首页 > 最新文献

2017 6th International Conference on Computer Science and Network Technology (ICCSNT)最新文献

英文 中文
Hidden information recognition based on multitask convolution neural network 基于多任务卷积神经网络的隐藏信息识别
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343685
Jiawen Liu, Huimei Yuan, Mingyang Li
With the continuous application of big data technology, machine learning is playing an increasingly important role in enterprise applications. User information, such as gender, age and educational level are the core factors for the research and application in the field of computer psychology, personalized search and social business promotion. This paper proposes a method for automatically inferring user information based on the search terms of users. We establish a multi task convolution neural network model based on word vectors. After the process of data cleaning, user search word segmentation, we use the word2vec to transform words into vector representation, and then build a multi task convolutional neural network model. This model is compared with other models based on word frequency, LDA methods. Experimental results show that our proposed multitasking based convolutional neural network approach works better than other methods.
随着大数据技术的不断应用,机器学习在企业应用中发挥着越来越重要的作用。性别、年龄、文化程度等用户信息是计算机心理学、个性化搜索、社会化商业推广等领域研究与应用的核心因素。提出了一种基于用户搜索词的用户信息自动推断方法。我们建立了一个基于词向量的多任务卷积神经网络模型。经过数据清洗、用户搜索分词等过程后,利用word2vec将词转化为向量表示,然后构建多任务卷积神经网络模型。该模型与其他基于词频、LDA方法的模型进行了比较。实验结果表明,我们提出的基于卷积神经网络的多任务处理方法比其他方法效果更好。
{"title":"Hidden information recognition based on multitask convolution neural network","authors":"Jiawen Liu, Huimei Yuan, Mingyang Li","doi":"10.1109/ICCSNT.2017.8343685","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343685","url":null,"abstract":"With the continuous application of big data technology, machine learning is playing an increasingly important role in enterprise applications. User information, such as gender, age and educational level are the core factors for the research and application in the field of computer psychology, personalized search and social business promotion. This paper proposes a method for automatically inferring user information based on the search terms of users. We establish a multi task convolution neural network model based on word vectors. After the process of data cleaning, user search word segmentation, we use the word2vec to transform words into vector representation, and then build a multi task convolutional neural network model. This model is compared with other models based on word frequency, LDA methods. Experimental results show that our proposed multitasking based convolutional neural network approach works better than other methods.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"24 23","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113984365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Global consensus making on multiplex scale-free networks 多路无标度网络的全球共识形成
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343716
Vu X Nguyen, Gaoxi Xiao
Most individuals, if not all, are active in various social networks. Opinion formation is an outcome of social interactions and information propagation occurring in such social systems. In this paper, we study on opinion formation on multiplex networks composed of two layers, each of which is a scale-free network, with a special focus on global consensus making in such networks. We impose a new rule of pair-wise interactions under inter-layer interplay termed as compromise following which two interacting nodes have a tendency to make a fair compromise in both senses of inter-and intra-layer interplay. It is found that in a duplex network composed of two identical layers, an increase in tolerance range in a layer declines the opinion diversity on the other layer and the two critical confidence bounds for achieving global consensus in both layers follow a one-sum rule; that is, each of the layers reaches a global consensus if the sum of two critical bounds on the two layers is approximately equal to 1, a double of critical bound on a single-layer network. However, in duplex networks of two non-identical layers with layer-layer coupling quantified by a link overlap parameter, the rule does not hold any longer. In this case, due to the larger portion of low-degree nodes in typical scale-free networks, a layer only can reach a complete consensus if its associated tolerance range is as large as nearly 0.5 even when the tolerance range on the other layer is utmost.
