检索结果-内蒙古大学图书馆

IEEE/ACM Symposium on Edge computing (SEC)

作者： Junquan Chen Xingzhou Zhang Wei Zhou Weisong Shi Engineering Research Center of Cyberspace Yunnan University Kunming China School of Software Yunnan University Kunming China Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer and Information Sciences University of Delaware Newark DE USA

ISBN: (数字)9798350378283

ISBN: (纸本)9798350378290

Vision Transformers ( $V$ iTs) have made significant progress in achieving performance comparable to traditional convolutional neural networks in computer vision tasks. However, high computational complexity restricts their application to resource-constrained edge devices. Previous methods for pruning redundant tokens have shown that it is possible to balance performance and computational cost by reducing the number of tokens. Unfortunately, simply removing redundant tokens often leads to the loss of crucial information. To address this issue, we propose a novel token compression scheme called TA-ASF. This scheme considers both the global role of low-importance tokens and the redundancy among similar tokens. TA-ASF employs novel approaches for token sampling and fusion, which are directly applicable to $V$ iTs without introducing additional trainable parameters. A comprehensive evaluation against several edge devices demonstrates our method effectively reduces model complexity while preserving Top-1 accuracy. Experimental results show that on the ImageNet dataset, the proposed method reduces FLOPs by 37% and increases throughput by 1.48 times on the DeiT-S model, with only a 0.1% decrease in accuracy. Specifically, on the DeiT-B model, the proposed method decreases FLOPs by 35% and increases throughput by 1.52 times while maintaining the same accuracy.

关键词： Performance evaluation Training Computer vision Visualization Accuracy Computational modeling Image edge detection Termination of employment Transformers Throughput

来源：评论

学校读者我要写书评

暂无评论

Protocol for biomodel engineering of unilevel to multilevel biological models using colored Petri nets

引用

STAR Protocols 2023年第4期4卷 102651页

作者： Liu, Fei Heiner, Monika Gilbert, David School of Software Engineering South China University of Technology Guangdong Guangzhou 510006 China Department of Computing Science Brandenburg University of Technology Cottbus-Senftenberg Cottbus D03013 Germany Department of Computing Science Brunel University London London UB8 3PH United Kingdom

Biological systems inherently span multiple levels, which can pose challenges in spatial representation for modelers. We present a protocol that utilizes colored Petri nets to construct and analyze biological models of systems, encompassing both unilevel and multilevel scenarios. We detail a modeling workflow exploiting the PetriNuts platform comprising a set of tools linked together via common file formats. We describe steps for modeling preparation, component-level modeling and analysis, followed by system-level modeling and analysis, and model use. © 2023 The Author(s)

关键词： Bioinformatics Computer sciences Systems biology

来源：评论

学校读者我要写书评

暂无评论

A Holistic QoS View of Crowdsourced Edge Cloud Platform

A Holistic QoS View of Crowdsourced Edge Cloud Platform

引用

International Workshop on Quality of Service

作者： Shihao Shen Yicheng Feng Mengwei Xu Cheng Zhang Xiaofei Wang Wenyu Wang Victor C.M. Leung College of Intelligence and Computing Tianjin University Tianjin China Beijing University of Posts and Telecommunications Beijing China Institute of Technology Tianjin University of Finance and Economics Tianjin China Paiou Cloud Computing (Shanghai) Co. Ltd. Shanghai China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

