Medium 9781601322517

Information and Knowledge Engineering: The 2013 WorldComp International Conference Proceedings

Views: 2006
Ratings: (0)

New research by international contributors on Information and Knowledge Engineering

List price: $49.95

Your Price: $39.96

You Save: 20%

Remix
Remove
 

52 Slices

Format Buy Remix

Session - Knowledge Engineering and Management + Knowledge Acquisition

PDF

 

Knowledge Management in a Large Organization: a Practical Case Study

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

3

Knowledge Management in a Large Organization: a

Practical Case Study

Antonio Ballarin1, Spartaco Coletta1, Daniela Principi4, Giulio Concas2, Marco Di Francesco3 and

Katiuscia Mannaro2

1

Sogei Spa, v. M. Carucci n. 99, 00143 Roma, Italy

2

Department of Electrics and Electronics Engineering, University of Cagliari, P.zza d'Armi

Cagliari, Italy

3

FlossLab Srl, v.le Elmas 142, Cagliari, Italy

4

General Administration, Personnel and Services Department, Ministry of Economy and Finance, v. XX

Settembre, 97, 00187 Roma, Italy

Abstract. In this work we present an approach, based on a

Knowledge Federation, for the management of the information regarding the life-cycle of Software Application ad IT services for organizations' operations. We need many information about software and IT to study the software product's life-cycle management, and to understand the lifecycle of information, which is based on four phases: introduction, growth, maturity, and decline. We need a knowledge base about the products and their costs to understand how to manage the single software products. We will focus our attention on mapping software applications,

 

Kukulcan: Semantic Web Framework for Knowledge Management in the Domain of Digital Circuits

PDF

8

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

Kukulcan: Semantic Web Framework for Knowledge Management in the

Domain of Digital Circuits

F. Edgar Castillo-Barrera1 , R. Carolina Medina-Ram´ırez2 ,

J. Emilio Labra Gayo3 , and S. Masoud Sadjadi4

1

School of Engineering, Universidad Aut´onoma de San Luis Potos´ı, San Luis Potos´ı, M´exico

2

Department of Electrical Engineering, Universidad Aut´onoma Metropolitana, Distrito Federal, M´exico

3

Department of Computer Science, Universidad de Oviedo, Espa˜na

4

School of Computing and Information Sciences, Florida International University (FIU), Miami, USA

Abstract

In recent years Ontologies have boomed as artifacts to represent a domain and they are considered an important key to the success of the Semantic Web. Thus, Humans and

Machines would be able to understand and share information on the Web which are also important in the context of Knowledge Management. Although the study of the relation between Ontologies and Knowledge Management is not new and this is applied in Knowledge Engineering, Semantic Web Techniques such as Reasoners and Ontology queries have been recently studied and applied. A Framework based on Semantic Web Techniques can give more options for sharing, increasing, reusing, and capitalizing the knowledge in organizations and companies. In digital circuits domain, a Semantic Web Framework can be employed for teaching logic gates (and, or, not, xor, etc.), and this approach has been deemed as an effective way for capturing and using the knowledge of the logic gates on assembling circuit systems. This knowledge can be reused by new developers gaining time and reducing circuits manufacturing costs. In addition, the correct assembling among logic gates and the right output of a circuit can be validated by using semantic techniques. In this paper, we describe a semantic web framework based on a core ontology, a Pellet reasoner and SPARQL queries for Knowledge Management based on the domain of digital circuits. We use an example and a prototype called Kukulcan to explain our approach.

 

Extracting Human-readable Knowledge Rules in Complex Time-evolving Environments

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

15

Extracting Human-readable Knowledge Rules in Complex

Time-evolving Environments

Pu Yang, and David L. Roberts

Department of Computer Science, North Carolina State University, Raleigh, North Carolina, USA

Abstract— A production rule system is a reasoning system that uses rules for knowledge representation. Manual rule acquisition requires a great amount of effort and time from humans. In this paper, we present a data-driven technique for autonomously extracting human-readable rules from complex, time-evolving environments that makes rule acquisition for production rule systems efficient. Complex, time-evolving environments are often highly dynamic and hard to predict.

