检索结果-南通市图书馆

PCT:Point cloud transformer

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第2期7卷 187-199页

作者： Meng-Hao Guo Jun-Xiong cai Zheng-Ning Liu Tai-Jiang Mu Ralph R.Martin Shi-Min Hu BNRist Department of Computer Science and TechnologyTsinghua UniversityBeiing 100084China Cardiff university Cardiff CF243

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud *** paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud *** is based on Transformer,which achieves huge success in natural language processing and displays great potential in image *** is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud *** better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor *** experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks.

关键词： 3D computer vision deep learning point cloud processing Transformer

Verification of SEU resistance in 65 nm high-performance SRAM with dual DICE interleaving and EDAC mitigation strategies

在线全文

学校读者我要写书评

暂无评论

Nuclear science and Techniques 2021年第12期32卷 64-76页

作者： Ze He Shi-Wei Zhao Tian-Qi Liu Chang cai Xiao-Yu Yan Shuai Gao Yu-Zhu Liu Jie Liu Institute of Modern Physics Chinese Academy of SciencesLanzhou 730000China department of computer science and technology Tsinghua UniversityBeijing 100084China School of Nuclear science and technology University of Chinese Academy of SciencesBeijing 100049China

A dual double interlocked storage cell(DICE)interleaving layout static random-access memory(SRAM)is designed and manufactured based on 65 nm bulk complementary metal oxide semiconductor *** single event upset(SEU)cross sections of this memory are obtained via heavy ion irradiation with a linear energy transfer(LET)value ranging from 1.7 to 83.4 MeV/(mg/cm^(2)).Experimental results show that the upset threshold(LETth)of a 4 KB block is approximately 6 MeV/(mg/cm^(2)),which is much better than that of a standard unhardened SRAM with an identical technology node.A 1 KB block has a higher LETth of 25 MeV/(mg/cm^(2))owing to the use of the error detection and correction(EDAC)*** a Ta ion irradiation test with the highest LET value(83.4 MeV/(mg/cm^(2))),the benefit of the EDAC code is reduced significantly because the multi-bit upset proportion in the SEU is increased *** with normal incident ions,the memory exhibits a higher SEU sensitivity in the tilt angle irradiation ***,the SEU cross section indicates a significant dependence on the data *** comprehensively considering HSPICE simulation results and the sensitive area distributions of the DICE cell,it is shown that the data pattern dependence is primarily associated with the arrangement of sensitive transistor pairs in the ***,some suggestions are provided to further improve the radiation resistance of the *** implementing a particular design at the layout level,the SEU tolerance of the memory is improved significantly at a low area ***,the designed 65 nm SRAM is suitable for electronic systems operating in serious radiation environments.

关键词： Double interlocked storage cell(DICE) Error detection and correction(EDAC)code Heavy ion Radiation hardening technology Single event upset(SEU) Static random-access memory(SRAM)

Register Clustering Methodology for Low Power Clock Tree Synthesis

在线全文

学校读者我要写书评

暂无评论

Journal of computer science & technology 2015年第2期30卷 391-403页

作者：邓超蔡懿慈周强 department of computer science and technology Tsinghua University Beijing 100084 China

Clock networks dissipate a significant fraction of the entire chip power budget. Therefore, the optimization for power consumption of clock networks has become one of the most important objectives in high performance IC designs. In contrast to most of the traditional studies that handle this problem with clock routing or buffer insertion strategy, this paper proposes a novel register clustering methodology in generating the leaf level topology of the clock tree to reduce the power consumption. Three register clustering algorithms called KMR, KSR and GSR are developed and a comprehensive study of them is discussed in this paper. Meanwhile~ a buffer allocation algorithm is proposed to satisfy the slew constraint within the clusters at a minimum cost of power consumption. We integrate our algorithms into a classical clock tree synthesis （CTS） flow to test the register clustering methodology on ISPD 2010 benchmark circuits. Experimental results show that all the three register clustering algorithms achieve more than 20% reduction in power consumption without affecting the skew and the maximum latency of the clock tree. As the most effective method among the three algorithms, GSR algorithm achieves a 31% reduction in power consumption as well as a 4% reduction in skew and a 5% reduction in maximum latency. Moreover, the total runtime of the CTS flow with our register clustering algorithms is significantly reduced by almost an order of magnitude.

