Ashraf M Elnagar

Ashraf M Elnagar
University of Sharjah | US · Department of Computer Science

About

128
Publications
45,854
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,596
Citations
Citations since 2017
49 Research Items
1126 Citations
2017201820192020202120222023050100150200250300
2017201820192020202120222023050100150200250300
2017201820192020202120222023050100150200250300
2017201820192020202120222023050100150200250300
Introduction
Ashraf M Elnagar currently works at the Department of Computer Science, University of Sharjah. Ashraf does research in Artificial Intelligence, NLP, and Robotics. Their current project is 'Deep Learning for Arabic Language.

Publications

Publications (128)
Article
Full-text available
Capsule Neural Network (CapsNet) models are regarded as efficient substitutes for convolutional neural networks (CNN) due to their powerful hierarchical representation capability. Nevertheless, CNN endure their inability of recording spatial information in spectrograms. The main constraint of CapsNet is related to the compression method which can b...
Article
Modelling the distributional semantics of such a morphologically rich language as Arabic needs to take into account its introflexive, fusional, and inflectional nature attributes that make up its combinatorial sequences and substitutional paradigms. To evaluate such word distributional models, the benchmarks that have been used thus far in Arabic h...
Article
Full-text available
Speech signals carry various bits of information relevant to the speaker such as age, gender, accent, language, health, and emotions. Emotions are conveyed through modulations of facial and vocal expressions. This paper conducts an empirical comparison of performances between the classical classifiers: Gaussian Mixture Model (GMM), Support Vector M...
Article
Full-text available
Social media is becoming a source of news for many people due to its ease and freedom of use. As a result, fake news has been spreading quickly and easily regardless of its credibility, especially in the last decade. Fake news publishers take advantage of critical situations such as the Covid-19 pandemic and the American presidential elections to a...
Article
The Covid-19 pandemic has galvanized scientists to apply machine learning methods to help combat the crisis. Despite the significant amount of research there exists no comprehensive survey devoted specifically to examining deep learning methods for Covid-19 forecasting. In this paper, we fill the gap in the literature by reviewing and analyzing the...
Article
Full-text available
There are various reasons why vaccine fear has resulted in public rejection. Students have raised concerns about vaccine effectiveness, leading to hesitation when it comes to vaccination. Vaccination apprehension impacts students' perceptions, which has an impact on the acceptability of an e-learning platform. As a result, the goal of this study is...
Article
Full-text available
Speaker identification systems perform almost ideally in neutral talking environments. However, these systems perform poorly in stressful talking environments. In this paper, we present an effective approach for enhancing the performance of speaker identification in stressful talking environments based on a novel radial basis function neural networ...
Preprint
Full-text available
Social media is becoming a source of news for many people due to its ease and freedom of use. As a result, fake news has been spreading quickly and easily regardless of its credibility, especially in the last decade. Fake news publishers take advantage of critical situations such as the Covid-19 pandemic and the American presidential elections to a...
Article
Full-text available
This study makes use of a cohesive yet innovative research model to identify the determinants of the adoption of smart watches using constructs from the Technology Acceptance Model (TAM) and constructs of smartwatches, including effectiveness, content richness, and personal innovativeness. The chief objective of the study was to encourage the use o...
Preprint
Speaker recognition systems are widely used in various applications to identify a person by their voice; however, the high degree of variability in speech signals makes this a challenging task. Dealing with emotional variations is very difficult because emotions alter the voice characteristics of a person; thus, the acoustic features differ from th...
Article
Full-text available
Speaker recognition systems are widely used in various applications to identify a person by their voice; however, the high degree of variability in speech signals makes this a challenging task. Dealing with emotional variations is very difficult because emotions alter the voice characteristics of a person; thus, the acoustic features differ from th...
Article
Full-text available
The process of tagging a given text or document with suitable labels is known as text categorization or classification. The aim of this work is to automatically tag a news article based on its vocabulary features. To accomplish this objective, 2 large datasets have been constructed from various Arabic news portals. The first dataset contains of 90k...
Article
Full-text available
The rapid growth of electronic documents has resulted from the expansion and development of internet technologies. Text-documents classification is a key task in natural language processing that converts unstructured data into structured form and then extract knowledge from it. This conversion generates a high dimensional data that needs further an...
