1457 Slices
Medium 9781601323163

Session - Graph Based Methods and Applications + Related Issues

Hamid R. Arabnia, George A. Gravvanis, George Jandieri, Ashu M. G. Solo, and Fernando G. Tinetti CSREA Press PDF
Medium 9781601323200

On the method for automatic determination of semantic similarity of the document texts

CSREA 2003 CSREA Press PDF

68

Int'l Conf. Artificial Intelligence | ICAI'14 |

On the method for automatic determination of semantic similarity of the document texts

Victor N. Zakharov1, Alexey A. Khoroshilov 2, and Alexandr A. Khoroshilov 2

Institute of Informatics Problems of the Russian Academy of Sciences, Moscow, Russia

2

Center of Information Technologies and Systems of Executive Power Organs, Moscow, Russia

1

Abstract - The paper describes the methods for automatic generation of the formalized semantic document description and determining of semantic proximity of document texts. These methods are based on the use of semantic-syntactic and conceptual analysis procedures providing the identification of the conceptual text content and the assignment of the characteristics to the concept names, corresponding to their semantic role in the text. Automatic thematic text content similarity assessment is made by comparison of the conceptual text content.

Keywords: Semantics, text similarity, natural language documents, information processing

See All Chapters
Medium 9781601323637

SESSION Recognition Systems, Tracking, Detection, and Applications

Hamid Arabnia, Leonidas Deligiannidis, Fernando G. Tinetti, Jane You CSREA Press PDF

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'16 |

SESSION

RECOGNITION SYSTEMS, TRACKING,

DETECTION, AND APPLICATIONS

Chair(s)

TBA

ISBN: 1-60132-442-1, CSREA Press ©

117

118

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'16 |

ISBN: 1-60132-442-1, CSREA Press ©

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'16 |

119

TRACKING A TABLE TENNIS BALL FOR UMPIRING PURPOSES USING A

MULTI-AGENT SYSTEM

Hnin Myint, Patrick Wong, Laurence Dooley

The Open University

United Kingdom

{hnin.myint, patrick.wong,

Laurence.Dooley}@open.ac.uk

ABSTRACT

Tracking a table tennis ball for umpiring purposes is a challenging task as, in real-match scenarios, the ball travels fast and can become occluded or merged with other background objects. This paper presents the design of a multiview based tracking system that can overcome the challenges of tracking a ball in real match sequences. The system has been tested on a complete table tennis rally and the results are very promising. The system is able to continuously track the ball with only marginal variations in detection. Furthermore, the initialization of the multi-camera system means it is both a portable and cost-effective solution for umpiring purposes.

See All Chapters
Medium 9781601323125

Building Fuzzy Inference System in the Political Domain

Hamid R. Arabnia, George A. Gravvanis, George Jandieri, Ashu M. G. Solo, and Fernando G. Tinetti CSREA Press PDF

116

Int'l Conf. Scientific Computing | CSC'14 |

Building Fuzzy Inference System in the Political Domain

Dr. Sameera Alshayji, Nasser Al-Sabah, and Abdulla Al-Sabah

Political and Economic Affairs Department, Amiri Diwan, Seif Palace, Kuwait

Abstract - The world’s increasing interconnectedness and the recent increase in the number of notable regional and international events pose ever-greater challenges for political decision-making. This is especially true when considering whether to strengthen bilateral economic relationships between nations, as such critical decisions are influenced by certain factors and variables that are based on scattered, heterogeneous, and vague information. A common language is thus needed to describe variables that require human interpretation. Applying a fuzzy ontology method is one of the possible solutions that address integration of information and lack of clarity of concept. Fuzzy logic is based on natural language and is tolerant of imprecise data. Furthermore, a

See All Chapters
Medium 9781601323132

A Framework for Flexible Educational Data Mining

Robert Stahlbock, Gary M. Weiss, Mahmoud Abou-Nasr, Hamid R. Arabnia CSREA Press PDF

176

Int'l Conf. Data Mining | DMIN'14 |

A Framework for Flexible Educational Data Mining

Kyle DeFreitas and Margaret Bernard,

Department of Computing and Information Technology

University of the West Indies, St Augustine Trinidad and Tobago

Abstract — Educational Data Mining (EDM) focuses on tools and techniques for discovering previously unknown patterns in the data generated by the educational process.

Despite the increased awareness of data mining, the adoption among educators has been slow because the data mining tools are complex and the use of the tools requires a detail understanding of the parameters and requirements of the algorithms used. In this paper, we present a framework for developing an educational data mining environment that is flexible in that it caters for educators who have little technical skills as well as for more advanced users with some data mining expertise.

Keywords: Educational Data Mining, Learning Management

Systems

1 Introduction

T

increased use of technology in education has brought about a fundamental change in the way educational institutions operate. The increased usage of electronic based systems has amplified the amount of data available for making better decisions, and improvements in the data mining algorithms make analysis of this volume of data easier and more accessible. In recent years, there has been tremendous interest and research in the field of Educational

See All Chapters

See All Slices