We represent these environments using sets of attributes, and transform those attributes to the frequency domain which enables analysis to extract important features. We extract human-readable knowledge rules from these features using rule-based classification techniques and translating the decision rules back to the time domain. We present an evaluation of our methodology on three environments: hurricane data, a real-time strategy game, and a currency exchange. Experiments show extracted rules are humanreadable and achieve good prediction accuracy.

 

Visualisation of Combinatorial Program Space and Related Metrics

PDF

22

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

Visualisation of Combinatorial Program Space and Related Metrics

A.V. Husselmann and K.A. Hawick

Computer Science, Massey University, North Shore 102-904, Auckland, New Zealand email: { a.v.husselmann, k.a.hawick }@massey.ac.nz

Tel: +64 9 414 0800 Fax: +64 9 441 8181

Abstract— Searching a large knowledge or information space for optimal regions demands sophisticated algorithms, and sometimes unusual hybrids or combined algorithms.

Choosing the best algorithm often requires obtaining a good intuitive or visual understanding of its properties and progress through a space. Visualisation in combinatorial optimizers is more challenging than visualising parametric optimizers. Each problem in combinatorial optimisation is qualitative and has a very different objective, whereas parametric optimizers are quantitative and can be visualised almost trivially. We present a method for visualising abstract syntax trees in an interactive manner, as well as some certain enhancements for evolutionary algorithms. We also discuss the use of this in improving the convergence performance of a Geometric Particle Swarm Optimiser.

 

A Study on Information Connection Model using Rule-based Connection Platform

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

29

A Study on Information Connection Model using Rulebased Connection Platform

Heeseok Choi , Jaesoo Kim

NTIS Center, Korea Institute of Science and Technology Information, Daejeon, Korea

Abstract - National Science & Technology Information

Service (NTIS) collects national R&D information through the connection system in real time with specialized institutions under government ministries for R&D information service.

However, because the information connection between the research management systems in each ministry (institution) and the NTIS is different, it is not easy to operate the connection system, and immediate data collection is thus not ensured. This study aims to propose an information connection model to be applied on the NTIS-like systems. To do this, we examine methods or styles of information connection and compare strength and weakness of connection methods. In this paper we also understand issues or characteristics of the methods through analyzing current information connection methods applied on the NTIS.

 

Management of Knowledge on the Basis of Stochastic Mathematical Models

PDF

34

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

Management of Knowledge on the Basis of Stochastic

Mathematical Models

James William Brooks1, Dmitry Zhukov2, Irina Samoylo3 and Victoria Hodges4

1

Chancellor, Salem International University, Salem, West Virginia, USA

2

Professor, Consultant, Department of Medical and Biological Physics,

I.M. Sechenov First Moscow State Medical University, Moscow, Russia

3

Professor, Department of Medical and Biological Physics,

I.M. Sechenov First Moscow State Medical University, Moscow, Russia

4

Consultant, Department of Medical and Biological Physics,

I.M. Sechenov First Moscow State Medical University, Moscow, Russia

Abstract - This article discusses the questions of the use of stochastic models in the description of an educational process, which includes such parts as obtaining, loss (forgetting), and self-organization of educational information. The probability approach used by the authors led them to the deduction of differential equations of the second order of the type of the

 

Session - Databases, Information Retrieval and Search

PDF

 

A Method for Search Result Accuracy and Indexing Efficiency on Author Name Search

PDF

 

A Novel G-tree for Accelerating the Time-consuming Skyline Query

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

47

A Novel G-tree for Accelerating the Time-consuming

Skyline Query

Y. C. Chen, H. C. Liao, and C. Lee

Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan,

Taiwan, R.O.C.

