检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Du, Wenbin Jin, Huaqing Yu, Chao Yin, Guosheng Shenzhen University College of Computer Science and Software Engineering Shenzhen China University of California Department of Radiology and Biomedical Imaging San FranciscoCA United States Sun Yat-Sen University School of Computer Science and Engineering Guangzhou China University of Hong Kong Department of Statistics and Actuarial Science Hong Kong

ISBN: (纸本)9781665480451

In the multi-armed bandit (MAB) framework, we investigate the problem of learning the means of distributions that are associated with a finite n umber o f a rms under a monotonic constraint. Different from the traditional MAB, our problem involves a parameter constraint and a limited trial budget (i.e., the number of arm pulls is small). However, the number of training samples can be as large as possible through (infinite) simulations, while each training sample is of limited size. This situation arises when some additional information is provided before the trial starts and each arm pull (or testing) could be of extraordinary cost. For example, in cancer dose-finding clinical trials, higher toxicity probabilities are typically associated with higher dose levels (i.e., the monotonic dose-toxicity constraint), and the loss due to the drug's toxicity, side-effects or death of patients can be enormous. We formulate this problem in the reinforcement learning (RL) paradigm, which is referred to as a bandit arm localization problem. We propose a novel approach in a double deep Q-learning framework, which is integrated with a state-of-the-art statistical model to preserve the parameter constraint and develop a more effective learning strategy. The double deep Q-learning model can be trained with a large (can be as large as infinite) number of simulated trials, which is the first time to cast dose finding in the RL framework. We evaluate the performance of our approach through extensive simulation studies in realistic settings of phase I clinical trials. The proposed double deep Q-learning is shown to outperform the baseline methods in cancer dose-finding trials. © 2022 IEEE.

关键词： Toxicity

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control for Automated Network Assurance in Intent-Based Networking enabled Service Function Chains 36

Model Predictive Control for Automated Network Assurance in ...

引用

36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023

作者： Avgeris, Marios Leivadeas, Aris Athanasopoulos, Nikolaos Lambadaris, Ioannis Falkner, Matthias Carleton University Department of Systems and Computer Engineering Ottawa Canada Ácole de Technologie Supérieure Department of Software and It Engineering Montreal Canada Queen's University School of Electronics Electrical Engineering and Computer Science Belfast United Kingdom Cisco Systems Ottawa Canada

ISBN: (纸本)9781665477161

Recent trends in Network Function Virtualization (NFV) combined with Internet of Things (IoT) and 5G applications have reshaped the network service offering. In particular, Service Function Chains (SFCs) can associate network functions with physical and virtual resources towards providing a complete network service. Concurrently, the management of a continuously expanding network and the fulfillment of the applications' requirements pave the way for autonomic network solutions. Intent Based Networking (IBN) is a novel paradigm that aims to achieve the automatic orchestration of network services and the assurance of their performance. Accordingly, in this paper, we propose a novel automated network assurance model, based on Model Predictive Control, to guarantee the Quality of Service (QoS) and security requirements of multi-tenant and IBN-enabled SFCs. In this context, corrective decisions are proactively taken, in the form of incoming intent relocations among the SFCs. The results reveal that our model can assure with high probability the application requirements and minimize QoS violations. © 2023 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

A Novel(n,n)Secret Image Sharing Scheme Based on Sudoku

引用

Journal of Electronic science and Technology 2013年第1期11卷 44-50页

作者： Zhi-Hui Wang Cheng Guo Chin-Chen Chang the School of Software Dalian University of Technology the Department of Computer Science National Tsing Hua University the Department of Information Engineering and Computer Science Feng Chia University the Department of Computer Science and Information Engineering Asia University

Recently, Chang et al. proposed a Sudoku-based secret image sharing scheme. They utilized the Sudoku grid to generate meaningful shadow images, and their scheme satisfied all essential requirements. Based on Chang et al.＇s scheme, we propose a novel （n, n） secret image sharing scheme based on Sudoku. In the proposed scheme, a secret image can be shared among n different cover images by generating n shadow images, and the secret image can be reconstructed without distortion using only these n shadow images. Also, the proposed scheme can solve the overflow and underflow problems. The experimental results show that the visual quality of the shadow images is satisfactory. Furthermore, the proposed scheme allows for a large embedding capacity.

关键词： Secret sharing (n n) secret image sharing Sudoku steganography.