大多数人,如果不是全部,都活跃在各种社交网络中。舆论的形成是在这种社会系统中发生的社会互动和信息传播的结果。在本文中,我们研究了由两层组成的多路网络(每层都是一个无标度网络)上的意见形成问题,并特别关注了这种网络中的全局共识形成问题。我们提出了一种新的层间相互作用下的对明智的相互作用规则,称为妥协,在此规则下,两个相互作用的节点在层间和层内相互作用的两种意义上都倾向于做出公平的妥协。研究发现,在由两层相同网络组成的双工网络中,一层容忍范围的增加会降低另一层的意见多样性,两层达成全局共识的两个关键置信区间遵循一和规则;即,如果两层上的两个临界边界之和近似等于1,则每一层都达到全局共识,这是单层网络上临界边界的两倍。然而,在两层不相同的双工网络中,用链路重叠参数量化层与层之间的耦合,该规则不再成立。在这种情况下,由于典型无标度网络中低度节点的比例较大,即使另一层的容差范围最大,但只有当一层的关联容差范围大到接近0.5时,才能达成完全共识。
{"title":"Global consensus making on multiplex scale-free networks","authors":"Vu X Nguyen, Gaoxi Xiao","doi":"10.1109/ICCSNT.2017.8343716","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343716","url":null,"abstract":"Most individuals, if not all, are active in various social networks. Opinion formation is an outcome of social interactions and information propagation occurring in such social systems. In this paper, we study on opinion formation on multiplex networks composed of two layers, each of which is a scale-free network, with a special focus on global consensus making in such networks. We impose a new rule of pair-wise interactions under inter-layer interplay termed as compromise following which two interacting nodes have a tendency to make a fair compromise in both senses of inter-and intra-layer interplay. It is found that in a duplex network composed of two identical layers, an increase in tolerance range in a layer declines the opinion diversity on the other layer and the two critical confidence bounds for achieving global consensus in both layers follow a one-sum rule; that is, each of the layers reaches a global consensus if the sum of two critical bounds on the two layers is approximately equal to 1, a double of critical bound on a single-layer network. However, in duplex networks of two non-identical layers with layer-layer coupling quantified by a link overlap parameter, the rule does not hold any longer. In this case, due to the larger portion of low-degree nodes in typical scale-free networks, a layer only can reach a complete consensus if its associated tolerance range is as large as nearly 0.5 even when the tolerance range on the other layer is utmost.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115119361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research on DICOM file compression and offline storage platform DICOM文件压缩及离线存储平台的研究
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343753
Wangping Xiong, Jianqiang Du, Bin Nie, Liping Huang, Xian Zhou
Digital Imaging and Communications in Medicine (DICOM) is an industry standard for the delivery of medical images and their information across a variety of devices, which standardizes the format of various medical images and supports both TCP / IP protocols. With the rapid development and popularization of network technology, it is required to communicate with PACS system through medical image browser and display PACS image and related information in medical image browser, so as to realize fast access of DICOM permanent object. This paper focuses on the main content and structure, which is related to DCM4CHEE system, by using PACS system based on message and service-oriented open source, such as DCM4CHEE, for the medical image browser and the server-side interaction. In this paper, DCM4CHEE system uses MYSQL as DICOM database and uses JBOSS as an application server to build a PACS system experiment. According to the basic needs of users and functional requirements, the system is divided into various functional modules, the design of its commonly used sub-system functions, the design of the basic functions of the system, according to the actual needs of research and study to make the overall design of the image file be browsed. The paper chooses Java as the development platform, carries on the inquiry into the image document and carries on the design and realization of it. The system has a good interactive interface, which can greatly enhance the users' experience.
