检索结果-内蒙古大学图书馆

2016 IEEE International Conference on Progress in Informatics and Computing

作者： Xiaoying Shi Zhenhai Yu Xinyu Qu Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University Zhejiang Institute of Communications

Public bicycle sharing services are becoming popular over the past decade. The behavior of using public bicycle system(PBS) produces numerous hire records involving citizens' movement. This paper presents a visual analytics system-Touching PBSData, to help both traffic administrators and ordinary citizens visually explore and understand PBS data on multi-touch devices. Tasks and design principles are put forward firstly. Four views are designed to show different aspects of the dataset, including the geographical distribution, the spatio-temporal pattern and personal relevant information. In order to enhance the flexibility and usability of system, the organization mode of views and rich user interaction suitable for multi-touch device are further studied. By adopting real PBS dataset, the results of case studies certify that our method is able to help analyzers to find stations' main function and citizens' travel habits. Moreover, the feedback from the participants with various backgrounds is very affirmative through the user study.

关键词： traffic system management public bicycle system multi-touch device human mobility analysis visual analytics

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Security Analysis Framework Based on Threat Matrix

Machine Learning Security Analysis Framework Based on Threat...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Hu Li Qiongmin Ma Ming Zhang Xiaohui Kuang National Key Laboratory of Science and Technology on Information System Security Beijing China National Key Laboratory for Complex Systems Simulation Beijing China

Machine Learning and Artificial Intelligence technology accelerates technological progress and promotes social development, but also brings many security problems. Machine learning models may be affected, deceived, controlled or destroyed at different stages, e.g. training and inference, which may lead to serious consequences. In view of the main stages of the life cycle of machine learning, we summarizes the related attack and defense technologies based on threat matrix, makes a comprehensive and systematic analysis on the security issues of machine learning, and puts forward several security protection suggestions for intelligent information systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A system-of-systems architecture-driven modeling method for combat system effectiveness simulation 2

A system-of-systems architecture-driven modeling method for ...

引用

2nd Annual IEEE International Symposium on systems Engineering, ISSE 2016

作者： Li, Xiaobo Wang, Weiping Shu, Zhe Zhu, Ning He, Hua Liao, Tianjun College of Information Systems and Management National University of Defense Technology Changsha Hunan410073 China Department of Mathematics and Computer Science University of Antwerp Antwerp2020 Belgium State Key Laboratory of Complex System Simulation Beijing Institute of Systems Engineering Beijing China

ISBN: (纸本)9781509007936

Under the background of system-of-systems (SoS) counterwork, it is more apparent that the simulation modeling of the equipment should be domain-specific, formal, automatic and composable. Current equipment effectiveness simulation modeling approaches are mainly based on the methods and techniques from the modeling and simulation (M&S) community and software engineering community, and they are not capable to satisfy these four requirements systematically. Thus the systems engineering architecture model and domain knowledge should be used to support effectiveness simulation modeling more effectively. In this research, we propose an architecture-driven modeling method which conforms to the principle of architecture-driven development, uses ontology techniques to build equipment SoS architecture model and sub-domain ontology. This method performs architecture driven simulation modeling to realize the transformation from architecture models to simulation model frameworks;employs ontological metamodeling to design domain-specific modeling languages (DSML) based on the comprehensive usage of architecture models, sub-domain ontologies and M&S formalisms;integrates domain-specific simulation models from various domains using the model framework, and supports the composable development of simulation applications. © 2016 IEEE.

关键词： System of systems

来源：评论

学校读者我要写书评

暂无评论

Double Improved Genetic Simulated Annealing Algorithm for Logistics Distribution Routing Optimization

Double Improved Genetic Simulated Annealing Algorithm for Lo...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Yuanhang Li Jichao Li Yiyin Zhang Jianing Li Xiaoke Zhang College of Systems Engineering National University of Defense Technology Changsha China National Key Laboratory for Complex Systems Simulation Beijign China

Traveling Salesman Problem (TSP) is a NP-hard problem, which has important application value in various fields. This paper optimizes and improves Genetic Algorithm and Simulates Annealing Algorithms respectively, combines each other's advantages and complements each other, and develops a Double-improved genetic-simulates annealing algorithm (DIGASA), which can solve TSP with better results and shorter time. The main improvements are as follows: (1) A new fitness function is defined that can increase with the evolution process; (2) The F-adaptive function is designed to optimize the crossover and mutation probability; (3) The local optimal search is introduced to speed up the convergence of the algorithm; (4) The adaptive Metropolis criterion is adopted in the group update part to make individual changes more adaptive; (5) The cooling function is improved to increase the tempering process. Subsequently, DIGASA is tested on eight standard TSP datasets of three sizes. Experimental results show that DAGASA performs well, almost reach the known optimal solution, and the running time is short, which proves the effectiveness and rationality of DIGASA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Virtual Page Behavior Based Page Management Policy for Hybrid Main Memory in Cloud Computing 12

Virtual Page Behavior Based Page Management Policy for Hybri...

引用

12th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2016

作者： Huang, Jie Zhang, Xuan Han, Guangjie Jia, Gangyong Liyou, Huizi Wan, Jian Department of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou310018 China Department of Information and Communication Systems Hohai University Changzhou213022 China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou310023 China

ISBN: (纸本)9781509056965

A new generation memory, Non-Volatile Memory (NVM), such as Phase-Change Memory (PCM), has been adopted together with DRAM in the main memory to form the hybrid main memory for low energy consumption and high capacity. The biggest challenge of hybrid memory is how to decrease the average memory access cost for the higher cost of NVM's read/write operation. Currently, most researches are based on migration. However, the page migration itself is a high cost operation. And the migration based policy produces many migration operations, which induces high cost in memory access. Therefore, in order to decrease the cost, we present a virtual page behavior based page management policy (VBPM) in this paper. According to the virtual pages' behavior, we allocate virtual pages into DRAM or PCM physical pages correspondingly. The whole process is migration independent. The experimental results show our VBPM decreases the average memory access time by 24%, moreover, VBPM improves real-time performance in critical path. © 2016 IEEE.

