Amin Shoukry

On-line recognition of handwritten isolated arabic characters

Abstract This paper is concerned with the recognition of isolated handwritten Arabic characters drawn on a graphic tablet. At first, features that are suitable for recognition are proposed. Features that are found to be independent of the writer style are represented as a list (vector) of integer values, while those that are subjected to more variations are represented using a Freeman-like chain code. This mixing of the representation combined with a hierarchial organization of the characters proved to be useful in reducing recognition time. The proposed system has been implemented and tested on a PDP11/70 mini-computer using BASIC PLUS-2 programming language and real data samples that have been drawn on a Tektronix graphic tablet. Results concerning the effect of different parameters and classification strategies on the performance of the system are given.

Adaptive traffic control system based on Bayesian probability interpretation

Traffic control (TC) is a challenging problem in todays modern society. This is due to several factors including the huge number of vehicles, the high dynamics of the system, and the nonlinear behavior exhibited by the different components of the system. Poor traffic management inflicts considerable cost due to the high rate of accidents, time losses, and negative impact on the economy as well as the environment. In this paper, we develop a traffic control system based on the Bayesian interpretation of probability that is adaptive to the high dynamics and non-stationarity of the road network. In order to simulate the traffic non-stationarity, we extend the Green Light District (GLD) vehicle traffic simulator. The change in road conditions is modeled by varying vehicle spawning probability distributions. We also implement the acceleration and lane changing models in GLD based on the Intelligent Driver Model (IDM).

Neural network approach for solving the maximal common subgraph problem

A new formulation of the maximal common subgraph problem (MCSP), that is implemented using a two-stage Hopfield neural network, is given. Relative merits of this proposed formulation, with respect to current neural network-based solutions as well as classical sequential-search-based solutions, are discussed.

CMUNE: A clustering using mutual nearest neighbors algorithm

A novel clustering algorithm CMune is presented for the purpose of finding clusters of arbitrary shapes, sizes and densities in high dimensional feature spaces. It can be considered as a variation of the Shared Nearest Neighbor algorithm (SNN), in which each sample data point votes for the points in its k-nearest neighborhood. Sets of points sharing a common mutual nearest neighbor are considered as dense regions/blocks. These blocks are the seeds from which clusters may grow up. Therefore, CMune is not a point-to-point clustering algorithm. Rather, it is a block-to-block clustering technique. Much of its advantages come from this fact: Noise points and outliers correspond to blocks of small sizes, and homogeneous blocks highly overlap. The algorithm has been applied to a variety of low and high dimensional data sets with superior results over existing techniques such as K-means, DBScan, Mitosis and Spectral clustering. The quality of its results as well as its time complexity, place it at the front of these techniques.

Constrained Dynamic Differential Evolution using a novel hybrid constraint handling technique

In this paper, a Constrained Dynamic Differential Evolution (CDDE) algorithm is proposed to solve constrained optimization problems. In CDDE, the crossover rate CR and scale factor F are dynamically changed and selected randomly from the range [0.5,1]. This way, CDDE has degrees of exploration abilities for the landscape of the constrained optimization problems and can be able to discover the search space and reach the feasible regions. Also, a novel hybrid simple constraint handling technique is suggested, which combines two well-known techniques: feasible rules and adaptive penalty function. Near convergence, CDDE uses the Sequential quadratic programming (SQP) method to enhance its local search ability. CDDE performance has been tested on the constrained benchmark functions of the CEC 2010 competition. The results demonstrate that CDDE outperforms other state-of-the-art algorithms and consistently reaches feasible solutions.

A Novel Taxonomy of Black-Hole Attack Detection Techniques in Mobile Ad-hoc Network (MANET)

Mobile Ad-Hoc Networks (MANETs) are characterized by the lack of infrastructure, dynamic topology, and their use of the open wireless medium. Black-hole attack represents a major threat for such type of networks. The purpose of this paper is two folds. First, to present an extensive survey of the known black-hole detection and prevention approaches. Another objective is to present new dimensions for their classification.

