检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Shiqi Wu, Dapeng Wang, Honggang Wang, Ruyan School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China Chongqing Key Laboratory of Ubiquitous Sensing and Networking China Department of Graduate Computer Science and Engineering Katz School of Science and Health Yeshiva University in New York City United States

The Internet of Behaviors (IoB) is an emerging concept that utilizes devices to collect human behavior and provide intelligent services. Although some research has focused on human behavior analysis and data collection within IoB, the associated security and privacy challenges remain insufficiently explored. This paper analyzes the security and privacy risks at different stages of behavioral data generating, uploading, and using, while also considering the dynamic characteristics of user activity areas. Then, we propose a blockchain-based distributed IoB data storage and sharing framework, which is categorized into sensing, processing, and management layers based on these stages. To accommodate both identity authentication and behavioral privacy, zero-knowledge proofs are used in the sensing layer to separate the correlation between behavior and identity, which is further extended to a distributed architecture for cross-domain authentication. In the processing layer, an improved consensus protocol is proposed to enhance the decision-making efficiency of distributed IoB by analyzing the geographical and computational capability of the servers. In the management layer, user permission differences and the privacy of access targets are considered. Different types of behavior are modeled as corresponding relationships between keys, and fine-grained secure access is achieved through function secret sharing. Simulation results demonstrate the effectiveness of the proposed framework in multi-scenario IoB, with average consensus and authentication times reduced by 74% and 56%, respectively. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Clustering and Distribution Matching with Bandit Feedback

arXiv

引用

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of Blockchain-based Travel Rule Compliance System

arXiv

引用

arXiv 2022年

作者： Lee, Chaehyeon Kang, Changhoon Choi, Wonseok Lee, Jehoon Cha, Myunghun Woo, Jongsoo Hong, James Won-Ki Department of Computer Science and Engineering POSTECH Korea Republic of Coinone Seoul Korea Republic of Graduate School of Information Technology POSTECH Korea Republic of

In accordance with the guidelines of the Financial Action Task Force (FATF), Virtual Asset Service Providers (VASPs) should comply with a 'travel rule', which requires them to exchange originator's and beneficiary's personal information when transferring virtual assets. In this paper, we propose a novel blockchain-based travel rule compliance system that supports fully-decentralized data exchange. The proposed system uses a permissioned blockchain, and thereby eliminates the possibility of leakage of personal information to third parties or even to travel rule service providers, and ensures that travel rule data can be managed securely. © 2022, CC BY.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Accuracy Evaluation of Stereo Visual SLAM with Unnecessary Feature Point Elimination Using Blur Processing for AR Surgical Support System

Accuracy Evaluation of Stereo Visual SLAM with Unnecessary F...

引用

International Conference on Intelligent Informatics and Biomedical sciences (ICIIBMS)

作者： Masanao Koeda Yuto Kaihara Atsuro Sawada Akihiro Hamada Toshihiro Magaribuchi Osamu Ogawa Katsuhiko Onishi Hiroshi Noborio Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama Japan Department of Urology Graduate School of Medicine Kyoto University Kyoto Japan Faculty of Information Science and Arts Osaka Electro-Communication University Osaka Japan

In this study, we describe an evaluation of the positional accuracy of stereo Visual SLAM with noisy feature points removed by blurring. We constructed an experimental environment that intentionally degrades the accuracy of Visual SLAM. In this environment, we placed the objects that are likely to generate noisy feature points. We evaluated the accuracy of the estimated positions of the original video and the video in which blurred regions of noise in the original video were provided to Visual SLAM. Consequently, we confirmed that the accuracy was improved compared to that of the original video.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Targeted Advertising Strategy for Secure Wireless Edge Metaverse

Optimal Targeted Advertising Strategy for Secure Wireless Ed...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Hongyang Du Dusit Niyato Chunyan Miao Jiawen Kang Dong In Kim Interdisciplinary Graduate Program School of Computer Science and Engineering the Energy Research Institute @ NTU Nanyang Technological University Singapore School of Computer Science and Engineering Nanyang Technological University Singapore School of of Automation Guangdong University of Technology China Department of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea

ISBN: (纸本)9781665435413

Recently, Metaverse has attracted increasing attention from both industry and academia, because of the significant potential to integrate real and digital worlds ever more seam-lessly. By combining advanced wireless communications, edge computing and virtual reality (VR) technologies into Metaverse, a multidimensional, intelligent and powerful wireless edge Meta-verse is created for future human society. In this paper, we design a privacy preserving targeted advertising strategy for the wireless edge Metaverse. Specifically, a Metaverse service provider (MSP) allocates bandwidth to the VR users so that the users can access Metaverse from edge access points. To protect users' privacy, the covert communication technique is used in the downlink. Then, the MSP can offer high-quality access services to earn more profits. Motivated by the concept of “covert”, targeted advertising is used to promote the sale of bandwidth and ensure that the advertising strategy cannot be detected by competitors who may make counter-offer and by attackers who want to disrupt the services. We derive the best advertising strategy in terms of budget input, with the help of the Vidale-Wolfe model and Hamiltonian function. Furthermore, we propose a novel metric named Meta-Immersion to represent the user's experience feelings. The performance evaluation shows that the MSP can boost its revenue with an optimal targeted advertising strategy, especially compared with that without the advertising.

