检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Zhang, Zhi Zhong, Sheng-Hua Liu, Yan College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9781665438643

Video abnormal event detection is a significant research subject in intelligent surveillance, referring to identifying events that do not conform to expected behaviors. It is a challenging task due to the diversity of video content and the various definition of anomaly depending on contexts. How to grasp the nuances of anomalies from diverse video content under associated contexts? In this paper, we propose a context cueing generative adversarial network (CC-GAN) to scop attention to specific regions of interest (ROIs). Different from existing work, the designed framework takes advantage of the context cues to preserve the associations between ROIs and contexts. By intrinsic learning of static spatial layouts and apparent velocities, context cues can help to understand ROIs. Optimized in a crop-inpainting fashion, CC-GAN learns to generate ROIs matching given spatio-temporal context and discriminate the distorted or incongruous ones, corresponding to abnormal scenes. Compared with the state-of-the-art method and other abnormal event detection approaches, the proposed framework demonstrates its effectiveness, reliability, and good generalization ability across various scenes and events. © 2021 IEEE computer Society. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Fast Local Community Detection Algorithm in Signed Social Networks 9

A Fast Local Community Detection Algorithm in Signed Social ...

引用

9th International Conference on Social Networks Analysis, Management and Security, SNAMS 2022

作者： Bakhtar, Sahar Harutyunyan, Hovhannes A. Department of Software Engineering and Computer Science Concordia University MontrealH3G 1M8 Canada

ISBN: (纸本)9798350320480

Recent years have witnessed the rapid growth of social network services and consequently, research problems investigated in this area. Community detection is one of the most important problems in social networks. A good community can be defined as a group of vertices that are highly connected and loosely connected to the vertices outside the group. Community detection includes exploring the community partitioning in social networks. Regarding the fact that social networks are huge, having complete information about the whole network is almost impossible. As a result, the problem of local community detection has become more popular in recent years. This problem can be defined as the detection of a community for a given node by using local information. Many networks contain both positive and negative relations. A community in signed networks is defined as a group of nodes that are densely connected by positive links within the community and negative links between communities. In this paper, considering the problem of local community detection in signed networks, a new fast algorithm, noted as AlgSP, is developed to identify a dense community for a given node in signed networks. Experimental results show that the proposed algorithm can detect the ground-truth communities independently from the starting nodes. © 2022 IEEE.

关键词： Population dynamics

来源：评论

学校读者我要写书评

暂无评论

V-index an index based on consistent researcher productivity

V-index an index based on consistent researcher productivity

引用

2013 16th International Multi Topic Conference, INMIC 2013

作者： Daud, Ali Saleem Yasir, S.M. Muhammad, Faqir Department of Computer Science and Software Engineering International Islamic University Islamabad 44000 Pakistan Department of Business Administration Air University Islamabad 44000 Pakistan

ISBN: (纸本)9781479930432

In the current era, tremendous amount of scientific research work is published by thousands of researchers annually. Different methods have been proposed for researcher productivity indexing based on quantity and quality of publications. Unfortunately, none of them considered the variation among the number of citations received by a researcher for his papers. In this paper, a novel method named Variation-Index (v-index) is proposed to handle this issue. It will consider variation in number of citations received by the researcher's publications. V-index considers the consistency in citations of researcher's publication in addition to their number of publications (quantity) and number of citations (quality) for indexing. Experimental results show the effectiveness of our proposed v-index over the existing state of the art indexing methods. This citation variation enhancement is quite general and can be merged in any of the existing indexing measures with ease. © 2013 IEEE.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

PARSECS: A predictable data communication system for smart sensors and hard real-time applications

PARSECS: A predictable data communication system for smart s...

