Print E-mail

Visual Decomposition of UML 2.0 Interactions

Abdelkrim Amirat and Ahcen Menasria

Department of Computer Science, University of Souk-Ahras, Algeria

Abstract: Interaction Fragment model (IF) is a specific notion added in Unified Modeling Language (UML) 2.0 superstructures. Using the graphical notation, it can be used to represent the behavioral aspect of a system in a given scenario. Transforming such models, at early stages, requires the identification of elementary elements and their chronology. In this paper, we propose a visual and intuitive solution to identify and isolate each of which of graphical components while preserving the initial control flow. To that end, we suggest a reusable graph grammar to establish and update the control flow leading to a decomposed interaction. Our proposal can be used as first step to each transformation process whose having an UML 2.0 interaction as a source model.

Keywords: UML 2.0 interaction, control flow, graph transformation, AToM3.

Received September 4, 2013; accepted March 27, 2014


Print E-mail

A Novel Baseline Estimation Method for Arabic Handwritten Text Based on Exploited Components of Voronoi Diagrams

Atallah AL-Shatnawi

Department of Computer Information System, Al-albayt University, Jordan

Abstract: The goal of this paper is to present an efficient novel baseline estimation method for Arabic handwritten text based on the exploited components of Voronoi Diagrams (VD). The proposed based-VD method is constructed from three stages including: Preliminary stages, VD construction and baseline estimation process. The edges of the text are firstly extracted and then both inner and outer contour are traced in order to be converted into a set of sampling points. These sampling points are used to be the VD generators. Then, the baseline is detected from those edges and vertices which are positioned within the text boundaries. The proposed method is implemented, verified and validated on the IFN/ENIT Arabic handwritten dataset. It is discussed and compared with the horizontal projection method against the IFN/ENIT dataset based on affecting by noise, working properly with or without diacritics, working properly with the skewed images and running time efficiently. The results obtained are shown in graphs and output images. The results demonstrated that the proposed method works properly with the skewed and noisy images and with or without diacritics. It also, able to estimate the Arabic text baseline in straight or in curved line.


Keywords: Arabic text recognition, baseline estimation, VD, horizontal projection.

Received December 7, 2013; accepted July 9, 2014

Print E-mail

Role of References in Similarity Estimation of Publications

Muhammad Shoaib1, Ali Daud1, and Malik Khiyal2

1Department of Computer Science and Software Engineering, International Islamic University, Pakistan

2Faculty of Computer Sciences, Preston University, Pakistan

Abstract: Similarity estimation among publications is very important in classification and clustering techniques for grouping, indexing, citation matching and Author Name Disambiguation (AND)  purposes. Publication attributes are basic sources of information and play important role in similarity estimation. Most of the works in AND use title, co-authors and venue attributes for estimating similarity among publications. Many other sources of information such as self-citations, shared citations and references, topic of the publications and abstracts have also been employed to estimate optimal similarity among publications. Recently, in the field of Academic Document Clustering (ADC), reference marker contexts have been utilized for this purpose. However, the use of citations and references is less common since only a few databases include this information. In this paper, we propose to use two components of references (co-authors and titles of references) as sources of information and investigate the importance of these components in similarity estimation. To the best of our knowledge, this is the first endeavour to exploit components of references as sources of information. Experiments conducted on real publication datasets reveal that these components of references are significant source of information for similarity estimation among publications. 

Keywords: AND, references, vector space model, cosine similarity, citation matching. 

Received May 16, 2014; accepted September 11, 2014


Print E-mail

Effects of the College Major on Assessments of Arabic Text Summaries

Bassam Hammo1, Martha Evens2, and Hani Abu-Salem3

1Department of Computer Information Systems, the University of Jordan, Jordan

2Department of Computer Science, Illinois Institute of Technology, USA

3Department of Mathematics and Computer Science, University of South Carolina-Aiken, USA

Abstract: We set out to discover whether or not the summaries produced by our Arabic text summarization software were potentially useful to a wide range of people. 1200 students at the University of Jordan were each given a copy of a newspaper article and a system-generated summary and asked to classify the summary as Rejected (R), Not-Related (N), Satisfactory (S), Good (G) or Accepted (A). 76.92% of the summaries were judged to be good or accepted and 92.34% were judged to be satisfactory, good or accepted. These students came from four different majors: 300 from Arabic studies, 300 from humanities, 300 from Information Technology (IT) and 300 from a one-year program designed to help K-12 teachers to learn how to use computers effectively in the classroom. To our surprise, students from these four different majors differed significantly in their assessments; the teachers rated the summaries significantly more favourably; the IT students rated them significantly lower than did the students in Arabic and the humanities.


