Ghada Khoriba

Bio: Ghada Khoriba is an academic researcher from Helwan University. The author has contributed to research in topics: Local optimum & Support vector machine. The author has an hindex of 5, co-authored 14 publications receiving 238 citations.

A novel chaotic salp swarm algorithm for global optimization and feature selection

Abstract: Salp Swarm Algorithm (SSA) is one of the most recently proposed algorithms driven by the simulation behavior of salps. However, similar to most of the meta-heuristic algorithms, it suffered from stagnation in local optima and low convergence rate. Recently, chaos theory has been successfully applied to solve these problems. In this paper, a novel hybrid solution based on SSA and chaos theory is proposed. The proposed Chaotic Salp Swarm Algorithm (CSSA) is applied on 14 unimodal and multimodal benchmark optimization problems and 20 benchmark datasets. Ten different chaotic maps are employed to enhance the convergence rate and resulting precision. Simulation results showed that the proposed CSSA is a promising algorithm. Also, the results reveal the capability of CSSA in finding an optimal feature subset, which maximizes the classification accuracy, while minimizing the number of selected features. Moreover, the results showed that logistic chaotic map is the optimal map of the used ten, which can significantly boost the performance of original SSA.

Credibility Detection in Twitter Using Word N-gram Analysis and Supervised Machine Learning Techniques

Abstract: With the evolution of social media platforms, the Internet is used as a source for obtaining news about current events. Recently, Twitter has become one of the most popular social media platforms that allows public users to share the news. The platform is growing rapidly especially among young people who may be influenced by the information from anonymous sources. Therefore, predicting the credibility of news in Twitter becomes a necessity especially in the case of emergencies. This paper introduces a classification model based on supervised machine learning techniques and word-based N-gram analysis to classify Twitter messages automatically into credible and not credible. Five different supervised classification techniques are applied and compared namely: Linear Support Vector Machines (LSVM), Logistic Regression (LR), Random Forests (RF), Naïve Bayes (NB) and K-Nearest Neighbors (KNN). The research investigates two feature representations (TF and TF-IDF) and different word N-gram ranges. For model training and testing, 10-fold cross validation is performed on two datasets in different languages (English and Arabic). The best performance is achieved using a combination of both unigrams and bigrams, LSVM as a classifier and TF-IDF as a feature extraction technique. The proposed model achieves 84.9% Accuracy, 86.6% Precision, 91.9% Recall, and 89% F-Measure on the English dataset. Regarding the Arabic dataset, the model achieves 73.2% Accuracy, 76.4% Precision, 80.7% Recall, and 78.5% F-Measure. The obtained results indicate that word N-gram features are more relevant for the credibility prediction compared with content and source-based features, also compared with character N-gram features. Experiments also show that the proposed model achieved an improvement when compared to two models existing in the literature.

Improved White Blood Cells Classification based on Pre-trained Deep Learning Models

Abstract: Leukocytes, or white blood cells (WBCs), are microscopic organisms that fight against infectious disease, bacteria, viruses, and others. The manual method to classify and count WBCs is tedious, time-consuming and may has inaccurate results, whereas the automated methods are costly. The objective of this work is to automatically identify and classify WBCs in a microscopic image into four types with higher accuracy. BCCD is the used dataset in this study, which is a scaleddown blood cell detection dataset. BCCD is firstly pre-processed by passing through several processes such as segmentation and augmentation,then it is passed to the proposed model. Our model combines the privilege of deep models in automatically extracting features with the higher classification accuracy of traditional machine learning classifiers.The proposed model consists of two main layers; a shallow tuning pre-trained model and a traditional machine learning classifier on top of it. Here, ten different pretrained models with six different machine learning are used in this study. Moreover, the fully connected network (FCN) of pretrained models is used as a baseline classifier for comparison. The evaluation process shows that the hybrid between MobileNet-224 as feature extractor with logistic regression as classifier has a higher rank-1 accuracy with 97.03%. Besides, the proposed hybrid model outperformed the baseline FCN with 25.78% on average.