关键词： Wireless communication Privacy Metaverse Bandwidth Virtual reality Downlink User experience

来源：评论

学校读者我要写书评

暂无评论

Enhancing Incremental Learning of CNN model using Filtered New Added Samples Assisted with XAI

Enhancing Incremental Learning of CNN model using Filtered N...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Kuei-Chung Chang Chun-Yu Kuo International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Taiwan R.O.C. Dept. of Information Engineering and Computer Science Feng Chia University Taiwan R.O.C.

In the incremental learning technique, the accuracy of the model is improved by increasing the number of training samples. However, there are some problems when making this training mode. First, it is not known whether the newly added training samples will affect the learning effect of the model. Second, we know the result of the model identification, but we don't know what features are used to identify this object. In this paper, we propose a training dataset curation approach to improve model accuracy with incremental learning. To select the most appropriate explainable AI (XAI) method, we use the intersection over union (IOU) metric to measure the range calculation of real objects and model features to know the rationality of the model explanation. As we know that increase suitable training samples can improve the accuracy of the model, we added the XAI method to filter out new samples that are not suitable for the training set. We use the crack identification dataset in our method, and the accuracy can be improved from 0.895 to 0.93.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benefits and drawbacks of radiofrequency ablation via percutaneous or minimally invasive surgery for treating hepatocellular carcinoma

引用

World Journal of Gastrointestinal Surgery 2024年第11期16卷 3400-3407页

作者： Ching-Lung Hsieh Cheng-Ming Peng Chun-Wen Chen Chang-Hsien Liu Chih-Tao Teng Yi-Jui Liu Department of Computer Science and Information Engineering Feng Chia UniversityTaichung 40724Taiwan Department of Surgery Chung Shan Medical University HospitalTaichung 40201Taiwan School of Medicine Chung Shan Medical UniversityTaichung 40201Taiwan Department of Radiology Taichung Armed Forces General HospitalTaichung 406Taiwan Department of Medical Imaging and Radiological Sciences Central Taiwan University of Science and TechnologyTaichung 406Taiwan Department of Radiology School of MedicineNational Defense Medical CenterTaipei 11490Taiwan Department of Medical Imaging China Medical University Hsinchu Hospital and China Medical UniversityHsinchu 302Taiwan Institute of Nuclear Engineering and Science National Tsing Hua UniversityHsinchu 300Taiwan Department of Radiology Nantou Hospital of the Ministry of Health and WelfareNantou 540Taiwan Master’s Program of Biomedical Informatics and Biomedical Engineering Feng Chia UniversityTaichung 407Taiwan Department of Automatic Control Engineering Feng Chia UniversityTaichung 407Taiwan

The management of early stage hepatocellular carcinoma(HCC)presents significant *** radiofrequency ablation(RFA)has shown safety and effectiveness in treating HCC,with lower mortality rates and shorter hospital stays,its high recurrence rate remains a significant ***,achieving improved survival solely through RFA is challenging,particularly in retrospective studies with inherent *** is commonly used for guiding percutaneous RFA,but its low contrast can lead to missed tumors and the risk of HCC *** enhance the efficiency of ultrasound-guided percutaneous RFA,various techniques such as artificial ascites and contrast-enhanced ultrasound have been developed to facilitate complete tumor *** invasive surgery(MIS)offers advantages over open surgery and has gained traction in various surgical *** studies suggest that laparoscopic intraoperative RFA(IORFA)may be more effective than percutaneous RFA in terms of survival for HCC patients unsuitable for surgery,highlighting its ***,combining MIS-IORFA with these enhanced percutaneous RFA techniques may hold greater significance for HCC treatment using the MIS-IORFA *** article reviews liver resection and RFA in HCC treatment,comparing their merits and proposing a trajectory involving their combination in future therapy.

关键词： Percutaneous radiofrequency ablation Minimally invasive surgery Hepatocellular carcinoma Intraoperative radiofrequency ablation Contrast-enhanced ultrasound

来源：评论

学校读者我要写书评

暂无评论

LayOut Loud: An AI-Powered Augmented Reality and Mobile Application for Room Interior Design and Layout Optimization

LayOut Loud: An AI-Powered Augmented Reality and Mobile Appl...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： John Raphael G. Cuevas John Kenneth R. Rili Anny Neolicia G. Santillan Vivien A. Agustin Mary Grace N. Gonzales Criselle J. Centeno Richard C. Regala Department of Information Technology College of Information Systems and Technology Management Pamantasan ng Lungsod ng Maynila Manila Philippines Department of Computer Science Associate Dean of College of Information Systems and Technology Management Pamantasan ng Lungsod ng Maynila Manila Philippines Department of Information Technology Faculty of College of Engineering and Technology Pamantasan ng Lungsod ng Maynila Manila Philippines Department of Information Technology Director of Graduate Program of College of Information Systems and Technology Management Pamantasan ng Lungsod ng Maynila Manila Philippines Department of Computer Science Computer Lab Administrator of College of Engineering and Technology Pamantasan ng Lungsod ng Maynila Manila Philippines

