检索结果-内蒙古大学图书馆

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Yu, Ziqing Chang, Zheng Li, Jian Li, Yuan Zhang, Yulu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China University of Jyväskylä Faculty of Information Technology JyväskyläFIN-40014 Finland School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China China Mobile Research Institute Department of IoT Technology Research Beijing China

ISBN: (纸本)9798350370218

Utilizing the flexibility advantages of the unmanned aerial vehicle (UAV), the emerging vehicular edge computing (VEC) is able to expand service and computing capability to the vehicular network. In this paper, we consider a crowdsourcing problem and propose a joint blockchain-based framework that enables end users to request services from UAV-assisted VEC system in emergency scenarios. Our framework leverages the global data relevant to the task by uploading it to the public blockchain for storage and tracing, where UAV and vehicles play important roles. Meanwhile, data specific to private networks is stored in the consortium blockchain to relieve data pressure on the public blockchain and improve the efficiency of the lookup process of public blockchain. During the task processing phase, we create a two-layer contract for the crowdsourcing network to incentivize the UAV network and vehicles to participate in task processing phase. We validate the feasibility of our two-layer contract through extensive simulations, which demonstrate the potential of our proposed framework to improve the efficiency of crowdsourcing in an UAV-assisted VEC. © 2023 IEEE.

关键词： Consortium Blockchain Contract Theory Crowdsourcing Incentive Mechanism Unmanned Aerial Vehicles Vehicular Edge Computing

来源：评论

学校读者我要写书评

暂无评论

Edge-Guided and Cross-Scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution 27th

Edge-Guided and Cross-Scale Feature Fusion Network for Effic...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Yang, Zhiyuan Zhang, Bo Zeng, Zhiqiang Yeo, Si Yong School of Electronic and Information Engineering Beihang University Beijing China College of Computing and Data Science Nanyang Technological University Singapore Singapore Beijing Institute of Remote Sensing Equipment Beijing China Lee Kong Chian School of Medicine Nanyang Technological University Singapore Singapore

ISBN: (纸本)9783031783975

In recent years, MRI super-resolution techniques have achieved great success, especially multi-contrast methods that extract texture information from reference images to guide the super-resolution reconstruction. However, current methods primarily focus on texture similarities at the same scale, neglecting cross-scale similarities that provide comprehensive information. Moreover, the misalignment between features of different scales impedes effective aggregation of information flow. To address the limitations, we propose a novel edge-guided and cross-scale feature fusion network, namely ECFNet. Specifically, we develop a pipeline consisting of the deformable convolution and the cross-attention transformer to align features of different scales. The cross-scale fusion strategy fully integrates the texture information from different scales, significantly enhancing the super-resolution. In addition, a novel structure information collaboration module is developed to guide the super-resolution reconstruction with implicit structure priors. The structure information enables the network to focus on high-frequency components of the image, resulting in sharper details. Extensive experiments on the IXI and BraTS2020 datasets demonstrate that our method achieves state-of-the-art performance compared to other multi-contrast MRI super-resolution methods, and our method is robust in terms of different super-resolution scales. Our code is available at https://***/zhiyuan-yang/Edge-Guided-Cross-Scale-MRI-Super-resolution. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ProMamba: Prompt-Mamba for polyp segmentation

arXiv

引用

arXiv 2024年

作者： Xie, Jianhao Liao, Ruofan Zhang, Ziang Yi, Sida Zhu, Yuesheng Luo, Guibo School of Electronic and Computer Engineering Peking University China Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University China

Detecting polyps through colonoscopy is an important task in medical image segmentation, which provides significant assistance and reference value for clinical surgery. However, accurate segmentation of polyps is a challenging task due to two main reasons. Firstly, polyps exhibit various shapes and colors. Secondly, the boundaries between polyps and their normal surroundings are often unclear. Additionally, significant differences between different datasets lead to limited generalization capabilities of existing methods. To address these issues, we propose a segmentation model based on Prompt-Mamba, which incorporates the latest Vision-Mamba and prompt technologies. Compared to previous models trained on the same dataset, our model not only maintains high segmentation accuracy on the validation part of the same dataset but also demonstrates superior accuracy on unseen datasets, exhibiting excellent generalization capabilities. Notably, we are the first to apply the Vision-Mamba architecture to polyp segmentation and the first to utilize prompt technology in a polyp segmentation model. Our model efficiently accomplishes segmentation tasks, surpassing previous state-of-the-art methods by an average of 5% across six datasets. Furthermore, we have developed multiple versions of our model with scaled parameter counts, achieving better performance than previous models even with fewer parameters. Our code and trained weights will be released soon. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

