检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yin, Junbo Shen, Jianbing Chen, Runnan Li, Wei Yang, Ruigang Frossard, Pascal Wang, Wenguan School of Computer Science and Technology Beijing Institute of Technology China SKL-IOTSC CIS University of Macau China The University of Hong Kong Hong Kong Inceptio United States Switzerland ReLER CCAI Zhejiang University China

Bird’s eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-FUSION, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-FUSION essentially differs from existing approaches that only focus on the BEV scene-level fusion by explicitly incorporating instance-level multimodal information, thus facilitating the instance-centric tasks like 3D object detection. It comprises a Hierarchical Scene Fusion (HSF) module and an Instance-Guided Fusion (IGF) module. HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities. IGF mines instance candidates, explores their relationships, and aggregates the local multimodal context for each instance. These instances then serve as guidance to enhance the scene feature and yield an instance-aware BEV representation. On the challenging nuScenes benchmark, IS-FUSION outperforms all the published multimodal works to date. Code is available at: https://***/yinjunbo/IS-Fusion. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ultra-low Precision Multiplication-free Training for Deep Neural Networks

arXiv

引用

arXiv 2023年

作者： Liu, Chang Zhang, Rui Zhang, Xishan Hao, Yifan Du, Zidong Hu, Xing Li, Ling Guo, Qi SKL of Processor Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Cambricon Technologies Beijing China SKL of Computer Science Institute of Software CAS

The training for deep neural networks (DNNs) demands immense energy consumption, which restricts the development of deep learning as well as increases carbon emissions. Thus, the study of energy-efficient training for DNNs is essential. In training, the linear layers consume the most energy because of the intense use of energy-consuming full-precision (FP32) multiplication in multiply-accumulate (MAC). The energy-efficient works try to decrease the precision of multiplication or replace the multiplication with energy-efficient operations such as addition or bitwise shift, to reduce the energy consumption of FP32 multiplications. However, the existing energy-efficient works cannot replace all of the FP32 multiplications during both forward and backward propagation with low-precision energy-efficient operations. In this work, we propose an Adaptive Layer-wise Scaling PoT Quantization (ALS-POTQ) method and a Multiplication-Free MAC (MF-MAC) to replace all of the FP32 multiplications with the INT4 additions and 1-bit XOR operations. In addition, we propose Weight Bias Correction and Parameterized Ratio Clipping techniques for stable training and improving accuracy. In our training scheme, all of the above methods do not introduce extra multiplications, so we reduce up to 95.8% of the energy consumption in linear layers during training. Experimentally, we achieve an accuracy degradation of less than 1% for CNN models on ImageNet and Transformer model on the WMT En-De task. In summary, we significantly outperform the existing methods for both energy efficiency and accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A Trusted and Decentralized Federated Learning Framework for IoT devices in Smart City 17

A Trusted and Decentralized Federated Learning Framework for...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Wang, Sheng Chen, Chun Han, Bing Zhu, Jun Nanjing Construction Market Supervision Station Nanjing China Jiangsu Public Works Co.Ltd Nanjing China Nanjing University of Aeronautics and Astronautics Department of College of Computer Science and Technology Nanjing China City University of Hong Kong Department of Architecture and Civil Engineering Hong Kong

ISBN: (纸本)9798350351637

Smart cities, through investment in human and social capital as well as traditional and modern communications infrastructure, drive sustainable economic growth and high quality of life. IoT devices, as crucial components of smart cities, leverage the Federated Learning (FL) paradigm to contribute significantly to the advancement of smart cities by providing the value of data while safeguarding local data. However, existing federated learning frameworks for smart cities face several issues, including excessive centralization of decision-making and data, unbalanced resource allocation, and security and privacy concerns. To address these challenges, This paper aims to propose a blockchain-based federated learning framework for IoT devices in smart cities. We combine multiple security and privacy-preserving techniques such as differential privacy and Trusted Execution Environments (TEE) with federated learning to establish a framework that facilitates secure and trustworthy data exchange and FL requirements for IoT devices in smart cities. Moreover, we offload the local training computation from the limited IoT devices to the edge server and execute trust aggregation on the blockchain smart contracts. We build a prototype of our designed system and conduct experiments on diverse federated learning datasets. Experimental results demonstrate that our scheme achieves high efficiency while ensuring security and privacy. Through this work, we provide a viable solution for federated learning in smart cities, thereby advancing the sustainable development and intelligence of smart cities. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Automatic visual inspection system based on LCD screen 4

