Seifedine Kadry

Classification of focal and non focal EEG using entropies

Entropy based features and non linear features are used for classification.NNGE Classifier with optimized features enhances sensitivity.The computation time is very low leading to real time identification. Electroencephalogram (EEG) is the recording of the electrical activity of the brain which can be used to identify different disease conditions. In the case of a partial epilepsy, some portions of the brain is affected and the EEG measured from that portions are called as Focal EEG and the EEG measured from other regions is termed as Non Focal EEG. The identification of Focal EEG assists the doctors in finding the epileptogenic focus and thereby go for surgical removal of those portions of the brain for those who are having drug resistant epilepsy. In this work, we have proposed a classification methodology to classify Focal and Non Focal EEG. We used the Bern Barcelona database and used entropies such as Approximate entropy (ApEn), Sample entropy (SampEn) and Reynis entropy as features. These features were fed into six different classifiers such as Nave Bayes (NBC), Radial Basis function (RBF), Support Vector Machines (SVM), KNN classifier, Non-Nested Generalized Exemplars classifier (NNge) and Best First Decision Tree (BFDT) classifier. It was found that NNge classifier gave the highest accuracy of 98%, sensitivity of 100% and specificity of 96%, which is the highest comparing to other methods in the literature. In addition to the above, the maximum computation time of our features is 0.054 seconds which opens the window for real time processing. Thus our method can be written as a handy software tool towards assisting the physician.

Understanding expert finding systems: domains and techniques

Expert finding can be required for a variety of purposes: finding referees for a conference paper, recommending consultants for a software project, and identifying qualified answerers for a question in online knowledge-sharing communities, to name a few. This paper presents taxonomy of the task of expert finding that highlights the differences between finding experts, from the type of expertise indicator’s point of view. The taxonomy supports deep understanding of different sources of expertise information in the enterprise or online communities; for example, authored documents, emails, online posts, and social networks. In addition, different content and non-content features that characterize the evidence of expertise are discussed. The goal is to guide researchers who seek to conduct studies regarding the different types of expertise indicators and state-of-the-art techniques for expert finding in organizations or online communities. The paper concludes that although researchers have utilized a large number of graph and machine-learning techniques for locating expertise, there are still technical issues associated with the implementation of some of these methods. It also corroborates that combining content-based expertise indicators and social relationships has the benefit of alleviating some of the issues related to identifying and ranking answer experts. The above findings give implications for developing new techniques for expert finding that can overcome the technical issues associated with the performance of current methods.

An efficient image integration algorithm for night mode vision applications

The night mode visible images are often fused with infrared images for increased visual perception and contextual enhancement as the later is equipped with the complimentary information which is otherwise missing due to night mode image acquisition. This technology finds extensive application in the field of armed forces and surveillance. The night mode visible images, due to under-exposure and poor atmospheric conditions are prone to noise and artefacts which leads deterred level of information analysis and extraction. This article not only provides higher visual perception of the individual source images but also proposes an efficient fusion algorithm for visible and infrared images in night mode which is able to generate high quality results with increased focus on the objects of interest competitive with the state-of-the-art methods.

Deep neural network assisted diagnosis of time-frequency transformed electromyograms

Electromyograms (EMG) are recorded electrical signals generated from the muscles and these signals are closely interrelated with the muscle activity and hence are useful for the investigation of neuro-muscular disorders. The feature mining, feature collection and development of classification systems are greatly significant steps in the differentiation of normal and abnormal EMG signals to evaluate the abnormality. In this work, time-frequency domain based features of regular, myopathy and Amyotrophic Lateral Sclerosis (ALS) EMG signals were extracted from four different techniques namely Stockwell-Transform (ST), Wigner-Ville Transform (WVT), Synchro-Extracting Transform (SET) and Short-Time Fourier Transform (STFT). The Particle Swarm Optimization (PSO) with fractional velocity update technique was implemented for feature reduction. Further, the classifier based on the Deep Neural Networks (DNN) was developed by employing the features selected using fractional PSO. Finally, the performance of the DNN was compared with that of the Shallow Neural Network (SNN) classifier. Results of this work demonstrate that, the performance measure of the DNN classifiers is higher than that of the SNN classifier. This work appears to be of good clinical significance since efficient classification techniques are required for the development of robust neuro-muscular diagnosis systems.

A Recent Systematic Review on Simulation Modeling and Emergency Departments

Healthcare, being a complex and huge system, suffers from low quality of care delivered to arriving patients. The quality of care depends on the patient’s condition and the availability of hospital’s resources. Therefore, many authors have studied the problems faced by such systems and emphasized in their articles the importance of a system review for better performance. In healthcare, different departments interact with each other in order to deliver a certain service to arriving patients and provide the recommended care. In particular, the emergency department (ED) is proven to be the busiest unit of the hospital; thus, the exiting problems and recommended solutions are highlighted in this study by a literature systematic review. The main goal of this article is to study the problems that EDs face nowadays and how simulation modeling can interfere in order to alleviate these problems, propose corresponding solutions and increase patient satisfaction.