DTBVis:An interactive visual comparison system for digital twin brain and human brain

引用

Visual Informatics 2023年第2期7卷 41-53页

作者： Yuxiao Li Xinhong Li Siqi Shen Longbin Zeng Richen Liu Qibao Zheng Jianfeng Feng Siming Chena School of Data Science Fudan UniversityChina Institute of Science and Technology for Brain-Inspired Intellignece Fudan UniversityChina School of Computer and Electronic Information Nanjing Normal UniversityChina

The digital twin brain(DTB)computing model from brain-inspired computing research is an emerging artificial intelligence technique,which is realized by a computational modeling approach of hardware and *** can achieve various cognitive abilities and their synergistic mechanisms in a manner similar to the human *** that the task of the DTB is to simulate the functions of the human brain,comparing the similarities and differences between the two is ***,the visualization study of the DTB is still ***,the complexity of the datasets(multilevel spatiotemporal granularity and different types of comparison tasks)presents new challenges to the analysis and exploration of ***,in this study,we proposed DTBVis,a visual analytics system that supports comparison tasks for the *** supports iterative explorations from different levels and at different *** with automatic similarity recommendation,and high-dimensional exploration,DTBVis can assist experts in understanding the similarities and differences between the DTB and the human brain,thus helping them adjust their model and enhance its *** highest level of DTBVis shows an overview of the datasets from the brain,which is used for comparison and exploration of the function and structure of the DTB and the human *** medium level is used for the comparison and exploration of a designated brain *** low level can analyze a designated brain *** worked closely with experts of brain science and held regular seminars with *** from the experts indicates that our approach helps them conduct comparative studies of the DTB and human brain and make modeling adjustments of the DTB through intuitive visual comparisons and interactive explorations.

关键词： Brain Digital twin brain Visual analytics Comparative analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Smart Manufacturing Systems Through AR for data-Driven Digital Twin System

引用

SN computer science 2023年第5期4卷 1-13页

作者： Ashok, J. Kumar, N. Anil Raj, David Winster Praveen Bhushan, A. Vinay Edem, Swathi Department of Electronic and Communication Engineering V. S. B. Engineering College Tamil Nadu Karur India Department of Electronics and Communication Engineering School of Engineering & Technology Mohan Babu University Andhra Pradesh Tirupati India School of Business and Management CHRIST (Deemed to be University) Karnataka Bengaluru India Department of Business Analytics Kirloskar Institute of Management Karnataka Harihar India Computer Science and Engineering Chaitanya Bharathi Institute of Technology Hyderabad India

Modification of size, residual stress, and surface roughness have an enormous impact on a complex mechanical product’s final machining quality. Machine quality can be ensured using Digital Twin (DT) technology by checking the real-time machining process. The virtual–real separation display method is the most modern DT System (DTS). It results in the ineffective transmission of the necessary restricting the use of the DTS by processing data on-site technicians to support field processing. Augmented Reality (AR) monitoring the manufacturing process approach to solve this problem is proposed based on the DT. First, the dynamic multi-view for AR is built using data from multiple sources. Second, real-time monitoring of complex product’s intermediate processes incorporates AR to encourage communication between the users of the DT machining system. The outcome of the system can prevent errors that cannot be fixed. An application case for observing will be used to confirm the viability and the efficacy of the proposed method. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality Digital twin Effectiveness Machining technology Monitoring application

来源：评论

学校读者我要写书评

暂无评论

Variance-Constrained Filtering Fusion for Nonlinear Cyber-Physical Systems With the Denial-of-Service Attacks and Stochastic Communication Protocol

