检索结果-内蒙古大学图书馆

international conference of soft computing and pattern recognition (socpar)

作者： Halimah Mohamed Shahida Sulaiman Maziani Sabudin Information Technology Session Fisheries Research Institute Batu Maung Penang Malaysia School of Computer Sciences Universiti Sains Islam Malaysia Penang Malaysia

Hajj is the fifth commandment in Islamic religion that is compulsory to all able bodied Muslims to perform at least once in their whole life. Hajj pilgrims must be well prepared before going to Mecca. They may face complex problems when preparing for and performing Hajj. In such situations they require experts' guidance. Accessing information from explicit and tacit knowledge from Hajj experts has some limitations in the aspects of availability, time and cost. Thus, it motivates us to propose a hybrid of rule and frame based knowledge representation approach to eliminate current drawbacks on using both methods separately. The main objective is to solve complex and layered problems with regards to Hajj rituals. The proposed Hajj knowledge base applies the hybrid approach due to several factors such as more structured, support large number of conditions and rules, support complex tasks, more flexible and easy to use. We implement the approach in a prototype. We conducted both lab experiment for comparative study and usability study to evaluate the effectiveness of the proposed approach. The result shows that the hybrid approach never fails to solve problems given since this approach predetermine the problems and solutions before transforming the knowledge into the Hajj knowledge base. The knowledge becomes cases to be used in future reasoning. In addition, the approach reduces the time to solve a problem as compared to searching static information via the Internet.

关键词： Knowledge representation Books Knowledge based systems Internet Problem-solving Humans Knowledge engineering pattern recognition Information technology Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Situation-Awareness and Sensor Stream Mining for Sustainable Human Life

Situation-Awareness and Sensor Stream Mining for Sustainable...

引用

international conference of soft computing and pattern recognition (socpar)

作者： Zahoor ur Rehman Muhammad Shahbaz Muhammad Shaheen Aziz Guergachi Department of CS & E University of Engineering and Technology Lahore Pakistan Ryerson University Toronto ONT Canada Information Technology Management Ryerson University Toronto Canada

Criminal activities cause a huge amount of loss both financially and in terms of human lives. Because of these acts, business and social sectors are struggling. This paper illustrates the development of an online sensor stream mining system that is able to analyze the situational behavior of all of the persons in specific areas and in turn propose real-time alert systems to take countermeasures. This system gathers different information from heterogeneous sensors, fuse that information, and generate real-time alerts to minimize the likelihood of disaster. These alerts and alarms assist security personnel in making appropriate decisions in real-time scenarios. The novelty of this approach comprises context-awareness with online diagnoses to take countermeasures in real-time to reduce the loss of lives, and damage to societies and economies. This technique makes the sensor stream mining process more dependable and increases the reliability of the overall system. To fulfill the objectives of this research, we incorporate lightweight online mining algorithms to extract useful but hidden information from the data gathered. Contextual information such as a person's pattern of movement, current location, personal profile, and area of residence are exploited to detect anomalous behaviors. The major goal of this research is to detect those persons performing malicious activities and in turn minimize society's exposure to risks and vulnerabilities.

关键词： Humans Design optimization Printing Integer linear programming Constraint optimization Testing Containers pattern recognition Computer applications Laboratories

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 1st international conference on soft computing Technology in Civil, Structural and Environmental Engineering, CSC 2009

Proceedings of the 1st International Conference on Soft Comp...

引用

1st international conference on soft computing Technology in Civil, Structural and Environmental Engineering, CSC 2009

ISBN: (纸本)9781905088331

The proceedings contain 34 papers. The topics discussed include: a system model for the lifecycle monitoring of bridges;robust truss optimization with uncertain load directions;optimization of an architectural floor plan for a smooth crowd flow;non-parametric stochastic subset optimization for system design optimization under uncertainty;identification of neural network based material models under uncertainty;influence of data density on grade estimation in a limestone quarry using kriging;influence of exceptional data on bridge damage assessment based on one-class SVM pattern recognition;performance-based topology optimization of wind excited tall buildings;multi-objective reconstruction of random media;multi-objective optimization with asymptotic sampling for RBDO;numerical concepts for structural analysis and design with polymorphic uncertainty modelling;preliminary results for pipe-Z knot optimization;and load and energy billing forecasting of an electricity utility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of exceptional data on bridge damage assessment based on one-class SVM pattern recognition

Influence of exceptional data on bridge damage assessment ba...