Edge clouds have become a de-facto paradigm to deliver low and stable networks to delay-critical applications such as web services and AR/VR. A unique form of edge clouds is those crowdsourced from third parties, e.g., idle PCs or workstations. Such crowdsourced edge platforms can better sink computations closer to users, reduce the purchase cost, and eliminates the carbon generated during manufacturing. Yet, they also face the challenge of out-of-control hardware, e.g., a server dropping in/out anytime. In this paper, we perform the first-of-its-kind measurement of Quality of Service (QoS) for a large-scale crowdsourced edge platform, which covers over 10,000 edge servers, 100,000 users and 10,000,000 user requests. The measurement takes a holistic QoS view: (1) First, we look at how much hardware resources are provided by edge servers, how much time they are available for service deployment, and what are the major abnormal behaviors. (2) Second, we analyze the factors affecting service stability and quantify the resource utilization pattern of containerized services hosted on those edge servers. (3) Third, we investigate the spatial and temporal features of user requests handled by the platform. Many useful and somehow surprising findings are obtained through the above measurements. We also derive insightful implications that could help edge platforms and edge applications to better deliver their services to users.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network using Image Processing for Digital Forensics Crime Scene Object Detection

Artificial Neural Network using Image Processing for Digital...

引用

International Conference on Edge computing and Applications (ICECAA)

作者： Deepa Devasenapathy M Raja Rajat Kumar Dwibedi N Vinoth T. Jayasudha V Dilli Ganesh Instructor-II/ Computing & Software Engineering U.A. Whitaker College of Engineering Florida Gulf Coast University Department of Computer Science and Engineeting CMR Institute of Technology Bengaluru India Aarupadai Veedu Institute of Technology VMRF Chennai India Department of Mechatronics Engineering Chennai Institute of Technology Chennai India Department of English KPR Institute of Engineering and Technology Coimbatore India Saveetha School of Engineering Saveetha Institute of Medical and Technical Science-(SIMATS) Chennai India

Digital forensics science places a significant emphasis on the detection of objects as one of the most vital areas of study. Several industries and institutions may benefit from the object detection method, including those concerned with medical diagnostic scanning, traffic monitoring, airport security, law enforcement, and data rescue on a local and global scale. This study aims to detect weapons in video surveillance images by using various enhancement, segmentation, feature extraction, and classification methods by Artificial Neural Network to improve the detection accuracy. Yet, several mathematical and algorithmic models are computed to provide the appropriate approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model Ownership Protection for Healthcare Consumer Electronics in Federated Edge Learning

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Wang, Rong Liang, Junchuan Feng, Chaosheng Chakraborty, Chinmay Alqahtani, Fayez Yu, Keping Sichuan Normal University College of Computer Science Chengdu610101 China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Chengdu610068 China Birla Institute of Technology Mesra India King Saud University College of Computer and Information Sciences Software Engineering Department Riyadh12372 Saudi Arabia Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan

With the rising demand for intelligent services and privacy protection in consumer artificial intelligence (AI), federated edge learning has emerged as a beacon for privacy-preserving distributed machine learning. This non-centralized approach offers distinct data privacy advantages, making it especially suitable for applications with strict privacy policies, such as consumer-centric healthcare systems. However, consumer electronics/devices in federated edge learning might unlawfully violate model ownership by duplicating or distributing models. Another concern is that a central server, if compromised, can become a conduit for model leakage, whether for profit motives or due to external intrusions, thus exacerbating the model ownership violation. To our knowledge, few works have focused on model ownership protection for federated edge learning in the consumer-centric healthcare domain. In this paper, we introduce a federated model ownership protection (FedMOP) approach. FedMOP is a model ownership safeguard and a formidable fortress built upon two core innovations. First, FedMOP can swiftly embed and replace watermarks during local training, allowing for the accurate identification and subsequent flagging of deceitful consumer devices. Second, FedMOP ensures that the server only accesses encrypted versions of the federated model, keeping the model a secret. Extensive evaluations demonstrate the robustness and effectiveness of FedMOP. We hope that FedMOP can light the way for surmounting similar ethical challenges in the broader realm of consumer-edge AI. © 1975-2011 IEEE.

关键词： ethical AI Federated edge learning healthcare consumer electronicss model ownership protection

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Crowdsourcing for Data Labeling with Heterogeneous Crowd

Hierarchical Crowdsourcing for Data Labeling with Heterogene...