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

LayOut Loud is an AI-powered augmented reality (AR) and mobile application designed to revolutionize room interior design by offering tailored, real-time solutions for layout optimization. The primary objective of this tool is to design AI-powered features that analyze user-provided room dimensions, furniture types, and style preferences. By leveraging advanced algorithms, LayOut Loud generates personalized design suggestions that cater to the individual needs and aesthetic tastes of users, ensuring that each interior design experience is customized and unique. A key goal of the application is to enhance user experience and decision-making through a clustering algorithm. This algorithm categorizes furniture pieces based on their suitability and appearance in living spaces, streamlining the selection process for users. By enabling the visualization of these items in a 3D model, users can make informed decisions about their interior design choices, ensuring that each piece contributes to the overall aesthetic and functional harmony of the space. Additionally, LayOut Loud focuses on improving its AR capabilities by allowing users to capture their room layouts and view virtual furniture arrangements in real time. This feature provides practical, interactive design solutions, empowering users to experiment with different configurations and instantly see how potential changes would appear in their actual living environments. Ultimately, LayOut Loud offers a user-friendly, immersive platform that transforms the way individuals approach interior design.

关键词： Solid modeling Three-dimensional displays Layout Decision making Clustering algorithms Real-time systems User experience Mobile applications Augmented reality Optimization

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Learning-based Indoor mmWave Channel Prediction Under Concept Drift

Robust Deep Learning-based Indoor mmWave Channel Prediction ...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Eslam Hasan Elmahedi Mahalal Muhammad Ismail Zi-Yang Wu Mostafa M. Fouda Tiago Koketsu Rodrigues Nei Kato Department of Computer Science Tennessee Technological University Cookeville TN USA College of Information Science and Engineering Northeastern University Shenyang China Department of Electrical and Computer Engineering Idaho State University Pocatello ID USA Center for Advanced Energy Studies (CAES) Idaho Falls ID USA Graduate School of Information Sciences Tohoku University Sendai Japan

The mmWave WiGig frequency band can support high throughput and low latency emerging applications. In this context, accurate prediction of channel gain enables seamless connectivity with user mobility via proactive handover and beamforming. Machine learning techniques have been widely adopted in literature for mmWave channel prediction. However, the existing techniques assume that the indoor mmWave channel follows a stationary stochastic process. This paper demonstrates that indoor WiGig mmWave channels are non-stationary where the channel’s cumulative distribution function (CDF) changes with the user’s spatio-temporal mobility. Specifically, we show significant differences in the empirical CDF of the channel gain based on the user’s mobility stage, namely, room entering, wandering, and exiting. Thus, the dynamic WiGig mmWave indoor channel suffers from concept drift that impedes the generalization ability of deep learning-based channel prediction models. Our results demonstrate that a state-of-the-art deep learning channel prediction model based on a hybrid convolutional neural network (CNN) long-short-term memory (LSTM) recurrent neural network suffers from a deterioration in the prediction accuracy by 11–68% depending on the user’s mobility stage and the model’s training. To mitigate the negative effect of concept drift and improve the generalization ability of the channel prediction model, we develop a robust deep learning model based on an ensemble strategy. Our results show that the weight average ensemble-based model maintains a stable prediction that keeps the performance deterioration below 4%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tailored Multi-Organ Segmentation with Model Adaptation and Ensemble

arXiv

引用

arXiv 2023年

作者： Dong, Jiahua Cheng, Guohua Zhang, Yue Peng, Chengtao Song, Yu Tong, Ruofeng Lin, Lanfen Chen, Yen-Wei College of Computer Science and Technology Zhejiang University Hangzhou310027 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215163 China Graduate School of Information Science and Engineering Ritsumeikan University Shiga525-8577 Japan Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230026 China School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China

Multi-organ segmentation, which identifies and separates different organs in medical images, is a fundamental task in medical image analysis. Recently, the immense success of deep learning motivated its wide adoption in multi-organ segmentation tasks. However, due to expensive labor costs and expertise, the availability of multi-organ annotations is usually limited and hence poses a challenge in obtaining sufficient training data for deep learning-based methods. In this paper, we aim to address this issue by combining off-the-shelf single-organ segmentation models to develop a multi-organ segmentation model on the target dataset, which helps get rid of the dependence on annotated data for multi-organ segmentation. To this end, we propose a novel dual-stage method that consists of a Model Adaptation stage and a Model Ensemble stage. The first stage enhances the generalization of each off-the-shelf segmentation model on the target domain, while the second stage distills and integrates knowledge from multiple adapted single-organ segmentation models. Extensive experiments on four abdomen datasets demonstrate that our proposed method can effectively leverage off-the-shelf single-organ segmentation models to obtain a tailored model for multi-organ segmentation with high accuracy. © 2023, CC0.

关键词： Image segmentation

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：