来源：评论

学校读者我要写书评

暂无评论

Target detection method based on improved YOLOv3 3

Target detection method based on improved YOLOv3

引用

3rd International Conference on computer Vision, Image and Deep Learning and International Conference on computer engineering and Applications, CVIDL and ICCEA 2022

作者： Jia, YiXin Liu, LuYang Zhang, LiJie Li, Hai Changchun University of Technology Department of Software Engineering Jilin Province Changchun China Changchun University of Technology Department of Computer Science and Technology Jilin Province Changchun China Changchun University of Technology School of Computer Science and Engineering Jilin Province Changchun China Jilin University Computer Technology Jilin Province Changchun China

ISBN: (纸本)9781665459112

With the continuous development of the field of computer vision and the need for the accuracy and timeliness of model recognition in practical applications, YOLOv3 draws on YOLOvl and YOLOv2. Although there are not many innovations, it maintains the speed advantage of the YOLO family and the detection accuracy is improved, especially for the detection ability of small objects [1]. However, in the three-layer feature network structure of YOLOv3, the correlation between the layers is not strong, which may lead to the situation that the information of the input image cannot be used efficiently, thus affecting the final accuracy. In this regard, this paper mainly studies the improvement method for the YOLOv3 feature pyramid network, and there are many improvement methods for this network. This paper uses residual linking and attention mechanism methods. The fusion judgment of features is realized by introducing the CBAM attention module and adding residual links in the same layer and residual links across layers. Finally, we use the VOC07+12 dataset [2] to obtain an accuracy of 79.5% under the condition of IoU=0.75 after 150 iterations, which is an improvement compared to the 73.6% accuracy of the original model. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

JMLAutoTest: A novel automated testing framework based on JML and JUnit

JMLAutoTest: A novel automated testing framework based on JM...

引用

3rd International Workshop on Formal Approaches to Testing of software, FATES 2003

作者： Xu, Guoqing Yang, Zongyuang Software Engineering Lab The Department of Computer Science East China Normal University 3663 N Zhongshan Rd Shanghai200062 China

ISBN: (纸本)3540208941

Writing specifications using Java Modeling Language has been accepted for a long time as a practical approach to increasing the correctness and quality of Java programs. However, the current JML testing system (the JML and JUnit framework) can only generate skeletons of test fixture and test case class. Writing codes for generating test cases, especially those with a complicated data structure is still a labor-intensive job in the test for programs annotated with JML specifications. This paper presents JMLAutoTest, a novel framework for automated testing of Java programs annotated with JML specifications. Firstly, given a method, three test classes (a skeleton of test client class, a JUnit test class and a test case class) can be generated. Secondly, JMLAutoTest can generate all nonisomorphic test cases that satisfy the requirements defined in the test client class. Thirdly, JMLAutoTest can avoid most meaningless cases by running the test in a double-phase way which saves much time of exploring meaningless cases in the test. This method can be adopted in the testing not only for Java programs, but also for programs written with other languages. Finally, JMLAutoTest executes the method and uses JML runtime assertion checker to decide whether its post-condition is violated. That is whether the method works correctly. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Call data record based big data analytics for smart cities 2

Call data record based big data analytics for smart cities

引用

2nd International Conference on Data science, E-Learning and Information Systems, DATA 2019

作者： Mouchili, Mama Nsangou Atwood, John William Aljawarneh, Shadi Concordia University Computer Science and Software Engineering Department 1455 de Maisonneuve Blvd. W. MontrealQCH3G 1M8 Canada Jordan University of Science and Technology Software Engineering Department Ar ramtha 3030 Irbid22110 Jordan

ISBN: (纸本)9781450372848

A Call Data Record (CDR) is produced for each call (or other interaction) handled by a telephone company. CDRs have traditionally been used for billing and network engineering purposes. Given how mobile phones have become an integral part of - and have undoubtedly transformed - the everyday life of a great part of the earth's population, and given that 90% or more of phone subscriptions are registered in any city, if CDRs are collected from the mobile phone and cellular networks, and combined with other data from the organization or from elsewhere, this will allow managers to identify trends, detect patterns, and glean other valuable findings from the data. This paper highlights the applicability of CDR-based big data, to gathering such insights. By stitching events together into clusters of related events across runtime environments and/or geographies, raw data becomes business insight to make decisions either to understand customer needs, to mitigate problems, or to ultimately gain a competitive advantage. © 2019 Association for Computing Machinery. ACM

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Security conscious composition of Semantic Web services based on AI planning and description logic 09

Security conscious composition of Semantic Web services base...