Keywords: Arabic natural language processing, arabic text summarization, extraction, software testing, evaluation.

Received June 18, 2014; accepted December 16, 2014


Print E-mail

Unmanned Vehicle Trajectory Tracking by Neural Networks

Samira Chouraqui and Boumediene Selma

Department of Computer Sciences, University of Sciences and Technologies of Oran USTO’MB, Algeria


Abstract: This paper, deals with a path planning and intelligent control of an autonomous vehicle which should move safely in its road partially structured. This road, involves a number of obstacles like donkey, traffic lights and other vehicles. In this paper, the Neural Networks (NN)-based technique Artificial Neural Network (ANN) is described to solve the motion-planning problem in Unmanned Vehicle (UV) control. This is accomplished by choosing the appropriate inputs/outputs and by carefully training the ANN. The network is supplied with distances of the closest obstacles around the vehicle to imitate what a human driver would see. The output is the acceleration and steering of the vehicle. The network has been trained with a set of strategic input-output. The results show the effectiveness of the technique used, the UV drives around avoiding obstacles.

Keywords: UV, NN, control.

Received March 22, 2013; accepted March 19, 2014


Print E-mail

Arabic Handwritten Word Recognition based on Dynamic Bayesian Network

Khaoula Jayech, Mohamed Mahjoub, and Najoua Ben Amara

Research Unit SAGE, Team Signals, Image and Document, National Engineering School of Sousse

University of Sousse-Tunisia

Abstract: Distinguishing an Arabic handwritten text is a hard task because the Arabic word is morphologically complex and the writing style from one model is highly variable, like the recognition of words representing the names of Tunisian cities.  Actually, this is the first work based on the Dynamic Hierarchical Bayesian Network (DHBN). Its objective is to get the best model by learning the structure and parameter of Arabic handwriting to decrease the complexity of the recognition process by allowing the partial recognition. In fact, we propose segmenting the word based on a vertical smoothed histogram projection using various width values to put down the segmentation error. After that, we extract the characteristics of each cell using the Zernike and HU moments, which are invariant to rotation, translation and scaling. Then, the sub-character is estimated at the lowest level of the Bayesian Network (BN) and the character is estimated at the highest level of the BN. The overall Arabic words are processed by a dynamic BN. Our approach is tested using the IFN/ENIT database, where the experiment results are very promising.

Keywords: Arabic handwriting recognition, dynamic BN, hierarchical model, OCR, IFN/ENIT databases.

Received October 21, 2013; accepted June 18, 2014


Print E-mail

An Efficient Spiking Neural Network Approach based on Spike Response Model for Breast Cancer Diagnostic

Asmaa Ourdighi and Abdelkader Benyettou

Department of Computer Science, University of Sciences and Technology of Oran-Mohamed Boudiaf, Algeria

Abstract: This study investigates the efficiency of the one-layered Spiking Neural Network (SNN) on the enhancing of the breast cancer diagnostic results. The proposed network is based on Spike Response Model (SRM) with multiple delays per connection. Beside its simplicity, this model allows to modeling the production of a biologically realistic response to incoming synaptic events. By using a supervised learning, the training process was founded around of an error-backpropagation algorithm depending only on the time of the first spike emitted. In experimentation, our approach was exclusively tested on Wisconsin Breast Cancer Database (WBCD). The results were evaluated in accuracy classification and the area under Receiver Operating Characteristics (ROC) curve (AUC). In summary, we achieved 99.26% of accuracy classification with an AUC equal to 0.992.

Keywords: SNN, SRM, a gradient descent rule, WBCD.