Keywords: Database, Skyline, Tree Structure

1

Introduction

In recent years, skyline algorithms [1] have been widely applied in database searches. These algorithms allow users to select their prefer objects. For example, if a user were planning a seaside holiday, he/she could search a hotel database. It is assumed that this database would provide hotel prices and the distance from each hotel to the beach, as shown in Table I. Figure 1 shows the results of mapping the hotel data to biaxial coordinates where the x axis is price and the y axis is distance from the beach. The figure shows that Hotel F is better than Hotel L in both price and distance to the beach

(i.e., F dominates L). Users will therefore select Hotel F rather than Hotel L. Compared to Hotel F, Hotel B is closer to the beach but has higher prices. The two hotels therefore cannot be compared (i.e., incomparable). Skyline algorithms operate by identifying all non-dominated data points. In this case study, the skyline data points are B, F and G, as these hotels are not dominated by any other hotels.

 

Relevance Feedback for Collaborative Retrieval Based on Semantic Annotations

PDF

54

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

Relevance Feedback for Collaborative Retrieval Based on

Semantic Annotations

Fatiha NAOUAR*, Lobna HLAOUA*, Mohamed Nazih OMRI*

*MARS Unit of Research, Department of computer sciences

Faculty of sciences of Monastir, University of Monastir

Monastir, 5000, Tunisia

Abstract - A collaborative retrieval, based on the concept of sharing between users, is increasingly used to

assigning

facilitate the research and to satisfy the needs. In this

collaborative environment, the user still has many

context, we suggest to improve the performance of

problems to express his needs by the bad choice of

collaborative research, taking account of the

terms for his modest knowledge. It is in this context

annotations as a new source of information

that we suggest to improve the performance of

describing the documents. In our contribution, we

collaborative research using the relevance feedback

suggest to apply the relevance feedback to expand the

to expand the original query. This technique consists

 

A System for Keyword Search on Probability XML Data

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

61

A System for Keyword Search on Probability XML Data

Weidong Yang1 , Hao Zhu1 , Zheng Zheng1 , Huirong Chen2 , Lei Wang2

1 Computer School, Fudan University, Shanghai, China

2 Commercial Aircraft Corporation of China, Ltd, Shanghai, China

Abstract— Many probabilistic XML data models have been proposed to store XML data with uncertainty information, and based on them the issues such as structured querying are extensively studied. As an alternative to structured querying, keyword search in probabilistic XML data needs to be concerned. In this paper we addressed the issue of keyword search on probabilistic XML data. The probabilistic XML data is viewed as a labeled tree, and a concept of Minimum

Meaningful Fragment (MMF) is defined as the searching result. A MMF is a minimum subtree of the probabilistic

XML data which has a positive probability of containing all keywords. To sort the MMFs a novel scoring function mainly considering the degree of uncertainty information is presented. We propose a system to compute top-k searching results efficiently based on the scoring function. The experiments shows the efficiency for our system.

 

Session - Decision Support Systems

PDF

 

A Fuzzy Multiple Objective Decision Making Methodology for Electricity Generation Planning

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

71

A Fuzzy Multiple Objective Decision Making Methodology for Electricity Generation Planning

Mehtap Dursun, E. Ertugrul Karsak, and Zeynep Sener

Industrial Engineering Department, Galatasaray University, Istanbul, Turkey

Abstract - Although conventional energy resources are widely used for electricity generation globally as well as in Turkey, the renewable energy resources that do not deteriorate environmental quality and economic efficiency are increasingly favored to meet the energy demands in a sustainable way. Alternatively, limitations on land availability and high initial investment costs impede the development of renewable energy resources. This paper proposes a decision model based on fuzzy multiple objective programming for electricity generation planning in Turkey. Conflicting objectives with their corresponding importance degrees are taken into account to improve the quality of decision making process. Linguistic variables are employed to represent the qualitative data concerning energy alternatives and the importance degree of each objective. The proposed methodology enables to illustrate the trade-off between economic, environmental, social, and political factors in energy planning.