引用

1st international conference on soft computing Technology in Civil, Structural and Environmental Engineering, CSC 2009

作者： Furuta, H. Nomura, Y. Nakatsu, K. Hattori, H. Yasuda, S. Faculty of Informatics Kansai University Japan Department of Science and Engineering Ritsumeikan University Japan Department of Modern Life Osaka Jonan Women's Junior College Japan Graduate School of Engineering Kyoto University Japan Graduate School of Informatics Kansai University Japan

ISBN: (纸本)9781905088331

Recently, it has become difficult to ensure the skill level of bridge maintenance engineers as a result of the retirement of experienced engineers. Hence, the daily inspection of bridges cannot be performed accurately and efficiently for the early detection of damage and to ensure appropriate measures. In previous research, damage assessment by introducing the technology of pattern recognition of digital images has been proposed. However, in the previous research, it was confirmed that there were some images which might be considered as exceptional data among the images of cracks of concrete decks. This paper describes the development of a support system for decision making in the damage assessment of bridges based on the pattern recognition by using the exception extraction. In this system, the exception extraction with one-class SVM removes some data that may cause the decrease of generalization capability of pattern recognition from the database. Thus, it may be expected that the accuracy and confidence of the results are improved. Numerical examples applying digital images of reinforced-concrete slabs of bridges with cracks are presented to demonstrate the practical use of the approach of this approach. © Civil-Comp Press, 2013.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Finding the number of clusters in ordered dissimilarities

引用

soft computing 2009年第12期13卷 1125-1142页

作者： Sledge, Isaac J. Havens, Timothy C. Huband, Jacalyn M. Bezdek, James C. Keller, James M. Univ Missouri Dept Elect & Comp Engn Columbia MO 65211 USA Univ W Florida Dept Comp Sci Pensacola FL 32514 USA

As humans, we have innate faculties that allow us to efficiently segment groups of objects. Computers, to some degree, can be programmed with similar categorical capabilities, which stem from exploratory data analysis. Out of the various subsets of data reasoning, clustering provides insight into the structure and relationships of input samples situated in a number of distributions. To determine these relationships, many clustering methods rely on one or more human inputs;the most important being the number of distributions, c, to seek. This work investigates a technique for estimating the number of clusters from a general type of data called relational data. Several numerical examples are presented to illustrate the effectiveness of the proposed method.

关键词： Data analysis pattern recognition Clustering Cluster tendency Cluster count extraction

来源：评论

学校读者我要写书评

暂无评论

Hypertext Classification Using Tensor Space Model and Rough Set Based Ensemble Classifier

Hypertext Classification Using Tensor Space Model and Rough ...

引用

3rd international conference on pattern recognition and Machine Intelligence

作者： Saha, Suman Murthy, C. A. Pal, Sankar K. Center for Soft Computing Research Indian Statistical Institute India

ISBN: (纸本)9783642111631

As WWW grows at an increasing speed, a. classifier targeted at hypertext has become in high demand. While document categorization is quite a mature, the issue of utilizing hypertext structure and hyperlinks has been relatively unexplored. In this paper, we introduce tensor space model for representing hypertext documents. We exploit the local-structure and neighborhood recommendation encapsulated in the proposed representation model. Instead of using the text on a page for representing features in a vector space model, we have used features on the page and neighborhood features to represent a hypertext document in a tensor space model. Tensor similarity measure is defined. We have demonstrated the use of rough set based ensemble classifier on proposed tensor space model. Experimental results of classification obtained by using our method outperform existing hypertext classification techniques.