Received February 2, 2013; accepted March 19, 2014


Print E-mail

Generating a Language-Independent Graphical User Interfaces from UML Models

Amany Shatnawi1 and Raed Shatnawi2

1Department of Computer Science, Jordan University of science and Technology, Jordan,

2Department of Software Engineering, Jordan University of science and Technology, Jordan

Abstract: The cost of the software development is high and there is a need to automate parts or all activities of the software development to reduce the development costs. In this work, the User Interface (UI) design is automated and UIs are generated for language-independent code from Unified Modeling Language (UML) diagrams. These diagrams are used to generate both the content of the UIs and the navigation through the use interfaces. Based on end-user feedback, the UML diagrams and the UI prototype can be iteratively refined. To demonstrate this work, a tool that automates the generation of UI prototype is built. The tool generates a prototype that is coded using an eXtensable Markup Language (XML) called the User Interface Markup Language (UIML). The proposed approach is validated and user interfaces are generated for two case studies.

Keywords: UI Prototyping, UIML, UML, language-independent UI.

Received September 20, 2013; accepted May 6, 2014


Print E-mail

FAGA: Hybridization of Fractional Order ABC and GA for Optimization

Lavanya Gunasekaran and Srinivasan Subramaniam

2Department of Computer Science and Engineering, Anna University Regional Centre, Madurai

Abstract: In order to solve problems of optimization, Swarm Intelligence (SI) algorithms are extensively becoming more popular. Many swarm intelligence based optimization techniques are present but most face problems like convergence problem and local minimization problem. In this paper, a hybrid optimization algorithm is proposed using fractional order Artificial Bee Colony (ABC) and Genetic Algorithm (GA) for optimization to solve the existing problems. The proposed algorithm has four phases such as, employee bee, onlooker bee, mutation and scout bee. In employee bee phase, neighbour solution is generated based on ABC algorithm. Then, in onlooker bee, the probability is used to select a solution and new solution is generated based on fractional calculus-dependent neighbor solution. The mutation operation of genetic algorithm is used in the mutation module and then the scout bee phase is carried out. The proposed algorithm is implemented in MATLAB. For experimentation, the unimodal benchmark functions such as: De jong’s, axis parallel hyper-ellipsoid, rotated hyper-ellipsoid and multi-modal functions such as: Griewank and rastrigin are utilzed to anlayse the performance of the algorithm. Then, the comparison of the algorithm is also, carried out with the existing ABC, GA and hybrid algorithm. From the results, we can see that the proposed technique has obtained better results by acquiring better minimization and convergence rate.


Keywords: Optimization, ABC, GA, fractional order, mutation, test functions.


                                                                Received April 2, 2013; accepted December 24, 2013


Print E-mail

Cryptanalysis of AES-128 and AES-256 Block Ciphers Using Lorenz Information Measure

Vetrivel Karuvandan1, Senthamarai Chellamuthu2, and Shantharajah Periyasamy3     

1 Department of Computer Applications, Anna University Regional Centre, India

2Government Arts College, India

3Sona College of Technology, India


Abstract: Encryption algorithms will transform a human interpretable text block or information in to a non-interpretable block of symbols. The objective of any such encryption algorithm will be making the cipher block more non-interpretable and seemingly random block of symbols. So any cipher block will always be random and will purely be a set of random permutations of symbols. The efforts of distinguishing the cipher text of a cipher from random permutation and distinguishing a cipher blocks of different algorithms are called as distinguisher attacks. Generally, almost all the classical ciphers are distinguishable and even breakable. But the modern ciphers have been designed to withstand against several kinds of attacks and even withstand against distinguisher attack. It means, we cannot even guess the type of cipher used for encryption only by seeing/analyzing the encrypted block of symbols. In this work our focus will be only on distinguisher attack on modern ciphers. For that, we have attempted to distinguish the cipher blocks of AES-128 and AES-256 using a metric called Lorenz Information Measure (LIM) which is commonly used in image and signal classification systems. In our findings, we showed that the cipher blocks of AES-128 and AES-256 are certainly distinguishable from one another.


Keywords: Encryption, cryptography, cryptanalysis, attack, distinguisher attack, AES.