引用

International Conference on Data engineering

作者： Haodi Zhang Wenxi Huang Zhenhan Su Junyang Chen Di Jiang Lixin Fan Chen Zhang Defu Lian Kaishun Wu College of Computer Science and Software Engineering Shenzhen University Department of Computing Hong Kong Polytechnic University WeBank Institute of Financial Technology Shenzhen University Webank Co. Ltd. School of Data Science University of Science and Technology of China

With the rapid and continuous development of data-driven technologies such as supervised learning, high-quality labeled data sets are commonly required by many applications. Due to the easiness of crowdsourcing small tasks with low cost, a straightforward solution for label quality improvement is to collect multiple labels from a crowd, and then aggregate the answers. The aggregation strategies include majority voting and its many variants, EM-based approaches, Graph Neural Nets and so on. However, due to the uncertainty information loss and commonly existing task correlations, the aggregated labels usually contain errors and may damnify the downstream model *** address the above problem, we propose a hierarchical crowdsourcing framework 1 for data labeling with noisy answers about correlated data. We make use of the heterogeneity of the labeling crowd and form an initialization-checking-update loop to improve the quality of labeled data. We formalize and successfully solve the core optimization problem, namely, selecting a proper set of checking tasks for each round. We prove that maximizing the expected quality improvement is equivalent to minimizing the conditional entropy of the observations given the crowdsourced answer families for the selected task set, which is NP-hard to solve. Therefore, we design an efficient approximation algorithm and conduct a series of experiments on real data. The experimental results show that the proposed method effectively improves the quality of the labeled data sets as well as the SOTA performance, yet without extra human labor costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SUMMER: Bias-aware Prediction of Graduate Employment Based on Educational Big Data

引用

ACM/IMS Transactions on Data Science 2021年第4期2卷 1–24页

作者： Xia, Feng Guo, Teng Bai, Xiaomei Shatte, Adrian Liu, Zitao Tang, Jiliang School of Engineering It and Physical Sciences Federation University Australia Ballarat3353 Australia School of Software Dalian University of Technology Dalian116620 China Computing Center Anshan Normal University Anshan114007 China Tal Education Group Beijing100080 China Department of Computer Science and Engineering Michigan State University East LansingMI48824 United States

The failure of obtaining employment could lead to serious psychosocial outcomes such as depression and substance abuse, especially for college students who may be less cognitively and emotionally mature. In addition to academic performance, employers' unconscious biases are a potential obstacle to graduating students in becoming employed. Thus, it is necessary to understand the nature of such unconscious biases to assist students at an early stage with personalized intervention. In this paper, we analyze the existing bias in college graduate employment through a large-scale education dataset and develop a framework called SUMMER (biaS-aware gradUate eMployMEnt pRediction) to predict students' employment status and employment preference while considering biases. The framework consists of four major components. Firstly, we resolve the heterogeneity of student courses by embedding academic performance into a unified space. Next, we apply a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) to overcome the label imbalance problem of employment data. Thirdly, we adopt a temporal convolutional network to comprehensively capture sequential information of academic performance across semesters. Finally, we design a bias-based regularization to smooth the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework. © 2022 Association for computing Machinery.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Data-Driven DLT3 Federated Deep Reinforcement Learning for Secure and Efficient Autonomous Driving

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Fei, Rong Li, Qianxi Wang, Kan Khan, Fazlullah Alturki, Ryan Lan, Dapeng Xi’an University of Technology School of Computer and Engineering Xi’an710000 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Ningbo315104 China Umm Al-Qura University College of Computing Department of Software Engineering Makkah21955 Saudi Arabia Chinese Academy of Sciences Shenyang Institute of Automation Shenyang110003 China

