检索结果-内蒙古大学图书馆

Evolutionary recurrent neural network based on equilibrium optimization method for cloud-edge resource management in internet of things

引用

Neural Computing and Applications 2025年第6期37卷 4957-4969页

作者： Ebrahimi Mood, Sepehr Rouhbakhsh, Adel Souri, Alireza Department of Computer Science Yazd University Yazd Iran Department of Computer Engineering Faculty of Engineering Haliç University Istanbul34060 Turkey School of Electrical and Electronic Engineering Shandong University of Technology Zibo255000 China

Cloud computing is an emerging field in information technology, enabling users to access a shared pool of computing resources. Despite its potential, cloud technology presents various challenges, with one of the most significant being resource management within the cloud environment. Specifically, the allocation of physical machines (PMs) to virtual machines (VMs) in the Infrastructure as a service (IaaS) layer aims to achieve optimal efficiency. To address this challenge, we propose an evolutionary recurrent neural network (RNN) for resource allocation, enhanced by the equilibrium optimization (EO) algorithm. This method improves the generalization performance and reduces the architecture complexity of RNNs, while ensuring better adaptability to various demand patterns in cloud environments. Additionally, the effectiveness of RNNs heavily relies on the quality of training data;hence, we generate appropriate training data to facilitate the development of an efficient resource management model. Through extensive simulations, our method demonstrates superior performance compared to traditional algorithms. However, it is worth noting that this study is primarily based on simulation results, highlighting the need for real-world validation to confirm its practical applicability. The proposed method's applicability to different cloud computing environments and scenarios, including various service models (IaaS, PaaS, and SaaS) and deployment models (public, private, and hybrid), is also briefly discussed. Future studies should explore the computational efficiency and potential optimization techniques of the EO-RNN approach and consider real-world implementations to validate its effectiveness and uncover practical challenges. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Optimizing breast cancer diagnosis: Harnessing the power of nature-inspired metaheuristics for feature selection with soft voting classifiers

引用

International Journal of Cognitive Computing in engineering 2025年第1期6卷 1-20页

作者： Benghazouani, Salsabila Nouh, Said Zakrani, Abdelali Department of Mathematics and Computer Science Faculty of Sciences Ben M'Sick Hassan II University Casablanca Morocco Department of Computer Science Engineering ENSAM Hassan II University Casablanca Morocco

Breast cancer is a widespread and serious condition that poses a significant threat to women's health globally, contributing significantly to mortality rates. Machine learning tools play a critical role in both the effective management and early detection of this disease. Feature selection (FS) methods are essential for identifying the most impactful features to improve breast cancer diagnosis. These methods reduce data dimensionality, eliminate irrelevant information, enhance learning accuracy, and improve the comprehensibility of results. However, the increasing complexity and dimensionality of cancer data pose substantial challenges to many existing FS methods, thereby reducing their efficiency and effectiveness. To overcome these challenges, numerous studies have demonstrated the success of nature-inspired optimization (NIO) algorithms across various domains. These algorithms excel in mimicking natural processes and efficiently solving complex optimization problems. Building on these advancements, we propose an innovative approach that combines powerful feature selection methods based on NIO techniques with a soft voting classifier. The NIO techniques employed include the Genetic Algorithm, Cuckoo Search, Salp Swarm, Jaya, Flower Pollination, Whale Optimization, Sine Cosine, Harris Hawks, and Grey Wolf Optimization algorithms. The Soft Voting Classifier integrates various machine learning models, including Support Vector Machines, Gaussian Naive Bayes, Logistic Regression, Decision Tree, and Gradient Boosting. These are used to improve the effectiveness and accuracy of breast cancer diagnosis. The proposed approach has been empirically evaluated using a variety of evaluation measures, such as F1 score, precision, recall, accuracy and Area Under the Curve (AUC), for performance comparison with individual machine learning techniques. The results demonstrate that the soft-voting ensemble technique, particularly when combined with feature selection based on the Jaya

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Binary Stochastic Flip Optimization for Training Binary Neural Networks

Binary Stochastic Flip Optimization for Training Binary Neur...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shibuya, Tatsukichi Inoue, Nakamasa Kawakami, Rei Sato, Ikuro Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (纸本)9798350368741

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in finetuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising

