International Journal of Computer Networks and Communications Security

Volume 4, Issue 5, May 2015

 

 

 

Arabic Text Classification on Full Word

Pages: 114-120 (7) | [Full Text] PDF (477 KB)
R Elhassan, M Ahmed
Computer science Department Mathematical Science collage, University of Khartoum, Khartoum, 11111, Sudan
Dean of Mathematical Science collage, University of Khartoum, Khartoum, 11111, Sudan

Abstract -
Text classification aims to extract the useful information from a large data. The documents may contain unnecessary data which may affect the accuracy of the classifier. Data preprocessing phase aims to clean the texts by removing unnecessary information. The main object of this paper is to explain and determine the effectiveness of the data preprocessing on full word in the accuracy of both training model and classifier. This will be done by two approaches: first the observation of data set contain and second the stop word estimation technique. In the experiment, the Sequential Minimal Optimization (SMO), Naive Bayesian (NB) J48 and K-nearest neighbors (KNN) were used to build the training models. By implement the two approaches and measured the accuracy by precision, recall and f- measure, the results showed that the SMO classifier outperforms the three other classifiers as a training model and a classifier.
 
Index Terms - Text classification, Arabic Text Classification, Stops Words, Data Preprocess Classifier, ESWF, SWF

Citation - R Elhassan, M Ahmed. "Arabic Text Classification on Full Word." International Journal of Computer Science and Software Engineering 4, no. 5 (2015): 114-120.

 

A Non-Parametric Approach for Paper Currency Recognition

Pages: 121-125 (5) | [Full Text] PDF (429 KB)
AM Ali Fattouh
King Abdulaziz University, Faculty of Computing and Information Technology, Department of Computer Science, Jeddah, 21589, Saudi Arabia

Abstract -
In this paper, a non-parametric approach is proposed for the recognition of paper currency. The proposed approach is based on the development of a non-parametric model for each kind of paper currency. The model is obtained by averaging all available samples of a banknote. In order to get a reliable model, all banknotes should be aligned which is ensured in this work by a new proposed capturing system. A non-known banknote can be recognized by finding the coefficients of determination between the banknote and the non-parametric models and discriminate based on these values. The proposed method is applied to three kinds of Saudi banknotes, and it was able to recognize correctly 100% of tested banknotes.
 
Index Terms - Paper Currency, Recognition, Non-Parametric model, Averaging, Coefficient of Determination

Citation - AM Ali Fattouh. "A Non-Parametric Approach for Paper Currency Recognition." International Journal of Computer Science and Software Engineering 4, no. 5 (2015): 121-125.

 

A Comparative Study of Agile Methods: XP versus SCRUM

Pages: 126-129 (4) | [Full Text] PDF (254 KB)
M Almseidin, K Alrfou, N Alnidami, A Tarawneh
Information Technology, MUTAH UNIVERSITY, Karak, Jordan
Information Technology ,Tafila Technical University, Tafila, Jordan

Abstract -
Extreme programming (XP) and SCRUM are both agile software development methodologies. Each of one has its own way to be applied on specific projects also each one has own value compare with the other. When applied on project or used to improve the productivity of projects through managing the most necessary elements like stakeholder managements.The research work presents a comparative analysis between XP and SCRUM. The focus will be applicability on the objective of outline the similarities and difference between the two methods. Finally a recommended is made on the possibility of using both of them in an individual project. Also each one focused on field of practices like communication, product development and feedback for the project so on; in this research would be focused on each method by doing comparison between XP and SCRUM through applicability to software project, contract issue, incremental style, iterative level for each method to get some of feature like similarities and differences for tow method to reach point how can useful if XP or SCRUM operate with each other for some project.
 
Index Terms - Agile, XP, SCRUM and PUB

Citation - M Almseidin, K Alrfou, N Alnidami, A Tarawneh. "A Comparative Study of Agile Methods: XP versus SCRUM." International Journal of Computer Science and Software Engineering 4, no. 5 (2015): 126-129.

 

Contribution of Artificial Neural Networks to the Identification and Detection of Targets Concerning Mobility on Remote Sensing Images

Pages: 130-136 (7) | [Full Text] PDF (940 KB)
S Zeriouh, M Boutahri, SE Yamani, A Roukhe
Information Optronic Treatment Team, Atomic, Mechanical, Photonic and Energy Laboratory, Faculty of Science, Moulay Ismail Uni., Zitoune, Meknes, Morocco

Abstract -
Targets identification on remote sensing images depends essentially on efficiency of the followed classification and analysis methods. In this context, this paper is to present a system for detection and identification of targets on a multi-band satellite image by connectionist methods. From a database comprising reflectance samples of four desired target, the proposed system performs a supervised classification of the wanted objects on a multispectral image by the gradient algorithms. Compared with principal component analysis (PCA), the method provides more meaningful results. Then, the system performs automatic identification of suspected targets on the studied image.
 
Index Terms - Multispectral Image, Supervised Classification, Identification, Principal Component Analysis, Artificial Neural Networks, Gradient Algorithms

Citation - S Zeriouh, M Boutahri, SE Yamani, A Roukhe. "Contribution of Artificial Neural Networks to the Identification and Detection of Targets Concerning Mobility on Remote Sensing Images." International Journal of Computer Science and Software Engineering 4, no. 5 (2015): 130-136.