检索结果-内蒙古大学图书馆

International Conference on Innovation and Technological Advances for Sustainability, ITAS 2023

作者： Dandoush, Abdulhalim Gouissem, Ala Ciftler, Bekir Sait Division of Information Technology College of Computing and Information Technology University of Doha for Science and Technology Doha Qatar ESME Sduria/L2TI at Sorbonne University Paris Nord France Division of Data Science and Artificial Intelligence College of Computing and Information Technology University of Doha for Science and Technology Doha Qatar

ISBN: (纸本)9781032803722

This paper surveys recent research on federated learning-based resource allocation for next-generation networks in order to identify research gaps and potential future directions. We start by outlining the main challenges and requirements for secure and privacy-preserving resource allocation in these networks. The existing solutions and techniques proposed in the literature are then reviewed. The strengths and limitations of these solutions are analyzed, and trade-offs in terms of security, privacy, efficiency, and scalability are discussed. The research gaps and promising directions for future research are identified, such as integrating multiple solutions (e.g., game theory or optimization techniques with federated learning) and developing new models and algorithms for AI-based resource allocation that address specific challenges and requirements of next-generation networks. The goal is to inspire further research in this critical and rapidly evolving field. © 2025 The Author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ALCS-PP: Adaptive Latency Control Scheme for Packet Pacing in Self-Clocked Congestion Control

引用

IEEE Access 2025年 13卷 77080-77123页

作者： Zubaydi, Haider Dhia Jagmagji, Ahmed Samir Molnár, Sándor Alzubaidi, Mahmood Department of Telecommunications and Artificial Intelligence Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Hungary Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Qatar Foundation Doha Qatar

Effective congestion control is crucial for maintaining network stability, especially in dynamic environments. Self-Clocked Rate Adaptation for Multimedia (SCReAM) is a hybrid loss and delay-based algorithm for real-time multimedia transmission. It encounters challenges with static pacing and low latency under fluctuating round-trip time (RTT) and jitter resulting in ineffective bandwidth utilization. To address these issues, we propose ALCS-PP, a novel congestion control scheme featuring dynamic rate adjustment and adaptive packet pacing. The evaluation process is divided into three phases. The first phase involves initial performance evaluation using default parameters to establish a baseline comparison. The next phase explores parameter-specific experiments, where individual parameters such as target latency, jitter thresholds, and rate scaling factors are tuned to assess their impact on performance. The last phase investigates multi-parameter combinations to optimize the overall system configuration under various network conditions. Our proposed scheme effectively reduced network queue delay (NQD) by up to 21.91% and smoothed RTT (sRTT) by 13.44%, ensuring better responsiveness in real-time multimedia transmission. These improvements are achieved through adaptive tuning using dynamic soft clamping and gradual corrections, minimizing performance oscillations. Additionally, the scheme maintains metrics such as network throughput (NThput), congestion window (CWND), and bytes in flight (BiF) close to SCReAM’s baseline values, ensuring stable performance. The experimental evaluation highlights the algorithm’s capability to balance delay reduction and network stability, making it suitable for delay-sensitive applications such as 5G, Internet of Things (IoT), and real-time multimedia streaming. © 2013 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Classification of nuclei in whole slide imaging based on ensemble deep learning

Classification of nuclei in whole slide imaging based on ens...

引用

International Conference on Innovation and Technological Advances for Sustainability, ITAS 2023

作者： Al-Thelaya, Khaled Alzubaidi, Mahmood Majeed, Fahad Ullah, Gilal Nauman Agus, Marco Schneider, Jens Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Qatar Foundation Doha Qatar

ISBN: (纸本)9781032803722

Recently, several innovative digital imaging technologies led to the development of several medical imaging data representations. Whole slide imaging (WSI) refers to capturing and storing tissue glass slides and biopsy samples in a digital form. This newly emerging modality is increasingly gaining huge interest in pathology departments worldwide due to the unique advantages introduced by this medical imaging modality for diagnostic, educational, and research purposes. This work provides a comparative analysis of multiple classification approaches of nuclei in WSI where multiple nuclei context-aware manipulation strategies are evaluated by our nuclei classification experiments. We propose a contextaware deep ensemble approach based on ResNet deep architecture using different forms of input images pre-processed using multiple manual feature extraction techniques. Results show that our approach attains higher accuracy performance compared to traditional context-ware strategies in the literature. © 2025 The Author(s).

