,conventionalMLP,and other optimized versions of MLP show that FHONO-MLP outperforms the others,achieving an average RootMean Square Error(RMSE)of 0.105,Mean Absolute Error(MAE)of 0.082,and Coefficient of Determination(R^(2))of 0.967 across all *** findings underscore the significant enhancement in predictive accuracy provided by FHONO and demonstrate its effectiveness in improving wind power forecasting.

关键词： Wind power forecasting multilayer perceptron fire hawk optimizer non-monopolize search

来源：评论

学校读者我要写书评

暂无评论

The Risks & Realities of Picking an IoT OS

The Risks & Realities of Picking an IoT OS

引用

computer Applications (ICCA), IEEE Conference on

作者： Pyae Sone Hein Zar Zar Linn Master of Engineering in Computer Science Myanmar Institute of Information Technology Faculty of Computer Science Myanmar Institute of Information Technology

ISBN: (数字)9798331534592

ISBN: (纸本)9798331534608

Internet of Things is no longer a new topic. Long ago, the network of things was a rare thing which could be seen only in offices, industries, and labs. Nowadays it is approaching becoming a ubiquitous appliance as a commonplace in everyday environments. Homes and public places such as traffic and city parks have changed to adapt with things within the ability to connect to a network. As a result, even commoners are becoming familiar with IoT. Researchers lay the new technologies into IoT networks. Developers drive them into industry and practitioners carry the aesthetic essence by carrying on the practice among people. In doing so, choosing the correct operating system for the correct device is a step not to be skipped as the learning curve grows up to advanced. This study aims to aid the practitioners by discussing the risks and realities concerned with the role of OS in IoT devices or systems.

关键词： Industries Job shop scheduling Systematics Operating systems Urban areas Switches Systems engineering and theory Real-time systems Internet of Things Stress

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Efficient Byzantine-Robust Federated Learning Based on the Multi-Message Shuffle Protocol for Consumer Internet of Things

引用

IEEE Internet of Things Journal 2025年

作者： Jin, Chunhua Li, Lulu Wang, Jiahao Li, Jinbiao Liu, Junyi Chen, Guanhua Zhang, Hao Weng, Jian Faculty of Computer Software Engineering with Huaiyin Institute of Technology Huai’an China Huaiyin Institute of Technology Faculty of Computer Software Engineering Huai’an China Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China Jinan University College of Information Science and Technology China

The accelerated advancement of consumer Internet of Things (CIoT) devices has resulted in their pervasive integration into the fabric of contemporary lifestyles. As these devices are capable of collecting vast quantities of data pertaining to users, they present a significant risk to the privacy and security of individuals. Federated learning is an advanced machine learning paradigm that prioritises the preservation of user data privacy and enhances security by eliminating the need for centralised data collection. As a result, it is a promising approach to address user data privacy and security concerns. However, federated learning still faces challenges such as privacy attacks, Byzantine attacks and high communication overheads. To address these challenges, we propose an efficient Byzantine-robust federated learning method based on multi-message shuffle protocol. To achieve privacy protection and Byzantine robustness, we introduce an innovative aggregation strategy inspired by the multi-message shuffle protocol for differential privacy. To improve communication efficiency, we develop an adaptive gradient compression scheme. Theoretical analysis indicates that our multi-message shuffle protocol is capable of satisfying the requisite differential privacy conditions. Compared with the state-of-the-art methods, our proposed scheme demonstrates superior convergence capabilities on the real-world dataset when approximately 40% of participants are Byzantine, achieving accuracies of 96.78%, which illustrates its strong robustness. Upon reduction of the transmitted model parameters to 1% of the original size, the proposed scheme exhibits a maximum accuracy degradation of 0.35%. which significantly reduces the communication overhead while achieving high accuracy. In addition, the scheme also achieves an accuracy of 88.73% on the Non-iid MotionSense dataset, which is superior to other schemes. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive resource allocation and routing for integrated sensing and communications for wireless technologies

引用

Eurasip Journal on Wireless Communications and Networking 2025年第1期2025卷 1-27页

作者： Subramaniyan, Manochandar Venkatasamy, Thiruppathy Kesavan Thotakuruchi Mathiyalagan, Nithya Jakir Hossen, Md. Faculty of Digital Business & Analytics Bharathidasan Institute of Management Tamil Nadu Tiruchirappalli 620014 India Faculty of Information Technology Dhanalakshmi Srinivasan Engineering College Tamil Nadu Perambalur 621212 India Center for Advanced Analytics (CAA) COE for Artificial Intelligence Faculty of Engineering & Technology (FET) Multimedia University Melaka 75450 Malaysia Faculty of Computer Science and Engineering K. Ramakrishnan College of Engineering Tamil Nadu Samayapuram 621112 India Post Doctoral Fellow Department of Engineering & Technology Multimedia University Melaka 75450 Malaysia