Automatic visual inspection system based on LCD screen

引用

4th IEEE International Conference on Civil Aviation Safety and Information technology, ICCASIT 2022

作者： Han, Juntao Xue, Hao Tang, Haitong Wu, Ting Ye, Yantong Li, Jingyang Jiangsu University of Science and Technology Computer Science Jiangsu Zhenjiang212028 China Jiangsu University of Science and Technology Institute of Telecommunication Jiangsu Zhenjiang212028 China Jiangsu University of Science and Technology Institute of Shenlan Jiangsu Zhenjiang212028 China Jiangsu University of Science and Technology Institute of Civil Engineering and Architecture Jiangsu Zhenjiang212028 China

ISBN: (数字)9781665467667

ISBN: (纸本)9781665467667

In the face of traditional detection technology, the efficiency is low, the accuracy is poor, the degree of human influence is large, and the cost is high;the key technologies in the automatic detection system in foreign markets are not disclosed to the public, and will not be provided to other companies for use, which is difficult to popularize and use on a large scale. External conditions;the machine vision-based LCD screen dead pixel detection system designed and developed in this paper integrates the advantages of high integration, low cost, high efficiency and high accuracy, which greatly meets the needs of the domestic mobile phone market and can be widely used in china. Major mobile phone manufacturers and LCD screen manufacturers. The system supporting automatic control platform designed and developed in this paper can meet the quality inspection of LCD screens of various sizes, and can also be invested in the maintenance of LCD screens of various electronic products to detect whether there are dead pixels on the mobile phone screen. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Data Availability Optimization for Cyber-Physical Systems 15

Data Availability Optimization for Cyber-Physical Systems

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Li, Liying Cong, Peijin Zhou, Junlong Gu, Zonghua Li, Keqin School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Department of Applied Physics and Electronics Ume˚a University Sweden Department of Computer Science State University of New York United States

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

As the backbone of Industry 4.0, Cyber-Physical Systems (CPSs) have attracted extensive attention from industry, academia, and government. Missing data is a common problem in CPS data processing and may cause incorrect results and eventually serious malfunction. Existing data availability optimization methods either rely on a large amount of complete training data or suffer from poor performance. To solve these problems, this paper proposes an iterative data availability optimization method for CPSs. Specifically, the proposed method first pre-processes the raw dataset by using a Singular Value Decomposition-based feature selection approach to identify crucial features and reduce computation overheads. It then makes an initial guess for missing values via a designed K-Means-based imputation approach. The appropriate initial estimation decreases the probability of the proposed method falling into the local optimum. Finally, the proposed method iteratively estimates missing data based on the Orthogonal Matching Pursuit algorithm. The proposed method optimizes data availability by accurately imputing missing values. Simulation results on two datasets demonstrate that compared to multiple state-of-the-art approaches, the proposed data availability optimization method can reduce imputation error by up to 99.65%. © 2022 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Modeling journal quality evaluation by enhancing population diversity based gene expression programming

引用

Expert Systems with Applications 2025年 283卷

作者： Yue, Xuezhi Jiang, Bingyu Wang, Dongsheng Zeng, Weiming Peng, Hu College of Science Jiangxi University of Science and Technology Jiangxi Ganzhou341000 China School of Architecture and Design Jiangxi University of Science and Technology Jiangxi Ganzhou341000 China Periodical Press Jiangxi University of Science and Technology Jiangxi Ganzhou341000 China School of Computer and Big Data Science Jiujiang University Jiangxi Jiujiang332005 China