Received May 7, 2012; accepted February 11, 2013


Print E-mail

A Novel Image Alignment and a Fast Efficient Localized Euclidean Distance Minutia Matching Algorithm for Fingerprint Recognition System

Jaganathan Palanichamy and Rajinikannan Marimuthu

Department of Computer Applications, PSNA College of Engineering and Technology, India

Abstract: A fingerprint recognition system involves several steps. In such recognition systems, the matching of unequal number of minutia features is the most important and challenging step in fingerprint based bio-metrics recognition systems. In this paper, we used clustering based fingerprint image rotation algorithm, to improve the performance of the fingerprint recognition system and proposed a Localized Euclidean Distance Minutia Matching (LEDMM) algorithm for matching, which will give better results while comparing minutia sets of different sizes as well as in slightly different orientation during the matching process. The experimental results on the fingerprint image database demonstrate that the proposed methods can achieve much better minutia detection as well as better matching with improved performance in terms of accuracy.


Keywords: Clustering, LEDMM, euclidean distance, fingerprint image enhancement, fingerprint minutia detection, alignment, fingerprint matching.


Received December 13, 2012; accepted February 11, 2013


Print E-mail

ER7ST-Algorithm for Extracting Facial Expressions

Ahmad Tayyar1, Shadi Al-shehabi2, and Majida AlBakoor3

1Department of Computer Science, Isra University, Jordan

2Department of Statistics, Aleppo University, Syria

3Department of Mathematics, Aleppo University, Syria

Abstract: This paper, proposes a new algorithm for recognition of facial expressions, called ER7ST. Studied expressions are anger, disgust, fear, happiness natural, sadness and surprise. Proposed method is based on extraction of the essential objects, then finding of characteristic points positions of each object. Detected points slant and its average are calculated on the basis of fixed points. Mug database is considered as data source for training and testing. We collect set of images. ER7ST is designed to define the work area of face that contains characteristic expressions, which its centre is face centre and its dimensions are 8×16 supposed squares. ER7ST algorithm discovers the essential objects depending on the coordinate of minimum and maximum points of each object in defined area, considering the length of object is larger than the major-axis of formed ellipse on studied object. Object gradient is ranked between [-60, +60] degrees. Our algorithm detects ConvexHull points upon detected objects and then its slant is calculated. Slant vectors are formed; some calculations are done to be a good input to network. Net contains input, three hidden layers and output layer. After training on set of faces and testing on new data, the recognition rate was promising. Algorithm can be maintained with different types of images and it did not need to scale. Finally, recognition rate is ranked between 60% and 95%, experiments have shown that method was efficient and results were very encouraging in this field, especially network can be trained on new situations of expressions.

Keywords: Facial expressions, feature extraction, Essential objects, slant.


Received September 24, 2014; accepted February 5, 2015


Print E-mail

An Adaptive Approach for Real-Time Road Traffic Congestion Detection Using Adaptive Background Extraction

 Nijad Al-Najdawi1, Asma Abu-Roman1, Sara Tedmori2, and Mohammad Al-Najdawi1

1Department of Comuter Science, Al-Balqa Applied University, Jordan

2Department of Computer Science, Princess Sumaya University for Technology, Jordan

Abstract: Traffic congestion is a situation on road networks that occurs as road use increases. When traffic demand increase, the interaction between vehicles slows the speed of the traffic stream and congestion occurs. As demand approaches the capacity of a road, extreme traffic congestion sets in. Current techniques for road-traffic monitoring rely on sensors which have limited capabilities, inflexibility, and are often costly and disruptive to install. The use of video cameras coupled with computer vision techniques offers an attractive alternative to the current sensors. Vision based sensors have the potential to measure a far greater variety of traffic parameters compared to conventional sensors. This work presents an approach for traffic congestion detection based an adaptive background extraction and edge detection techniques using rang filtering. The proposed work uses a special shadow detection algorithm that reduces the chances of misclassification and enhances the segmentation process. An adaptive background extraction technique is used for better object segmentation. In addition, this approach provides real-time statistical information for traffic surveillance on highways such as, the total number of vehicles on the road and the average speed of those vehicles. The proposed system is capable of detecting cars and vans simultaneously.


Keywords: Congestion detection, video surveillance, shadow detection, background updating.

