检索结果-内蒙古大学图书馆

Congestion Control Using In-Network Telemetry for Lossless Datacenters

computers, Materials & Continua 2023年第4期75卷 1195-1212页

作者： Jin Wang Dongzhi Yuan Wangqing Luo Shuying Rao R.Simon Sherratt Jinbin Hu School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410004China School of Systems Engineering The University of ReadingReadingRG66AYUK

In the Ethernet lossless Data Center Networks (DCNs) deployedwith Priority-based Flow Control (PFC), the head-of-line blocking problemis still difficult to prevent due to PFC triggering under burst trafficscenarios even with the existing congestion control solutions. To addressthe head-of-line blocking problem of PFC, we propose a new congestioncontrol mechanism. The key point of Congestion Control Using In-NetworkTelemetry for Lossless Datacenters (ICC) is to use In-Network Telemetry(INT) technology to obtain comprehensive congestion information, which isthen fed back to the sender to adjust the sending rate timely and *** is possible to control congestion in time, converge to the target rate quickly,and maintain a near-zero queue length at the switch when using ICC. Weconducted Network Simulator-3 (NS-3) simulation experiments to test theICC’s performance. When compared to Congestion Control for Large-ScaleRDMA Deployments (DCQCN), TIMELY: RTT-based Congestion Controlfor the Datacenter (TIMELY), and Re-architecting Congestion Managementin Lossless Ethernet (PCN), ICC effectively reduces PFC pause messages andFlow Completion Time (FCT) by 47%, 56%, 34%, and 15.3×, 14.8×, and11.2×, respectively.

关键词： Data center lossless networks congestion control head of line blocking in-network telemetry

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Interaction and Multi-Scale Reconstruction: A Hybrid Attention Network for Skin Lesion Image Segmentation 10

Multi-Stage Interaction and Multi-Scale Reconstruction: A Hy...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wang, Wei Luo, Yuewen Wang, Xin Changsha University of Science and Technology School of Computer and Communication Engineering Changsha China

ISBN: (纸本)9798331520861

Accurate segmentation of skin lesion areas is significant for the diagnosis and analysis of skin diseases. Due to the irregular and blurred boundaries between healthy skin and lesion areas and sometimes the interference of hair and pigmentation deposits, it is still a challenging task to accomplish accurate segmentation. To solve the above problems, a hybrid attention network (SISR-HANet) based on stage interaction and scale reconstruction is proposed. The network contains three main modules: The Multi-Scale Global Perception (MSGP) module perceives global features through multi-scale receptive fields, thus compensating for the lack of global contextual information. The Multi-Stage Spatial Reconstruction (MSSR) module utilizes the cross-mixing of features from different stages to adaptively generate feature masks corresponding to each stage for reconstructing the features in each stage, thus eliminating the semantic differences between feature maps at different scales. The Channel-Optimized Inter-Group Aggregation (COGA) module helps the model recover more detailed features during the up-sampling process by optimizing and regrouping the channel information. To evaluate the effectiveness of SISR-HANet, we conducted experimental validation on the public datasets ISIC2017, ISIC2018, and PH2. The experimental results show that the DSC scores of these datasets are improved by 1.58%, 1.53%, and 1.34%, respectively, compared with the suboptimal networks. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Optimizing Species Recognition in Medicinal Plants: A Comprehensive Evaluation of Deep Learning Models 14

Optimizing Species Recognition in Medicinal Plants: A Compre...

引用

14th International Conference on Cloud Computing, Data Science and engineering, Confluence 2024

作者： Sharma, Vishal Chaurasia, Kuldeep Bansal, Abhay School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9798350344837

Medicinal plants have the potential to both significantly progress the pharmaceutical and medical industries and shield people from fatal diseases like cancer and cardiovascular conditions. Since there are hundreds of kinds of plants in the globe and because their characteristics: -like color, texture, and form are all the same, it might be difficult to identify them. The manual process is laborious and time-consuming. In view of current technological breakthroughs, more efficient methods for meeting the need for species identification have required to be devised. Pattern recognition and digital image processing are two examples of these methods. Despite several prior research, there are still difficulties in reliably automating plant species identification in a sequential and adaptive manner to identify a variety of plant species. In this article, the most recent deep learning models (VGG19, InceptionV3, LeNet, and Resnet50) are compared for medicinal plant identification and categorization. The system is trained using 1835 leaf samples from 30 distinct medicinal plants. For every model, confusion and performance metrics were used. In contrast to the other models in this investigation VGG19 fared better, with an accuracy rate of 99.85%. © 2024 IEEE.

