Showing papers by "Hossam M. Zawbaa published in 2017"

Feature selection approach based on whale optimization algorithm

Abstract: In this paper, a feature selection system is introduced applies the whale optimization algorithm (WOA). WOA is a recently introduced meta-heuristic optimization algorithm that mimics the natural behavior of the humpback whales. The proposed model applies the wrapper-based method to reach the optimal subset of features. This technique was applied to find the best feature subset that maximizes the accuracy of the classification while preserving the minimum number of features. The proposed model is compared with the particle swarm optimization (PSO) and genetic algorithm (GA) using a number of assessment indicators on 16 different data-sets from UCI data repository. The results demonstrate the advantage of the introduced algorithm compared to the other optimizers.

Multi-objective retinal vessel localization using flower pollination search algorithm with pattern search

Abstract: This paper presents a multi-objective retinal blood vessels localization approach based on flower pollination search algorithm (FPSA) and pattern search (PS) algorithm. FPSA is a new evolutionary algorithm based on the flower pollination process of flowering plants. The proposed multi-objective fitness function uses the flower pollination search algorithm (FPSA) that searches for the optimal clustering of the given retinal image into compact clusters under some constraints. Pattern search (PS) as local search method is then applied to further enhance the segmentation results using another objective function based on shape features. The proposed approach for retinal blood vessels localization is applied on public database namely DRIVE data set. Results demonstrate that the performance of the proposed approach is comparable with state of the art techniques in terms of accuracy, sensitivity, and specificity with many extendable features.

A proposed whale search algorithm with adaptive random walk

Abstract: In this paper, a variant of the recently introduced whale optimization algorithm (WOA) was proposed based on adaptive switching of random walk per individual search agent. WOA is recently proposed bio-inspired optimizers that employ two different random walks. The original optimizer stochastically switches between the two random walk at each iteration regardless of the search agents performance and regardless of the fitness terrain around it. In the proposed adaptive walk whale optimization algorithm (AWOA), an adaptive switching between the two random walk is recommended based on the agent's performance. Moreover, a random explorative switch of the walk is applied to allow search agents to try different walks. The proposed AWOA was benchmarked using 29 standard test functions with uni-modal, multi-modal, and composite test functions. Performance over such functions proves the capability of the proposed variant to outperform the original WOA.

Diagnosis of breast cancer using secured classifiers

Abstract: One of the most important tasks for variant approaches such as text categorization, voice recognition, image processing, proteins structure predictions, microarray gene expression and so on is classification. The majority of the current supervised classification techniques are based on traditional statistics, that can provide perfect results when the sample size is tending to infinity. However, samples can be acquired if only they are finite in practice. In this paper, we applied four different classifiers on the patients' data collected. The data consists of breast cancer parameters of 423 Egyptian females. This study aimed to early detect the existence of breast cancer in Egyptian society. After measuring the accuracy of each classifier across all classes, we concluded that ANN classifier can be considered as the nearly best classifier with 95% 72% and 81% accuracy to class 1, class 2 and class 3 respectively.

Hybrid Biometrics and Watermarking Authentication

Abstract: There are many tools and techniques that can support management in the information security field. In order to deal with any kind of security, authentication plays an important role. In biometrics, a human being needs to be identified based on some unique personal characteristics and parameters. In this book chapter, the researchers will present an automatic Face Recognition and Authentication Methodology (FRAM). The most significant contribution of this work is using three face recognition methods; the Eigenface, the Fisherface, and color histogram quantization. Finally, the researchers proposed a hybrid approach which is based on a DNA encoding process and embedding the resulting data into a face image using the discrete wavelet transform. In the reverse process, the researchers performed DNA decoding based on the data extracted from the face image. Kareem Kamal A. Ghany Beni-Suef University, Egypt Hossam M. Zawbaa Babes-Bolyai University, Romania Hybrid Biometrics and Watermarking Authentication