检索结果-内蒙古大学图书馆

第25届中国过程控制会议

作者： Shijin Ren Zhihuan Song Maoyun Yang Jianguo Ren National Laboratory of Industrial Control Technology Zhejiang University School of Computer Science& Technology Jiangsu Normal University

Complex processes often work with multiple operation regions,it is critical to develop effective monitoring approaches to ensure the safety of chemical *** this paper,a novel multimode process monitoring method called local consistency Gaussian mixture model（LCGMM）for discriminant analysis（DLCGMM）,is proposed by integrating a local consistency Gaussian mixture model（LCGMM）with a modified localized Fisher discriminant analysis（MLFDA）in this ***,a local consistency Gaussian mixture model is iteratively refined in any dimensionality discriminant space specified by *** a result,the soft clustering analysis in the optimal discriminant space and the optimal discriminant analysis are performed simultaneously,and the optimal clusters can be achieved due to multimodality within the multiple clusters uncovered by exploiting the results of LCGMM and computing the localized between-class and within-class scatter matrices for the generalized eigenvalue decomposition ***,PCA is performed on each cluster that represents a specific operation condition and a global Bayesian inference-based fault monitoring index is established by combining all the monitoring results of all *** efficiency and effectiveness of the proposed method are validated though UCI datasets and the Tennessee Eastman benchmark process..

关键词： Multimode process monitoring local consistency Gaussian mixture model for discriminant analysis modified localized Fisher discriminant analysis global fault detection index Tennessee Eastman process

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Classification for Assessment of Emotion Recognition in Speech

SSRN

引用

SSRN 2019年

作者： Agrawal, Akshat Jain, Anurag Kumar, B. Suresh University School of Information Communication and Technology Computer Science& Engineering Amity University Rajasthan Jaipur India Department of Computer Science and Engineering

In recent events, expanding consideration has been coordinated to the investigation of the emotional material of Voice signals, and thus, numerous frameworks have been proposed to distinguish the emotional material of a verbally expressed articulation. This paper is an analysis of voice sentiments grouping tending to three critical parts of the structure for a Voice feeling acknowledgment framework. The first problem is the decision of reasonable features for voice signal portrayal. The second problem is the structure of a fitting grouping plan and the third problem is the best possible planning of a passionate voice signal database for assessing framework execution. In this paper we will try to recommend conceivable methods for enhancing voice signal acknowledgment frameworks. © 2019, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A New Distributed Intrusion Detection Model Based on Immune Mobile Agent

A New Distributed Intrusion Detection Model Based on Immune ...

引用

Asia-Pacific Conference on Information Processing, APCIP

作者： Jing Xu Yongzhong Li College of information engineering Yancheng Institute of Technology Yancheng China School of Computer Science& Engineering Jiangsu University of Science and Technology Zhenjiang China

The development direction of intrusion detection system is intelligent and distributed in future. However, current distributed intrusion detection system mostly uses distributed component to collect data then sent to processing center. Data is analyzed in the processing center. These models have the following problems: bad real time capability, bottleneck, and single point of failure. In order to overcome these shortcomings of current intrusion detection techniques, a new distributed intrusion detection model based on mobile agent is proposed in this paper. Intelligent and mobile characteristics of the agent are used to make computing move to data. As mobile agent can only improve the structure of system and can not supply fundamental new detecting techniques, improved dynamic clonal selection algorithm and collaborative signal mechanism are adopted for reducing false positive rate and increasing detection rate in this paper. Finally, the proposed model and algorithm were simulated by KDDpsila99 datasets. Comparing with winning entry of KDDpsila99 classifier learning contest, the proposed model has low false positive rate and higher detection rate in both Dos and Probing attacks, and greatly higher detection rate in U2R attack. Robustness and dynamic adaptability of the system are validated.

