检索结果-内蒙古大学图书馆

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Gobi, N. Singh, B.P. Yadav, Surendra Department of Computer Science and Information Technology Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Application Jaipur India

ISBN: (纸本)9798350343274

The research investigates the efficacy of a comprehensive machine learning and data mining approach in predictive modeling of stroke risk and post-stroke care management. A holistic methodology is proposed, integrating diverse datasets and advanced algorithms, including Logistic Regression, Random Forest, and Long Short-Term Memory (LSTM) networks. Data preprocessing, feature extraction, and personalized care plan generation are key components. Performance evaluation using accuracy, sensitivity, specificity, precision, F1 Score, AUC, and MAE demonstrates the superior predictive capabilities and efficiency of the proposed method compared to traditional approaches. The study highlights the potential for revolutionizing stroke care, emphasizing personalized risk assessment and post-stroke management for improved patient outcomes and healthcare delivery. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-based Dynamic Resource Provisioning Using Deep Q-Network on 6G-enabled Mobile Edge Networks 17

Digital Twin-based Dynamic Resource Provisioning Using Deep ...

引用

17th International Conference on COMmunication systems and NETworkS, COMSNETS 2025

作者： Alex, Suja A. Singh, Neha Adhikari, Mainak St. Xavier's Catholic College of Engineering Department of Information Technology Nagercoil India Indian Institute of Information Technology Lucknow Department of Computer Science Lucknow India Indian Institute of Science Education and Research Thiruvananthapuram School of Data Science Thiruvananthapuram India

ISBN: (纸本)9798331531195

The advancement of Digital Twin (DT) technology has enabled the creation of digital replicas of physical entitics, significantly enhancing the functionality and performance of mobile networks. However, this innovative approach also introduces considerable overload and performance challenges for mobile edge networks. To address these issucs, we propose a novel DT-enabled edge architecture for 6G-capable technology, employing a dynamic resource allocation strategy. The proposed approach, termed DT-based Dynamic Resource Provisioning (DT-DRP), leverages the capabilities of DT technology and Decp Reinforcement Learning (DRL) to dynamically allocate incoming tasks from mobile devices to edge devices. An intelligent DT server facilitates this allocation, optimizing resource use and improving network performance. The predictive capabilities of the framework are validated using the K-Nearest Neighbor (KNN) dlassifier at the edge network. Experimental results demonstrate that the proposed DT-DRP framework incorporates mobile devices into the DT network scamlessly, achieving superior performance in terms of minimum latency and high accuracy compared to bascline Q-learning algorithms across two medical datasets and various exccution scenarios. This research underscores the potential of DT technology in 6G networks and highlights its efficacy in enhancing mobile edge computing performance through intelligent resource management. © 2025 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

On the Deployment and Operation of Correlated Data-Intensive vNF-SCs in Inter-DC EONs 32

On the Deployment and Operation of Correlated Data-Intensive...

引用

32nd Wireless and Optical Communications Conference, WOCC 2023

作者： Zhu, Zuqing Zhang, Liang Jabbari, Bijan School of Information Science and Technology University of Science and Technology of China China George Mason University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350337150

In this work, we study the problem of deploying and operating correlated data-intensive vNF-SCs in inter-datacenter elastic optical networks. Requiring for a set of correlated data-intensive vNF-SCs, the service completion time (SCT) of a network service is related to the maximum branch completion time of those vNF-SC branches, making the correlation awareness of importance for the problem optimization. Being aware of it, we propose a dynamic programming based optimization scheme for the deployment and operation of single vNF-SC branch and two correlation-aware service provisioning algorithms to minimize the average SCT of network services. Simulation results verified that the proposed algorithms can effectively reduce the average SCT of network services compared with a benchmark algorithm that ignores the importance of correlation awareness. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

BiRSwinT: Bilinear full-scale residual swin-transformer for fine-grained driver behavior recognition