医学数字成像和通信(DICOM)是一个行业标准,用于在各种设备上传输医学图像及其信息,它标准化了各种医学图像的格式,并支持TCP / IP协议。随着网络技术的快速发展和普及,需要通过医学图像浏览器与PACS系统进行通信,并在医学图像浏览器中显示PACS图像及相关信息,从而实现DICOM永久对象的快速访问。本文重点介绍了与DCM4CHEE系统相关的主要内容和结构,利用基于消息和面向服务的开源PACS系统,如DCM4CHEE,进行医学图像浏览器和服务器端交互。本文的DCM4CHEE系统采用MYSQL作为DICOM数据库,JBOSS作为应用服务器来构建PACS系统实验。根据用户的基本需求和功能要求,将系统划分为各个功能模块,对其常用的子系统功能进行设计,对系统的基本功能进行设计,根据实际需要进行调研和学习,做出图像文件浏览的总体设计。本文选择Java作为开发平台,对图像文档进行查询并进行设计与实现。系统具有良好的交互界面,极大地提升了用户的使用体验。
{"title":"Research on DICOM file compression and offline storage platform","authors":"Wangping Xiong, Jianqiang Du, Bin Nie, Liping Huang, Xian Zhou","doi":"10.1109/ICCSNT.2017.8343753","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343753","url":null,"abstract":"Digital Imaging and Communications in Medicine (DICOM) is an industry standard for the delivery of medical images and their information across a variety of devices, which standardizes the format of various medical images and supports both TCP / IP protocols. With the rapid development and popularization of network technology, it is required to communicate with PACS system through medical image browser and display PACS image and related information in medical image browser, so as to realize fast access of DICOM permanent object. This paper focuses on the main content and structure, which is related to DCM4CHEE system, by using PACS system based on message and service-oriented open source, such as DCM4CHEE, for the medical image browser and the server-side interaction. In this paper, DCM4CHEE system uses MYSQL as DICOM database and uses JBOSS as an application server to build a PACS system experiment. According to the basic needs of users and functional requirements, the system is divided into various functional modules, the design of its commonly used sub-system functions, the design of the basic functions of the system, according to the actual needs of research and study to make the overall design of the image file be browsed. The paper chooses Java as the development platform, carries on the inquiry into the image document and carries on the design and realization of it. The system has a good interactive interface, which can greatly enhance the users' experience.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123692104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
TGCEL: A Chinese entity linking method based on topic relation graph TGCEL:一种基于主题关系图的中文实体链接方法
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343692
Yi Chen, Yusong Tan, Q. Wu, Wei Wang
Entity linking has an important basic research value for Natural Language Processing, the task of which is to link different entity mentions in the given text with their referent entities in a knowledge base. And it is widely used in such fields as expanding knowledge base, Q&A system, machine translation. We propose a Chinese collective entity linking algorithm based on the extracted topic features. We construct the topic relation graph of ambiguous entities in the same text, extract the topic characteristics from the multiple topic models, calculate the topic relevance, and select the topic subgraph with maximum score to reason and realize the batch linking. We experiment with both the news test corpus and the microblog test corpus, compare the performance of the adopted topic model, and analyze their applicable scene. When compared with the traditional algorithm, the maximum performance of our algorithm is improved by about 9% in microblog corpus and over 15% in news corpus, which indicates that our algorithm is potentially effective.
实体链接在自然语言处理中具有重要的基础研究价值,它的任务是将给定文本中提到的不同实体与其知识库中的参考实体联系起来。广泛应用于知识库扩展、问答系统、机器翻译等领域。我们提出了一种基于抽取主题特征的中文集体实体链接算法。我们构建同一文本中歧义实体的主题关系图,从多个主题模型中提取主题特征,计算主题相关性,选择得分最高的主题子图进行推理,实现批量链接。我们对新闻测试语料库和微博测试语料库进行了实验,比较了所采用的主题模型的性能,并分析了它们的适用场景。与传统算法相比,本文算法在微博语料库上的最大性能提高了9%左右,在新闻语料库上的最大性能提高了15%以上,表明本文算法具有潜在的有效性。
{"title":"TGCEL: A Chinese entity linking method based on topic relation graph","authors":"Yi Chen, Yusong Tan, Q. Wu, Wei Wang","doi":"10.1109/ICCSNT.2017.8343692","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343692","url":null,"abstract":"Entity linking has an important basic research value for Natural Language Processing, the task of which is to link different entity mentions in the given text with their referent entities in a knowledge base. And it is widely used in such fields as expanding knowledge base, Q&A system, machine translation. We propose a Chinese collective entity linking algorithm based on the extracted topic features. We construct the topic relation graph of ambiguous entities in the same text, extract the topic characteristics from the multiple topic models, calculate the topic relevance, and select the topic subgraph with maximum score to reason and realize the batch linking. We experiment with both the news test corpus and the microblog test corpus, compare the performance of the adopted topic model, and analyze their applicable scene. When compared with the traditional algorithm, the maximum performance of our algorithm is improved by about 9% in microblog corpus and over 15% in news corpus, which indicates that our algorithm is potentially effective.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122683567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Research on cattle farm management information system 牛场管理信息系统的研究
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343750
P. He, Hongli Chang, Han Gao, ZiYi Wang
Nowadays, People put increasingly higher demands on the quality of life. How to develop a set of health and efficient dairy farm system has become an important issue. This paper mainly researches dairy farm management, using AVR and 24L01 wireless module to design a set of zap automation management system. It realizes the full automation of the dairy farm management. First, this paper puts forward the implementation of the system function and the overall scheme. I design the structure of the system, then, I design the hardware circuit of the system, including the function of each module and the working process of the system, Finally, the cow management system software is designed.