关键词： Intrusion detection Mobile agents Heuristic algorithms Collaboration computerized monitoring Intelligent agent Condition monitoring Autonomous agents Immune system Detectors

来源：评论

学校读者我要写书评

暂无评论

Dual-Role Based Access Control Framework for Grid Services

Dual-Role Based Access Control Framework for Grid Services

引用

2006 Asia-Pacific Services Computing Conference(IEEE亚太地区服务计算会议)

作者： Lina Ge Shaohua Tang Qiao Kuang School of Computer Science& Engineering South China University of Technology Guangzhou 510640 CH Department of Computer Science The University of Chicago Illinois 60637 USA

In the grid environment, the resource providers should maintain the ultimate authority over their resources, including access authorization and grain scale control. Apparently, the traditional RBAC model will be inappropriate in multi-autonomous domains environment. Focusing on the autonomous, heterogeneous and dynamic features of grid computing, we propose the concept of "Resource Role". We also initiate the Dual-Role Based Access Control (DRBAC) framework, where the resource role permission mapping is defined in resource domain and user role resource role mapping is negotiated by user domain and resource domain. This framework is simple and works better than the traditional RBAC in multi domains environment.

关键词： Access control Permission computer science Authorization Maintenance engineering XML Grid computing Intelligent control Traffic control Collaborative work

来源：评论

学校读者我要写书评

暂无评论

Boost search relevance for tag-based social image retrieval

Boost search relevance for tag-based social image retrieval

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Dong Liu Xian-Sheng Hua Meng Wang HongJiang Zhang School of Computer Science& Tec. Harbin Institute of Technology China Microsoft Research Asia China Microsoft Advanced Technology Center USA

Social media sharing Web sites like Flickr allow users to annotate images with free tags, which greatly facilitate social image search and browsing. However, currently tag-based image search on Flickr does not provide the option of relevance-based ranking, i.e., the search results cannot be ranked according to their relevance levels with respect to the query tag, and this has limited the effectiveness of tagbased search. In this paper, we propose a relevance-based ranking scheme for social image search, aiming to automatically rank images according to their relevance to the query tag. It integrates both the visual consistency between images and the semantic correlation between tags in a unified optimization framework. We propose an iterative method to solve the optimization problem, and the relevance-based ranking can thus be accomplished. Experimental results on real Flickr image collection demonstrate the effectiveness of the proposed approach.

关键词： Image retrieval Birds Asia Iterative methods Information services Web sites Internet Optimization methods Explosions YouTube

来源：评论

学校读者我要写书评

暂无评论

IoT and AI Synergy in Society: Robotics and Automation Perspectives 7

IoT and AI Synergy in Society: Robotics and Automation Persp...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Geetha, B.T. Jothi, J. Salomi Backia Pal, Shaunak Islam, Imam Taqi Deen Raghuram, K.S. Soni, Mukesh Simats Saveetha University Saveetha School of Engineering Department of Ece Tamil Nadu India Srm Institute of Science and Technology Faculty of Science and Humanities Department of Commerce Ramapuram campus Chennai600089 India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Vellore India University of Electrical Science and Technology of China Sichuan Chengdu China Department of Mechanical Engineering Visakhapatnam India Dr. D. Y. Patil Vidyapeeth Pune Dr. D. Y. Patil School of Science& Technology Tathawade Pune India

ISBN: (纸本)9798350350067

The Internet of Things, or IoT, is a relatively new Internet revolution that is being successfully adopted by the corporate, industrial, healthcare, and economic sectors as well as other areas of the modern information society. Specifically, IoT with artificial intelligence (AI) support improves a great deal the performance in a wide range of daily applications with a focus on automation systems, robotics, transportation, and business. Smart automation in the manufacturing sector is now possible thanks to the development of Industry 4.0. The BRDT algorithm is used in this work to track how much energy appliances and machinery use, forecast behaviour, and identifies unusual conduct. When the suggested system's efficiency is compared to current approaches, it provides an efficiency of 85%. The application of this technology raises a number of standardisation, security, resource planning, legal, and paradigm-shifting business challenge problems. The whole supply chain and all of its actors, from producers to end users, are crucial to the success or failure of Industry 4.0 deployment. © 2024 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Tag quality improvement for social images

Tag quality improvement for social images

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Dong Liu Meng Wang Linjun Yang Xian-Sheng Hua Hong Jiang Zhang School of Computer Science& Tec. Harbin Institute of Technology China Microsoft Research Asia China Microsoft Advanced Technology Center USA

Online social media sharing Web sites like Flickr allow users to manually annotate images with tags, which can facilitate image search and organization. However, the tags provided by users are often imprecise and incomplete, which severely limits the application of tags to image search and browse. In this paper, we propose a scheme to improve poorly annotated tags associated with social images. Two properties are exploited and integrated in an unified optimization framework: (1) consistency between visual and semantic similarities, where the semantic similarity is estimated using tags; (2) compatibility of tags before and after improvement, since the initial user provided tags carry valuable information. An iterative bound optimization method is derived to solve the optimization problem. Experimental results on Flickr dataset show that the proposed method can significantly improve the quality of tags.