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Communication Modeling Approaches in Energy System Applications: A Systematic Overview

引用

IEEE Access 2025年 13卷 80329-80339页

作者： Radtke, Malin Frost, Emilie Nieße, Astrid Lehnhoff, Sebastian Carl von Ossietzky Universität Department of Computing Science Oldenburg Germany OFFIS - Institute for Information Technology Energy Division Oldenburg Germany

The integration and consideration of communication networks in energy system studies is of critical importance due to the mutual dependencies that exist between the systems. These interdependencies have an impact on the overall performance, stability, and robustness of the energy system. There is no comprehensive guide or overview for integrating communication into power system applications, despite its recognized importance and the wide variety of existing solutions that take into account interdependencies. By providing a detailed overview, characterization, and classification of existing approaches to communication modeling, this paper contributes to filling this gap in existing guidelines or general descriptions for the integration of communication in power system applications. In addition to discussing the multiple objectives associated with different focus for modeling communication, we consider the required data and system perspectives. Therefore, this paper provides guidance on the selection of a suitable and applicable communication modeling approach, given the specific objective and prerequisite. © 2013 IEEE.

关键词： Data communication systems

来源：评论

学校读者我要写书评

暂无评论

An Enhancement of Object Detection Using YOLO V8 and Mobile Net in Challenging Conditions

引用

SN Computer Science 2025年第4期6卷 1-20页

作者： Pasupuleti, Shailaja Ramalakshmi, K. Gunasekaran, Hemalatha Arokiaraj, Rex Macedo Debnath, Saswati Jebaseeli, T. Jemima Department of Computer Science and Engineering Alliance University Karnataka Anekal Bangalore India AU-Centre of Excellence Department of Computer Vision Alliance University Karnataka Anekal Bangalore India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Computer Science and Engineering Alliance University Karnataka Bangalore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

Autonomous drones and deep learning neural networks are becoming popular tools to revolutionize aircraft operations by partially automating visual inspection processes in aircraft maintenance. The research aims to provide a trustworthy method for locating and classifying surface flaws on aircraft, such as dents, fractures, corrosion, and a few other anomalies. To assess the model performance with and without a lightweight network integration, the implementation merges YOLOv8 and Mobile Net architectures, using dropout regularization and data augmentation approaches. To guarantee the model's performance in low-light situations, the dataset has been carefully selected to contain images replicating such settings. Annotation, environment setup, model training, and online dataset scraping are all covered by the thorough technique. A web-scraped dataset is used to train and validate two popular semantic segmentation algorithms, YOLOv8 and Mobile Net, which show enough performance for segmenting and grading aircraft surface problems in practical settings. The results show that precision and recall values are improved using a hybrid technique that ensembles trained Mobile Net and YOLOv8 models. Using COCO metrics, in the proposed approach an assessment of Ensemble WBF, Mobile Net-YOLO, and YOLOv8 outcomes on test and validation sets, guaranteed reliable object recognition and classification abilities. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Aircraft Classification Mobile-Net Object detection Weighted Box Fusion YOLOv8

来源：评论

学校读者我要写书评

暂无评论

An anisotropic nonlinear stabilization for finite element approximation of Vlasov-Poisson equations

arXiv

引用

arXiv 2025年

作者： Wen, Junjie Nazarov, Murtazo Department of Information Technology Division of Scientific Computing Uppsala University Sweden

We introduce a high-order finite element method for approximating the Vlasov-Poisson equations. This approach employs continuous Lagrange polynomials in space and explicit Runge-Kutta schemes for time discretization. To stabilize the numerical oscillations inherent in the scheme, a new anisotropic nonlinear artificial viscosity method is introduced. Numerical results demonstrate that this method achieves optimal convergence order with respect to both the polynomial space and time integration. The method is validated using classic benchmark problems for the Vlasov-Poisson equations, including Landau damping, two-stream instability, and bump-on-tail instability in a two-dimensional phase space. © 2025, CC BY.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