如今,人们对生活质量的要求越来越高。如何发展一套健康高效的奶牛场体系已成为一个重要课题。本文主要研究奶牛场管理,利用AVR和24L01无线模块设计了一套zap自动化管理系统。实现了奶牛场管理的全自动化。本文首先提出了系统功能的实现和总体方案。首先设计了系统的总体结构,然后设计了系统的硬件电路,包括各个模块的功能和系统的工作流程,最后设计了奶牛管理系统的软件。
{"title":"Research on cattle farm management information system","authors":"P. He, Hongli Chang, Han Gao, ZiYi Wang","doi":"10.1109/ICCSNT.2017.8343750","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343750","url":null,"abstract":"Nowadays, People put increasingly higher demands on the quality of life. How to develop a set of health and efficient dairy farm system has become an important issue. This paper mainly researches dairy farm management, using AVR and 24L01 wireless module to design a set of zap automation management system. It realizes the full automation of the dairy farm management. First, this paper puts forward the implementation of the system function and the overall scheme. I design the structure of the system, then, I design the hardware circuit of the system, including the function of each module and the working process of the system, Finally, the cow management system software is designed.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122876054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimal design and applied research of a trailing suction hopper dredger loading system 耙吸式挖泥船装载系统的优化设计与应用研究
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343478
Wei Li, Zhen Su, Guojun Hong
In view of the nonlinear characteristics of dynamic model of dredging process, this paper adopts intelligent control algorithm such as pattern search and genetic algorithm to solve optimal control parameters, and obtains the optimal control strategy of dredging efficiency. Based on the combined application of database technology, LabVIEW, network communication and modern control technology, the optimization system of suction hopper dredger loading hopper is constructed. The system can be displayed to operators by man-machine interface, which provides a powerful technical support for the intelligent dredging of trailing suction dredger.
针对疏浚过程动态模型的非线性特点,采用模式搜索、遗传算法等智能控制算法求解最优控制参数,得出疏浚效率的最优控制策略。基于数据库技术、LabVIEW、网络通信和现代控制技术的综合应用,构建了挖泥船吸斗装料斗优化系统。该系统可通过人机界面显示给操作人员,为拖吸式挖泥船的智能化疏浚提供了有力的技术支持。
{"title":"Optimal design and applied research of a trailing suction hopper dredger loading system","authors":"Wei Li, Zhen Su, Guojun Hong","doi":"10.1109/ICCSNT.2017.8343478","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343478","url":null,"abstract":"In view of the nonlinear characteristics of dynamic model of dredging process, this paper adopts intelligent control algorithm such as pattern search and genetic algorithm to solve optimal control parameters, and obtains the optimal control strategy of dredging efficiency. Based on the combined application of database technology, LabVIEW, network communication and modern control technology, the optimization system of suction hopper dredger loading hopper is constructed. The system can be displayed to operators by man-machine interface, which provides a powerful technical support for the intelligent dredging of trailing suction dredger.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126099592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Organizing tactics based optimization theory 基于优化理论的组织策略
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343702
A. Xie, D. Liu
This paper proposed a new general framework for intelligent optimization based on organizing tactics rather than probability rules. Compared with the existing intelligent optimization algorithms, like Particle Swarm Optimization, this framework has several significant advantages. First, the “intelligence” does not depend on the probability rules of the operators, but their organizing tactics. Thus there are no probability equations that need to be updated, and involved control parameters are fewer, so it is easier to use in practice. Second, synergistic coexistence and automatic balance of the exploration and the exploitation are achieved in the running. Third, population diversity has been kept during the running. Fourth, most useless and ineffective repetitious operations are avoided, and thus the needed consumption of storage space and running time are lessened largely.