关键词： Optimization methods Tagging Asia Iterative methods Technical Activities Guide -TAG Explosions YouTube Large-scale systems Content based retrieval Clouds

来源：评论

学校读者我要写书评

暂无评论

Radiated Electromagnetic Disturbance for the DC Trolley Locomotive System in Underground Coal Mines

Radiated Electromagnetic Disturbance for the DC Trolley Loco...

引用

IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference (IMCEC)

作者： Hui Chen Mu Zhang Zi-jian Tian College of computer science and engineering Anhui university of science& technology Huainan China School of Mechanical Electronic& Information Engineering China University of Mining& Technology Beijing China

Since the large amount of electro-mechanical equipments are used in underground coal mines, the electromagnetic environment become more and more complex. For the radiated electromagnetic disturbance from the DC trolley locomotive system in underground coal mines, the distributed parameter circuit model of the DC trolley locomotive system is established based on circuit theory. The mechanism of electromagnetic radiation from the pantograph arc is analyzed, and the expression of discharge current of electric arc is also deduced. Moreover, the radiated electromagnetic fields are measured when the DC electric locomotive is running. The measurement results show that the frequency spectrum of radiated electric-field mainly ranges from 250kHz to 3GHz; the maximum of electric field intensity is 93dBuV/m, which is about 40dBuV/m more than the background noise; the frequency spectrum of radiated magnetic-field intensity mainly distributes in the low frequency band, and the maximum is about 101dBpT. Besides, the overhead lines and other axial conductors in the tunnel are propitious to propagate electromagnetic waves. Therefore, the wireless communication system and personnel positioning system can be interfered by the radiated electromagnetic noise in locomotive haulage tunnels.

关键词： Coal mining Electromagnetic radiation Magnetic field measurement Antenna measurements Electric variables measurement Power supplies

来源：评论

学校读者我要写书评

暂无评论

AjCQFr: AOP-based Code Quality Framework

AjCQFr: AOP-based Code Quality Framework

引用

2010 International Conference on computer and Information Application(2010年计算机与信息应用国际会议 ICCIA 2010)

作者： Yuanyuan Li Xiufeng Zhang School of Computer Science& Software Engineering Tianjin Polytechnic University Tianjin China Wisenergy Software Technology Service ltd Inc Beijing China

Code quality is an important part in the software quality hierarchy. Given the joint-point model provided by AOP, this paper proposed a framework named AjCQFr under which several tools were developed to enhance the code quality. With these tools, it greatly improved the code quality and development productivity, and shortened the quality assurance process.

关键词： code quality AjCQFr AOP joint-point quality assurance process

来源：评论

学校读者我要写书评

暂无评论

A Rule Based Model for Efficient Representation and Accurate Recognition of Human Faces

A Rule Based Model for Efficient Representation and Accurate...

引用

International Conference on Advances in computer Engineering (ACE)

作者： B.H. Shekar G. Thippeswamy P. Shivakumara Department of Computer Science Mangalore University Mangalore India Department of Computer Science& Engineering Sir M Visvesvaraya Institute of Technology Bangalore India School of Computing National University of Singapore Singapore

ISBN: (纸本)9781424471546;9780769540580

In this paper, we investigate whether the rule based system derived from edges are effective and efficient for face representation and recognition when the number of classes is fixed and known. The characteristics of edges namely straightness and crookedness are used to derive rules. During training, a representative feature value is calculated for each class based on the average percentage of edges that satisfy the rule. In recognition, the representative feature value of an unknown face image is compared against the class representative feature value to assign a label to it. The proposed system does not require extensive feature extraction and classification techniques. Our experimental analysis on the standard CALTECH face databases shows that the edge based system is suitable for real time environment.

关键词： Face recognition Humans Image edge detection Principal component analysis Linear discriminant analysis Optical computing Image recognition computer science Spatial databases Feature extraction

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：