检索结果-内蒙古大学图书馆

Rely-Guarantee Reasoning about Messaging System for Autonomous Vehicles

学校读者我要写书评

暂无评论

Rely-Guarantee Reasoning about Messaging System for Autonomo...

Theoretical Aspects of software Engineering (TASE)

作者： Wenjing Xu Yongwang Zhao Dianfu Ma YuXin Zhang Qian Xiao State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang Univerisity Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China State Key Laboratory of Automotive Simulation and Control College of Automotive Engineering Jilin University Jilin China School of Computer Science and Technology Guizhou University Guiyang China

Messaging system as a communicating infrastructure is a safety-critical component of autonomous vehicles. For the purpose of safety certification of Level 4 autonomous driving systems, its necessary to provide a formally verified specification of messaging systems. This paper presents a realistic case study using the PiCore rely-guarantee framework to formally verify the DGPS (Differential Global Positioning System) of UISEE autonomous driving systems. We first create an axiom model of messaging systems by extending PiCore, which is reusable for concrete applications. The model supports dynamic configuration of message buffers as well as the automatic generation of the rely and guarantee conditions for compositional reasoning. It is instantiated when developing the formal specification of DGPS. Then, we use the rely-guarantee proof system of PiCore to verify the functional correctness and invariant of DGPS. The specification and its proof provide a strong evidence for the ongoing safety certification of DGPS.

关键词： Cognition Safety Formal specifications Vehicle dynamics Autonomous vehicles Certification Global Positioning System

A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Zekun Zhao, Wei Shi, Feng Qi, Lei Xie, Xingzhi Wei, Ying Ding, Zhongxiang Gao, Yang Wu, Shangjie Liu, Jun Shi, Yinghuan Shen, Dinggang State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University Nanjing210046 China School of Computer Science and Artificial Intelligence Southeast University Nanjing210018 China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai201807 China School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Artificial Intelligence Korea University Seoul02841 Korea Republic of Department of Radiology Second Xiangya Hospital Central South University Hunan410011 China Department of Radiology Quality Control Center Changsha410011 China Department of Radiology Hangzhou First People's Hospital Zhejiang University School of Medicine Hangzhou Zhejiang China Department of Pulmonary and Critical Care Medicine Second Xiangya Hospital Central South University Changsha410011 China

How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world. Currently, the chest CT is regarded as a popular and informative imaging tool for COVID-19 diagnosis. However, we observe that there are two issues - weak annotation and insufficient data that may obstruct automatic COVID-19 severity assessment with CT images. To address these challenges, we propose a novel three-component method, i.e., 1) a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, 2) a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and 3) a self-supervised pretext component to aid the learning process. We have systematically evaluated our method on the CT images of 229 COVID-19 cases, including 50 severe and 179 non-severe cases. Our method could obtain an average accuracy of 95.8%, with 93.6% sensitivity and 96.4% specificity, which outperformed previous works. Copyright © 2021, The Authors. All rights reserved.

关键词： computerized tomography

RAPID MIXING FROM SPECTRAL INDEPENDENCE BEYOND THE BOOLEAN DOMAIN

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Feng, Weiming Heng, G.U.O. Yitong, Y.I.N. Zhang, Chihao State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Avenue Nanjing Jiangsu Province China School of Informatics University of Edinburgh Informatics Forum EdinburghEH8 9AB United Kingdom John Hopcroft Center for Computer Science Shanghai Jiao Tong University 800 Dongchuan Road Minhang District Shanghai China

We extend the notion of spectral independence (introduced by Anari, Liu, and Oveis Gharan [ALO20]) from the Boolean domain to general discrete domains. This property characterises distributions with limited correlations, and implies that the corresponding Glauber dynamics is rapidly mixing. As a concrete application, we show that Glauber dynamics for sampling proper q-colourings mixes in polynomial-time for the family of triangle-free graphs with maximum degree ∆ provided q ≥ (α∗ + δ)∆ where α∗ ≈ 1.763 is the unique solution to α∗ = exp (1/α∗) and δ > 0 is any constant. This is the first efficient algorithm for sampling proper q-colourings in this regime with possibly unbounded ∆. Our main tool of establishing spectral independence is the recursive coupling by Goldberg, Martin, and Paterson [GMP05]. Copyright © 2020, The Authors. All rights reserved.