引用

IEEE Access 2025年 13卷 71880-71907页

作者： El-Nabi, Samy Abd Ibrahim, Ahmed F. El-Rabaie, El-Sayed M. Hassan, Osama F. Soliman, Naglaa F. Ramadan, Khalil F. El-Shafai, Walid Faculty of Computer Science and Engineering Department of Artificial Intelligence Engineering South Sinai 46511 Egypt Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Suez Canal University Faculty of Computers and Informatics Information Systems Department Ismailia41522 Egypt Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Computer Science Department Riyadh11586 Saudi Arabia

With the rapid development of intelligent transportation systems and growing emphasis on driver safety, real-time detection of driver drowsiness has become a critical area of research. This study presents a robust and scalable driver drowsiness detection framework that integrates a Swin Transformer-based deep learning model with a diffusion model for image denoising. While conventional convolutional neural networks (CNNs) are effective in standard vision tasks, they often suffer performance degradation in real-world driving scenarios due to noise, poor lighting, motion blur, and adversarial attacks. To address these challenges, the proposed model focuses on eye-state detection, specifically, prolonged eye closure, as a primary indicator of driver disengagement and fatigue. Our system introduces a novel preprocessing stage using a denoising diffusion model built on a U-Net encoder-decoder architecture, effectively mitigating the impact of Gaussian noise and adversarial perturbations. Additionally, we incorporate adversarial training with Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, demonstrating significant improvements in classification accuracy and resilience. Evaluations are conducted on two benchmark datasets, Eye-Blink and Closed Eyes in the Wild (CEW), under both clean and noisy conditions. Comparative experiments show that the proposed system outperforms several state-of-the-art models, including ViT, ResNet50V2, InceptionV3, MobileNet, DenseNet169, and VGG19, in terms of accuracy (up to 99.82%), PSNR (up to 41.61 dB), and SSIM (up to 0.984), while maintaining competitive inference times suitable for practical deployment. Moreover, a detailed sensitivity analysis of data augmentation strategies reveals that techniques such as rotation and horizontal flip substantially enhance the model’s generalization across variable visual inputs. The system also demonstrates improved robustness under real-world black-box scenarios and adver

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Multi-Objective Framework for Energy Optimization and Reliable Routing in Wireless Sensor Networks via Particle Swarm Optimization

引用

computers, Materials & Continua 2025年第5期83卷 2773-2792页

作者： Medhat A.Tawfeek Ibrahim Alrashdi Madallah Alruwaili Fatma M.Talaat Department of Computer Science College of Computer and Information SciencesJouf UniversitySakaka72341AljoufSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72341AljoufSaudi Arabia Faculty of Artificial Intelligence Kafrelsheikh UniversityKafrelsheikh33516Egypt Faculty of Computer Science&Engineering New Mansoura UniversityGamasa35712Egypt

Wireless Sensor Networks(WSNs)are one of the best technologies of the 21st century and have seen tremendous growth over the past *** work has been put into its development in various aspects such as architectural attention,routing protocols,location exploration,time exploration,*** research aims to optimize routing protocols and address the challenges arising from conflicting objectives in WSN environments,such as balancing energy consumption,ensuring routing reliability,distributing network load,and selecting the shortest *** optimization techniques have shown success in achieving one or two objectives but struggle to achieve the right balance between multiple conflicting *** address this gap,this paper proposes an innovative approach that integrates Particle Swarm Optimization(PSO)with a fuzzy multi-objective *** proposed method uses fuzzy logic to effectively control multiple competing objectives to represent its major development beyond existing methods that only deal with one or two *** search efficiency is improved by particle swarm optimization(PSO)which overcomes the large computational requirements that serve as a major drawback of existing *** PSO algorithm is adapted for WSNs to optimize routing paths based on fuzzy multi-objective *** fuzzy logic framework uses predefined membership functions and rule-based reasoning to adjust routing *** adjustments influence PSO’s velocity updates,ensuring continuous adaptation under varying network *** proposed multi-objective PSO-fuzzy model is evaluated using NS-3 *** results show that the proposed model is capable of improving the network lifetime by 15.2%–22.4%,increasing the stabilization time by 18.7%–25.5%,and increasing the residual energy by 8.9%–16.2% compared to the state-of-the-art *** proposed model also achieves a 15%–24% reduction in load variance,demonstrating balanced routing and extended net

关键词： Wireless sensor networks particle swarm optimization fuzzy multi-objective framework routing stability