引用

IEEE/CAA Journal of Automatica Sinica 2022年第6期9卷 978-989页

作者： Hang Geng Zidong Wang Yun Chen Xiaojian Yi Yuhua Cheng IEEE School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China Department of Computer Science Brunel University LondonUxbridgeMiddlesexUB83PHUnited Kingdom Key Laboratory for IoT and Information Fusion Technology of Zhejiang School of AutomationHangzhou Dianzi UniversityHangzhou 310018China School of Mechatronical Engineering Beijing Institute of TechnologyBeijing 100081China

In this paper,a new filtering fusion problem is studied for nonlinear cyber-physical systems under errorvariance constraints and denial-of-service *** prevent data collision and reduce communication cost,the stochastic communication protocol is adopted in the sensor-to-filter channels to regulate the transmission order of *** sensor is allowed to enter the network according to the transmission priority decided by a set of independent and identicallydistributed random *** the defenders’view,the occurrence of the denial-of-service attack is governed by the randomly Bernoulli-distributed *** the local filtering stage,a set of variance-constrained local filters are designed where the upper bounds(on the filtering error covariances)are first acquired and later minimized by appropriately designing filter *** the fusion stage,all local estimates and error covariances are combined to develop a variance-constrained fusion estimator under the federated fusion ***,the performance of the fusion estimator is examined by studying the boundedness of the fused error covariance.A simulation example is finally presented to demonstrate the effectiveness of the proposed fusion estimator.

关键词： Cyber-physical system(CPS) denial-of-service attack stochastic communication protocol(SCP) variance-constrained filtering fusion

来源：评论

学校读者我要写书评

暂无评论

When Zero-Trust Meets Federated Learning

When Zero-Trust Meets Federated Learning

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Zhang, Xinran Wang, Dan Zhu, Yifei Chen, Weilong Chang, Zheng Han, Zhu The Hong Kong Polytechnic University Department of Computing Hong Kong Shanghai Jiao Tong University UM-SJTU Joint Institute Shanghai China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China University of Jyväskylä Faculty of Information Technology Jyväskylä Finland University of Houston Department of Electrical and Computer Engineering HoustonTX United States Kyung Hee University Department of Computer Science and Engineering Seoul Korea Republic of

ISBN: (纸本)9798350351255

Nowadays, Federated Learning (FL) has emerged as a promising and critical machine learning scheme to protect data privacy and reduce communication overhead. As the scale and connectivity expand in the FL system, enhancing the model's robustness against security threats from malicious clients grows ever more critical. An effective defensive solution involves selecting benign clients appropriately, thereby mitigating the vulnerability of the FL system to malicious attacks. However, clients exhibit varying behaviors over time, which complicates the task of accurately modeling their future trustworthiness. Moreover, blindly trusting clients with high trust values poses risks, given the potential for severe losses from betrayal. To tackle these problems, we propose a zero-trust policy in FL aimed at establishing continuous trust in each client while maintaining skepticism towards potential betrayal attacks. Specifically, we develop a Dirichlet-based trust evaluation technique to enable a comprehensive selection of trustworthy participants. This technique leverages the posterior distribution to estimate clients' trust values from their evolving behavior records over time. Then, we anticipate potential betrayal from a selected client and formulate a min-max optimization problem to minimize the worst-case betrayal loss, thereby boosting the system's betrayalaware robustness. Next, we convert this problem into a convex optimization problem and utilize the interior point method for resolution. We conduct extensive simulations to validate the efficacy of our proposed zero-trust policy in accurately assessing trust and enhancing the model's robustness to betrayal. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Big data: A Technical Preview of Technology 4

Big Data: A Technical Preview of Technology

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Dhatterwal, Jagjit Singh Gupta, Sonali Malik, Kiran Kaswan, Kuldeep Singh Bharti, Sunil Koneru Lakshmaiah Education Foundation Department of Artificial Intelligence & Data Science AP Vaddeswaram India Graphic Era Hill University Department of Computer Science & Engineering Dehradun India Graphic Era Deemed to Be University Dehradun India Matu Ram Institute of Engineering and Management Haryana Rohtak India Galgotias University School of Computer Science & Engineering Uttar Pradesh Greater Noida India Galgotias College of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350360165

