Volume 6, Issue 9, September 2015

Investigation of Talent Components in Educational Performance Prediction, A Data Mining Approach
Pages: 1-6 (6) | [Full Text] PDF (387K)
Shahpar. Zahra, Khatibi Bardsiri. Vahid, and Khatami. Saideh
Islamic Azad University, Kerman Branch, Iran

Abstract -
The present study aims at investigating and predicting students’ performance based on educational talent components. All Birjand’s 3rd-grade high school male and female gifted students are the population of the study. 195 individual were selected as the sample of the study through available sampling approach. Job Strong test results were used for assessing talent administered homogenously among the 1st-garade high-school students. Data mining techniques are used for studying and prediction applying three models of multiple linear regression, step-wise multivariable regression, and decision-making tree with cart algorithm. The results of step-wise regression model also indicate that among talent components, information sufficiency, space imagination, and mechanical reasoning are significant predictors for educational performance.
 Index Terms - Data Mining, Educational Performance, Job Strong Test and Talent
Improved Morphological Image Segmentation Techniques for Identifying Edge and Background Detection in Poor Lighting
Pages: 7-13 (7) | [Full Text] PDF (481K)
Akshay P. Vartak and V.R. Mankar
HVPM's College of Engineering and Technology, Deputy Secretary RBTE, Pune, India

Abstract -
Image enhancement is a technique that increases the visual contrast in a designated intensity range. Contrast is an act of distinguishing by comparing differences. Morphological transformation and block analysis are used to detect the background of various social and medical images. Opening by reconstruction method of contrast image transformation can be defined by two operators - opening and closing. The first operator makes use of the information from block analysis, while the second transformation utilizes the opening by reconstruction. The Later is used to define the multi background notion. The complete image processing is done using JAVA simulation model. Quality of image enhancement is assessed by different techniques. In this paper, high performance computational techniques involving contrast enhancement and noise filtering on various medical, social images are developed using Weber’s law. Image quality assessment is compared by different techniques. The values of all the quality assessment parameters are found to be in the standard ranges thereby confirming the enhancement of quality of images.
 Index Terms - Morphological Transformation, Morphological Reconstruction, Contrast Enhancement, Weber’s Law and Quality Assessment
LASPEA: Learning Automata-based Strength Pareto Evolutionary Algorithm for Multi-objective Optimization
Pages: 14-19 (6) | [Full Text] PDF (745K)
Seyed Mahdi Jameii, Mostafa Haghi Kashani and Ramin Karimi
Department of Computer Engineering, Shahr-e-Qods Branch, Islamic Azad University, Tehran, Iran
Department of Computer Engineering, Malard Branch, Islamic Azad University, Tehran, Iran

Abstract -
Multi-objective optimization problems are currently gaining significant attentions from researchers because many real-world optimization problems consist of contradictory objectives. SPEA (Strength Pareto Evolutionary Algorithm) is one of the most successful multi-objective evolutionary algorithms for approximating the Pareto-optimal set for multi-objective optimization problems. In this paper, an improved version of SPEA-II, called LASPEA (Learning Automata-based Strength Pareto Evolutionary Algorithm) is proposed. The proposed algorithm incorporates problem-specific genetic operators and learning automata to improve the behavior of the optimization algorithm. Simulation results demonstrate the efficiency of the LASPEA in terms of convergence and diversity.
 Index Terms - Multi-Objective Optimization, Evolutionary Algorithm, Learning Automata and Pareto-Front
A Comparative Study on Gene Selection and Classification Methods for the Cancer Subtypes Prediction
Pages: 20-24 (5) | [Full Text] PDF (454K)
Pheba Thomas
Computer Science and Engineering, Adi Shankara Institute of Engineering and Technology, Kalady, India

Abstract -
Microarray gene expression data gained great importance in recent years due to its role in disease diagnoses and prognoses which help to choose the appropriate treatment plan for patients. Interpreting gene expression data remains a difficult problem and an active research area due to their native nature of high dimensional low sample size. These issues poses great challenges to existing classification methods. Thus effective feature selection techniques are often needed in this case to aid to correctly classify different tumor types and consequently lead to improve treatment strategies. Small sample size remains a bottleneck to design suitable classifiers. Traditional supervised classifiers can only work with labeled data. On the other hand, a large number of microarray data that do not have adequate follow-up information are disregarded. Particular, the study report focus on the most used data mining techniques for gene selection and semi supervised cancer classification. In addition, it provides a general idea for future improvement in this field.
 Index Terms - KFRS, Microarray Data, TSVM, Unlabeled Samples and Gene selection
End-to-End Service Level Agreement Monitoring
Pages: 25-28 (4) | [Full Text] PDF (356K)
Almahdi Ibrahim Khojali Mohi Eldeen, Abd Elgaffar Hamed Ahmed and Robert Colomb
College of Computer Science and Information Technology, Sudan University of Science and Technlogy (SUST), Khartoum, Sudan
IBM Almaden

Abstract -
There is no doubt that information technology infrastructure is growing due to business requirements which are needed to accomplish business needs. As it is clear that business needs require cross organizational processes. Enterprises need to communicate, share and work together to get the benefits of integration, interoperation which provided by Service Oriented Architecture (SOA). This situation highlights the necessity of Service Level Agreement (SLA). SLA is meaningless without monitoring the Quality of Services (QoS) which specified by SLAs. The aim of this paper is to explain fundamental issues that monitoring of contractual SLAs involves and we presented an architecture for monitoring end-to-end SLAs.
 Index Terms - SLA, SOA, Monitoring and Service