关键词： low power register clustering clock tree synthesis

Automated object recognition in high-resolution optical remote sensing imagery

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

National science Review 2023年第6期10卷 38-41页

作者： Yazhou Yao Tao Chen Hanbo Bi Xinhao cai Gensheng Pei Guoye Yang Zhiyuan Yan Xian Sun Xing Xu Hai Zhang School of computer science and Engineering Nanjing University of Science and Technology Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Key Laboratory of Network Information System technology (NIST) Aerospace Information Research Institute Chinese Academy of Sciences department of computer science and technology Tsinghua University School of computer science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION With the rapid development of remote sensing technology,high-quality remote sensing images have become widely *** automated object detection and recognition of these images,which aims to automatically locate objects of interest in remote sensing images and distinguish their specific categories,is an important fundamental task in the *** provides an effective means for geospatial object monitoring in many social applications,such as intelligent transportation,urban planning,environmental monitoring and homeland security.

关键词：

Time-domain analysis methodology for large-scale RLC circuits and its applications

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science in China(Series F) 2006年第5期49卷 665-680页

作者： LUO Zuying cai Yici Sheldon X.-D Tan HONG Xianlong WANG Xiaoyi PAN Zhu FU Jingjing department of computer science and technology Tsinghua University Beijing 100084 China College of Information science and technology Beijing Normal University Beijing 100875 China department of Electrical Engineering University of California at Riverside Riverside CA92521 USA

With soaring work frequency and decreasing feature sizes, VLSI circuits with RLC parasitic components are more like analog circuits and should be carefully analyzed in physical design. However, the number of extracted RLC components is typically too large to be analyzed efficiently by using present analog circuit simulators like SPICE. In order to speedup the simulations without error penalty, this paper proposes a novel methodology to compress the time-descritized circuits resulted from numerical integration approximation at every time step. The main contribution of the methodology is the efficient structure-level compression of DC circuits containing many current sources, which is an important complement to present circuit analysis theory. The methodology consists of the following parts： 1） An approach is proposed to delete all intermediate nodes of RL branches. 2） An efficient approach is proposed to compress and back-solve parallel and serial branches so that it is error-free and of linear complexity to analyze circuits of tree topology. 3） The Y to πtransformation method is used to error-free reduce and back-solve the intermediate nodes of ladder circuits with the linear complexity. Thus, the whole simulation method is very accurate and of linear complexity to analyze circuits of chain topology. Based on the methodology, we propose several novel algorithms for efficiently solving RLC-model transient power/ground （P/G） networks. Among them, EQU-ADI algorithm of linear-complexity is proposed to solve RLC P/G networks with mesh-tree or mesh-chain topologies. Experimental results show that the proposed method is at least two orders of magnitude faster than SPICE while it can scale linearly in both time- and memory-complexity to solve very large P/G networks.

关键词： RLC circuits analog circuit analysis time-domain analysis PIG networks algorithm complexity

Minimum Error Based Affine Arithmetic for Variational Timing Analysis

在线全文

学校读者我要写书评

暂无评论

Minimum Error Based Affine Arithmetic for Variational Timing...

Trusted Integrated Circuits: The Problem and Challenges

2005 6th International Conference on ASIC

作者： Yi Zou Mengsheng Zhang Yici cai Qiang Zhou Xianlong Hong department of computer science and technology tsinghua university

ISBN: (纸本)0780392108;9780780392106

＜正＞In this paper,we describes a novel improvement for affine arithmetic which is widely used in statistical timing analysis and circuit *** representation and calculation method for affine arithmetic is both simple and accurate comparing with previous *** rule for calculating interval multiplication is simple and *** can both give a conservative bound and a minimum error affine approximation at the same *** application for variational timing analysis demonstrated the usefulness of affine arithmetic.

关键词： Timing Circuit simulation Circuit analysis Upper bound Analytical models computer errors computer science Digital arithmetic Sensitivity analysis Convergence

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of computer science & technology 2014年第5期29卷 918-928页

作者：吕勇强周强蔡懿慈屈钢 tsinghua National Laboratory for Information science and technology Research Institute of Information Technology Tsinghua University department of computer science and technology Tsinghua University department of Electrical and computer Engineering University of Maryland College Park MD 20742 U.S.A. Senior MemberIEEE

Hardware security has become more and more important in current information security architecture. Recently collected reports have shown that there may have been considerable hardware attacks prepared for possible military usage from all over the world. Due to the intrinsic difference from software security, hardware security has some special features and challenges. In order to guarantee hardware security, academia has proposed the concept of trusted integrated circuits,which aims at a secure circulation of IC design, manufacture and chip using. This paper reviews the main problems of trusted integrated circuits, and concludes four key domains of the trusted IC, namely the trusted IC design, trusted manufacture,trusted IP protection, and trusted chip authentication. The main challenges in those domains are also analyzed based on the current known techniques. Finally, the main limitations of the current techniques and possible future trends are discussed.