本文提出了一种新的基于组织策略而非概率规则的智能优化通用框架。与现有的智能优化算法(如粒子群优化)相比,该框架具有几个显著的优点。首先,“智能”不取决于操作者的概率规则,而取决于他们的组织策略。因此不需要更新概率方程,涉及的控制参数较少,便于实际应用。二是在运行中实现了勘探与开发的协同共存和自动平衡。三是在运行过程中保持了种群多样性。第四,避免了大多数无用和无效的重复操作,从而大大减少了所需的存储空间消耗和运行时间。
{"title":"Organizing tactics based optimization theory","authors":"A. Xie, D. Liu","doi":"10.1109/ICCSNT.2017.8343702","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343702","url":null,"abstract":"This paper proposed a new general framework for intelligent optimization based on organizing tactics rather than probability rules. Compared with the existing intelligent optimization algorithms, like Particle Swarm Optimization, this framework has several significant advantages. First, the “intelligence” does not depend on the probability rules of the operators, but their organizing tactics. Thus there are no probability equations that need to be updated, and involved control parameters are fewer, so it is easier to use in practice. Second, synergistic coexistence and automatic balance of the exploration and the exploitation are achieved in the running. Third, population diversity has been kept during the running. Fourth, most useless and ineffective repetitious operations are avoided, and thus the needed consumption of storage space and running time are lessened largely.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126188531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Discovering latent spatial structured patterns using graph models for scene classification 利用图模型发现潜在的空间结构模式用于场景分类
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343745
Yuhua Fan
Despite progress in scene recognition tasks such as image classification and attribute detection, computers still be difficult to understand the scenes as a whole. Existing methods often ignore global spatial constructed pattern among different local semantic objects. This paper propose a method for discovering the Latent spatial structured patterns to describe the visual semantic characters of images to improve the performance of scene recognition tasks. Unlike the existing approaches that mainly rely on the discriminant visual feature cues, we learn the latent spatial structured pattern to model the interaction relationships by using the graph models, which consider semantics and their localization information. We first train the pLSA models to obtain the latent semantic topics. Then we construct the graph models to discover the latent spatial structure patterns with combing the character vector and localization cues. Meanwhile, we treat the edge in model as link-affinity matrix to describe the interaction relationships between semantics. The extensive experiments on public datasets have demonstrated that the suggested method can significantly boost the performance of scene classification tasks.
尽管在图像分类和属性检测等场景识别任务方面取得了进展,但计算机仍然难以从整体上理解场景。现有的方法往往忽略了不同局部语义对象之间的全局空间构造模式。本文提出了一种发现潜在空间结构模式的方法来描述图像的视觉语义特征,以提高场景识别任务的性能。与现有的主要依赖于判别性视觉特征线索的方法不同,我们利用考虑语义及其定位信息的图模型,学习潜在的空间结构模式来建模交互关系。我们首先训练pLSA模型来获得潜在的语义主题。然后结合特征向量和定位线索构建图形模型,发现潜在的空间结构模式。同时,我们将模型中的边缘作为链接关联矩阵来描述语义之间的交互关系。在公共数据集上的大量实验表明,该方法可以显著提高场景分类任务的性能。
{"title":"Discovering latent spatial structured patterns using graph models for scene classification","authors":"Yuhua Fan","doi":"10.1109/ICCSNT.2017.8343745","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343745","url":null,"abstract":"Despite progress in scene recognition tasks such as image classification and attribute detection, computers still be difficult to understand the scenes as a whole. Existing methods often ignore global spatial constructed pattern among different local semantic objects. This paper propose a method for discovering the Latent spatial structured patterns to describe the visual semantic characters of images to improve the performance of scene recognition tasks. Unlike the existing approaches that mainly rely on the discriminant visual feature cues, we learn the latent spatial structured pattern to model the interaction relationships by using the graph models, which consider semantics and their localization information. We first train the pLSA models to obtain the latent semantic topics. Then we construct the graph models to discover the latent spatial structure patterns with combing the character vector and localization cues. Meanwhile, we treat the edge in model as link-affinity matrix to describe the interaction relationships between semantics. The extensive experiments on public datasets have demonstrated that the suggested method can significantly boost the performance of scene classification tasks.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129818117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The research of efficient publishing of subscription system 高效出版订阅系统的研究
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343469
Yan Xiao, Zongmin Cui, Jing Yu, Guangyong Gao, Cai-xue Zhou
This article discusses a system in detail. The design and implementation of an efficient subscription system is based on the PC. In a publishing subscription system, the subscription is represented by a Boolean expression. When the data is published by the master, the data owner publishes an event that corresponds to the data. When the data event matches the subscription Boolean expression, the data is sent to the user who subscribes to the data. Publishers publish data for this operation by using the conjunction index. The matching results are given automatically by the system. The system has a clean interface and simple operation. It is easy to maintain later.