引用

11th International Conference on Information Integration and Web-based Applications and Services, iiWAS2009

作者： Tabatabaei, Sayed Gholam Hassan Dastjerdi, Amir Vahid Wan Kadir, Wan M. N. Ibrahim, Suhaimi Sarafian, Elahe 81310 Skudai Johor Malaysia Department of Computer Science and Software Engineering University of Melbourne Melbourne VIC Australia Shahid Bahonar University of Kerman Kerman Iran

ISBN: (纸本)9781605586601

Automated composition of Semantic Web services has become one of the recent critical issues in today's Web environment. Despite the importance of AI-planning techniques for Web service composition, previous works in that area do not address security issues, which is the focus of this paper. Based on our prior work, i.e. AIMO, we present an approach called SCAIMO to achieve security conscious composition of Semantic Web services. Moreover, we propose a Secure Task Matchmaker which is responsible of matching security conscious tasks with operators and methods based on Description Logics and Web Service Modeling Ontology (WSMO). We test our approach on a case study and the result shows SCAIMO can provide an applicable solution. © 2010 ACM.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Visual modeler for grid modeling and simulation (GridSim) toolkit

Visual modeler for grid modeling and simulation (GridSim) to...

引用

International Conference on Computational science, ICCS 2003

作者： Sulistio, Anthony Yeo, Chee Shin Buyya, Rajkumar Laboratory Department of Computer Science and Software Engineering The University of Melbourne ICT Building 111 Barry Street CarltonVIC3053 Australia

ISBN: (纸本)9783540401964

The Grid Modeling and Simulation (GridSim) toolkit provides a comprehensive facility for simulation of application scheduling in different Grid computing environments. However, using the GridSim toolkit to create a Grid simulation model can be a challenging task, especially when the user has no prior experience in using the toolkit before. This paper presents a Java-based Graphical User Interface (GUI) tool called Visual Modeler (VM) which is developed as an additional component on top of the GridSim toolkit. It aims to reduce the learning curve of users and enable fast creation of simulation models. The usefulness of VM is illustrated by a case study on simulating a Grid computing environment similar to that of the World-Wide Grid (WWG) testbed [1]. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Banking theory based distributed resource management and scheduling for hybrid cloud computing

Banking theory based distributed resource management and sch...

引用

2nd International Conference on Mechanical engineering, Industrial Electronics and Informatization, MEIEI 2013

作者： Yun, Feng Li, Hao Lu, Joan The Department of Computer and Information Science Zunyi Normal College China School of Software Yunnan University China School of Computing and Engineering University of Huddersfield United Kingdom

ISBN: (纸本)9783037858905

Cloud computing is becoming more and more mature, and an IaaS could computing model called Cloud Bank [1], which is based on commercial bank model, has been designed. Could Bank model can be partly distinguished from other traditional IaaS providers by the sources of infrastructure resources. This new model cloud offers new way to manage resource consumer, bank, and resource provider and maximize all participants' benefits. Meanwhile, the new cloud bank model follows the way of commerce bank to against the risk during the transaction. This model may be new solutions for hybrid cloud computing management. © (2013) Trans Tech Publications, Switzerland.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Architectural design decision visualization for architecture design: Preliminary results of a controlled experiment 11

Architectural design decision visualization for architecture...

引用

5th European Conference on software Architecture, ECSA 2011 - Workshop on Traceability, Dependencies and software Architecture, TDSA 2011, 1st International Workshop on software Architecture Variability, SAVA 2011

作者： Shahin, Mojtaba Liang, Peng Li, Zengyang State Key Lab of Software Engineering Wuhan University Wuhan China Department of Computer Engineering Neyriz Branch Islamic Azad University Neyriz Iran Department of Computing Science University of Groningen Groningen Netherlands

ISBN: (纸本)9781450306188

Visualization of architectural design decision (ADD) and its rationale, as a kind of traceability information, is supposed to facilitate the understanding of architecture design and the reasoning behind the design rationale, which is supposed to improve the architecting process and gets better architecture design results. But the lack of empirical evaluation that supports this statement prevents industrial practitioners from using ADD visualization in their daily architecting activities. In this paper, we conducted a controlled experiment to investigate how visualization of ADD can improve the understanding of architecture design by using Compendium, an open source tool for rationale visualization. The preliminary results show that visualization of ADD and its rationale does not increase the total time for reading architecture document (including visualization diagrams of ADDs) plus designing task, and it improves the understanding of architects on existing architecture design with better new design results. Copyright © 2011 ACM.

关键词： Visualization

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：