检索结果-内蒙古大学图书馆

International Conference on systems Integration

作者： K. Yamashita O. Sasaki Computer Application Systems Engineering Center Fuchu Works Toshiba Corporation

This paper presents Toshiba Corporation's computer application systems engineering center (CASEC). First, an overview of CASEC is described, including the center's production environment. Then, some of the management systems-including SOFPIT (software profit improvement tactics) designed for delegated cost management, and Toshiba's corporate-wide software-reuse library system. The decades of experience have demonstrated that the production of high-quality software is heavily dependent on human factors. For this reason the authors devised schemes and mechanisms to enforce basic rules for software production and management. These mechanisms include involving management and experts in the design-review process, FFQM (feed forward quality management), the introduction of management-level rankings, and software QCC (quality control circles) activities. Finally, the paper presents an education system by which CASEC trains systems engineers and programmers.< >

关键词： computer applications systems engineering and theory Production facilities Quality management Software systems Costs Software libraries Human factors Process design Feeds

来源：评论

学校读者我要写书评

暂无评论

Enhancing Building Safety: A Brief Review of Agent-Based Modeling for Fire Evacuation Simulation

引用

Procedia computer Science 2025年 257卷 668-675页

作者： Selain K. Kasereka Ortega M. Kabwe Maria W.K. Kinyanta Audrey L. Kasongo Godwill W.K. Ilunga Katya Muhambya Tasho Tashev Kyandoghere Kyamakya Mathematics Statistics and Computer Science Department University of Kinshasa Kinshasa DR. Congo Faculty of English Engineering Studies Technical University of Sofia Sofia Bulgaria ABIL Research Center Kinshasa DR. Congo Faculty of Computer Science Université Nouveaux Horizons Lubumbashi DR Congo Ganpat University Faculty of Computer Application Gujarat India Université Libre des Pays des Grands Lacs Faculty of Sciences and Technology Goma DR Congo Institute of Smart Systems Technologies University of Klagenfurt Klagenfurt Austria Polytechnic Faculty University of Kinshasa Kinshasa Democratic Republic of the Congo

The issue of building evacuation in the event of a fire is a significant concern in urban planning and architecture. In the absence of appropriate measures, an emergency situation can potentially result in disastrous outcomes. In this review article, we explore the application of agent-based modeling (ABM) in the simulation of building evacuations in the event of a free breakout. To address this issue, we present a synthesis of findings from several studies, highlighting the advantages of ABM in modeling complex evacuation dynamics such as crowd behavior, consideration of multiple parameters, and decision-making processes. Additionally, we provide insight into the simulation tools and techniques used in studies that demonstrate the practical applications of ABM in enhancing evacuation strategies. Furthermore, we identify current challenges, research gaps, and propose future directions to enhance the accuracy and effectiveness of fire evacuation modeling and simulations. This study aims to contribute to the improvement of proposed solutions and models for the development of successful, effective, and reliable evacuation plans to enhance the safety of occupants in buildings.

关键词： Agent-based Modeling Evacuation Fire Breakout Building Safety Disaster Agent-Based Simulation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China The School of Computing Kent Interdisciplinary Research Centre in Cyber Security University of Kent CanterburyCT2 7NF United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The Intelligent Transportation Systems Lab Innopolis University Innopolis Russia The School of Computer Science and Technology Xidian University China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. © 2004-2012 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

引用

IEEE Internet of Things Journal 2025年

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

On/Off-Line Prediction Applied to Job Scheduling on Non-Dedicated NOWs

引用

Journal of computer Science & Technology 2011年第1期26卷 99-116页

作者： Mauricio Hanzich Porfidio Hernandez Francesc Gine Francesc Solsona Josep L.Lerida Department of Computer Application in Science and Engineering Barcelona Supercomputing CenterBarcelonaSpain Department of Computer Architecture & Operating Systems Autonomous University of BarcelonaBarcelonaSpain Department of Computer Science University of LleidaLleidaSpain

This paper proposes a prediction engine designed for non-dedicated clusters, which is able to estimate the turnaround time for parallel applications, even in the presence of serial workload of the workstation owner. The prediction engine can be configured to work with three different estimation kernels： a Historical kernel, a Simulation kernel based on analytical models and an integration of both, named Hybrid kernel. These estimation proposals were integrated into a scheduling system, named CISNE, which can be executed in an on-line or off-line mode. The accuracy of the proposed estimation methods was evaluated in relation to different job scheduling policies in a real and a simulated cluster environment. In both environments, we observed that the Hybrid system gives the best results because it combines the ability of a simulation engine to capture the dynamism of a non-dedicated environment together with the accuracy of the historical methods to estimate the application runtime considering the state of the resources.