引用

作者： Micea, Mihai Victor Carstoiu, Gabriel N. Ungurean, Lucian Chiciudean, Dan Cretu, Vladimir-Ioan Groza, Voicu Department of Computer and Software Engineering Politehnica University of Timisoara Timisoara 300223 Romania School of Information Technology and Engineering University of Ottawa Ottawa ON KIN 6N5 Canada

This paper studies the problem of data communication protocols for multiprocessor smart sensors and embedded applications with hard real-time (HRT) or critical requirements. We propose a time-triggered communication interface and set of protocols, called Predictable ARchitecture for Sensor Communication Systems (PARSECS), specifically designed to sustain, at low costs and complexity, the predictable operation of such HRT systems. The general interface architecture, data format, and communication protocols are discussed, along with a case studythe implementation of PARSECS on the full-duplex serial peripheral interface for the COllaborative Robotic Environmentthe Timisoara eXperiment (CORE-TX) smart sensors platform. Its predictability, timeliness, and overall performance evaluation and validation are presented in detail based on experimental results and measurements. A comparative study with some of the most prominent systems in the field is also provided. © 2010 IEEE.

关键词： Smart sensors

来源：评论

学校读者我要写书评

暂无评论

Perceptional approach to design of industrial plant monitoring systems 8

Perceptional approach to design of industrial plant monitori...

引用

8th International Conference on Advances in computer-Human Interactions, ACHI 2015

作者： Göktürk, Mehmet Bakir, Mustafa Aydoǧan, Burak Aydin, Mehmet Department of Computer Engineering Gebze Institute of Technology Turkey Process Improvement and Software Division TÜPRAŞ Izmit Petroleum Refinery Turkey

ISBN: (纸本)9781612083827

In this paper, we have investigated the perceptional attitudes of a massive scale industrial plant staff towards process monitoring systems and focused on human factors that are influential in design of plant monitoring systems. The study is a part of a plant-wide monitoring system which is under development, aimed to help staff to monitor processes and plant performance in detail. The paper first gives focused introduction on large scale enterprise and plant monitoring and management information systems, then discusses human machine interaction relevance of these systems to the staff performance and perception. Examples from the literature and previous work are presented. Primary human factors in proactive monitoring and highly automated systems are briefly discussed. A design survey study follows the introduction and relevant literature sections. The survey is designed to collect perceptional status of the staff against such systems, including the perception of their current performance. Results are analyzed and discussed in order to enhance system design decisions in such plant monitoring systems. We believe that such perceptual studies, performed before attempting to implement large scale monitoring systems that are highly interactive to the existing staff, should be considered as essential part of the design process. The results of this study is being used as inputs in implementation of a recent petroleum plant monitoring system. Copyright © IARIA, 2015.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Appropriation of social media for fostering effective tacit knowledge sharing: Developing conceptual model 6

Appropriation of social media for fostering effective tacit ...

引用

6th International Conference on computer Science and Computational Mathematics, ICCSCM 2017

作者： Amidi, A. Jabar, M. Jusoh, Y.Y. Abdullah, R. Department of Software Engineering and Information System Faculty of Computer Science and Information Technology University Putra Malaysia UPM Serdang43400 Malaysia

With the rising popularity of social media in the past few years, several researches ratiocinate that this type of interactive and collaborative technology could be a beneficial tool for the sharing of tacit knowledge. Nevertheless, very few literatures have tackled the subject of how social media could facilitate tacit knowledge sharing among medical practitioners, and what are its contributions in the area. Thus, the factors that drive individuals to share tacit knowledge need to be investigated further and included in literature. Through a systematic literature review, this study proposes seven enabling conditions which could potentially facilitate the sharing of tacit knowledge. TAM was applied as a novelty in this study in investigating the factors influencing knowledge sharing via social media, whilst taking into account the mediation effects of Attitude in social media usage. This study uncovered an important correlation between virtual settings and the conversion of tacit knowledge, which affects organizational members who are not co-located physically but have a crucial need for sharing information. © Published under licence by IOP Publishing Ltd.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Distributed and Robust Support Vector Machine

引用

International Journal of Computational Geometry and Applications 2020年第3-4期30卷 213-233页

作者： Liu, Yangwei Ding, Hu Huang, Ziyun Xu, Jinhui Department of Computer Science and Engineering State University of New York at Buffalo Buffalo 14260-1660 NY United States School of Computer Science and Technology University of Science and Technology of China Hefei Anhui China Department of Computer Science and Software Engineering Penn State Erie Behrend College Erie 16563 PA United States