关键词： Hypertext classification tensor space model rough ensemble classifier

来源：评论

学校读者我要写书评

暂无评论

Robust Association of Pathological Respiratory Events in SAHS Patients: A Step towards Mining Polysomnograms

引用

10th international Work-conference on Artificial Neural Networks (IWANN 2009)

作者： Otero, Abraham Felix, Paulo Univ San Pablo CEU Dept Informat & Commun Syst Engn Madrid 28668 Spain Univ Santiago de Compostela Dept Elect & Comp Sci E-15782 Santiago De Compostela Spain

ISBN: (纸本)9783642024801

This paper presents a method for performing a robust association between the apneas and hypopneas recorded on a polysomnogram and the desaturations they cause. It is based on a structural algorithm that takes advantage of the fuzzy set theory to represent the medical knowledge on which it relies. The method aims to generate information that could serve as a starting point for gaining a deeper insight into the Sleep Apnea-Hypopnea Syndrome by means of data mining techniques. This has led to a sacrifice of sensitivity for specificity. We have validated our proposal over 37 hours of polysomnographic recordings. 88% of the hypoventilations present in the recordings were associated with the desaturations they caused, presenting a rate of false associations of 0.86%.

关键词： Sleep Apnea pattern recognition Biosignal Processing

来源：评论

学校读者我要写书评

暂无评论

String pattern recognition Using Evolving Spiking Neural Networks and Quantum Inspired Particle Swarm Optimization

引用

16th international conference on Neural Information Processing (ICONIP 2009)

作者： Hamed, Haza Nuzly Abdull Kasabov, Nikola Michlovsky, Zbynek Shamsuddin, Siti Mariyam Auckland Univ Technol KEDRI Auckland New Zealand Brno Univ Technol Fac Informat Technol Brno Czech Republic Univ Teknol Malaysia Soft Comp Res Grp Johor Baharu Malaysia

ISBN: (纸本)9783642106828

This paper proposes a novel method for string pattern recognition using an Evolving Spiking Neural Network (ESNN) with Quantum-inspired Particle Swarm Optimization (QiPSO). This study reveals an interesting concept of QiPSO by representing information as binary structures. The mechanism optimizes the ESNN parameters and relevant features using the wrapper approach simultaneously. The N-gram kernel is used to map Reuters string datasets into high dimensional feature matrix which acts as an input to the proposed method. The results show promising string classification results as well as satisfactory QiPSO performance in obtaining the best combination of ESNN parameters and in identifying the most relevant features:

关键词： String Kernels Text Classification Evolving Spiking Neural Network Particle Swarm Quantum computing

来源：评论

学校读者我要写书评

暂无评论

Disclosing patterns in IT Project Management - A Rough Set Perspective

Disclosing Patterns in IT Project Management - A Rough Set P...

引用

3rd international conference on pattern recognition and Machine Intelligence

作者： Peters, Georg Hunter, M. Gordon Munich Univ Appl Sci Dept Comp Sci & Math D-80335 Munich Germany Univ Lethbridge Fac Management Lethbridge AB T1K 3M4 Canada

ISBN: (纸本)9783642111631

Information technology has become one of the most important infrastructure components of virtually any organization. Although information technology has a crucial impact on the success of organizations it is reported that IT projects have rather high failure rates. Therefore, it is vitally important for organizations to improve the performance and success rates of IT projects. However, the reasons for failures are versatile and an ongoing very active fields of research especially in information systems and management. An established approach to evaluate IT projects is to define relevant so called critical success factors and analyze IT projects according to these criteria. This analysis is often of a qualitative nature. The objective of our paper is to enrich the analysis of critical success factors by alternative methods in particular rough set theory. We motivate the usage of rough sets to further improve the analysis of critical success factors with the goal to better manage IT projects and increase their success rate.

关键词： Uncertainty soft computing Rough Sets IT Project Management Critical Success Factors

来源：评论

学校读者我要写书评

暂无评论

United Zernike invariants for character images

United Zernike invariants for character images

引用

1st international Visual Informatics conference, IVIC 2009

作者： Bakar, Norsharina Abu Mariyam Shamsuddin, Siti Soft Computing Research Group K-Economy Research Alliance Universiti Teknologi Malaysia Skudai Johor Malaysia

ISBN: (纸本)3642050352

Feature extraction is one of the major components in traditional pattern recognition. There are many methods for extracting the features, either structural approach or global approach. In this paper, we present integrated formulation of Zernike Moments and United Moment Invariant for extracting the character images accordingly. The extraction values are validated by measuring the Inter-class and intra-class analysis to illustrate the effectiveness of the proposed solution. The results yield that the proposed method are feasible and better for extracting the images for both inter-class and intra-class analysis. © 2009 Springer-Verlag.

关键词： 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：