引用

Journal of the Franklin Institute 2023年第2期360卷 1166-1183页

作者： Yang, Wenxuan Tan, Chenghao Chen, Yuxin Xia, Huang Tang, Xuexi Cao, Yifan Zhou, Wenhui Lin, Lili Dai, Guojun School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Hangzhou Ocean Engine Network Technology Co. Ltd. China School of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou China

Driver behavior recognition has attracted extensive attention recently. Numerous methods have been developed on the basis of various deep neural networks. However, the existing models still suffer from various challenges in solving the downstream fine-grained recognition task, because many driver behaviors share similar global shape / appearances, and can only be discriminated by subtle but meaningful actions of local body parts. To remedy this emerging issue of fine-grained driver behavior recognition, we present a bilinear full-scale residual Swin-Transformer network (BiRSwinT) to learn and fuse the global shape/appearance and the local discriminative cues of driver actions. Specifically, a transformer-based dual-stream structure is designed, which contains two parallel branches: a global representation branch and a local residual branch. To learn the multi-scale local cues implied in driver actions, a set of full-scale skip connections are introduced in the local residual branch. Then a bilinear fusion with multi-step training strategy is employed to leverage and combine the global representation and local detail features of driver actions. The proposed method has been validated on the AUC V1 and V2 datasets, and achieved the average Top-1 accuracy of 93.235% and 92.253%, respectively. Comparison experiments show that the proposed method has superior performance when compared to the state-of-the-art methods. The generalization experiments on the State-Farm dataset also demonstrate the superiority of the proposed framework and strategy. The source code is available at https://***/shadow2469/***. © 2022 The Franklin Institute

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Concatenated CNN Attention Model for the Classification of Lung Cancer With XAI Techniques

引用

IEEE Access 2025年 13卷 96317-96336页

作者： Haque, Fariha Asif Hasan, Mohammad Siddique, Md. Abu Ismail Roy, Tonmoy Kanti Shaha, Tonmoy Islam, Yamina Paul, Avijit Chowdhury, Muhammad E. H. Rajshahi University of Engineering and Technology Department of Electronics and Telecommunication Engineering Rajshahi6204 Bangladesh Utah State University Department of Data Analytics and Information Systems LoganUT84322 United States Chittagong University of Engineering and Technology Department of Electrical and Electronic Engineering Chattogram4349 Bangladesh International Islamic University Chittagong Department of Computer Science and Engineering Chattogram4318 Bangladesh Qatar University Department of Electrical Engineering Doha Qatar

In the field of medical imaging, deep learning (DL) techniques have made significant contributions to the detection and classification of various cancers. Identifying the precise regions in medical images containing cancerous cells plays a crucial role in the diagnostic process. Early and accurate cancer detection is essential for effective treatment and improved patient outcomes. However, manual diagnosis is labor-intensive, requiring the specialized expertise of radiologists, and the increasing number of cancer cases presents challenges in processing large volumes of image data efficiently. To address these challenges, an end-to-end concatenated Convolutional Neural Network (CNN) attention model has been proposed for automatic lung cancer classification. This approach integrates two distinct CNNs, followed by a multi-layer perceptron (MLP) and a multi-head attention (MHA) mechanism, to enhance performance. The model leverages explainable AI techniques, such as gradient-weighted class activation mapping (grad-CAM) and Shapley additive explanations (SHAP), to highlight critical regions within the images that influence the decision-making process. This model achieves impressive performance, with an accuracy of 99.54%, precision of 99.31%, recall of 99.95%, F1-score of 99.66%, and an AUC of 99.97%. These results demonstrate that this approach not only surpasses existing methods but also provides a highly accurate and interpretable solution. By reducing the need for extensive manual intervention, this model enables faster and more reliable lung cancer diagnosis, paving the way for timely and effective treatments. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

OntoDSO: an ontological-based dolphin swarm optimization (DSO) approach to perform energy efficient routing in Wireless Sensor Networks (WSNs)

引用

International Journal of information Technology (Singapore) 2024年第3期16卷 1551-1557页

