Faten Kharbat
Al Ain University of Science and Technology
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Faten Kharbat.
genetic and evolutionary computation conference | 2007
Faten Kharbat; Larry Bull; Mohammed Odeh
In this paper, we describe the use of a modern learning classifier system to a data mining task. In particular, in collaboration with a medical specialist, we apply XCS to a primary breast cancer data set. Our results indicate more effective knowledge discovery than with C4.5.
congress on evolutionary computation | 2005
Faten Kharbat; Larry Bull; Mohammed Odeh
The XCS learning classifier system has traditionally used roulette wheel selection within its genetic algorithm component. Recently, tournament selection has been suggested as providing a number of benefits over the original scheme, particularly a robustness to parameter settings and problem noise. This paper revisits the comparisons made between the behavior of tournament and roulette wheel selection within XCS in a number of different situations. Results indicate that roulette wheel selection is competitive in terms of performance, stability and generated solution size if the appropriate parameters are used.
Archive | 2008
Faten Kharbat; Haya El-Ghalayini
In the last decade, ontologies have been considered as the backbone technology in most knowledge-based applications. As ontologies have become more common, their applicability has ranged from artificial intelligence areas such as knowledge representation and natural language processing to different fields such as information integration and retrieval systems, requirements analysis, and lately in semantic web applications. In the literature, several methodologies and methods have been introduced for building ontologies. Some of these methods allow the development of ontologies from existing ontologies or data sources. However, the proposed method for building ontologies integrates different data mining techniques to assist in developing a given domain ontology. Thus, the extracted and representative rules generated from the original dataset can be utilised in developing ontology elements. The main research hypothesis in this chapter is that ontology can be developed from discovered hidden and interesting rules. In order to practically investigate this assumption, this chapter presents a complete developing discovery structure using one of the well known breast cancer test sets. The chapter is organised into five sections. A general overview is found in section two with a brief description of the main components of this research. The development engine framework is introduced in the section three. Section four demonstrates proposed method using Wisconsin Breast Cancer dataset as a case study. Finally, this practical investigation ends by presenting the learned lessons and conclusions.
Learning Classifier Systems in Data Mining | 2008
Faten Kharbat; Mohammed Odeh; Larry Bull
In this chapter we describe the use of a modern learning classifier system to a data mining task. In particular, in collaboration with a medical specialist, we apply XCS to a primary breast cancer data set. Our results indicate more effective knowledge discovery than with C4.5.
hybrid intelligent systems | 2007
Faten Kharbat; Mohammed Odeh; Larry Bull
In real-domain problems, having generated a complete map for a given problem, a Learning Classifier System needs further steps to extract minimal and representative rules from the original generated ruleset. In an attempt to understand the generated rules and their complex underlying knowledge, a new rule-driven approach is introduced which utilizes a quality-based clustering technique to generate clusters of rules. Two main outputs are extracted from each cluster: (1) an aggregate average rule which represents the common features of the group of rules, and (2) an aggregate definite rule which presents the common characteristics within the cluster. Initial experimental results show that these extracted patterns are able to classify future domain cases efficiently.
ieee international conference on information management and engineering | 2009
Faten Kharbat; Haya Ghalayini
From the fact that ontologies can help in making sense of huge amount of content, this paper proposes a case study for building ontology via set of rules generated by rule-based learning system. The proposed algorithm utilises the extracted and representative rules generated from the original dataset in developing ontology elements. The proposed algorithm is applied to a well known dataset in the breast cancer domain. The results are encouraging and support the potential role that this approach can play in providing a suitable starting point for ontology development.
Proceedings of the 2018 International Conference on Internet and e-Business | 2018
Faten Kharbat; John Girard
This project focuses on the first part of the knowledge management definition, expressly the process of creating knowledge. It explores the relationship between knowledge creation with the perception of improving productivity and collaboration. Also, the project addresses the preferences toward one or more knowledge creation forms in improving productivity and collaboration.
Archive | 2017
Faten Kharbat; Jehan A. Abo Sultan
A large amount of decision support systems for different management areas exist. Literature on decision systems supporting environmental management in particular is relatively limited. Given this evolving research field, the goal and purpose of this paper is to explore the scientific research in international scientific journals that focus on decision support systems for environmental management. In this paper, a brief review was conducted to recent publications in some of the respected journals and conferences. Published scientific research from 2010 to 2015 is reviewed based on the following: (i) what are the main components used in the decision support system, and (ii) how environmental support systems are integrating with other techniques and methods to optimize the needed solutions. The DSS tools and components play a great role in solving the complexity problem of the eco-system and in the environment. According to our review, researchers found that environmental problems have common characteristics. EDSS, also, has been used in different fields. A further critical analysis should be completed and gaps in the current literature are to be identified in the future to identify improvements for such systems and possible future directions.
arXiv: Computers and Society | 2013
Ajayeb Abu Dabbes; Faten Kharbat
This research aims to mine the relationship between demographic variables and brand associations, and study the relative importance of these variables. The study is conducted on fast-food restaurant brands chains in Jordan. The result ranks and evaluates the demographic variables in relation with the brand associations for the selected sample. Discovering brand associations according to demographic variables reveals many facts and linkages in the context of Jordanian culture. Suggestions are given accordingly for marketers to benefits from to build their strategies and direct their decisions. Also, data mining technique used in this study reflects a new trend for studying and analyzing marketing samples.
Archive | 2008
Faten Kharbat; M. ed Odeh; Larry Bull