检索结果-内蒙古大学图书馆

?-net: Dual supervised medical image segmentation with multi-dimensional self-attention and diversely-connected multi-scale convolution

引用

NEUROCOMPUTING 2022年 500卷 177-190页

作者： Xu, Zhenghua Liu, Shijie Yuan, Di Wang, Lei Chen, Junyang Lukasiewicz, Thomas Fu, Zhigang Zhang, Rui State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology China Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health Hebei University of Technology China College of Computer Science and Software Engineering Shenzhen University China Department of Computer Science University of Oxford United Kingdom Department of Health Management Center 983 Hospital of Joint Logistics Support Force China www.ruizhang.info

Although U-Net and its variants have achieved some great successes in medical image segmentation tasks, their segmentation performances for small objects are still unsatisfactory. Therefore, in this work, a new deep model, co-Net, is proposed to achieve more accurate medical image segmentations. The advancements of co-Net are mainly threefold: First, it incorporates an additional expansive path into U-Net to import an extra supervision signal and obtain a more effective and robust image segmentation by dual supervision. Then, a multi-dimensional self-attention mechanism is further developed to highlight salient features and suppress irrelevant ones consecutively in both spatial and channel dimensions. Finally, to reduce semantic disparity between the feature maps of the contracting and expansive paths, we further propose to integrate diversely-connected multi-scale convolution blocks into the skip connections, where several multi-scale convolutional operations are connected in both series and parallel. Extensive experimental results on three abdominal CT segmentation tasks show that (i) co-Net greatly outperforms the state-of-the-art image segmentation methods in medical image segmentation tasks;(ii) the proposed three advancements are all effective and essential for co-Net to achieve the superior performances;and (iii) the proposed multi-dimensional self-attention (resp., diversely-connected multi scale convolution) is more effective than the state-of-the-art attention mechanisms (resp., multi-scale solutions) for medical image segmentations. The code will be released online after this paper is formally accepted. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Medical image segmentation Dual supervision Multi-dimensional self-attention Diversely-connected multi-scale convolution

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection of Industrial Control Systems Based on Transfer Learning

引用

Tsinghua Science and Technology 2021年第6期26卷 821-832页

作者： Weiping Wang Zhaorong Wang Zhanfan Zhou Haixia Deng Weiliang Zhao Chunyang Wang Yongzhen Guo School of Computer and Communication Engineering the Beijing Key Laboratory of Knowledge Engineering for Materials Scienceand the Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China Shunde Graduate School University of Science and Technology BeijingGuangzhou 528399China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China School of Mechanical Engineering University of Science and Technology BeijingBeijing 100083China Donlinks School of Economics and Management University of Science and Technology Beijing Beijing 100083China School of Automation Beijing Institute of TechnologyBeijing 100081 China Software Testing Center Beijing 100048China.

Industrial Control Systems(ICSs)are the lifeline of a ***,the anomaly detection of ICS traffic is an important *** paper proposes a model based on a deep residual Convolution Neural Network(CNN)to prevent gradient explosion or gradient disappearance and guarantee *** developed methodology addresses two limitations:most traditional machine learning methods can only detect known network attacks and deep learning algorithms require a long time to *** utilization of transfer learning under the modification of the existing residual CNN structure guarantees the detection of unknown ***-dimensional ICS flow data are converted into two-dimensional grayscale images to take full advantage of the features of *** show that the proposed method achieves a high score and solves the time problem associated with deep learning model *** model can give reliable predictions for unknown or differently distributed abnormal data through short-term ***,the proposed model ensures the safety of ICSs and verifies the feasibility of transfer learning for ICS anomaly detection.

关键词： anomaly detection transfer learning deep learning Industrial Control System(ICS)

来源：评论

学校读者我要写书评

暂无评论

A software reliability prediction based on RBM algorithm improvement method

引用

International Journal of Electrical Engineering 2016年第3期23卷 105-112页

作者： Yang, Chunhui Chen, Songli Dai, Qingyun Liu, Yihong Chen, Dingfang Software Quality Engineering Research Center College of Computer Science and Technology Wuhan University of Technology China Information Engineering College Guangdong University of Technology China Software Quality Engineering Research Center China Electronic Product Reliability and Environmental Testing Research Institute China College of Computer Science and Technology Wuhan University of Technology China

College of computer science and technology, Wuhan University of Technology;software Quality Engineering Research center, China Electronic Product reliability and Environmental testing Research Institute, China Songli Chen, Although the classic DBN has a good capability of feature extraction layer by layer and plays an important role in the area of software reliability prediction, training data still costs more time, and test error rate is relatively large. Therefore, the algorithm and network structure of DBN still has room for improvement. In this paper, the algorithms and architectures of DBN model is improved by determining the input dimension combined with self-organizing algorithm, automatically adjusting the number of hidden units and adding the support vector machine (SVM) classifier with the model output. In this way, it will not only substantially reduce the amount of information loss in each layer and the time of training data, but also improving the prediction accuracy of software reliability prediction. In order to verify the superiority of the improved software reliability prediction model, we have compared the traditional DBN software reliability prediction model with the improved one by experiment in this paper.