本文详细讨论了一个系统。基于PC机的高效订阅系统的设计与实现。在发布订阅系统中,订阅由布尔表达式表示。当数据由主服务器发布时,数据所有者发布与该数据对应的事件。当数据事件匹配订阅布尔表达式时,将数据发送给订阅该数据的用户。发布者通过使用连接索引发布此操作的数据。系统自动给出匹配结果。该系统界面简洁,操作简单。以后很容易维护。
{"title":"The research of efficient publishing of subscription system","authors":"Yan Xiao, Zongmin Cui, Jing Yu, Guangyong Gao, Cai-xue Zhou","doi":"10.1109/ICCSNT.2017.8343469","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343469","url":null,"abstract":"This article discusses a system in detail. The design and implementation of an efficient subscription system is based on the PC. In a publishing subscription system, the subscription is represented by a Boolean expression. When the data is published by the master, the data owner publishes an event that corresponds to the data. When the data event matches the subscription Boolean expression, the data is sent to the user who subscribes to the data. Publishers publish data for this operation by using the conjunction index. The matching results are given automatically by the system. The system has a clean interface and simple operation. It is easy to maintain later.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129630019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research on the overall design scheme of consistency test system 一致性测试系统总体设计方案的研究
Pub Date : 2017-10-01 DOI: 10.1109/ICCSNT.2017.8343680
Songsong Chen, Dezhi Li, Mingyu Dong, Bin Yang, Changli Liu, Yi Sun, Bin Li
As the rapidly expanding of Demand Response and some other intelligent power usage business, the types of related equipment and systems increase sharply. The problem of connectivity between diversified systems needed to be solved urgently, and the vast need of consistency test in domestic was motivated. Started from the bottom logic of consistency test, combined with consistency test model of protocol specified in ISO/IEC-9646, as well as the black box test and some other specific test methods, overall design scheme about consistency test system was presented in this paper, with the characteristics of well universality. Meanwhile, the development tendency about consistency test was analyzed. This paper could provide some references for the consistency test of Demand Response technology field, and play a basic support role in the Demand Response business and some other relevant energy technology fields.
随着需求响应和其他智能用电业务的迅速发展,相关设备和系统的种类急剧增加。多系统间的连通性问题亟待解决,国内对一致性测试的需求巨大。本文从一致性测试的底层逻辑出发,结合ISO/IEC-9646中规定的协议一致性测试模型,以及黑盒测试等一些具体的测试方法,提出了一致性测试系统的总体设计方案,具有较好的通用性。同时,分析了一致性检验的发展趋势。本文可为需求响应技术领域的一致性测试提供一定的参考,并对需求响应业务及其他相关能源技术领域起到基础性支撑作用。
{"title":"Research on the overall design scheme of consistency test system","authors":"Songsong Chen, Dezhi Li, Mingyu Dong, Bin Yang, Changli Liu, Yi Sun, Bin Li","doi":"10.1109/ICCSNT.2017.8343680","DOIUrl":"https://doi.org/10.1109/ICCSNT.2017.8343680","url":null,"abstract":"As the rapidly expanding of Demand Response and some other intelligent power usage business, the types of related equipment and systems increase sharply. The problem of connectivity between diversified systems needed to be solved urgently, and the vast need of consistency test in domestic was motivated. Started from the bottom logic of consistency test, combined with consistency test model of protocol specified in ISO/IEC-9646, as well as the black box test and some other specific test methods, overall design scheme about consistency test system was presented in this paper, with the characteristics of well universality. Meanwhile, the development tendency about consistency test was analyzed. This paper could provide some references for the consistency test of Demand Response technology field, and play a basic support role in the Demand Response business and some other relevant energy technology fields.","PeriodicalId":163433,"journal":{"name":"2017 6th International Conference on Computer Science and Network Technology (ICCSNT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124977214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
2017 6th International Conference on Computer Science and Network Technology (ICCSNT)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1