关键词： Polynomial approximation

Binary neural networks: A survey

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qin, Haotong Gong, Ruihao Liu, Xianglong Bai, Xiao Song, Jingkuan Sebe, Nicu State Key Lab of Software Development Environment Beihang University Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

A survey of software trustworthiness measurements

学校读者我要写书评

暂无评论

International Journal of Performability Engineering 2019年第9期15卷 2364-2372页

作者： Tao, Hongwei Chen, Yixiang Wu, Hengyang Deng, Rumei School of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou450002 China MoE Engineering Center for Software/Hardware Co-Design Technology and Application East China Normal University Shanghai200062 China School of Computer and Information Engineering Shanghai Polytechnic University Shanghai200062 China

As people depend more and more on software, there exists an increasing demand for software trustworthiness. The quantification of software trustworthiness can not only help users choose the right software, but also provide evidence for increasing the trustworthiness of the design and implementation of software. It has important practical significance to software development and application. In this paper, software trustworthiness measurements are surveyed from two aspects of product and process. The advances in the product-oriented software trustworthiness measurements are summarized in the view of attributes and behaviors, and the research progress of the process-based software trustworthiness measurements is studied from the perspective of expert experience and process data. Lastly, the challenges of software trustworthiness measurements are analyzed．. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： software design

WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Chu Pan, Xipeng Yan, Lixu Lin, Huan Li, Bingbing Yao, Su Lv, Shanshan Shi, Zhenwei Mai, Jinhai Lin, Jiatai Zhao, Bingchao Xu, Zeyan Wang, Zhizhen Wang, Yumeng Zhang, Yuan Wang, Huihui Zhu, Chao Lin, Chunhui Mao, Lijian Wu, Min Duan, Luwen Zhu, Jingsong Hu, Dong Fang, Zijie Chen, Yang Zhang, Yongbing Li, Yi Zou, Yiwen Yu, Yiduo Li, Xiaomeng Li, Haiming Cui, Yanfen Han, Guoqiang Xu, Yan Xu, Jun Yang, Huihua Li, Chunming Liu, Zhenbing Lu, Cheng Chen, Xin Liang, Changhong Zhang, Qingling Liu, Zaiyi The Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China Guangdong Prov. Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China The Department of Pathology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China The School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi541004 China The Department of Pathology Guangdong Provicial People's Hospital Ganzhou Hospital Ganzhou China The College of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The School of Computer Science and Engineering South China University of Technology Guangzhou510640 China The Institute for AI in Medicine School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China The School of Biological Science and Medical Engineering State Key Laboratory of Software Development Environment Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education Research Institute of Beihang University in Shenzhen Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing100191 China The Department of Radiology Guangzhou First People's Hospital Hospital of South China University of Technology Guangzhou510180 China The Zhejiang Dahua Technology Co. Ltd Zhejiang310053 China The School of Biomedical Engineering University of Science and Technology of China Hefei230022 China The Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Electronic and Computer Engineering & Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong The School of Automation Science and Engineering Xi'An Jiaotong University Xian710049 Chi

Lung cancer is the leading cause of cancer death worldwide, and adenocarcinoma (LUAD) is the most common subtype. Exploiting the potential value of the histopathology images can promote precision medicine in oncology. Tissue segmentation is the basic upstream task of histopathology image analysis. Existing deep learning models have achieved superior segmentation performance but require sufficient pixel-level annotations, which is time-consuming and expensive. To enrich the label resources of LUAD and to alleviate the annotation efforts, we organize this challenge WSSS4LUAD to call for the outstanding weakly-supervised semantic segmentation (WSSS) techniques for histopathology images of LUAD. Participants have to design the algorithm to segment tumor epithelial, tumor-associated stroma and normal tissue with only patch-level labels. This challenge includes 10,091 patch-level annotations (the training set) and over 130 million labeled pixels (the validation and test sets), from 87 WSIs (67 from GDPH, 20 from TCGA). All the labels were generated by a pathologist-in-the-loop pipeline with the help of AI models and checked by the label review board. Among 532 registrations, 28 teams submitted the results in the test phase with over 1,000 submissions. Finally, the first place team achieved mIoU of 0.8413 (tumor: 0.8389, stroma: 0.7931, normal: 0.8919). According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS. Cutmix data augmentation has been widely adopted to generate more reliable samples. With the success of this challenge, we believe that WSSS approaches with patch-level annotations can be a complement to the traditional pixel annotations while reducing the annotation efforts. The entire dataset has been released to encourage more researches on computational pathology in LUAD and more novel WSSS techniques. © 2022, CC BY.