关键词： software reliability

来源：评论

学校读者我要写书评

暂无评论

Real-time embedded software test case generation based on time-extended EFSM: A case study

Real-time embedded software test case generation based on ti...

引用

WASE International Conference on Information Engineering

作者： Yin, Yongfeng Li, Zhen Liu, Bin Dept. of System Engineering of Engineering Technology BeiHang University China Computer Software Reliability Management and Testing Center Aviation Industry Corporation of China Beijing China

ISBN: (纸本)9780769540801

software testing techniques based on formal methods can reduce the uncertainty, improve accuracy, validity and degree of automation. In this paper, formal methods were introduced into the real-time embedded software testing field and a time-extended finite state machine, called t-EFSM, was proposed firstly. And then, based on the t-EFSM and combined with testing process of flight control software of an unmanned aerial vehicle (UAV), a method to generate the time-extended UIO sequence (t-UIO) was put forward. Finally, the method to generate test cases automatically according to t-UIO sequence was brought forward. © 2010 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

The integrated application based on real-time extended UML and improved formal method in real-time embedded software testing

引用

Journal of Networks 2010年第12期5卷 1410-1416页

作者： Yin, Yongfeng Liu, Bin Li, Zhen Zhang, Chun Wu, Ning School of Reliability and System Engineering BeiHang University Beijing China Software Reliability Management and Testing Center of Aviation Industry Corporation of China Beijing China

In this paper, formal methods were introduced into the real-time embedded software testing field and a real-time extended finite state machine, called rt_EFSM, was studied firstly. And then, the process of the integrated application based on real-time extended Unified Modeling Language (UML) and improved formal method in real-time embedded software testing are put forward. Furthermore, the extension scheme of the real-time UML, including the improvement and extension of state transitions and time constraints described mechanism, and the conversion method from real-time UML to rt_EFSM ware proposed. Finally, combined with the testing process of flight control software of an unmanned aerial vehicle (UAV), a method to generate the time-extended UIO sequence (ex_UIO) was put forward. Finally, the method to generate test cases automatically according to ex_UIO sequence was brought forward. The method proposed in this paper can fully make use of the advantages of tool resources of the UML which has been as the industry standard, but also the advantages of formal methods in accuracy, effectiveness and automation support. © 2010 ACADEMY PUBLISHER.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Real-time Embedded software Test Case Generation Based on Time-extended EFSM: A Case Study

Real-time Embedded Software Test Case Generation Based on Ti...

引用

WASE International Conference on Information Engineering, ICIE

作者： Yongfeng Yin Zhen Li Bin Liu Department of System Engineering of Engineering Technology Beihang University China Computer Software Reliability Management and Testing Center Aviation Industry Corporation of China Beijing China

software testing techniques based on formal methods can reduce the uncertainty, improve accuracy, validity and degree of automation. In this paper, formal methods were introduced into the real-time embedded software testing field and a time-extended finite state machine, called t_EFSM, was proposed firstly. And then, based on the t_EFSM and combined with testing process of flight control software of an unmanned aerial vehicle (UAV), a method to generate the time-extended UIO sequence (t_UIO) was put forward. Finally, the method to generate test cases automatically according to t_UIO sequence was brought forward.

关键词： testing Real time systems Unmanned aerial vehicles Embedded software Aerospace control Integrated circuits