来源：评论

学校读者我要写书评

暂无评论

Multi-orthogonal-oppositional enhanced African vultures optimization for combined heat and power economic dispatch under uncertainty

引用

Neural Computing and Applications 2025年第8期37卷 6097-6123页

作者： Rizk-Allah, Rizk M. Snášel, Václav Hassanien, Aboul Ella Basic Engineering Science Department Faculty of Engineering Menoufia University Shebin El-Kom32511 Egypt Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Poruba-Ostrava70800 Czech Republic Faculty of Computers and AI Cairo University Giza Egypt

This paper attempts to conceptualize a potent methodology by combining the African vultures optimization algorithm (AVOA) with a multi-orthogonal-oppositional strategy (M2OS), named AVO-M2OS, to address the nonconvexity and multidimensional nature of the combined heat and power economic dispatch (CHPED) problem under both crisp and uncertainty aspects. The AVO-M2OS uses the M2OS to simultaneously explore the search region, improving solutions’ diversity as well as solution quality. Therefore, AVO-M2OS can perform deeper exploration and exploitation features and thus mitigate the trapping at local optima, especially when tackling the more complicated nature of the CHPED problem. A three-stage analysis is conducted to assess the effectiveness of the proposed AVO-M2OS algorithm. During the first stage, the algorithm’s performance is evaluated on benchmark problems such as CEC 2005 and CEC 2019, employing statistical verifications and convergence characteristics. In the second stage, the significance of the results is evaluated using the nonparametric Friedman test to demonstrate that the results did not occur by chance. The results indicate that the AVO-M2OS algorithm outperforms the best existing algorithm (AVOA) by an average rank of the Friedman test exceeding 26% for the CEC 2005 suite while outperforming the gray wolf optimization (GWO) by 60% for the CEC 2019 suite. Moreover, the AVO-M2OS demonstrates exceptional performance compared to existing state-of-the-art algorithms, surpassing the best algorithm available by an average rank of the Friedman test that exceeds 41%. Finally, the AVO-M2OS’s applicability is achieved by minimizing the operational costs by finding the optimal power and heat generation scheduling for the CHPED problem. The recorded results realize that the AVO-M2OS algorithm offers accurate performance compared to competing optimizers, where it saves the operational cost of the 48-unit system by 24% on the original AVO variant. Furthermore, the u

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Adaptive control Approach for Enhancing the Dynamic Response of VSGs in Varying Grid Conditions

引用

IEEE Transactions on Power Delivery 2025年第3期40卷 1421-1433页

作者： Fahad, Shah She, Buxin Yin, Junjie Li, Fangxing Cui, Hantao Bo, Rui Department of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO USA Senior Power Systems Engineer ETAP Irvine CA USA Optimization & Control Group Parcific Northwest National Laboratory Richland USA Department of Electrical Engineering and Computer Science University of Tennessee at Knoxville Knoxville TN USA Department of Electrical and Computer Engineering North Carolina State University Raleigh NC USA

Conventionally, a virtual synchronous generator (VSG) is designed for islanded mode (IM) operation to meet specific operational requirements such as the rate of change of frequency (RoCoF). However, the operation of VSG designed for IM may not meet the operational and control criteria in grid connected mode (GCM) when the grid conditions vary. In addition, conventional VSG control technology does not consider the influence of the presynchronization scheme when connected to a weak grid, which degrades the RoCoF in IM. To overcome the aforementioned challenges, the proposed study presents a twin-delayed deep deterministic policy gradient (TD3) algorithm to improve the seamless transition performance of VSG from IM to GCM and vice versa. In the first step, the VSG-based power system model is used as a foundation for problem formulation of the proposed TD3 algorithm. Secondly, a reward function is designed according to the performance requirements, i.e., frequency and RoCoF requirements, of the VSG in order to guide the training of the agent in varying load, power reference, and grid conditions. Finally, the superiority of the proposed algorithm over existing methods is validated in MATLAB/SIMULINK and RTDS based real-time simulation environment. © 1986-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Collision avoidance and routing based on location access (CARLA) of mobile robots