As autonomous vehicles (AVs) become increasingly widespread, the intelligent driving control and safety concerns have emerged. Recent advents in Internet of Things (IoTs) and 6G technologies have vastly boosted AVs’ sensing and communication capabilities, thereby enabling the high-speed and real-time data exchange. However, efficiently utilizing data while safeguarding the privacy remains challenges. Thus, we propose a federated learning (FL) framework with the privacy protection to facilitate the deep reinforcement learning (DRL) for longitudinal vehicle safety tracking control. First, the proposed framework enables the efficient information sharing and policy updates via encrypted policy gradient transmission. Then, the twin delayed deep deterministic policy gradient (TD3) method makes the velocity decision in the local model, while the dual long short-term memory (LSTM) network captures the temporal trajectory information. Finally, stacked denoising autoencoders (SDAE) is used to extract high-level environmental features, and the dual-LSTM-TD3 (DLT3)-SDAE model is introduced to enhance the policy decision efficiency and accuracy. Experimental results demonstrate that within the FL framework supported by homomorphic encryption, the DLT3-SDAE-based AV agent surpasses other DRL methods in terms of collision avoidance and average rewards, in the LAF environment. The safety, efficiency and comfort of the DLT3-SDAE AV agent are also evaluated and demonstrated. © 1975-2011 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

arXiv

引用

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Prevalence, rate, and predictors of virologic failure among adult HIV-Infected clients on second-line antiretroviral therapy (ART) in Tanzania (2018–2020): a retrospective cohort study

引用

Bulletin of the National Research Centre 2024年第1期48卷 1-13页

作者： Mwavika, Ester Timothy Kunambi, Peter Ponsian Masasi, Samuel Joseph Lema, Nsiande Kamori, Doreen Matee, Mecky Department of Epidemiology and Biostatistics Muhimbili University of Health and Allied Sciences Dar es Salaam Tanzania Tanzania Field Epidemiology and Laboratory Training Program Dar es Salaam Tanzania Department of Clinical Pharmacology Muhimbili University of Health and Allied Sciences Dar es Salaam Tanzania Department of Software Engineering University of Dar es Salaam Computing Centre Dar es Salaam Tanzania Department of Microbiology and Immunology School of Diagnostic Medicine Muhimbili University of Health and Allied Sciences Dar es Salaam Tanzania

Antiretroviral therapy (ART) has been proven to be highly effective in reducing the impact of human immunodeficiency virus (HIV) infection. However, as more people receive initial ART treatment, the risk of developing resistance and eventual treatment failure increases, leading to the need for second-line treatment regimens. Understanding the factors that contribute to virologic failure to second-line ART is crucial in preventing switching to the more expensive and toxic third-line regimens. This study provides information on the prevalence, rate, and predictors of virologic failure (VF) among clients on second-line ART in Tanzania. We followed 4718 clients for 15100 person-years (PY) of observations. Of them, 1402 (29.72%) experienced virologic failure at a rate of 92.85 per 1000 PY of observations (95% CI 88.11, 97.84). Factors that were associated with VF included: having a viral load count of ≥ 1000 copies/mL during first-line ART, with a hazard ratio (HR) 4.65 (95% CI 3.57, 6.07), using lopinavir (LPV/r) as a protease inhibitor during second-line ART (HR 4.20 (95% CI 3.12, 7.10), having a CD4 count < 200 cells/mm3 during second-line ART (HR 1.89 (95% CI 1.46, 2.44), and being on ART for 13–35 months (HR 8.22 (95% CI 2.21, 30.61). Paradoxically, having a CD4 count < 200 cells/mm3 during first-line ART treatment was associated with a reduced risk of virologic failure (HR 0.77 (95% CI 0.60, 0.99). In Tanzania, approximately 30% of adult clients on second-line ART experience VF at a rate of 92.71 per 1000 person-years. This high virologic failure rate underscores the urgent need for targeted interventions, such as enhancing adherence support, optimizing drug regimens, and regular viral load monitoring. These interventions will reduce the need for switching to the more costly and toxic third-line ART therapy and are also crucial for achieving the UNAIDS goal of 95% viral suppression among treated individuals by 2030.

关键词：

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：