April 2009, No. 2
Print E-mail

Investigation Arabic Speech Recognition
Using CMU Sphinx System

Hassan Satori1, 2, Hussein Hiyassat3, Mostafa Harti1, 2, and Noureddine Chenfour1, 2
1UFR Informatique et Nouvelles Technologies d'Information, Dhar Mehraz Fès, Morocco
2Département de Mathématiques et Informatique, Faculté des Sciences, Morocco
3Arab Academy for Banking and Financial Sciences, Amman, Jordan


Abstract: In this paper, Arabic was investigated from the speech recognition problem point of view.  We propose a novel approach to build an Arabic automated speech recognition system using Arabic environment. The system, based on the open source CMU Sphinx-4, was trained using Arabic characters.

Keywords: Speech recognition, Arabic language, HMMs, CMUSphinx-4, artificial intelligence.

Received August 19, 2007; accepted December 9, 2007  

Full Text
Read more...
 
Print E-mail

Discrete Time NHPP Models for Software Reliability Growth Phenomenon

Omar Shatnawi
 Prince Hussein bin Abdullah Information Technology College, al-Bayt University, Jordan


Abstract: Nonhomogeneous poisson process based software reliability growth models are generally classified into two groups. The first group contains models, which use the machine execution time or calendar time as a unit of fault detection/removal period. Such models are called continuous time models. The second group contains models, which use the number of test occasions/cases as a unit of fault detection period. Such models are called discrete time models, since the unit of software fault detection period is countable. A large number of models have been developed in the first group while there are fewer in the second group. Discrete time models in software reliability are important and a little effort has been made in this direction. In this paper, we develop two discrete time SRGMs using probability generating function for the software failure occurrence / fault detection phenomenon based on a NHPP namely, basic and extended models. The basic model exploits the fault detection/removal rate during the initial and final test cases. Whereas, the extended model incorporates fault generation and imperfect debugging with learning. Actual software reliability data have been used to demonstrate the proposed models. The results are fairly encouraging in terms of goodness-of-fit and predictive validity criteria due to applicability and flexibility of the proposed models as they can capture a wide class of reliability growth curves ranging from purely exponential to highly S-shaped..

Keywords: Software engineering, software testing, software reliability, software reliability growth model, nonhomogeneous poisson process, test occasions.

Received August 19, 2007; accepted December 9, 2007  

Full Text
Read more...
 
Print E-mail

Artificial Neural Network Approach for Overlay Design of Flexible Pavements

Mostafa Abo-Hashema
Faculty of Engineering, Fayoum University, Egypt

Abstract: Pavements are constructed to deteriorate because of many factors such as traffic loading, material related factors, climate, and other environmental factors. In order to preserve these investments, a maintenance program should be carried out at right time and right places. One of the most important maintenance activities is asphalt overlays. Designing an overlay is more challenging since it restricts the pavement design engineer to a vast number of boundary conditions that must be observed and designed for. The most important factor in this process is the assessment of the existing pavement structural capacity, and relating it to the new overlay. The process becomes more complicated when considering environmental changes of the pavement materials. Such process should be implemented using a computer model to overcome complexity procedures, repeated tasks and time consuming. An artificial neural network approach can be used for the elimination of this drawback. This study presents an attempt to apply artificial neural network to recommend pavement overlay thickness based on learning from Mechanistic-Empirical overlay design cases. Results of this study reveal that artificial neural network is appropriate for implementation in calculating flexible overlay thickness based on mechanistic-based design procedure.

Keywords: Overlay, ANN, pavement design, neural network, mechanistic-empirical, flexible pavements.

Received December 10, 2007; accepted February 19, 2008

  

Full Text

Read more...
 