关键词： Plants (botany)

来源：评论

学校读者我要写书评

暂无评论

Probing the Convergence of Vehicular Edge Metaverse and 6G: Blockchain-enabled Framework 18

Probing the Convergence of Vehicular Edge Metaverse and 6G: ...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Kumar, Shree Chaudhary, Rajat Budhiraja, Ishan Bennett University School of Computer Science and Engineering Technology Greater Noida India

ISBN: (纸本)9798350391725

The convergence of vehicular networks and the Meta-verse, referred to as the Vehicular Edge Metaverse is set to revolutionize both transportation and in-car experiences. This paradigm shift envisions vehicles not only as modes of transport but also as immersive gateways to the Metaverse, offering passengers interactive and engaging experiences while on the move. The advent of 6G, with its ultra-fast speeds and minimal latency is crucial in enabling the real-time data synchronization and low-latency communication required for a seamless Vehicular Edge Metaverse experience. Additionally, blockchain technology can play a key role in ensuring secure and transparent data sharing and transactions within this ecosystem, fostering trust and enabling new business models. This paper explores the potential of this convergence, discussing the key enabling technologies such as 6G, edge computing, and blockchain, and their role in addressing the challenges of real-time synchronization, resource management, and security. Furthermore, we discuss the potential applications like augmented reality-enhanced driving assistance and immersive in-car entertainment, highlighting the transformative impact of the Vehicular Edge Metaverse on the future of transportation. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Heart Disease Prediction and Identification with Machine Learning and FFT-Based Recommender System 23th

Revolutionizing Heart Disease Prediction and Identification ...

引用

23rd International Conference on Intelligent Systems Design and Applications, ISDA 2023

作者： Verma, Manisha Singh, Jagendra Kumari, Sangeeta School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9783031648120

The escalating prevalence of heart diseases necessitates innovative methods for early detection. This research introduced the Heart Disease Fast Fourier Transform Prediction (HDFFTP) approach, a novel method combining Fast Fourier Transform (FFT) with advanced machine learning to analyze time-series cardiac data. By transitioning from a time-based to a frequency-based view via FFT, the system unveils nuanced patterns integral to heart health. Upon implementing the XGBoost model, an accuracy of 93.5%, precision of 91.2%, and a commendable recall of 95.4% were achieved. Notably, the model spotlighted specific frequency components, like 1.2 Hz, as crucial indicators of cardiac conditions. Such insights, derived from the analysis of feature importance, underscore the potential of FFT in enhancing diagnostic precision. In summation, the HDFFTP approach provides a promising avenue for heart disease prediction, bridging computational excellence with clinical utility to foster timely interventions and improve patient outcomes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Neural Networks for Breast Cancer Detection and Prognosis

Leveraging Artificial Neural Networks for Breast Cancer Dete...

引用

2025 IEEE International Conference on Computational, Communication and Information technology, ICCCIT 2025

作者： Goel, Aadya Mishra, Pallavi Bhatia, Rachna School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Advanced Sciences Vellore Institute of Technology Vellore India

ISBN: (纸本)9798331512965

Breast cancer remains one of the leading causes of mortality among women worldwide, making early detection and accurate classification critical for improving patient out-comes. This study explores the application of Artificial Neural Networks (ANN) for breast cancer multiclass classification and prediction using the CBIS-DDSM: Breast Cancer Image Dataset. The model was trained to classify mammographic images into three categories: benign, malignant, and benign without callback, achieving an impressive accuracy of 99.6%. The choice of ANN was driven by its proven capability to model complex, nonlinear relationships within data, offering a significant improvement over traditional machine learning technique. Despite the challenges posed by the limited size and heterogeneity of the dataset, the ANN demonstrated robust performance, highlighting its potential for clinical applications. The high accuracy of the model underscores its value as a reliable tool for aiding radiologists in the early detection and prognosis of breast cancer, which could lead to more effective treatment planning and better patient outcomes. This study lays the foundation for integrating advanced AI technologies into clinical settings, offering promise for more precise, timely breast cancer diagnoses. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Fano Resonance Biosensor of Asymmetric Splitting Ring in The-Band 12

Fano Resonance Biosensor of Asymmetric Splitting Ring in The...

