Bassam El-Zaghmouri | Jerash University (original) (raw)

Uploads

Papers by Bassam El-Zaghmouri

Speech recognition is an important part of human-machine interaction which represents a hot area ... more Speech recognition is an important part of human-machine interaction which represents a hot area of researches in the field of computer systems, electronic engineering, communications, and artificial intelligence. While speech signal is very complex and contains huge number of sampling points, the extraction of features from its time and frequency domain is very complex by analytical methods. The neural network capabilities to estimate the complex functions make it very reliable in such applications. This paper presents speech recognizer based on feed forward neural network with multi layer perceptron structure. The speech is preprocessed by two methods; discrete wavelet transformation (DWT) and principal component analysis (PCA). The results and structure are presented and comparison is make over them.

Software maintainability has been considered as a main characteristic in many software product qu... more Software maintainability has been considered as a main
characteristic in many software product quality models. However,
these models have different definitions for maintainability and
sub characteristics. ISO 9126 is one of the main and most
frequently used models in software product quality. This model
has been revised and replaced by ISO 25010 as a new model of
software product quality. In addition to the many modifications
that were performed on ISO 9126 model, maintainability was one
of the main modified characteristics. However, it was developed
unclearly without any standard base, and with no clear definition
or evidence of how the sub characteristics were defined and
modified. This paper investigates these modifications and the
differences between the definitions of the maintainability in the
two models, ISO 9126 and ISO 25010. As a result of this
discussion, it has been concluded that both models ISO 9126 and
ISO 25010 lack of a clear definition or standard base for defining
software maintainability and its sub characteristics

In the rise rabid research related to biometrics, bio-informatics and genome; many researches, fi... more In the rise rabid research related to biometrics, bio-informatics and genome; many researches, fields, and issues are still undergo any uncertainties. One of the hottest areas in this field of research is the proteins informatics, that is relates the protein data with the modern information technology and it includes portions mapping and classification. This paper contributes an intelligent system which consists of adaptive neuro-fuzzy computations that is able to recognize and classify the proteins in families. An intelligent trainer will be structured based on Perceptron neural network in order to build an intelligent fuzzy inference system that is capable of predicting and classifying that data into categories according to the function of each protein. The structured system preprocesses that data set and extracts unique features from it. The system was built using a highly developed programming language. This paper will clearly show the results that such system achievement about 92% of accuracy when over 1000 inputs sequence of the validation sample was processed.

Clustering is a type of classification under optimization problems, which is considered as a crit... more Clustering is a type of classification under optimization problems, which is considered as a critical area of data mining. Medical clustering problem is a type of unsupervised learning in data mining. This work present a hybridization between our previous proposed Iterative Simulated Annealing (ISA) and Modified Great Deluge (MGD) algorithms for medical clustering problems. The aim of this work is to produce an effective algorithm for partitioning N objects into K clusters. The idea of the hybridization between MGD and ISA is to incorporate the strength of one approach with the strength of the other hoping a more promising algorithm. Also this combination can help to diverse the search space. Experimental results obtained two way of calculating the minimal distance that have been tested on six benchmark medical datasets show that, ISA-MGD is able to outperform some instances of MGD and ISA algorithms

Many clustering algorithms with different methodologies are subjected to be common techniques and... more Many clustering algorithms with different methodologies are subjected to be common techniques and main step in
many applications in the computer science world. The need of adapting efficient clustering algorithm increases in critical
applications (i.e. wireless sensors networks). Utilizing the Fuzzy Logic power; Fuzzy C-mean (FCM) clustering has a major role
in most clustering applications. But in many cases, the result of FCM is considered to be non-complete clustering strategy. This
paper adapted the FCM algorithm to enable of generating clusters with equal sizes. Also, scattered points that are located far
away from all clusters are grouped out of clusters. Another modification is to localize specific points that have ability to locate in
more than one cluster; hence this has a non-negligible importance in some fields such as cellular communications

As a completion of Arabic hand written recognition, the Arabic numbers which are commonly known a... more As a completion of Arabic hand written recognition, the Arabic numbers which are commonly known as “Old-Indian Numbers” are taken place in full text recognition and applications. Hand written Arabic numbers have less complexity than Arabic characters, but such researches are has few interests. The curves shape of these numbers make its characteristics difficult to be recognized by intelligent systems. This paper adapts and implements neural network to takes the features of number segment and recognize it in high reliability and accuracy. The numbers are being segmented by morphological approach. A MATLAB based program is developed to validity testing of the proposed system enhance the accuracy to by 98% over the testing data set.

Requirements establishment and definition are very critical tasks in software development. This s... more Requirements establishment and definition are very critical tasks in software development. This study discusses the process of requirements definition, and key characteristics affecting the success of software projects development. An evaluation framework is proposed in order to verify users’ requirements and reduce associated risks on software project development. The framework was developed based on the relationships between the components of software project request. A preliminary assessment study was conducted and confirmed the applicability and usefulness of the proposed framework in detecting errors in user’s requirements.

the use of biometric information has been widely known for both people identification and securit... more the use of biometric information has been widely known for both people identification and security application. It is common knowledge that each person can be identified by the unique characteristics of one or more of biometric features. One most unique and identifiable biometric characteristics is the iris, wherever the second is the voice, and the third is finger print. This research attempts to apply iris recognition techniques based on the technology invented by Dr. John G. Daugman, an attempt of implementing a build an end user application. Iris Recognition is expected to play a major role in a wide range of applications in which a person's identity must be established or confirmed in high reliability and high privacy, Including access controls, authorizations, ID detection, etc. This research depends on standard iris images was token from CASIA database. The most efficient computer language for simulation and technical computing (MATLAB) will be used to make the problem statement and result in addition to mathematical and AI modelling more easier and reliable.