Print E-mail

Empirical Validation of Requirements Management Measures

Mahmoud Khraiwesh1 and Asim El Sheikh2
1Faculty of Science and Information Technology, Zarqa Private University, Jordan     
2Faculty of Information System, Arab Academy for Banking and Financial Sciences, Jordan

Abstract: Requirements management measures help organizations to understand, control and assess requirements management process. This paper validates empirically a set of requirements management measures. The measures were defined for the five specific practices of requirement’s management key process area in capability maturity model integration by applying the goal question metrics paradigm to the five specific practices. We have applied the defined measures on three information systems using historical data. Then, for each information system some hypotheses have been followed to confirm the validity of the defined measures empirically.

Keywords:

Requirements management, measures, measures validation, CMMI, GQM.

Received August 19, 2007; accepted December 9, 2007

Read more...
 
Print E-mail

A Framework to Automate the Parsing of  Arabic Language Sentences

Essam Al Daoud and Abdullah Basata
Faculty of Science and Information Technology, Zarqa Private University, Jordan

Abstract: This paper proposes a framework to automate the parsing (إعراب) of Arabic language sentences in general, although it focuses on the simple verbal sentences but it can be extended to any Arabic language sentence. The proposed system is divided into two separated phases which are lexical analysis and syntax analysis. Lexical phase analyses the words, finds its originals and roots, separates it from prefixes and suffixes, and assigns the filtered words to special tokens. Syntax analysis receives all the tokens and finds the best grammar for the given sequence of the tokens by using context free grammar. Our system assumes that the entered sentences are correct lexically and grammatically.

Keywords: Lexical analysis, syntax analysis, Arabic language parser.

Received December 5, 2007; accepted February 20, 2007

 

Full Text

 

Read more...
 
Print E-mail

A Fuzzy Approach to Energy Optimized Routing for Wireless Sensor Networks

Tarique Haider1 and Mariam Yusuf 2
1 Hamdard Institute of Information Technology, Hamdard University Karachi, Pakistan
2 Departments of Telecommunication and Computer Engineering, Pakistan


Abstract: : In recent years, many approaches and techniques have been explored for the optimization of energy usage in wireless sensor networks. Routing is one of these areas in which attempts for efficient utilization of energy have been made.  These attempts use fixed (crisp) metrics for making energy-aware routing decisions.  In this paper, we present a generalized fuzzy logic based approach for energy-aware routing in wireless sensor networks. This generalized approach is soft and tunable and hence it can accommodate sensor networks comprising of different types of sensor nodes having different energy metrics.

Keywords: Wireless sensor networks, fuzzy logic, routing.

Received April 27, 2007; accepted December 26, 2007

Read more...
 
Print E-mail

Performance Enhancement of UWB Power  Control Using Ranging and Narrowband Interference Mitigation

Rashid Saeed1, Sabira Khatun2, Borhanuddin Ali3, and Mohamad Abdullah2
1Telekom Malaysia, Research and Development Innovation Centre, Malaysia
2Department of Computer and Communications Engineering, University Putra Malaysia, Malaysia

Abstract: Power control is a critical parameter for the design and evaluation of UWB-based WPAN networks due to its distributed control nature and non-fixed topology. The main issues in UWB PC are the channel gain fluctuations induced by indoor channel fluctuation and interference arising from narrowband systems. In this paper we introduce a joint PHY/MAC technique for DS-UWB power control design by exploiting the high time resolution of the UWB signal for channel gain improvement and mitigate the narrowband interference to reduce transmitted power.  The results indicate that the proposed approach achieves better BER and throughput over previous works.

Keywords:

Information technology transfer, major issues, Delphi study, Arab world.

Received July 9, 2007; accepted December 24, 2007

Read more...
 
Print E-mail

        Cases Base Memory Modelling for Medical Pictures Reuse

Abdelkrim Meziane1 and  Nour El Islam Bachari2
1CERIST Centre of Research in Scientific and Technical Information, Algeria
2USTHB University Algiers, Algeria

Abstract: The mass of multimedia data produced annually in hospitals are measured in terabytes; the need to manage this gigantic information mass becomes quickly extremely crucial. The actual management information systems of medical pictures present some limits like their capacities to answer the needs of the users. These limits are due to the fact that these systems don't take in consideration the semantic content of the pictures. Content research aims to pass this problem. One of the possible means consists in using description criteria of the picture semantic content for being able to reuse it. These criteria are known in the medical knowledge domain. We think that the use of an enterprise memory for managing this knowledge would be able to satisfy this need. We demonstrate our subjects by the realization of a prototype named "MECIM ".