作者： Boopathi, Mythili Parikh, Swapnil Awasthi, Aishwary Malviya, Ashwini Nachappa, M.N. Mishra, Awakash Shyam, Gopal Krishna Narula, Gagandeep Singh Department of Information Technology Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul University Gujarat Vadodara India Department of Mechanical Engineering Sanskriti University UP Mathura India Department of UGDX ATLAS SkillTech University Mumbai India Department of Computer Science and Information Technology Jain (Deemed to be University) Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Noida India Department of Computer Science Engineering Presidency University Bengaluru India Guru Gobind Singh Indraprastha University Delhi Dwarka India

The aim of the paper is to perform an energy-efficient routing for moving nodes in Wireless Sensor Networks (WSNs) by using an ontological-based dolphin swarm optimization (DSO) approach. It makes use of echolocation and ontology to locate and represent cluster nodes close to the sink thereby maintaining optimal energy consumption during simulation. A comparative analysis for 20 samples (N = 10 each) is performed between OntoDSO, Ad-hoc On-demand Distance Vector (AODV) algorithm and existing literature review studies by taking several parameters namely mean delay, mean packet delivery ratio and mean energy consumption into consideration. The simulation of results is performed using MATLAB Simulink with implementation parameters such as number of nodes (n) and initial battery life. As a result, it is found that the OntoDSO approach identifies a set of optimized routes that can satisfy delay constraints and consume less energy, thereby achieving higher performance than AODV and existing studies in the context of WSNs. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Ad-hoc On-demand Distance Vector (AODV) algorithm Dolphin Swarm Optimization (DSO) algorithm Packet delivery ratio and energy consumption Wireless Sensor Network (WSN)

来源：评论

学校读者我要写书评

暂无评论

Analysis and Assessment of Wind Energy Potential of Socotra Archipelago in Yemen

引用

computers, Materials & Continua 2022年第1期70卷 1177-1193页

作者： Murad A.Almekhlafi Fahd N.Al-Wesabi Imran Khan Nadhem Nemri Khalid Mahmood Hany Mahgoub Noha Negm Amin M.El-Kustaban Ammar Zahary Department of Electrical Engineering–Communication Engineering Sana’a UniversityYemen Department of Computer Science King Khalid UniversityMuhayel AseerKingdom of Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Electrical Engineering University of Engineering and TechnologyPeshawarP.O.B 814Pakistan Department of Information Systems King Khalid UniversityMayahel AseerKSA Computer Science Department King Khaled UniversityKSA&Faculty of Computers and InformationComputer Science DepartmentMenoufia UniversityEgypt Computer Science Department King Khaled UniversityKSA&Faculty of ScienceDepartment of Mathematics and Computer ScienceMenoufia UniversityEgypt Electronics Department Faculty of EngineeringUSTSana’aYemen Faculty of Computer and IT Sana’a UniversityYemen

The increasing use of fossil fuels has a significant impact on the environment and ecosystem,which increases the rate of *** the high potential of renewable energy sources inYemen and the absence of similar studies in the region,this study aims to examine the potential of wind energy in Socotra *** was done by analyzing and evaluating wind properties,determining available energy density,calculating wind energy extracted at different altitudes,and then computing the capacity factor for a number of wind turbines and determining the *** average wind speed in Socotra Island was obtained from the Civil Aviation and Meteorology Authority data,only for the five-year data currently *** results showed high wind speeds from June to September(9.85-14.88 m/s)while the wind speed decreased for the rest of the *** average wind speed in the five years was 7.95 m/*** average annual wind speed,wind energy density,and annual energy density were calculated at different altitudes(10,30,and 50 m).According to the International Wind Energy Rating criteria,the region of Socotra Island falls under Category 7 and is classified as‘Superb’for most of the *** study provides useful information for developing wind energy and an efficient wind approach.

关键词： Energy potential wind characteristics Weibull distribution wind power density Socotra island

来源：评论

学校读者我要写书评

暂无评论

Futures Price Forecasting Based on LSTM Model Using Public Opinion Sentiment Analysis 42

Futures Price Forecasting Based on LSTM Model Using Public O...