Received June 6, 2013; accepted October 26, 2014


Print E-mail

Performance Analysis of Data Clustering Algorithms using Various Effectiveness Measures

Krishnamoorthi Murugasamy and natarajan Mathaiyan

Department of Computer Science and Engineering, Bannari Amman Institute of Technology, India            

Abstract: Data clustering is a method to group the data records that are similar to each other. In recent days, researcher show significant attention towards the use of swarm based optimization algorithms to improve the performance of clustering process. This Performance analysis concentrates on the effectiveness of five different algorithms with respect to various distances metrics to find the effective algorithm among them. The algorithms used for comparison are K-means algorithm, Artificial Bee Colony (ABC) algorithm, Fuzzy C-Means (FCM) incorporated ABC (ABFCM) algorithm, K-means incorporated Artificial Bee Colony (ABK) algorithm and Bacterial Foraging Optimization Algorithm. Among those algorithms, ABFCM and ABK algorithms are enhanced ABC algorithm in which the FCM and K-means operator are incorporated in the scout phase of the traditional ABC algorithm respectively. In this paper, the performance of these algorithms are compared in terms of various distances metrics like dice coefficient, jaccard coefficient, beta index and distance index by varying the cluster sizes and number of iteration. Finally, from the experimental results it proves that the proposed algorithms ABFCM and ABK outperforms better when compared with the existing algorithms.

Keywords: Data clustering, k-means algorithm, FCM, ABC, distances metrics.

Received November 5, 2012; accepted February 24, 2013


Print E-mail


Recognition of Handwritten Numerals using RBF-SVM Hybrid Model

  Muthukumarasamy Govindarajan

  Department of Computer Science and Engineering, Annamalai University, India

  Abstract: One of the major developments in machine learning in the past decade is the ensemble method, which finds highly accurate classifier by combining many moderately accurate component classifiers. This paper addresses using an ensemble of classification methods for recognizing totally unconstrained handwritten numerals. Due to a great variety of individual writing styles, the problem is very difficult and far from being solved. In this research work, new hybrid classification method is proposed by combining classifiers in a heterogeneous environment using arcing classifier and their performances are analyzed in terms of accuracy. A classifier ensemble is designed using Radial Basis Function (RBF) and Support Vector Machine (SVM). Here, modified training sets are formed by resampling from original training set; classifiers constructed using these training sets and then combined by voting. Empirical results illustrate that the proposed hybrid systems provide more accurate handwriting recognition system.

  Keywords: Handwriting recognition, ensemble, RBF, SVM classification, accuracy.

Received March 6, 2013; accepted December 11, 2013




Print E-mail

An Approach for Clustering Class Coupling Metrics to Mine Object Oriented Software Components

  Anshu Parashar and Jitender Chhabra

  Department of Computer Engineering, National Institute of Technology, India

Abstract: Unsupervised learning methods such as clustering techniques are a natural choice for analyzing software quality by mining its related metrics. It is well known that clustering plays an important role in data mining tasks like in data analysis and information retrieval. In this paper, we have proposed an approach to cluster the pool of java classes based on the proximity between them. To know the proximity, coupling between each pair of classes is calculated in terms of weights using the weighted coupling measures. We modified document representations scheme as per our requirement to represent collected class coupling measures before applying k-mean clustering algorithm. In order to, reduce the dependency of k-mean clustering results efficiency on the choice of initial centroids, neighbor and link based criteria’s for selecting initial k centroids have been proposed in the context of object oriented (OO) design artifacts i.e. classes. We demonstrate our work in detail and compare results of K-mean algorithm based on random and neighbor and link based initial centroids selection criteria’s. Further the results of clustering are analyzed through purity and F-measure. It has been observed that definition of neighbor and link can be interpreted well in terms of the coupling between OO classes and produces best K-mean clustering results. Our approach of software component clustering may become an integral part of a framework to analyze and predict software quality attributes.

Keywords: Software engineering, OO software clustering, mining coupling metric.

Received September 18, 2012; accepted March 20, 2014


Copyright 2006-2009 Zarqa Private University. All rights reserved.
Print ISSN: 1683-3198.
Warning: fsockopen(): php_network_getaddresses: getaddrinfo failed: Name or service not known in /hsphere/local/home/ccis2k/ on line 251 Warning: fsockopen(): unable to connect to (php_network_getaddresses: getaddrinfo failed: Name or service not known) in /hsphere/local/home/ccis2k/ on line 251 skterr