来源：评论

学校读者我要写书评

暂无评论

STATISTICAL PROCESS-CONTROL FOR software IN THE MAINTENANCE PHASE

引用

NAVAL ENGINEERS JOURNAL 1993年第3期105卷 192-200页

作者： LUKE, SR JACOBS, DA REED, BM Stephen R. Luke:is a registered professional engineer in the Commonwealth of Virginia. He received his B.S. in mechanical engineering from Virginia Polytechnic Institute in 1983 and is presently pursuing a master's degree in engineering management at Old Dominion University. Mr. Luke is experienced as a test engineer at the Norfolk Naval Shipyard (1978–1989) and as a reliability/quality engineer at the Naval Undersea Warfare Center Detachment Norfolk (1989-Present). Currently he is the group leader of the RMA/QA group for the AN/SQQ-89(V) Antisubmarine Warfare System at Naval Undersea Warfare Center Detachment Norfolk. Mr. Luke is a member of ASNE IEEE (Reliability Society) and ASQC and is an ASQC certified quality engineer and reliability engineer. Derya Alasya Jacobs:is an assistant professor in the Engineering Management Department at Old Dominion University (ODU). She has a B.S. in computer science and an M.S. and Ph.D in engineering management from the University of Missouri-Rolla. Prior to joining ODU Dr. Jacobs worked as a research engineer at the Center for Technology Transfer and Economic Development at the University of Missouri-Rolla. During the same period she served as a consultant in software development for Missouri Enterprise Rolla Missouri. Dr. Jacobs' research interests are in the areas of applied artificial intelligence decision support systems operations research and computer integrated manufacturing. Billie M. Reed:is an assistant professor in the Engineering Management Department at Old Dominion University. He received a B.S. degree in mechanical engineering from Auburn University in 1971. After completing undergraduate studies Dr. Reed was commissioned as an officer in the U.S. Navy where he served in the nuclear submarine force until 1982. Following his military career Dr. Reed worked for nine years as a systems engineer and human-machine interface designer of complex interactive computer based systems for use in aircraft space and ship systems. He received his M.S. and Ph

As technology advances and our dependency on software increases, the requirement to develop the correct means to improve quality in both the deveiopment phase and the maintenance phase of software life cycle support becomes increasingly significant. The focus of this paper is on the dilemma facing software engineering in maintaining quality within the constraints of the maintenance phase. The paper further proposes that the software maintenance process can also be analvzed and improved using statistical process control (SPC) techniques. The methods discussed in this paper have been proposed for use in the software Maintenance project at NUWC Detachment Norfolk. Upon successful testing at NUWC Detachment Norfolk, they will be forwarded to the AN/SQQ-89(V) (interagencv) software Quality Evaluation Committee for use by other agencies which are developing and maintaining AN/SQQ-89(V) software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AN EXPERT SYSTEM FOR REAL-TIME NOISE AND VIBRATION ANALYSIS OF SHIPBOARD EQUIPMENT

引用

NAVAL ENGINEERS JOURNAL 1986年第3期98卷 107-114页

作者： KLEIN, SK VAIL, JA BALON, K Jeannine A. Vailis a graduate of the University of Pittsburgh and Wheeling College where she earned MS and BS degrees in mathematics. She is currently the president of Vail Research and Technology Corporation. Experience includes twelve years in reliability maintainability and availability (RMA) engineering software development and cost analysis in NA VSEA the Naval Surface Weapons Center and industry. She developed RMA requirements and performed simulations on a wide variety of naval ships and underwater weapons. She is a co-developer of the computer simulation techniques used in this paper for which she received a Group Achievement A ward from NA VSEA in 1980. Ms. Vail is currently a member of ASNE IEEE and the Society of Reliability Engineers. Publications include “DDG-47 Reliability Engineering Analysis”Naval Engineers JournalApril 1978. Steven K. Kleinattended Indiana University where he earned BS and MS degrees in mathemtical physics and completed course work for PhD degrees in mathematical physics and inorganic chemistry. He is currently a division director with ORI Inc. He has taught physics and mathematics at Indiana University and has over fifteen years experience in RMA engineering and management including director of product assurance for the joint cruise missile project. He has provided RMA engineering support to a broad spectrum of Navy and Air Force tactical and strategic weapon systems and is a past member of the NASA microcircuit line certification team. Kevin Balonis a graduate of the University of Maryland where he earned a BSEE degree. He is currently employed with ORI Inc. where he is performing a variety of projects related with implementation of higher order languages in embedded firmware architectures.

An expert system is described which allows real-time analysis of the noise and vibration signature of vibrating machinery. The system presented consists of an adaptive algorithm which varies the band width of analysis channels as a function of a signal complexity factor and a measure of the rapidity of local signal change. Overall program architecture is presented as well as detailed discussion of signature functional identification and statistical trend modules which are adaptable to a wide variety of input data base configurations. Execution of the program on a “super-mini” in FORTRAN code with direct graphics output and on 68000 series based firmware using ADA is discussed. Results are presented of program execution on Navy hydrophone and propulsion gas turbine data showing current signature and projections of trend to future times compared with failed condition signatures. Correlation results for such predictions are also discussed.

关键词： SHIP EQUIPMENT

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：