Journal evaluation plays a crucial role in academic development and significantly influences the direction and quality of scholarly research. To address the limitations of traditional evaluation methods in integrating multidimensional indicators, this paper proposes a journal evaluation system based on Enhanced Population Diversity Gene Expression Programming (EPD-GEP). By incorporating a dual population generation strategy (DP) and a low fitness gene recombination mechanism (LR), the model's performance is substantially improved. Experimental results indicate that, compared with the traditional GEP algorithm, the EPD-GEP algorithm enhances optimal solution search and computational efficiency. Model validation demonstrates that the average prediction error of this evaluation system is only 0.11511, while its correlation coefficient with the journal impact factor reaches 0.9959, indicating outstanding predictive accuracy. Furthermore, the classification results of journals based on the proposed evaluation indexes achieve up to 95% consistency with the classification of Journal Citation Reports (JCR), fully confirming the model's reliability and practical applicability. © 2025 Elsevier Ltd

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

An enhanced scheme for mutual authentication for healthcare services

引用

Digital Communications and Networks 2022年第2期8卷 150-161页

作者： Salman Shamshad Muhammad Faizan Ayub Khalid Mahmood Saru Kumari Shehzad Ashraf Chaudhry Chien-Ming Chen Department of Computer Science COMSATS University IslamabadSahiwal Campus57000Pakistan Department of Mathematics Ch.Charan Singh UniversityMeerutUttar Pradesh250004India Department of Computer Engineering Faculty of Engineering and ArchitectureIstanbul Gelisim UniversityIstanbulTurkey College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China Riphah School of Computing&Innovation(RSCI) Riphah International UniversityLahore CampusLahore 55150Pakistan Department of Mathematics University of Padua35131 PaduaItaly

With the advent of state-of-art technologies,the Telecare Medicine Information System(TMIS)now offers fast and convenient healthcare services to patients at their ***,this architecture engenders new risks and challenges to patients'and the server's confidentiality,integrity and *** order to avoid any resource abuse and malicious attack,employing an authentication scheme is widely considered as the most effective approach for the TMIS to verify the legitimacy of patients and the ***,several authentication protocols have been proposed to this *** recently,Chaudhry et *** that there are vulnerabilities of impersonation attacks in Islam et al.'s ***,they introduced an improved protocol to mitigate those security ***,Qiu et *** that these schemes are vulnerable to the man-in-the-middle,impersonation and offline password guessing ***,they introduced an improved scheme based on the fuzzy verifier techniques,which overcome all the security flaws of Chaudhry et al.'s ***,there are still some security flaws in Qiu et al.'s *** this article,we prove that Qiu et al.'s protocol has an incorrect notion of perfect user anonymity and is vulnerable to user impersonation ***,we introduce an improved protocol for authentication,which reduces all the security flaws of Qiu et al.'s *** also make a comparison of our protocol with related protocols,which shows that our introduced protocol is more secure and efficient than previous protocols.

关键词： Authentication protocol Security protocol Anonymous protocol Impersonation attack TMIS

来源：评论

学校读者我要写书评

暂无评论

Delay-Driven Layer Assignment Algorithm Based on Integrating Multi-Strategy for Advanced technology Nodes

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of computer-Aided Design and computer Graphics 2024年第4期36卷 625-635页

作者： Liu, Genggeng Jiang, Lieqiu Li, Zepeng Wu, Ruoxin Xu, Ning College of Computer and Data Science Fuzhou University Fuzhou350116 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China College of Maynooth International Engineering Fuzhou University Fuzhou350116 China School of Information Engineering Wuhan University of Technology Wuhan430070 China