 

Relationship between DSS categories and different methodologies

PDF

78

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

Relationship between DSS categories and different methodologies

Marjan Abdyazdan1, Mohammad Ganji2, Mohammad Heidari Reyhani 3, Sheida Shirazi4

Department of Computer Engineering, Mahshahr branch, Islamic Azad University, Mahshahr, Iran.

E-mail: m.abdeyazdan@mahshahriau.ac.ir , abdeyazdan87@yahoo.com

2

Department of Computer Engineering, Tarbiat modares University, Tehran, Iran.

E-mail: m_ganji2011@yahoo.com

3

Department of Computer Engineering, Mahshahr branch, Islamic Azad University, Mahshahr, Iran.

E-mail: mohammad.hr2010@gmail.com

4

Department of Computer Engineering, Mahshahr branch, Islamic Azad University, Mahshahr, Iran. e-mail: shirazi85@gmail.com

1

Abstract

Decision support systems are information system that developed by utilization models, data, information, and collected knowledge for help the manager in solve the not made and simulated problems. Define a specific methodology for each project is needed. In this research by evaluation the decision support system and introduce well developed framework for category decision support system.

 

Session - Mining of Data Rich Sources

PDF

 

Visualization Tools for Results of Entity Resolution

PDF

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

87

Visualization Tools for Results of Entity Resolution

1

Cheng Chen1, Mahmood Mohammed1, and John R. Talburt1

Information Science Department, University of Arkansas at Little Rock, Little Rock, AR, USA

Abstract - This paper introduces methods for visualizing the results of Entity Resolution processes. They allow users to visualize the results from any resolution process. These tools will also help users to compare results from different rules-set in the process of Entity Resolution in Entity Identity

Information Management. This will facilitate finding false positive and false negative errors. These methods have been applied to the results produced by OYSTER, an open source entity resolution system.

Keywords: Entity Resolution, Entity Identity Information

Management, Visualization Tools, Information Visualization

1

Background

Entity Identity Information Management (EIIM) is a component of entity identity management (EIM) that utilizes data structures, data integration, and entity resolution (ER) methods and algorithms. EIIM aims at maintain entity identity integrity. Entity identity integrity requires that each entity in the domain should have one and only one representation in the system, which is called an identity. [1] Figure 1 shows a highlevel view of EIIM components and processes.

 

Evaluation of Entity Resolution Results through Benchmarking and Truth set Development

PDF

92

Int'l Conf. Information and Knowledge Engineering | IKE'13 |

Evaluation of Entity Resolution Results through

Benchmarking and Truth set Development

Huzaifa Syed, Fan Liu, Daniel Pullen, Pei Wang and John Talburt

Information Science Department, University of Arkansas at Little Rock, Little Rock, Arkansas, USA

Abstract -This paper describes methodology for creating a truth set for the evaluation of entity resolution (ER) results.

The methodology combines the techniques of benchmarking and truth set development into an iterative, easy to use process. The paper also describes how the truth set developed by the methodology can be applied to calculate five key measures of ER outcome.

Keywords: Entity Resolution Rules, Benchmarking in Entity

Resolution, Refining rules in Entity Resolution, OYSTER,

Truth Set Development.

1 Introduction

Entity Resolution (ER) is the process of determining whether the two references to real world objects in an information system are referring to the same object or two different objects [1]. References referring to the same realworld entity are said to be equivalent. An ER process tries to infer which references are equivalence by apply matching rules that compare the similarity between the values of certain attributes in the records.

 

Load more


Details

Print Book
E-Books
Slices

Format name
PDF
Encrypted
No
Sku
B000000030881
Isbn
9781601322517
File size
25.8 MB
Printing
Allowed
Copying
Allowed
Read aloud
Allowed
Format name
PDF
Encrypted
No
Printing
Allowed
Copying
Allowed
Read aloud
Allowed
Sku
In metadata
Isbn
In metadata
File size
In metadata