关键词： hardware security trusted integrated circuit hardware Trojan IC authentication IP protection

EyeHealer:A large-scale anterior eye segment dataset with eye structure and lesion annotations

在线全文

学校读者我要写书评

暂无评论

Precision Clinical Medicine 2021年第2期4卷 85-92页

作者： Wenjia cai Jie Xu Ke Wang Xiaohong Liu Wenqin Xu Huimin cai Yuanxu Gao Yuandong Su Meixia Zhang Jie Zhu Charlotte L.Zhang Edward E.Zhang Fangfei Wang Yun Yin Iat Fan Lai Guangyu Wang Kang Zhang Yingfeng Zheng State Key Laboratory of Ophthalmology Zhongshan Ophthalmic CenterSun Yat-sen UniversityGuangzhou 510060China Beijing Institute of Ophthalmology Capital Medical UniversityBeijing Tongren HospitalBeijing 100730China department of computer science and technology&BNRist Tsinghua UniversityBeijing 100084China Center for Biomedicine and Innovations Faculty of MedicineMacao University of Science and Technology and University HospitalMacao 999078China Guangzhou Women and Children’s Medical Center Guangzhou Medical UniversityGuangzhou 510623China Center for Translational Innovations West China Hospital and Sichuan UniversityChengdu 610041China Bioland Laboratory Guangzhou 510005China School of Business Macao University of Science and TechnologyMacao 999078China Ophthalmic Center Kiang Wu HospitalMacaoChina School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China

Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide,including diseases associated with corneal pathologies,anterior chamber abnormalities(*** or inflammation),and lens *** construction of an automatic tool for segmentation of anterior segment eye lesions would greatly improve the efficiency of clinical *** research on artificial intelligence progressing in recent years,deep learning models have shown their superiority in image classification and *** training and evaluation of deep learning models should be based on a large amount of data annotated with expertise;however,such data are relatively scarce in the domain of ***,the authors developed a new medical image annotation system,called *** is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel *** experiments were conducted to verify its performance in disease classification and eye lesion *** results showed that semantic segmentation models outperformed medical segmentation *** paper describes the establishment of the system for automated classification and segmentation *** dataset will be made publicly available to encourage future research in this area.

关键词： anterior segment eye diseases artificial intelligence annotation

Toward memristive in-memory computing:principles and applications

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Optoelectronics 2022年第2期15卷 101-125页

作者： Han Bao Houji Zhou Jiancong Li Huaizhi Pei Jing Tian Ling Yang Shengguang Ren Shaoqin Tong Yi Li Yuhui He Jia Chen Yimao cai Huaqiang Wu Qi Liu Qing Wan Xiangshui Miao School of Integrated Circuits School of Optical and Electronic InformationWuhan National Laboratory for OptoelectronicsOptics Valley LaboratoryHuazhong University of Science and TechnologyWuhan 430074China Hubei Yangtze Memory Laboratories Wuhan430205China AI Chip Center for Emerging Smart Systems InnoHK CentersHong Kong Science ParkHong KongChina School of Integrated Circuits Peking UniversityBeijing 100871China School of Integrated Circuits Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China Frontier Institute of Chip and System Fudan UniversityShanghai 200433China School of Electronic science and Engineering and Collaborative Innovation Centre of Advanced MicrostructuresNanjing UniversityNanjing 210093China

With the rapid growth of computer science and big data,the traditional von Neumann architecture suffers the aggravating data communication costs due to the separated structure of the processing units and *** in-memory computing paradigm is considered as a prominent candidate to address these issues,and plentiful applications have been demonstrated and *** applications can be broadly categorized into two major types:soft computing that can tolerant uncertain and imprecise results,and hard computing that emphasizes explicit and precise numerical results for each task,leading to different requirements on the computational accuracies and the corresponding hardware *** this review,we conduct a thorough survey of the recent advances of memristive in-memory computing applications,both on the soft computing type that focuses on artificial neural networks and other machine learning algorithms,and the hard computing type that includes scientific computing and digital image *** the end of the review,we discuss the remaining challenges and future opportunities of memristive in-memory computing in the incoming Artificial Intelligence of Things era.

关键词： Memristor In-memory computing Matrix-vector multiplication Machine learning Scientific computing Digital image processing