Ahmad Shahin

Driver stress level detection using HRV analysis

This paper intends to investigate stress level detection of a driver during real world driving experiment. This detection is based on heart rate variability (HRV) analysis which is derived from ECG signal and reflects autonomic nervous system state of the human body. The alteration of autonomic nervous system predicts the stress level of drivers during driving operation and permits a safe driving by the possibility of an early warning. This stress, taking place during driving, is caused by diverse factors such as changing mood, bio rhythm, fatigue, boredom or disease which can prevent the driver from reaching inappropriate state for driving. In our study, the ECG signal of the driver is extracted and preprocessed in order to perform the HRV analysis. This analysis is accomplished using one of the domain analysis approach such as time, frequency, time-frequency or non-linear methods including Wavelet and STFT. After HRV analysis, several parameters are extracted to build a vector of features for the classification phase. Our experimentation is performed with data issued from 16 different subjects from the Stress Recognition in Automobile Driver database (DRIVEDB). Several classification techniques were investigated including support vector machine with radial basis function (SVM-RBF) kernel, K nearest neighbor (KNN), and radial basis function (RBF) classifiers. Our results indicate that stress detection could be predicted with an accuracy of 83% using SVM-RBF classifier. This also points out the robustness of ECG biometric as an accurate physiological indicator of a driver state.

New XACML-AspectBPEL approach for composite web services security

Web services technology is the latest evolution in distributed computing. With all of the advantages of web services, one of the main hurdles remains security in composite web services. In this paper, we tackle this problem through a new approach towards the integration of security into the BPEL Business Process Execution Language process of composite web services. Our approach allows specifying the XACML eXtensible Access Control Markup Language policies that determine join points in a BPEL process where security is needed. Subsequently, BPEL flows with the needed security are generated into AspectBPEL security aspects to be weaved in the aforementioned process. The main contributions of our approach are: a describing dynamic security policies using a standard language XACML, b generating automatically the AspectBPEL aspects of the XACML policies and c separating the business and security concerns of composite web services, hence developing and updating them separately at the BPEL side.

An automatic algorithm for human identification using hand X-ray images

In this work we propose a fully automatic algorithm for human identification using hand X-ray images. More specifically, this approach is appropriate to prevent forgeries in high security level systems. The proposed algorithm consists of three steps, namely: (1) segmentation of phalanges, (2) feature extraction using complex Fourier descriptors, (3) identification based on k-nearest neighbor method. To evaluate the proposed protocol, we have constructed a database containing 32 hand X-ray images, acquired using Apollo EZ X-ray machine from 16 non-pathological adult individuals. Preliminary results show that a 100% identification rate is obtained in some specific conditions.

Dynamic programming applied to rough sets attribute reduction

Nowadays, and with the current progress in technologies and business sales, databases with large amount of data exist especially in retail companies. The main objective of this study is to reduce the complexity of the classifi cation problems while maintaining the prediction classifi cation quality. We propose to apply the promising technique Rough Set theory which is a new mathematical approach to data analysis based on classifi cation of objects of interest into similarity classes, which are indiscernible with respect to some features. Since some features are of high interest, this leads to the fundamental concept of “Attribute Reduction”. The goal of Rough set is to enumerate good attribute subsets that have high dependence, discriminating index and signifi cance. The naïve way of is to generate all possible subsets of attribute but in high dimension cases, this approach is very ineff icient while it will require iterations. Therefore, we apply Dynamic programming technique in order to enumerate dynamically the optimal subsets of the reduced attributes of high interest by reducing the degree of complexity. Implementation has been developed, applied, and tested over a 3 years historical business data in Retail Business. Simulations and visual analysis are shown and discussed in order to validate the accuracy of the proposed tool

CIMOR: An automatic segmentation to extract bone tissue in hand x-ray images

This paper presents a new method to segment bone tissue in an X-ray images. The proposed method is completely automatic. First of all, it enhances the contrast of the grayscale image using contrast-limited adaptive histogram equalization. Afterwards, the image intensity values are further modified by removing the background and soft tissue. Then a series of morphological operators, a opening-by-reconstruction followed by a closing-by-reconstruction, are applied to enhance the image by defining foreground objects and clean up the image. Finally holes are filled to preserve the bone structure.

Image compression based on fuzzy segmentation and anisotropic diffusion

In this paper we present a hybrid model for image compression based on fuzzy segmentation and Partial Differential Equations. The main motivation behind our approach is to produce immediate access to objects/features of interest in a high quality decoded image which could be useful on smart devices, for analysis purpose, as well as for multimedia content-based description standards. The image is approximated as a set of uniform regions: The technique will assign well-defined members to homogenous regions in order to achieve image segmentation. The fuzzy c-means (FcM) is a guide to cluster image data. A second stage coding is applied using entropy coding to remove the whole image entropy redundancy. In the decoding phase, we suggest the application of a nonlinear anisotropic diffusion to enhance the quality of the coded image.

Multidimensional segmentation of heterogeneous data

High-throughput methods are producing an ever increasing flood of-omics data that yield a more and more detailed and rich genomic annotation. Combining these data into coherently behaving regions lies at the heart of functional genome annotation efforts. The segmentation problem, which addresses the task of subdividing an ordered sequence of data into homogeneous, approximately constant intervals, therefore has rapidly gained practical importance in computational biology, with a strong emphasis on multi-dimensional data tracks. We suggest a new segmentation method based on decomposition thresholding, and local optimum differentiation, which detects significant breakpoints in the data to identify segment boundaries.

Complexity Reduction and Quality Enhancement in Image Coding

In this paper we propose an image coding approach based on Alternative Fuzzy c-Means. Our main objective is to provide an immediate access to targeted features of interest in a high quality decoded image. This technique is useful for intelligent devices, as well as for multimedia content-based description standards. The use of AFcM reduces the coding time in comparison to the traditional clustering algorithm FcM. A second stage coding is applied using entropy coding to remove the whole image entropy redundancy. In the decoding phase, we suggest the application of a nonlinear anisotropic diffusion, based on Perona-Malik equation, to enhance the quality of the coded image. Qualitative evaluation confirms the validity of the proposed approach.

Linear vs. non-linear dimensionality reduction techniques in predicting class-II MHC peptide binding

A key step in the development of an adaptive immune response to vaccines is the binding of peptides to molecules of the Major Histocompatibility Complex (MHC) for presentation to T lymphocytes, which are thereby activated. Several algorithms have been proposed for such binding predictions, but are limited to a small number of MHC molecules and present imperfect prediction power. We are undertaking an exploration of the power gained by taking advantage of a natural representation of the protein sequence amino acid in terms of their composition, structural and a series of associated physicochemical properties to form a representative descriptor vectors. We are proposing to use dimensionality reduction techniques to preprocess the descriptor vectors before feeding them into well known statistical classifiers for binding prediction. In all cases, coupling dimensionality reduction techniques with the physicochemical properties leads to substantially higher values for our evaluation criteria (Area Under ROC Curve) which means that misclassification errors is reaching lower rates.