The integrated sensing and communications (ISC) application completely changes the game regarding collecting, analyzing, and dispensing facts in real time via combining sensing skills with communication structure. The present research delves into how ISC can enhance decision-making in healthcare, smart towns, and environmental monitoring. Issues with interoperability, electricity intake, ecological resilience, and the worrying latency requirements of task-critical packages are many obstacles to easy integration. Our proposed mechanism, adaptive resource allocation and routing for integrated sensing (ARAR-IS), which uses new wireless technologies, attempts to clear up these problems by allocating and routing assets for incorporated sensing. ARAR-IS dynamically allocates sources and routes information considering the real global and network dynamics. Optimizing resource utilization, mitigating interference, and enhancing dependability in ISC systems are achieved using ARAR-IS, which leverages cognitive routing algorithms and software program-defined networking ideas. With ARAR-IS, various computer-aided engineering regions can benefit from customized remedy plans, far-off patient tracking, and real-time attempts to lessen pollution. These domains include healthcare, proper infrastructure, industrial automation, and environmental monitoring. Thorough simulation-based assessments show that ARAR-IS is a pleasant alternative for ISC systems in many one-of-a-kind situations because of its high reliability, low-strength intake, excessive throughput, and low latency. © The Author(s) 2025.

关键词： Adaptive control Data communication Resource allocation Routing protocols Wireless channels

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Projection Neural Network With Finite-Time Convergence for Energy Management of Multi-Energy System

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2156-2168页

作者： Liu, Xueying He, Xing Li, Chaojie Huang, Tingwen Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Chongqing400715 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources Beijing102206 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

In this paper, an approach based on projection neural network (PNN), sliding mode control technique, and deep learning is proposed to solve the energy management problem of multi-energy systems (MES) containing dynamic parameters. First, the sliding mode technique is introduced in the PNN to design a finite-time PNN (FTPNN). The stability and finite-time convergence of the proposed FTPNN are proved by the Lyapunov method and the setting time bound is given. Then, the deep FTPNN (DFTPNN) is designed by combining deep learning with the proposed FTPNN. The dynamic parameters in the MES that change over time are used as input variables for the DFTPNN, allowing the trained DFTPNN to respond immediately to changes in the dynamic parameters and to predict the solutions of the FTPNN with different parameters directly. Simulation experiments show that FTPNN has faster convergence compared to PNN. DFTPNN significantly reduces the computation time compared to FTPNN. DFTPNN provides predicted solutions to FTPNN. Since DFTPNN can respond immediately to changes in dynamic parameters and directly provide energy management strategies under different parameters, it can adapt to changing environments and promote the economic and stable operation of MES. © 2010-2012 IEEE.

关键词： Cogeneration Heuristic algorithms Convergence Deep learning Prediction algorithms Optimization Heating systems Energy management Approximation algorithms Power system stability

来源：评论

学校读者我要写书评

暂无评论

GPSOM: group-based particle swarm optimization with multiple strategies for engineering applications

引用

Journal of Big Data 2025年第1期12卷 1-40页

作者： Yan, Jialing Hu, Gang Jia, Heming Hussien, Abdelazim G. Abualigah, Laith Department of Applied Mathematics Xi’an University of Technology Xi’an710054 China School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China School of Information Engineering Sanming University Sanming365004 China Department of Computer and Information Science Linköping University Linköping58183 Sweden Faculty of Science Fayoum University Faiyum63514 Egypt Computer Science Department Al al-Bayt University Mafraq25113 Jordan

Particle Swarm Optimization (PSO) is a classic optimization algorithm;however, it has issues when solving high-dimensional complex optimization problems, such as sensitivity to initial parameters, insufficient population diversity, and susceptibility to becoming stuck in local optima. To this end, we propose a particle swarm optimization algorithm with multiple swarm strategies (GPSOM) that significantly improves the algorithm’s optimization performance by designing grouping and diversification strategies for the population. GPSOM divides the population into three subgroups and adopts targeted strategies based on different phases: sub-swarm 1 focuses on exploration and improves population diversity and local search ability by dynamically adjusting operators;sub-swarm 2 focuses on exploitation, introducing sine cosine factors and adaptive mechanisms to traverse the solution space efficiently;sub-swarm 3 achieves global and local balance, generating high-quality solutions through adaptive factors and position adjustment operators. The experimental results show that GPSOM performs significantly better than traditional algorithms on the Combinatorial Evolutionary Computing (CEC) 2020 benchmark test set (hereinafter referred to as 20TS), and its reliability and efficiency have been demonstrated in practical applications, such as 15 engineering examples, vehicle cruise control, and robot path optimization. GPSOM is an efficient, stable, practical optimization algorithm that effectively solves high-dimensional complex optimization problems. © The Author(s) 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Retinal disorder diagnosis based on hybrid deep learning models

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

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：