引用

42nd Chinese Control Conference, CCC 2023

作者： Shi, Panfeng Song, Shifan Lang, Qi Liu, Xiaodong School of Control Science and Engineering Dalian University of Technology Dalian116024 China School of Computer Science and Information Technology Northeast Normal University Changchun130117 China

ISBN: (纸本)9789887581543

As the economy continues to develop and the futures market grows, more and more attention is being paid to the subject of futures price forecasting. The factors influencing the futures market are complex, and the existing forecasting models tend to ignore the acquisition of information other than market information. Therefore, this paper proposes a futures price forecasting model based on sentiment analysis of online public opinions. Several futures products are selected for training and validation of the model, and the Chinese posts in the futures bar are used as input for public opinion, which is processed by the investor sentiment analysis fusion module to obtain sentiment values as a priori information for the task. Three groups of control experiments are set up to verify the validity of the proposed model and to compare the effect of sentiment feature fusion. Finally, the experimental results show that the proposed model incorporating public opinion gets better results in the selected futures product price prediction task. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Federated Learning with Globally Shared Model: A Modified FedAVG Approach (GSM-FedAVG) 6

Enhancing Federated Learning with Globally Shared Model: A M...

引用

6th International Conference on Electrical information and Communication Technology, EICT 2023

作者： Tanmoy, Oudarja Barman Mamun, Md. Al Hasan, Sakib Anwar, Adnan Rajshahi University of Engineering & Technology Department of Computer Science and Engineering Rajshahi6204 Bangladesh Deakin University School of Information Technology Melbourne Australia

ISBN: (纸本)9798350370836

The wireless communications industry is interested in using data-driven machine learning solutions to supplement traditional model-driven design processes. Decentralized ML algorithms that maintain data in its original location are more alluring due to the lack of accessibility of private data and significant communication overhead. Federated learning is crucial for wireless applications to protect user privacy. The Federated Averaging Algorithm is a technique used in the Federated Learning process, which cooperatively learns an ML model by using the simple arithmetic average. In this paper, we propose a technique for enhancing the robustness of FedAVG, which involves employing a globally shared model with each clients in addition to each client's local model. This method is referred to as the GSM-FedAVG approach. The GSM approach with FedAVG has shown promising results in improving the accuracy and robustness of the ML models used as global model in FL setting. The effectiveness of the proposed method is validated using a number of benchmark datasets. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Prepartition: Load Balancing Approach for Virtual Machine Reservations in a Cloud Data Center

引用

Journal of computer science & Technology 2023年第4期38卷 773-792页

作者：田文洪徐敏贤周光耀吴逵须成忠 Rajkumar Buyya School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu 610054China Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhou 313001China Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Department of Computer Science University of VictoriaVictoriaBCV8W 3P6Canada State Key Laboratory of Internet of Things for Smart City University of MacaoMacao 999078China School of Computing and Information Systems University of MelbourneMelbourne 3010Australia

Load balancing is vital for the efficient and long-term operation of cloud data *** virtualization,post(reactive)migration of virtual machines(VMs)after allocation is the traditional way for load balancing and consoli***,it is not easy for reactive migration to obtain predefined load balance objectives and it may interrupt services and bring ***,we provide a new approach,called Prepartition,for load *** partitions a VM request into a few sub-requests sequentially with start time,end time and capacity demands,and treats each sub-request as a regular VM *** this way,it can proactively set a bound for each VM request on each physical machine and makes the scheduler get ready before VM migration to obtain the predefined load balancing goal,which supports the resource allocation in a fine-grained *** with real-world trace and synthetic data show that our proposed approach with offline version(PrepartitionOff)scheduling has 10%–20%better performance than the existing load balancing baselines under several metrics,including average utilization,imbalance degree,makespan and Capacity_*** also extend Prepartition to online load *** results show that our proposed approach also outperforms state-of-the-art online algorithms.

关键词： cloud computing physical machine(PM) virtual machine(VM) reservation load balancing Prepartition

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：