引用

Neural Computing and Applications 2025年第9期37卷 6401-6430页

作者： ElSayyad, Shimaa Ezzat Saleh, Ahmed I. Ali, Hesham A. Saraya, M.S. Rabie, Asmaa H. Abdelsalam, Mohamed M. Computers Engineering Department MISR Higher Institute for Engineering and Technology Mansoura Round Road Mansoura City35516 Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Dean of Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa Mansoura Egypt Faculty of Engineering Mansoura National University Gamasa Mansoura Egypt

The paper introduces a new path-planning robotic system methodology called Collision Avoidance and Routing based on Location Access (CARLA) for use in critical environments such as hospitals and crises where quick action and saving human lives are vital. The main focus of our framework is on accuracy and fast responses, such as delivering tools or items in a specific area while avoiding collisions with other robots and obstacles. CARLA is designed to provide quick responses during emergencies, unlike most existing algorithms that are integrated into site control units or distributed among mobile robots on-site. By being loaded onto a remote server node rather than individual robots, CARLA helps to conserve the robots' capabilities, hardware resources, and power consumption. Additionally, our system utilizes cloud computing and Fog servers technology to improve data transmission times between the cloud and smart devices, especially for applications with strict timing requirements like emergency response. The Fog platform is also leveraged to enhance on-site access to real-time interaction and location-based services by bringing processing power closer to the robots from far-off Cloud servers. CARLA has various applications, such as in factories and warehouses, where mobile robots need to be selected and directed by a central control system remotely. The proposed framework consists of three main modules: Robot Knowledge Module, Robot Selection Module, and Route Reservation Module, which will all be discussed in detail in this paper. The results of simulations using this framework show that the robots have improved flexibility and efficiency in terms of computing paths and successfully fulfiling requests without colliding, compared to traditional methods used in similar scenarios. © The Author(s) 2025.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

ROUGE-SciQFS: A ROUGE-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization 31

ROUGE-SciQFS: A ROUGE-based Method to Automatically Create D...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Ramirez-Orta, Juan Milios, Evangelos Maguitman, Ana Soto, Axel J. Faculty of Computer Science Dalhousie University Canada Institute for Computer Science and Engineering UNS - CONICET Department of Computer Science and Engineering Universidad Nacional del Sur Argentina

ISBN: (纸本)9798891761964

So far, the task of Scientific Query-Focused Summarization (Sci-QFS) has lagged in development when compared to other areas of Scientific Natural Language Processing because of the lack of data. In this work, we propose a methodology to take advantage of existing collections of academic papers to obtain large-scale datasets for this task automatically. After applying it to the papers from our reading group, we introduce a novel dataset for Sci-QFS composed of 8,695 examples, each one with a query, the sentences of the full text from a paper and the relevance labels for each. After testing several classical and state-of-the-art embedding models on this data, we found that the task of Sci-QFS is far from being solved, although it is relatively straightforward for humans. Surprisingly, we found that classical methods outperformed modern pre-trained Deep Language Models (sometimes by a large margin), showing the need for large datasets to better fine-tune the latter. We share our experiments, data and models at https://***/jarobyte91/rouge_sciqfs. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

A Review on Meta-Learning: How Artificial Intelligence and Machine Learning Can Learn to Adapt Quickly 3

A Review on Meta-Learning: How Artificial Intelligence and M...

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Khadse, Shrikant Gourshettiwar, Palash Pawar, Adesh Faculty of Engineering and Technology Wardha442001 India Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Wardha442001 India Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331509675

Meta-learning aims to create Artificial Intelligence (AI) systems that can adapt to new tasks and improve their performance over time without extensive retraining. The advent of meta-learning paradigms has fundamentally changed how Artificial Intelligence (AI) and Machine Learning (ML) are handled, constantly reshaping these fields. Research study reviews the broad field of meta-learning, highlighting its critical function in bridging the AI-ML divide to improve adaptability. The study starts with a review of past developments, following the development of meta-learning algorithms and their underpinning theories. The historical view lays the groundwork for understanding the course of this dynamic regulation, spanning from early efforts in probabilistic program induction to modern discoveries in model-agnostic meta-learning. The study explores multiple meta-learning applications in AI and ML, revealing how they affect financial forecasting, computer vision, natural language processing, autonomous cars, health informatics, robotics, and personalized recommendation systems. When seen from the perspective of adaptive intelligence, meta-learning may be effectively applied to conditions with limited data, hyperparameter optimization, few-shot learning, and quick adaption in reinforcement learning settings. © 2025 IEEE.

关键词： Contrastive Learning

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：