引用

12th IEEE International Conference on Information and Communication Networks, ICICN 2024

作者： He, Quanlin Li, Qiming Yang, Hongyan Yang, Yuhang Sun, Hongrui Li, Jianqing Chen, Yunyi School of Optoelectronic Engineering Guilin University of Electronic Technology Guilin China School of Computer Science and Engineering Macau University of Science and Technology 999078 China

ISBN: (纸本)9798350355802

Metasurface is a kind of artificial layered material whose thickness is less than the wavelength, which can flexibly and effectively control the polarization, amplitude, phase, polarization mode and propagation mode of electromagnetic waves. In this paper, a split ring metasurface structure with two openings is designed to excite Fano resonance by breaking the symmetry of the structure. Based on the finite element method (FEM), the asymmetric splitting ring of Thz metsurface is studied. It is shown that the peak value of Fano resonance and the quality factor (Q) can be modulated by changing the inner and outer diameters of the splitting ring. The Fano resonance is very sensitive to the asymmetry of the structure. A small asymmetry will excite the Fano resonance with high intensity, high quality factor and very narrow resonance linewidth. The refractive index sensitivity of the designed sensor reaches 7.23THz/RIU, and the Q value is up to 93.33. It can be used as a sensor to monitor the ambient refractive index, ambient temperature and liquid concentration. © 2024 IEEE.

关键词： Terahertz waves

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks with Fine-Tuned Word Representations for Visual Question Answering 10

Graph Convolutional Networks with Fine-Tuned Word Representa...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Owusu, Jim Wilson Zakari, Rufai Yusuf Qin, Ke He, Tao University of Electronic Science and Technology of China School of Computer Science and Engineering China

ISBN: (纸本)9798331520861

Recent advances in graph convolutional networks (GCNs) have demonstrated their effectiveness in vision-language tasks such as visual question answering (VQA), primarily due to their ability to capture both spatial and semantic relationships. However, through a series of experiments applying GCNs to VQA tasks, we observe that the performance of GCNs is highly sensitive to various subtasks, often resulting in unstable outputs. This variability can be attributed to factors such as the size of the training and testing datasets, evaluation metrics, and the selection of hyperparameters. To ensure fair evaluations of GCN-based VQA models, it is essential to implement consistent evaluation schemes across these factors. In this study, we propose a GCN framework for VQA that leverages fine-tuned word representations from the GloVe model, specifically tailored to address reasoning-based questions. We comprehensively assess the performance of our framework using multiple evaluation metrics on both the GQA and VQA 2.0 datasets. Our experimental results demonstrate significant improvements over existing methods, showcasing the effectiveness of the proposed approach in evaluation setting. © 2024 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Enhancing User Experience and Design in Agricultural Information Portals: A Study of Websites for Indian Farmers

Enhancing User Experience and Design in Agricultural Informa...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Sharma, Mradula Garg, Sahil Srivastava, Ashutosh Srivastava, Divya Verma, Madhushi Bhardwaj, Arpit School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9798350379716

Agriculture plays a significant role in India's economy, not only in terms of its GDP share but also in employment, rural development, and food security. As per the 2022-2023 economic survey, the gross value added (GVA) of agriculture in Indian economy is 18.3%. The economic survey also shows that there has been a decline of this percentage from 35% to 18% in the last 20 years. This is an alarming situation! India has got a very good agricultural land but due to lack of awareness in this field its contribution in GVA is decreasing. The present article took a small initiative to present a study of various agriculture information portals that are although designed to help farmers, but are they actually helpful? This question is taken over in this article as it discusses the various issues like, technological literacy of Indian Farmers, user friendly website design, accessibility in rural areas, language differences, and etc. Total ten (10) government agricultural websites are analyzed and we suggest some changes/improvements that these websites can implement for a better user experience to reach out to more farmers and deliver better information regarding agricultural issues. © 2024 IEEE.

关键词： Agricultural economics

来源：评论

学校读者我要写书评

暂无评论

Investigation of Single Channel Speech Enhancement: A Comparative Study 4

Investigation of Single Channel Speech Enhancement: A Compar...

引用

4th International Conference on Neural Networks, Information and Communication engineering, NNICE 2024

作者： Ma, Songqi Lv, Zhen Du, Fei Zhang, Xiao University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China University of Science and Technology Beijing School of Advance Engineering Beijing China

ISBN: (纸本)9798350394375

Noise is a critical factor that impacts speech quality. Speech signals are often disturbed by noise during acquisition and transmission. Speech enhancement technology represents an important method to eliminate noise from noisy signal and extract clean speech, which holds significant value in the field of speech recognition, speech communication. This study first categorizes the prior characteristics of different types of noise, followed by an exposition and implementation of representative speech enhancement methods, including traditional signal processing methods and deep learning algorithms. Through three metrics of evaluation, the performance of various speech enhancement algorithms in distinct noise environments is compared, and the Entropy Weight-Topsis (EW-Topsis) method is used for synthesis. Finally, the applicability and development trends of existing speech enhancement algorithms were discussed. The innovation of this study lies in the comparison of different algorithms in various noisy environments using different evaluation metrics. Previous research has mainly focused on two of the evaluation, algorithms and noise. This study presents a comprehensive comparison to synthesize three aspects, providing a unified evaluation reference. © 2024 IEEE.

关键词： Speech enhancement

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：