Keywords: Medical picture, enterprise memory, cases base research

Received October 8, 2007; accepted December 23, 2007 

Full Text

Read more...
 
Print E-mail

 A Proposed Approach for Learner Evaluation
 in an Open Distance Environment

Amar Balla
National Institute of Computer Science, Algeria

Abstract: The remote learning evolution and particularly the e-learning permits to more and more people access to education. One of the learning fields which are to be developed is the learner evaluation. The accuracy and the pertinence of the evaluation results can provide information which can be very exploitable by the tutor in order to let the latter help the learner who has some troubles. The evaluation can also be exploitable by the learner because it provides a feedback on what he has really understood. Within this context we are interested by two types of cognitive evaluations, the first one concerning the self-evaluation by questionnaires with multiple choices and the second one concerning the collective work evaluation. For the first case, the work consists to make the questionnaires with multiple choices intelligent, e.g., the questions which will be asked will progress in function of the learner’s answers in order to identify the knowledge on which he has difficulties. In the second case, we will use a multi-agent system in order to achieve the evaluation of a group of learners working on the same project. 

Keywords: Learner evaluation, open distance environment, knowledge, multi-agent system.

Received September 28, 2007; accepted December 9, 2007

 

Full Text

Read more...
 
Print E-mail

Early Abandon to Accelerate Exact  Dynamic Time Warping

Li Junkui and Wang Yuanzhen
College of Computer Science and Technology, University of Science and Technology, China

Abstract: Dynamic time warping is one of the important distance measures in similarity search of time series; however, the exact calculation of dynamic time warping has become a bottleneck. We propose an approach, named early abandon dynamic time warping, to accelerate the calculation. The method checks if values of the neighbouring cells in the cumulative distance matrix exceed the tolerance, and if so, it will terminate the calculation of the related cell. We demonstrate the idea of early abandon on dynamic time warping by theoretical analysis, and show the utilities of early abandon dynamic time warping by thorough empirical experiments performed both on synthetic datasets and real datasets. The results show, early abandon dynamic time warping outperforms the dynamic time warping calculation in the light of processing time, and is much better when the tolerance is below the real dynamic time warping distance.

Keywords: Data mining, time series, similarity search, dynamic time warping, early abandon.

Received July 8, 2007; accepted December 20, 2007

Read more...
 
Print E-mail

Prediction of Time Series Using RBF Neural Networks: A New Approach of Clustering

Mohammed Awad2, Héctor Pomares1, Ignacio Rojas1, Osama Salameh2 and Mai Hamdon2
1Department of Computer Architecture and Technology, University of Granada, Spain
2Faculty of information Technology, Arab American University, Palestine

Abstract: In this paper, we deal with the problem of time series prediction from a given set of input/output data. This problem consists of the prediction of future values based on past and/or present data. We present a new method for prediction of time series data using radial basis functions. This approach is based on a new efficient method of clustering of the centers of the radial basis function neural network; it uses the error committed in every cluster using the real output of the radial basis function neural network trying to concentrate more clusters in those input regions where the error is bigger and move the clusters instead of just the input values of the I/O data. This method of clustering, improves the performance of the time series prediction system obtained, compared with other methods derived from traditional algorithms.

Keywords:

Clustering, time series prediction, RBF neural networks.

Received April 21, 2007; accepted December 14, 2007

Read more...
 