The spaceless accessibility of data has dramatically changed the environments of decision making in the digital age. 'Big data' technically refers to datasets that are not only large, but also diverse & fast, thus speeding up the process of managing them with traditional procedures & tools. However, with this more abundance of data, making use of these information, and extracting particular utilities from them will have to be explored and studied. Firstly, decisions must be made that give significant insights from such diverse and changing data which move from the level of transactions, consumer comprehension to the network interpersonal. Massive data analytics, which is an implication of large-scale data analysing by firing on huge data collections, brings such value. The objective of this article is to pursue some of the different kinds of analytical methods and software tools that can be used to analyze data, as well as the alternative decision-making facilitation modes which may be achieved through advanced analytics. © 2024 IEEE.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Improving Autoencoder-Based Recommendation Systems 7th

Improving Autoencoder-Based Recommendation Systems

引用

7th International Conference on data Management, analytics and Innovation, ICDMAI 2023

作者： Sinhababu, Nilanjan Sarma, Monalisa Samanta, Debasis Center for Computational and Data Sciences Indian Institute of Technology Kharagpur India Subir Chowdhury School of Quality and Reliability Indian Institute of Technology Kharagpur India Computer Science and Engineering Indian Institute of Technology Kharagpur India

ISBN: (纸本)9789819914135

Recommendation systems help in providing suggestions regarding the products/services that the users might be interested in by analyzing ratings, reviews, and other feedback obtained from the users on their previous purchases. These types of systems can be seen in domains like e-commerce, entertainment, news, etc. The ratings and reviews in e-commerce are obtained from user feedback which are far less in number when compared with the users and items count. This leads to data sparsity issues where the recommendation systems are prone to provide in-accurate recommendations. To counter this issue, in our study, we used both autoencoder and sentiment analysis on the reviews using the BERT language model to generate a more accurate version of the rating matrix. The empirical studies done on the Amazon baby product reviews dataset have shown that the approach has significantly increased the accuracy of predicted ratings. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Covid-19 Twitter data using Deep Learning Algorithm 2

Sentiment Analysis of Covid-19 Twitter Data using Deep Learn...

引用

2nd International Conference on Machine Learning and data engineering, ICMLDE 2023

作者： Valarmathi, B. Gupta, N. Srinivasa Karthick, V. Chellatamilan, T. Santhi, K. Chalicheemala, Dhanush Department of Software and Systems Engineering School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Manufacturing School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Assistant Systems Engineer Tata Consultancy Services Chennai India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

A key method used in the study of Natural Language Processing (NLP) is sentiment analysis, or emotion analysis, plays a pivotal role in text analysis. Its primary function is to discern and categorize the underlying emotions within textual content, classifying them as positive, neutral, or negative sentiments. A variety of textual inputs can be used with this process, including entire documents, individual sentences, and more. Understanding the sentiments expressed by individuals is of paramount importance to organizations in today's digital age. Clients and customers now have the means to express their thoughts and emotions with greater ease and immediacy than ever before. This wealth of sentiment data can offer valuable insights that organizations can leverage to enhance their products, services, and overall customer experience. The present study focuses on the sentiment analysis of Twitter data related to the COVID-19 pandemic, employing the Long Short-Term Memory (LSTM) algorithm. To improve the accuracy of sentiment analysis, a pre-processing procedure is introduced, which involves the use of the Neat Text module in Python to clean the tweets. In this research endeavor, a dataset comprising 1,79,107 COVID-19-related tweets is subjected to sentiment analysis using the proposed pre-processing module and LSTM. The results demonstrate an impressive accuracy rate of 96% in accurately determining the sentiments conveyed in these COVID-19 tweets. In contrast, the existing algorithm, based on Artificial Neural Network (ANN), achieved a significantly lower accuracy rate of 76%. This research not only showcases the effectiveness of LSTM and pre-processing in sentiment analysis but also highlights the significance of sentiment analysis in gaining valuable insights from vast amounts of textual data, especially when important events like the COVID-19 pandemic are involved. © 2024 Elsevier B.V.. All rights reserved.

关键词： COVID-19

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：