Essam Al-Daoud

Identifying DNA splice sites using patterns statistical properties and fuzzy neural networks

This study introduces a new approach to recognize the boundaries between the parts of the DNA sequence retained after splicing and the parts of the DNA that are spliced out. The basic idea is to derive a new dataset from the original data to enhance the accuracy of the wellknown classification algorithms. The most accurate results are obtained by using a derived dataset that consists from the highest correlated features and the interesting statistical properties of the DNA sequences. On the other hand, using adaptive network based fuzzy inference system (ANFIS) with the derived dataset outperforms well-known classification algorithms. The classification rate that is achieved by using the new approach is 95.23 %, while the classification rates 92.12 %, 86.75 %, 83.13 % and 84.51 % are obtained by LevenbergMarquardt, generalized regression neural networks, radial basis functions and learning vector quantization, respectively. Moreover, this approach can be used to represent the DNA splice sites problem in form if-then rules and hence provides an understanding about the properties of this problem.

Simplified features for email authorship identification

We present an investigation analysis approach for mining anonymous email content. The core idea behind our approach is concentrated on collecting various effective features from previous emails for all the possible suspects. The extracted features are then used with several machine learning algorithms to extract a unique writing style for each suspect. A sophisticated comparison between the investigated anonymous email and the suspects writing styles is employed to extract evidence of the possible email sender. Extensive experimental results on a real data sets show the improved performance of the proposed method with very limited number of features.

Simplified approach for generating integrity tests in distributed database systems

Distributed database systems (DDBS) usually contain massive collections of data that rapidly evolve over time. It is extremely time consuming to make a perfect checking at each database update operation. This paper introduces a new algorithm to generate simplified integrity tests which could be used to automatically verify that database updates does not introduce any violation of integrity. The main attractive features of this approach are simplicity, flexibility in generating sufficient and complete integrity tests, and considering all conjunctive and disjunctive constraints. The experiment results show that the new algorithm provides more tests in comparison with existing techniques.

A new iris localization method based on the competitive chords

This study introduces a novel iris localization method based on the competitive chords. The new method can be used to detect pupil–iris and iris–sclera boundaries. The basic idea is to construct a set of chords from the left edges and the right edges of the pupil (or iris), and then find the winner chords with aligned centers. The winner chords can be used to vote to the correct pupil’s (or iris’s) center and radius. To verify the effectiveness of the proposed method, it is compared with two efficient techniques and applied to five datasets. The experimental results show that the new method is faster, more accurate and more robust than the state-of-the-art iris localization methods.

Fast protein classification by using the most significant pairs

This study introduces a new approach to speed up the protein classification process. The basic idea is rewriting the sequences of each family by using the most significant pairs, where the total number of the pairs that can be appeared in the protein sequences is 400 different pairs. The sequence length could be reduced to 0.86, 0.91 and 0.95 by using the most 100, 200 and 300 significant pairs, respectively. The average time reduction is 0.53 %, 0.33 % and 0.22 % for 100, 200, and 300 pairs, respectively. In the three cases the suggested procedure can be adopted to speed up the testing time. However to get identical classification rate to the previous profile HMM, 300 pairs at least must be used.

Mobile agents modelling using UML

In software and system design, there are many views that can be demonstrated through visual diagram. State diagrams are widely used to express systems, entities or objects experiences different states according to different events or transitions. Typical state diagrams do not take the complexity of many currently existing systems. The singular view of definite possible states that a traditional state diagram allows is inapplicable for some hybrid complex systems such as mobile agents, graphical user interfaces, etc. In this paper, we take a look at the presented approach for modelling agent mobility with UML sequence diagrams and present a simplified form of UML state diagrams for modelling agent mobility. We proposed enhancements on the traditional state diagram to take into consideration modelling such hybrid complex systems as extension for the traditional state diagram. The concepts from the composite pattern are used in which there is a need for conformity in dealing with composite and component elements.

Texture recognition by using a non-linear kernel

This study proposes the use of features combination and a non-linear kernel to improve the classification rate of texture recognition. The feature vector concatenates three different sets of feature: the first set is extracted using grey-level cooccurrence matrix, the second set is collected from three different radii of local binary patterns, and the third set is generated using Gabor wavelet features. Gabor features are the mean, the standard deviation, and the skew of each scaling and orientation parameter. The aim of the new kernel is to incorporate the power of the kernel methods with the optimal balance derived from the features. To verify the effectiveness of the proposed method, numerous techniques are tested using the three data sets, which consist of various orientations, configurations and lighting conditions.