关键词： Semantic Segmentation

Design of Work Ticket System and Scheduling Algorithm based on Blockchain

学校读者我要写书评

暂无评论

Design of Work Ticket System and Scheduling Algorithm based ...

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Hongkai Wang Yiyang Yao Qitong Hou Xiaoyi Wang Lei Zeng Weiwei Qiu Dong He Qiang Wang State Grid Zhejiang Electric Power Corporation Information & Telecommunication Branch Hangzhou China School of Software Technology Zhejiang University Ningbo China DataMesh Labs Hangzhou Qulian Technology Co. Ltd Hangzhou China Government & Enterprise Business Hangzhou China Research and Development Center Hangzhou Qulian Technology Co. Ltd Hangzhou China College of Computer Science Zhejiang University Hangzhou China

ISBN: (数字)9781728125473

ISBN: (纸本)9781728125480

This paper proposes and designs a work ticket system based on blockchain technology to realize employee identity authentication, credible management of work ticket status circulation, and authority control. Allow users to fully control the private key and store it locally, effectively avoiding large-scale information leakage. After the work ticket data is encrypted with a hash algorithm, the private key is used to sign it for storage on the blockchain, which ensures that the work ticket data cannot be tampered with or forged, and the person responsible can be accurately located based on the signature information. In the circulation of work tickets from the distribution to the receiving state, in order to distribute the work tickets to the corresponding receivers more reasonably, this paper combines the Analytic Hierarchy Process in operations research to design the work ticket scheduling algorithm and the contrast matrix is used to define the weights of various characteristics of the receivers, and after the consistency check, the receiver with the highest score is calculated, making the system more intelligent and efficient.

关键词： Blockchain Servers Public key Task analysis Scheduling algorithms Receivers Hash functions

A Green Power Traceability technology Based on Timestamp in a Main-Side Chain System

学校读者我要写书评

暂无评论

A Green Power Traceability Technology Based on Timestamp in ...

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Hongkai Wang Yiyang Yao Xiaohui Wang Xiaoyi Wang Lei Zeng Weiwei Qiu Dong He Qiang Wang State Grid Zhejiang Electric Power Corporation Information & Telecommunication Branch Hangzhou China School of Software Technology Zhejiang University Ningbo China DataMesh Labs Hangzhou Qulian Technology Co. Ltd Hangzhou China Hangzhou Qulian Technology Co. Ltd Hangzhou China Research and Development Center Hangzhou Qulian Technology Co. Ltd Hangzhou China College of Computer Science Zhejiang University Hangzhou China

ISBN: (数字)9780738105451

ISBN: (纸本)9781665422994

With the low carbon emission target out of protecting environment, electric vehicle is a promising transportation tool. The number of electric vehicles is rising rapidly in recent years which creates lots of corresponding charging demands. With both users and charging piles rising, however, condition of charging pile and price of electricity in different district are not transparent for users. In order to promote the benign interaction of production, distribution and consumption of green power, merging blockchain technology is a promising strategy. Unchangeable and traceable property of blockchain can make green power traceable. In this paper, a green power traceable system based on blockchain technology is proposed for providing convenient green power charging services for users. This system consists of main chain, transaction side chain and data side chain. Through the three dimensions of quantity, price and time, the type of energy and the region can be traced. In this system, we proposed a fast tracing technology based on index by timestamp. Experiment contrast index technology with traversal and smart contact. It shows that index by timestamp technology is more effective than traversal and smart contract.