PneuX-Net: An Enhanced Feature Extraction and Transformation Approach for Pneumonia Detection in X-Ray Images

引用

IEEE Access 2025年 13卷 84024-84037页

作者： Kashif Munir Muhammad Usama Tanveer Hasan J. Alyamani Amine Bermak Atiq Ur Rehman Institute of Information Technology Khwaja Fareed University of Engineering and Information Technology Rahim Yar Khan Pakistan Department of Information Systems Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Jeddah Saudi Arabia Division of Information and Computing Technology College of Science and Engineering Hamad Bin Khalifa University Doha Qatar

Pneumonia is a critical respiratory condition characterized by inflammation in the alveoli, leading to impaired gas exchange and severe respiratory distress. It poses a significant threat to high-risk populations, including neonates, geriatric patients, and immunocompromised individuals. Early and precise detection is crucial to optimizing treatment strategies and reducing morbidity and mortality rates. To address this problem, we propose PneuX-Net, an ensemble-based feature extraction framework that integrates multiple machine learning (ML) models Random Forest (RF), Gaussian Naïve Bayes (GNB) and K-Nearest Centroid (KNC). Random Forest (RF) builds multiple decision trees to identify complex, non-linear patterns within the feature space. Gaussian Naïve Bayes (GNB) utilizes a probabilistic framework based on Bayes’ theorem to manage uncertainty in feature distributions. K-Nearest Centroid (KNC) improves class distinction by clustering feature vectors according to their proximity to centroids. The ensemble methodology harnesses the complementary strengths of these models, improving feature representation and mitigating overfitting, a prevalent issue in white-box models. To validate the effectiveness of PneuX-Net, we conduct extensive experimentation using a 10-fold cross-validation approach. Our results demonstrate that the PneuX-Net+KNC model achieves a remarkable 99.91% accuracy, highlighting its robustness and reliability in pneumonia classification tasks. This ensemble-driven methodology underscores the potential of machine learning in augmenting clinical decision-making by providing an accurate and automated pneumonia detection framework.

关键词： Pneumonia Accuracy Feature extraction X-ray imaging Deep learning Solid modeling Computational modeling Machine learning Lungs Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Modelling Population-Level Hes1 Dynamics: Insights from a Multi-framework Approach

引用

Bulletin of Mathematical Biology 2025年第6期87卷 1-31页

作者： Menz, Gesina Engblom, Stefan Division of Scientific Computing Department of Information Technology Uppsala University Uppsala Sweden Science for Life Laboratory Department of Information Technology Uppsala University Uppsala Sweden

Mathematical models of living cells have been successively refined with advancements in experimental techniques. A main concern is striking a balance between modelling power and the tractability of the associated mathematical analysis. In this work we model the dynamics for the transcription factor Hairy and enhancer of split-1 (Hes1), whose expression oscillates during neural development, and which critically enables stable fate decision in the embryonic brain. We design, parametrise, and analyse a detailed spatial model using ordinary differential equations (ODEs) over a grid capturing both transient oscillatory behaviour and fate decision on a population-level. We also investigate the relationship between this ODE model and a more realistic grid-based model involving intrinsic noise using mostly directly biologically motivated parameters. While we focus specifically on Hes1 in neural development, the approach of linking deterministic and stochastic grid-based models shows promise in modelling various biological processes taking place in a cell population. In this context, our work stresses the importance of the interpretability of complex computational models into a framework which is amenable to mathematical analysis.