By introducing layer assignment algorithm, it can effectively optimize multiple important indicators such as delay and via counts in physical design, and then improve the chip performance. Therefore, a delay optimization layer assignment algorithm integrating multiple strategies is proposed, which considers both non-default-rule wire and coupling effect. First, aiming at the problem that the difference of nets is not carefully considered in the previous work, the differentiated net strategy is proposed. Second, in order to solve the problem of unreasonable evaluation of grid edge congestion in previous work, the segment classifying strategy is proposed. Third, aiming at the problem that the existing work pays more attention to consider congestion constraint when reassigning illegal nets, which leads to high delay of routing results, an effective reassignment and adjustment strategy is proposed. Finally, aiming at the problem of unreasonable routing order in the previous work, a variety of novel methods to determine the routing order are designed, and then a multi-objective driven sorting strategy is proposed. The algorithm runs in the Linux environment with a 2.60 GHz CPU and 64 GB of RAM. The validation experiments use the DAC12 circuit, and the experimental results show that the proposed algorithm can effectively optimize both delay and via counts without overflow. © 2024 Institute of Computing technology. All rights reserved.

关键词： Delay circuits

来源：评论

学校读者我要写书评

暂无评论

Aware: Adaptive Distributed Training with Computation, Communication and Position Awareness for Deep Learning Model 24

Aware: Adaptive Distributed Training with Computation, Commu...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Zeng, Yan Yi, Guangzheng Yin, Yuyu Wu, Jiyang Xue, Meiting Zhang, Jilin Wan, Jian Zhang, Yunquan School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing China

ISBN: (纸本)9798350319934

The accuracy of the neural networks can usually be improved by increasing the size of the dataset and the layers or operators of the network, as it has strong composability. But, it makes a challenge to train these models efficiently, due to the limited resources of a single device, such as memory, computational resource and so on. For this challenge, it has become an inevitable trend to automatically implement model parallelism across multiple devices. This paper proposes Aware, an adaptive distributed parallel training method, to search distributed parallel strategy automatically for deep learning model. It firstly proposes an operator fusion strategy with computation and communication awareness to simplify the computational graph of deep learning model. And then, it introduces position-aware graph embedding algorithm to extract the structural features of models, which can make the searched parallel strategies to transplant to other networks with similar structures. On this basis, we use reinforcement learning algorithm to search distributed parallel strategy automatically. This paper makes experiments with neural networks such as Inception V3, NMT, GNM, NasNet and ResNet, and uses CIFAR10 and PTB datasets to compare the two methods of Hierarchical and Placeto. The results show that compared with Placeto, Aware achieves up to 5% reductions in runtime. Aware achieves more than 8% reductions in runtime compared with Hierarchical. Moreover, it has better transplantation and generalization capabilities, and supports pre-training for large-scale network parallel strategy search and accelerates convergence. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Transferable Physical Adversarial Patch Attack for Remote Sensing Object Detection

Transferable Physical Adversarial Patch Attack for Remote Se...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Di Wang Wenxuan Zhu Ke Li Xiao Gao Pengfei Yang School of Computer Science and Technology Xidian University Xi’an China College of Information and Control Engineering Xi’an University of Architecture and Technology Xi’an China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Deep neural networks (DNNs) have been widely used in remote sensing but demonstrated to be vulnerable with adversarial examples. By adding elaborately designed perturbations on the clean images, DNNs may output wrong prediction. Research on adversarial attack contributes to the study of model robustness. However, previous methods mainly focus on white-box scenario or digital domain for classification tasks, while the vulnerability of remote sensing detectors has not been fully explored. Aiming at attacking black-box remote sensing detectors in physical domain, we propose to generate a transferable physical adversarial patch (TPAP) as the perturbations. Specifically, the initial patch is optimized by a U-Net and modified by the plane mask and position mask before applied to the clean image. By attacking a surrogate model, TPAP can be transferred to the target model. Abundant experimental results validate the attack ability of TPAP and evaluate the robustness of current one-stage detectors.

关键词： YOLO Perturbation methods Closed box Detectors Robustness Sensors Task analysis

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：