Efficient parallel implementations of controlled optimization of traffic phases

Finding optimal phase durations for a controlled intersection is a computationally intensive task requiring O(N3) operations. In this paper we introduce cost-optimal parallelization of a dynamic programming algorithm that reduces the complexity to O(N2). Three implementations that span a wide range of parallel hardware are developed. The first is based on shared-memory architecture, using the OpenMP programming model. The second implementation is based on message passing, targeting massively parallel machines including high performance clusters, and supercomputers. The third implementation is based on the data parallel programming model mapped on Graphics Processing Units (GPUs). Key optimizations include loop reversal, communication pruning, load-balancing, and efficient thread to processors assignment. Experiments have been conducted on 8-core server, IBM BlueGene/L supercomputer 2-node boards with 128 processors, and GPU GTX470 GeForce Nvidia with 448 cores. Results indicate practical scalability on all platforms, with maximum speed up reaching 76x for the GTX470.

A Multistage Hierarchical Algorithm for Hand Shape Recognition

This paper represents a multistage hierarchical algorithm for hand shape recognition using principal component analysis (PCA) as a dimensionality reduction and a feature extraction method. The paper discusses the effect of image blurring to build data manifolds using PCA and the different ways to construct these manifolds. In_order to classify the hand shape of an incoming sign object and to be invariant to linear transformations like translation and rotation, a multistage hierarchical classifier structure is used. Computer generated images for different Irish Sign Language shapes are used in testing. Experimental results are given to show the accuracy and performance of the proposed algorithm.

Ensemble-based classification approach for micro-RNA mining applied on diverse metagenomic sequences

BackgroundMicroRNAs (miRNAs) are endogenous ∼22 nt RNAs that are identified in many species as powerful regulators of gene expressions. Experimental identification of miRNAs is still slow since miRNAs are difficult to isolate by cloning due to their low expression, low stability, tissue specificity and the high cost of the cloning procedure. Thus, computational identification of miRNAs from genomic sequences provide a valuable complement to cloning. Different approaches for identification of miRNAs have been proposed based on homology, thermodynamic parameters, and cross-species comparisons.ResultsThe present paper focuses on the integration of miRNA classifiers in a meta-classifier and the identification of miRNAs from metagenomic sequences collected from different environments. An ensemble of classifiers is proposed for miRNA hairpin prediction based on four well-known classifiers (Triplet SVM, Mipred, Virgo and EumiR), with non-identical features, and which have been trained on different data. Their decisions are combined using a single hidden layer neural network to increase the accuracy of the predictions. Our ensemble classifier achieved 89.3% accuracy, 82.2% f–measure, 74% sensitivity, 97% specificity, 92.5% precision and 88.2% negative predictive value when tested on real miRNA and pseudo sequence data. The area under the receiver operating characteristic curve of our classifier is 0.9 which represents a high performance index.The proposed classifier yields a significant performance improvement relative to Triplet-SVM, Virgo and EumiR and a minor refinement over MiPred.The developed ensemble classifier is used for miRNA prediction in mine drainage, groundwater and marine metagenomic sequences downloaded from the NCBI sequence reed archive. By consulting the miRBase repository, 179 miRNAs have been identified as highly probable miRNAs. Our new approach could thus be used for mining metagenomic sequences and finding new and homologous miRNAs.ConclusionsThe paper investigates a computational tool for miRNA prediction in genomic or metagenomic data. It has been applied on three metagenomic samples from different environments (mine drainage, groundwater and marine metagenomic sequences). The prediction results provide a set of extremely potential miRNA hairpins for cloning prediction methods. Among the ensemble prediction obtained results there are pre-miRNA candidates that have been validated using miRbase while they have not been recognized by some of the base classifiers.

Spectral clustering for optical confirmation and redshift estimation of X-ray selected galaxy cluster candidates in the SDSS Stripe 82

We develop a galaxy cluster finding algorithm based on spectral clustering technique to identify optical counterparts and estimate optical redshifts for X-ray selected cluster candidates. As an application, we run our algorithm on a sample of X-ray cluster candidates selected from the third XMM-Newton serendipitous source catalog (3XMM-DR5) that are located in the Stripe 82 of the Sloan Digital Sky Survey (SDSS). Our method works on galaxies described in the color-magnitude feature space. We begin by examining 45 galaxy clusters with published spectroscopic redshifts in the range of 0.1 to 0.8 with a median of 0.36. As a result, we are able to identify their optical counterparts and estimate their photometric redshifts, which have a typical accuracy of 0.025 and agree with the published ones. Then, we investigate another 40 X-ray cluster candidates (from the same cluster survey) with no redshift information in the literature and found that 12 candidates are considered as galaxy clusters in the redshift range from 0.29 to 0.76 with a median of 0.57. These systems are newly discovered clusters in X-rays and optical data. Among them 7 clusters have spectroscopic redshifts for at least one member galaxy.