关键词： Blockchain Logic gates Electric vehicles Smart contracts Green products Synchronization Indexes

NTIRE 2021 challenge on video super-resolution

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Son, Sanghyun Lee, Suyoung Nah, Seungjun Timofte, Radu Lee, Kyoung Mu Chan, Kelvin C.K. Zhou, Shangchen Xu, Xiangyu Loy, Chen Change Jiang, Boyuan Lin, Chuming Dong, Yuchun Luo, Donghao Chu, Wenqing Ji, Xiaozhong Yang, Siqian Tai, Ying Wang, Chengjie Li, Jilin Huang, Feiyue Chen, Chengpeng Chu, Xiaojie Zhang, Jie Lu, Xin Chen, Liangyu Lin, Jing Du, Guodong Hao, Jia Zou, Xueyi Zhang, Qi Jiang, Lielin Li, Xin Zheng, He Liu, Fanglong He, Dongliang Li, Fu Dang, Qingqing Yi, Peng Wang, Zhongyuan Jiang, Kui Jiang, Junjun Ma, Jiayi Chen, Yuxiang Wang, Yutong Liu, Ting Sun, Qichao Liang, Huanwei Li, Yiming Li, Zekun Ruan, Zhubo Shang, Fanjie Guo, Chen Li, Haining Luo, Renjun Shen, Longjie Zafirouli, Kassiani Karageorgos, Konstantinos Konstantoudakis, Konstantinos Dimou, Anastasios Daras, Petros Song, Xiaowei Zhuo, Xu Liu, Hanxi Guo, Mengxi Li, Junlin Li, Yu Zhu, Ye Wang, Qing Zhao, Shijie Sun, Xiaopeng Zhan, Gen Xie, Tangxin Jia, Yu Lu, Yunhua Zhang, Wenhao Sun, Mengdi Michelini, Pablo Navarrete Zhang, Xueheng Jiang, Hao Chen, Zhiyu Chen, Li Xiong, Zhiwei Xiao, Zeyu Xu, Ruikang Cheng, Zhen Fu, Xueyang Song, Fenglong Luo, Zhipeng Yao, Yuehan Dutta, Saikat Shah, Nisarg A. Das, Sourya Dipta Zhao, Peng Shi, Yukai Liu, Hongying Shang, Fanhua Liu, Yuanyuan Chen, Fei Yu, Fangxu Gao, Ruisheng Bai, Yixin Heo, Jeonghwan Yue, Shijie Li, Chenghua Li, Jinjing Zheng, Qian Gang, Ruipeng Song, Ruixia Wee, Seungwoo Jeong, Jechang Li, Chen Wen, Geyingjie Chai, Xinning Song, Li Department of ECE ASRI SNU Korea Republic of Computer Vision Lab ETH Zurich Switzerland S-Lab Nanyang Technological University Singapore YouTu Lab Tencent East China Normal University China Megvii Peking University China Fudan University China Noah's Ark Lab Huawei Canada Technologies Co. Ltd Baidu Inc National Engineering Research Center for Multimedia Software Wuhan University China School of Computer Science and Technology Harbin Institute of Technology China Electronic Information School Wuhan University China School of Computer Science and Engineering University of Electronic Science and Technology of China China MTlab Meitu Inc Xidian university China ITI CERTH Greece Southeast University China Tencent PCG South China University of Technology China ByteDance Sun Yat-Sen University China Electronic Technology Cyber Security Co. Ltd. AIoT R&D Centre BOE Technology Group Co. Ltd. Shanghai Jiao Tong University China University of Science and Technology of China China Huawei Noah's Ark Lab DeepBlue Technology Shanghai Co. Ltd Indian Institute of Technology Madras India Indian Institute of Technology Jodhpur India Jadavpur University India Xidian University China Hanyang University Korea Republic of NCUT China CASIA China CUC China NRTA China

Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart. This paper reviews the NTIRE 2021 Challenge on Video Super-Resolution. We present evaluation results from two competition tracks as well as the proposed solutions. Track 1 aims to develop conventional video SR methods focusing on the restoration quality. Track 2 assumes a more challenging environment with lower frame rates, casting spatio-temporal SR problem. In each competition, 247 and 223 participants have registered, respectively. During the final testing phase, 14 teams competed in each track to achieve state-of-the-art performance on video SR tasks. © 2021, CC BY-NC-ND.

关键词： Optical resolving power