关键词： Cellular synchronisation Fate decision Genetic oscillator Neurogenesis Pattern formation

来源：评论

学校读者我要写书评

暂无评论

Large Language Model Enhanced Particle Swarm Optimization for Hyperparameter Tuning for Deep Learning Models

IEEE Open Journal of the Computer Society

引用

IEEE Open Journal of the Computer Society 2025年第1期6卷 574-585页

作者： Hameed, Saad Qolomany, Basheer Belhaouari, Samir Brahim Abdallah, Mohamed Qadir, Junaid Al-Fuqaha, Ala Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha5825 Qatar Howard University Department of Medicine College of Medicine WashingtonDC20059 United States Qatar University Department of Computer Science and Engineering Doha5825 Qatar

Determining the ideal architecture for deep learning models, such as the number of layers and neurons, is a difficult and resource-intensive process that frequently relies on human tuning or computationally costly optimization approaches. While Particle Swarm Optimization (PSO) and Large Language Models (LLMs) have been individually applied in optimization and deep learning, their combined use for enhancing convergence in numerical optimization tasks remains underexplored. Our work addresses this gap by integrating LLMs into PSO to reduce model evaluations and improve convergence for deep learning hyperparameter tuning. The proposed LLM-enhanced PSO method addresses the difficulties of efficiency and convergence by using LLMs (particularly ChatGPT-3.5 and Llama3) to improve PSO performance, allowing for faster achievement of target objectives. Our method speeds up search space exploration by substituting underperforming particle placements with best suggestions offered by LLMs. Comprehensive experiments across three scenarios—(1) optimizing the Rastrigin function, (2) using Long Short-Term Memory (LSTM) networks for time series regression, and (3) using Convolutional Neural Networks (CNNs) for material classification—show that the method significantly improves convergence rates and lowers computational costs. Depending on the application, computational complexity is lowered by 20% to 60% compared to traditional PSO methods. Llama3 achieved a 20% to 40% reduction in model calls for regression tasks, whereas ChatGPT-3.5 reduced model calls by 60% for both regression and classification tasks, all while preserving accuracy and error rates. This groundbreaking methodology offers a very efficient and effective solution for optimizing deep learning models, leading to substantial computational performance improvements across a wide range of applications. © 2020 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Prediction of Recurrent Fragility Fractures Using Large Language Models

引用

IEEE Access 2025年 13卷 71503-71520页

作者： Alshraideh, Mohammad Al-Dhaqm, Arafat Alshammari, Ahmad Alshraideh, Abedalrahman Alshraideh, Bahaaldeen Mohamed Al-Fayoumi, Bayan Nasser, Maged Artificial Intelligence Department University of Jordan Amman11942 Jordan Lusail University Information Technology College Lusail Qatar Subang Jaya47500 Malaysia Northern Border University Faculty of Computing and Information Technology Department of Computer Sciences Rafha91911 Saudi Arabia East Midlands Deanery NHS England NottinghamDE74 2SA United Kingdom Division of Urology Department of Special Surgery University of Jordan Amman Jordan Universiti Teknologi PETRONAS Computer and Information Sciences Department Seri Iskandar32610 Malaysia

Recurrent fragility fractures are a big challenge in managing bone health, especially in older adults and people with osteoporosis or related disorders. The prediction of such fractures depends on the overall understanding of various clinical and lifestyle factors contributing to bone fragility. The goal of this analysis is to carry out advanced predictive analytics related to the problem of recurrent fragility fractures concerning several key features about each patient: age, sex, body mass index, physical activities, smoking status, and several others: T-score, along with biomarkers such as Vitamin D3, calcium levels, and the rest. Indeed, the results show that the features most indicative of recurrent fractures include age, T-score, physical activity, and glucocorticoid usage;greater emphasis has been laid on bone mineral density and lifestyle factors. The detailed feature importance analysis showed that age and T-score have the highest important values for fracture recurrence prediction, followed by physical activity and glucocorticoid treatment. The study finds that the proposed models achieved an accuracy of 91.3% (LLaMA 7GB) and 90.2% (Gamma 7GB), with ROC AUC scores of 93% and 92%, respectively. The study highlights that age, T-score, and glucocorticoid usage were the most significant predictive factors. These findings enable improved clinical decision-making for fracture prevention. This model can facilitate the identification of high-risk patients with recurrent fragility fractures by clinicians, thus allowing for targeted intervention and personalized treatment to reduce the risk of future fractures. The findings contribute to the development of fracture prediction, incorporating a wide array of clinical data that, in turn, will improve patient outcomes and their quality of life. © 2013 IEEE.

关键词： Predictive analytics

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：