A novel Chaotic Equilibrium Optimizer Algorithm with S-shaped and V-shaped transfer functions for feature selection

Abstract: Feature selection is considered one of the challenging machine learning tasks. Selecting a subset of relevant features can significantly influence on the classification accuracy and computational time of any machine learning algorithm. This paper introduces a novel wrapper-based feature selection algorithm based on using Equilibrium Optimizer (EO) algorithm and chaos theory. The principles of chaos theory is used to overcome the slow convergence rate and the entrapment in local optima problems of the original EO. Thus, ten different chaotic maps are embedded in the optimization process of EO to overcome these problems and achieve a more effective and robust search mechanism. Also, eight different S-shaped and V-shaped transfer functions are employed. The performance of the proposed hybrid algorithm is tested on fifteen benchmark datasets and four other large scale NLP datasets collected from the UCI machine learning repository. The experimental results showed the capability of the proposed hybrid algorithm. Moreover, the results proved that the proposed hybrid algorithm is a higly competitive algorithm and can find the optimal feature subset, which minimizes the number of selected features while maximizes the classification accuracy.

Supervised Learning Approach for Twitter Credibility Detection

Abstract: Twitter is the most popular micro-blogging medium that allows users to exchange short messages, provides a platform for public people to share the news. Nowadays, Twitter counts with an average of 328 million monthly active users and is growing rapidly. Detecting the credibility of shared information on Twitter becomes a necessity, especially during high impact events. In this paper a classification model based on supervised machine learning techniques is proposed to detect credibility. The proposed model uses an extensive set of features including both content-based and source-based features. The research compares the performance of five different machine learning classifiers using three feature sets: content based, source based and a combination of both sets. The best performance is achieved when using a combined set of features and applying Random Forests as a classifier with accuracy 78.4%, precision 79.6%, recall 91.6% and f1-measure 85.2%. Experiments also revealed that the proposed model achieves improvement of 22% when compared to CRF which applies the same approach in terms of F1-measure. Feature analysis is presented to highlight the importance of the source-based features compared with the content-based features as deciders for credibility.

Binary butterfly optimization approaches for feature selection

Abstract: In this paper, binary variants of the Butterfly Optimization Algorithm (BOA) are proposed and used to select the optimal feature subset for classification purposes in a wrapper-mode. BOA is a recently proposed algorithm that has not been systematically applied to feature selection problems yet. BOA can efficiently explore the feature space for optimal or near-optimal feature subset minimizing a given fitness function. The two proposed binary variants of BOA are applied to select the optimal feature combination that maximizes classification accuracy while minimizing the number of selected features. In these variants, the native BOA is utilized while its continuous steps are bounded in a threshold using a suitable threshold function after squashing them. The proposed binary algorithms are compared with five state-of-the-art approaches and four latest high performing optimization algorithms. A number of assessment indicators are utilized to properly assess and compare the performance of these algorithms over 21 datasets from the UCI repository. The experimental results confirm the efficiency of the proposed approaches in improving the classification accuracy compared to other wrapper-based algorithms, which proves the ability of BOA algorithm in searching the feature space and selecting the most informative attributes for classification tasks.

Recognition of COVID-19 disease from X-ray images by hybrid model consisting of 2D curvelet transform, chaotic salp swarm algorithm and deep learning technique

Abstract: The novel coronavirus disease 2019 (COVID-19), detected in Wuhan City, Hubei Province, China in late December 2019, is rapidly spreading and affecting all countries in the world Real-time reverse transcription-polymerase chain reaction (RT-PCR) test has been described by the World Health Organization (WHO) as the standard test method for the diagnosis of the disease However, considering that the results of this test are obtained between a few hours and two days, it is very important to apply another diagnostic method as an alternative to this test The fact that RT-PCR test kits are limited in number, the test results are obtained in a long time, and the high probability of healthcare personnel becoming infected with the disease during the test, necessitates the use of other diagnostic methods as an alternative to these test kits In this study, a hybrid model consisting of two-dimensional (2D) curvelet transformation, chaotic salp swarm algorithm (CSSA) and deep learning technique is developed in order to determine the patient infected with coronavirus pneumonia from X-ray images In the proposed model, 2D Curvelet transformation is applied to the images obtained from the patient's chest X-ray radiographs and a feature matrix is formed using the obtained coefficients The coefficients in the feature matrix are optimized with the help of the CSSA and COVID-19 disease is diagnosed by the EfficientNet-B0 model, which is one of the deep learning methods Experimental results show that the proposed hybrid model can diagnose COVID-19 disease with high accuracy from chest X-ray images