关键词： prediction method non-dedicated cluster cluster computing job scheduling simulation

来源：评论

学校读者我要写书评

暂无评论

Developing an expert system to assist in control system design

引用

Journal of Intelligent and Robotic systems 1989年第2-3期2卷 277-295页

作者： Butz, Brian P. Palumbo, N.F. Intelligent Systems Application Center College of Engineering Computer Sciences and Architecture Temple University Philadelphia 19122 PA United States

This paper addresses the problem of how to develop an expert system that is able to design or to assist in the design of a control system. The discussion includes how to structure the expert system, how to choose the relationship between the symbolic and numerical processor and how to divide the work among the expert system, the computer aided control systems analysis package and the design engineer. A prototype intelligent design associated is presented and an example of a compensator design is given. © 1989 Kluwer Academic Publishers.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

An intelligent circuit analysis module to analyze student queries in the Universal Virtual Laboratory

An intelligent circuit analysis module to analyze student qu...

引用

Frontiers in Education - 35th Annual Conference 2005, FIE' 05

作者： Mahalingam, Annapoorna Butz, Brian P. Duarte, Michael Intelligent Systems Application Center Electrical and Computer Engineering Department Temple University Philadelphia PA 19122

ISBN: (纸本)0780390776

This paper presents an intelligent circuit analysis module that is capable of analyzing electrical circuits and determining equivalence. We discuss the module in context of a National Science Foundation funded project - Universal Virtual laboratory (UVL). UVL is a virtual electrical engineering laboratory for able and disabled individuals to construct, simulate and understand the characteristics of basic electrical circuits. This paper discusses the development of an intelligent circuit analysis module called the Circuit Recognizer (CR). The CR is a program that has knowledge of circuit theory concepts, and is capable of using this knowledge to provide assistance to a student while he/she is performing the experiments in UVL. While verifying circuit configuration it identifies errors and provides explanations that guide the student to a better understanding of the experiment. The ultimate objective of the CR is to evaluate the effectiveness of the teaching strategies employed within the UVL as well as to enhance the learning abilities of students. © 2005 IEEE.

关键词： Electric network analysis

来源：评论

学校读者我要写书评

暂无评论

Human Detection System using Different Depths of the Resnet-50 in Faster R-CNN 4

Human Detection System using Different Depths of the Resnet-...

引用

4th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2020

作者： Oztel, Ismail Faculty of Computer and Information Sciences Department of Computer Engineering Sakarya Turkey Artificial Intelligence Systems Application and Research Center Sakarya University Serdivan Sakarya Turkey

ISBN: (数字)9781728190907

ISBN: (纸本)9781728190907

Locating people in an image or video sequence automatically is a challenging task due to different environmental conditions and wide variety of features. On the other hand, because of its variety of applications, automated human detection is a very popular area. This study proposes a deep learning model for automated human detection. In order to apply this task, the Pascal VOC database has been used for training and testing stages. The feature extraction step is performed using different depths of the Resnet-50 in a faster R-CNN model. Then, the obtained features are used for the classification step. When the results are compared for different depths of the Resnet-50, it is observed that the first 40 depth of the Resnet-50 showed the better performance than the first 46 depth. Also, the faster RCNN model used in this study outperforms the other studies used the same Pascal VOC database in the literature. The proposed system can detect humans indoor or outdoor environments. Also, it produces promising results in human detection task even in occlusion situations. It can be used for different applications such as monitoring people in public areas with security, health, or energy efficiency proposes, etc. © 2020 IEEE.

关键词： convolutional neural networks deep learning faster-RCNN human detection

来源：评论

学校读者我要写书评

暂无评论

Efficient and High-quality Recommendations via Momentum-incorporated Parallel Stochastic Gradient Descent-Based Learning

引用

IEEE/CAA Journal of Automatica Sinica 2021年第2期8卷 402-411页

作者： Xin Luo Wen Qin Ani Dong Khaled Sedraoui MengChu Zhou the School of Computer Science and Technology Dongguan University of TechnologyDongguan 523808 Hengrui(Chongqing)Artificial Intelligence Research Center Department of Big Data Analyses TechniquesCloudwalkChongqing 401331China the School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China the Department of Computer and Information Science City College of Dongguan University of TechnologyDongguan 523419China the Department of Electrical and Computer Engineering Faculty of Engineeringand Center of Research Excellence in Renewable Energy and Power SystemsKing Abdulaziz UniversityJeddah 21481Saudi Arabia the Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA the Center of Research Excellence in Renewable Energy and Power Systems King Abdulaziz UniversityJeddah 21481Saudi Arabia

A recommender system(RS)relying on latent factor analysis usually adopts stochastic gradient descent(SGD)as its learning ***,owing to its serial mechanism,an SGD algorithm suffers from low efficiency and scalability when handling large-scale industrial *** at addressing this issue,this study proposes a momentum-incorporated parallel stochastic gradient descent(MPSGD)algorithm,whose main idea is two-fold:a)implementing parallelization via a novel datasplitting strategy,and b)accelerating convergence rate by integrating momentum effects into its training *** it,an MPSGD-based latent factor(MLF)model is achieved,which is capable of performing efficient and high-quality *** results on four high-dimensional and sparse matrices generated by industrial RS indicate that owing to an MPSGD algorithm,an MLF model outperforms the existing state-of-the-art ones in both computational efficiency and scalability.

关键词： Big data industrial application industrial data latent factor analysis machine learning parallel algorithm recommender system(RS) stochastic gradient descent(SGD)

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：