Print E-mail

Towards A Distributed Arabic OCR Based on the DTW Algorithm: Performance Analysis

Maher Khemakhem1 and Abdelfettah Belghith2
1Miracl Lab Fsegs, University of Sfax, Tunisia
 2Rim-Cristal Lab, Ensi University of Manouba, Tunisia

Abstract: In spite of the diversity of printed Arabic optical character recognition products and proposals, the problem seems to be not yet well solved. The complex morphology and calligraphy of the Arabic writing on one hand and the use of some light approaches on the other hand are behind the poorness of these products. However, some strong proposed approaches didn’t find the opportunity to be commercialised because of generally their corresponding complex computing.  The dynamic time warping algorithm is considered as one among these strong approaches. In fact, several studies and experiments have shown and confirmed that the printed Arabic optical character recognition based on dynamic time warping algorithm provides a very interesting recognition rate especially for large and huge vocabularies. One of the attractive sides of the dynamic time warping algorithm is its ability to recognize properly connected or cursive characters (words or sub words) without prior segmentation. Furthermore, this algorithm performs the recognition process from within a reference library of isolated characters and owns a very good immunity against noises. Unfortunately, the big amount of its computing during the recognition process makes its execution time very slow and, hence, restricts its utilization. Many researchers attempted to speedup the execution time of this algorithm. Unfortunately, the corresponding proposed solutions require generally specific high cost architectures. Loosely coupled architectures such as grapes or grid computing can provide enough power without additional cost to distribute the complexity of some greedy applications. Consequently, we report in this paper the performance analysis of an analytical and an experimental study of a distributed Arabic optical character recognition based on the dynamic time warping algorithm within loosely coupled architectures. Obtained results confirm that loosely coupled architectures and more specifically grid computing present a very interesting framework to speedup the Arabic optical character recognition based on the dynamic time warping algorithm.

Keywords: Arabic OCR, DTW algorithm, loosely coupled architectures, grapes, grid computing, performance analysis.

Received September 11, 2007; accepted December 22, 2007

 

Full Text

 

Read more...
 
Print E-mail

Video Object Extraction Based on a Comparative
Study of Efficient Edge Detection Techniques

Kavitha Ganesan1 and Shanmugam Jalla2
1Lecturer Electronics Department, Anna University, India
2Principal Tagore Engineering College, India

Abstract: Segmentation of objects serves as a key of image analysis and pattern recognition. The main focus of the paper is related to the development of efficient algorithms for automatic segmentation of objects in image sequences. Fast, automatic and robust segmentation are necessary in many aspects of multimedia applications due to its capability that it can automatically detect objects appearance and in addition  it can be used for object tracking system. The extraction of semantically meaningful video object for tracking and surveillance application can be obtained in the process of implementing the proposed algorithms. Further in this paper a comparative study between video object extraction based on change detection and model matching techniques is given. Experimental results prove the effectiveness of the proposed algorithms.

Keywords:
Segmentation, video object extraction, change detection, model matching.

Received August 23, 2007; accepted November 7, 2007 

Full Text

 
Print E-mail

Binding Semantic to a Sketch Based
Query Specification Tool

Shahrul Noah and Saiful Sabtu
Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Malaysia

Abstract: In image retrieval systems, user information needs is expressed using multiple types of query. Unfortunately, due to user subjectivity perception to visual features and semantic depths of images, the conventional query submitted to the system encounter difficulties to identify user information need. The blooming of interest in semantic image retrieval requires current research direction to be more concerned into semantics. This paper describes our on-going research work in formulating a new query approach for image databases. The enabling technologies of the semantic web formed the building blocks of our query specification. Using the MRML as the communication protocol, XML in the form of SVG as the visual content description (sketch based) and RDF for binding the semantic meanings of images, this research provides an initial framework towards semantic based query formulation framework.

Keywords: Image retrieval system, semantic retrieval, multimedia retrieval markup language, semantic web

Received March 19, 2007; accepted November 16, 2007

Read more...
 
<
 
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/ccis2k.org/iajit/templates/rt_chromatophore/index.php on line 251 Warning: fsockopen(): unable to connect to oucha.net:80 (php_network_getaddresses: getaddrinfo failed: Name or service not known) in /hsphere/local/home/ccis2k/ccis2k.org/iajit/templates/rt_chromatophore/index.php on line 251 skterr