In this paper, we consider the distributed version of Support Vector Machine (SVM) under the coordinator model, where all input data (i.e., points in d space) of SVM are arbitrarily distributed among k nodes in some network with a coordinator which can communicate with all nodes. We investigate two variants of this problem, with and without outliers. For distributed SVM without outliers, we prove a lower bound on the communication complexity and give a distributed (1 - )-approximation algorithm to reach this lower bound, where is a user specified small constant. For distributed SVM with outliers, we present a (1 - )-approximation algorithm to explicitly remove the influence of outliers. Our algorithm is based on a deterministic distributed top t selection algorithm with communication complexity of O(klog(t)) in the coordinator model. © 2020 World Scientific Publishing Company.

关键词： communication complexity Distributed algorithm robust algorithm SVM

来源：评论

学校读者我要写书评

暂无评论

ACORN : TTTowards automating domain specific ontology construction process

引用

10th Asia Pacific Conference on Web Technology, APWeb 2008

作者： Bae, Eric Vasudevan, Bintu G. Balakrishnan, Rajesh NICTA Victoria Laboratory Department of Computer Science and Software Engineering University of Melbourne Australia SETLabs Infosys Technologies Limited Bangalore India

ISBN: (纸本)3540788484

A number of ontologies have been recently developed in order to represent common knowledge in a structured manner. This allows users and agents involved in a particular domain to make inquiries and discover the underlying conceptual differences present in the data. However, currently the majority of ontology construction tools are heavily dependent on the human domain experts for selecting concepts and defining their relationships. In this paper, we would like to present a new tool called ACORN, which implements novel techniques for automatically extracting concepts and building concept-to-concept relationships. We first utilize the WordNet lexical database and term co-occurrence frequency for discovering domain specific concepts and introduce 'cluster mapping' and 'generality ordering' techniques for connecting these concepts. We apply our techniques to a widely available dataset and show that ACORN is able to produce high quality ontologies. © 2008 Springer-Verlag Berlin Heidelberg.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

How do modelers code artificial societies? Investigating practices and quality of netlogo codes from large repositories

How do modelers code artificial societies? Investigating pra...

引用

2020 Spring Simulation Multiconference, SpringSim 2020

作者： Vendome, Christopher Rao, Dhananjai M. Giabbanelli, Philippe J. Department of Computer Science and Software Engineering Miami University 510 E. High St. OxfordOH United States

ISBN: (纸本)9781713812883

Many guidelines have been developed for simulations in general or for agent-based models which support artificial societies. When applying such guidelines to examine existing practices, assessment studies are limited by the artifacts released by modelers. Although code is the final product defining an artificial society, 90% of the code produced is not released hence previous assessments necessarily focused on higher-level items such as conceptual design or validation. We address this gap by collecting 338 artificial societies from two hosting platforms, CoMSES/OpenABM and GitHub. An innovation of our approach is the use of software engineering techniques to automatically examine the models with respect to items such as commenting the code, using libraries, or dividing code into functions. We found that developers of artificial societies code the decision-making of their agents from scratch in every model, despite the existence of several libraries that could be used as building blocks. © 2020 Society for Modeling & Simulation International (SCS)

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

An algorithm of image classification based on BP neural network

An algorithm of image classification based on BP neural netw...

引用

2012 IEEE International Conference on computer Science and Automation engineering, CSAE 2012

作者： Xiong, Zhiyong Chen, Ke Gu, Caidong Liang, Yinhong Yu, Fusheng JiangSu Province Support Software Engineering R and D Center for Modern Information Technology Application in Enterprise SuZhou China Department of Computer Engineering SuZhou Vocational University SuZhou China

ISBN: (纸本)9781467300865

To improve the performance of image classification, we propose an image classification method based on BP neural network. Firstly, one image is segmented and clustered several visual objects. By means of the unit image library, we calculate one probability vector, which is composed by probability of every visual object of the image and every unit image of the unit image library. So a total feature vector of one image can been attain. By means of the BP neural network, which we construct, we attain a class about the image, thereby we can realize image classification. The end, Ground Truth Database is adopted experimental image library in this paper. The method attains good effect based on experimental result. © 2012 IEEE.

关键词： Image classification

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：