关键词： Phase change memory

来源：评论

学校读者我要写书评

暂无评论

Effect of Different Migration Strategies on Evolution of Cooperation in Spatial Prisoner's Dilemma Game

Effect of Different Migration Strategies on Evolution of Coo...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Hong Ding Xiangyu Chen Benyun Shi Yanming Ye Yizhi Ren School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Hangzhou Dianzi University Hangzhou China Key Lab. of Complex Syst. Modeling & Simulation Dianzi Univ. Hangzhou China

Many migration strategies have been proposed forPrisoner's Dilemma game on square lattice, such as randommigration, success-driven migration and adaptive migration. Inthis paper, we introduce three novel migration strategies: failure driven migration, hate-driven migration and global-scope migration. Based on the length of migration, individual with one of the first two strategies decides when and where to move into empty nearby places based on its performance in current site, while individual with a global-scope migration can move to anywhere. Then we compare them with the cases of no migration, random migration and success-driven migration. The simulations show that the failure-driven migration has the best performance in most circumstances. While defectors dominate in success-driven migration cases.

关键词： High definition video Big data

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-agent Based C4ISR Effectiveness simulation and Evaluation

Research on Multi-agent Based C4ISR Effectiveness Simulation...

引用

International Conference on Computer modeling and simulation, ICCMS

作者： Zhang Ying-chao Ye Feng Yu Qin-zhang Chen Xin National Key Laboratory of Science and Technology on Complex Systems Simulation Beijing Institute of System Engineering Beijing China

The effectiveness evaluation of C4ISR is playing a more and more important role in its designing, developing and using. According to its characters, such as complexity and intelligence, the traditional evaluation methods and systems are not feasible and effective enough. In this paper, a multi-agent based simulation and evaluation framework of C4ISR is advanced, which includes the architecture and the working procedure. The agent-based simulation model of C4ISR is put forward, according to which the C2 Agent, Armament Agent and the Evaluation Agent are founded. The interaction model between each agent is also designed. At final, based on the Swarm, a multi-agent based C4ISR effectiveness simulation and evaluation prototype is developed, through which NATO C2 effectiveness evaluation is thoroughly analyzed.

关键词： Analytical models Computational modeling Computer simulation Adaptive systems Intelligent agent Design engineering systems engineering and theory Laboratories Virtual prototyping Information technology

来源：评论

学校读者我要写书评

暂无评论

MD-TransUNet: TransUNet with Multi-attention and Dilated Convolution for Brain Stroke Lesion Segmentation 19th

MD-TransUNet: TransUNet with Multi-attention and Dilated C...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Xu, Jie Wan, Jian Zhang, Xin School of Computer Science and Technology Hangzhou Dianzi University Zhejiang310018 China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Ministry of Education Beijing China School of Information and Electronic Engineering Zhejiang University of Science and Technology Zhejiang China Key Laboratory of Marine Ecosystem Dynamics Second Institute of Oceanography Ministry of Natural Resources Hangzhou China

ISBN: (纸本)9783031545276

The accurate segmentation of stroke lesion regions holds immense significance in shaping treatment strategies and rehabilitation protocols. Due to the large difference in the volume of stroke lesion areas and the great similarity between lesion areas and normal tissues, most of the existing methods for lesion segmentation cannot deal with these problems well. This paper proposes a novel network named MD-TransUNet for the segmentation of stroke lesions, whose framework is based on the UNet architecture. To fully obtain deep image features, it uses ResNet50 for downsampling. MD (multi-dilated) module is employed as the skip connection to gain more receptive fields. Different receptive fields can adapt to varying volumes of lesion areas. Then, a feature extraction module with multi-level attention mechanism is designed using ConvLSTM, non-local spatial attention, and channel attention modules to suppress useless information expression in skip connections and upsampling processes while focusing more on effective spatial and channel information in features. The experiments show that our proposed network gets superior performance than benchmark methods and indicates the generalization and effectiveness of the proposed model. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Survey of Knowledge Enhanced Pre-trained Models

arXiv

引用

arXiv 2021年

作者： Yang, Jian Hu, Xinyu Xiao, Gang Shen, Yulong Computer Science and Technology Xidian University Xi’an China National Key Laboratory for Complex Systems Simulation Beijing China

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Demo: A Multi-Agent Communication Framework in Cooperative Detection System

Demo: A Multi-Agent Communication Framework in Cooperative D...

引用

IEEE/ACM Symposium on Edge Computing (SEC)

作者： Hongye Gao Yichen Shi Weixiong Rao Qiongmin Ma School of Software Engineering Tongji University Shanghai China National Key Laboratory for Complex Systems Simulation Beijing China

Communication is an effective mechanism to coordinate the be-havior of mobile multi-agents. We propose a general multi-agent communication framework. With help of graph neural networks and reinforcement learning, this framework can provide a coop-erative detection method with more powerful capabilities. In this paper, we demonstrate the configurable co-detection simulation system. Moreover, the evaluation of the multi-agent communication framework validates that the agents can effectively cooperate with each other through decentralized communication, and effectively reduce computation overhead meanwhile with high scalability.

关键词：

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：