Preprint
Full-text available
In this work, we conducted an empirical comparative study of the performance of text-independent speaker verification in emotional and stressful environments. This work combined deep models with shallow architecture, which resulted in novel hybrid classifiers. Four distinct hybrid models were utilized: deep neural network-hidden Markov model (DNN-H...
Article
Full-text available
In this work, we conducted an empirical comparative study of the performance of text-independent speaker verification in emotional and stressful environments. This work combined deep models with shallow architecture, which resulted in novel hybrid classifiers. Four distinct hybrid models were utilized: deep neural network-hidden Markov model (DNN-H...
Preprint
Full-text available
This work presents a detailed comparison of the performance of deep learning models such as convolutional neural networks (CNN), long short-term memory (LSTM), gated recurrent units (GRU), their hybrids, and a selection of shallow learning classifiers for sentiment analysis of Arabic reviews. Additionally, the comparison includes state-of-the-art m...
Article
Full-text available
This work presents a detailed comparison of the performance of deep learning models such as convolutional neural networks, long short-term memory, gated recurrent units, their hybrids, and a selection of shallow learning classifiers for sentiment analysis of Arabic reviews. Additionally, the comparison includes state-of-the-art models such as the t...
Preprint
Full-text available
There are several reasons why the fear of vaccination has caused population rejection. Questions have been raised by students regarding the effectiveness of vaccines, which in turn has led to vaccination hesitancy. Students perceptions are influenced by vaccination hesitancy, which affects the acceptance of e-learning platforms. Hence, this researc...
Article
Full-text available
Text Generation using Generative Adversarial Networks (GANs) has been successful in domains such as sentiment analysis using Sentimental GAN (SentiGAN) model. We adopt a similar model to generate sentences for five regional Arabic dialects (Egypt, Gulf, Maghreb, Levant, and Iraq). The objective is to overcome the scarcity of richly annotated Dialec...
Conference Paper
Automatic document categorization gains more importance in view of the plethora of textual documents added constantly on the web. Text categorization or classification is the process of automatically tagging a textual document with most relevant label. Text categorization for Arabic language become more challenging in the absence of large and free...
Chapter
Full-text available
Recently, Sentiment Analysis (SA) in Arabic has gained considerable interest in the research community. Several surveys were conducted concerning Arabic sentiment analysis at one hand and the Arabic dialects on the other hand. However, analyzing the Arabic dialect sentiment analysis in social media context is still questioned and requires further e...
Chapter
Full-text available
Text classification is the process of automatically tagging a textual document with the most relevant set of labels. This work aims to automatically map an input document based on its vocabulary features to multiple tags. To achieve this goal, a large dataset has been constructed from various Arabic news portals. The dataset has over 290k multi-tag...
Chapter
Sentiment Analysis is the process of classifying data according to its sentiment polarity as positive or negative or multiclass. In this paper, our goal is twofold: Firstly, to experiment and evaluate different approaches to dialectal Arabic sentiment analysis, including various classifiers and features. Secondly, we have curated a dataset of Arabi...
Article
Full-text available
It is becoming increasingly difficult to know who is working on what and how in computational studies of Dialectal Arabic. This study comes to chart the field by conducting a systematic literature review that is intended to give insight into the most and least popular research areas, dialects, machine learning approaches, neural network input featu...
Article
Full-text available
Language disparities in Arabic-speaking individuals with Speech and Language Impairment (SLI) can increase the limitations faced by SLI specialists. There is a need to improve neurofeedback interventions for patients who belong to this group. In contrast to studies that rely solely on behavioral measures, neurofeedback training can capture cognitiv...
Article
Full-text available
Language disparities in Arabic-speaking individuals with Speech and Language Impairment (SLI) can increase the limitations faced by SLI specialists. There is a need to improve neurofeedback interventions for patients who belong to this group. In contrast to studies that rely solely on behavioral measures, neurofeedback training can capture cognitiv...
Article
Full-text available
Language disparities in Arabic-speaking individuals with Speech and Language Impairment (SLI) can increase the limitations faced by SLI specialists. There is a need to improve neurofeedback interventions for patients who belong to this group. In contrast to studies that rely solely on behavioral measures, neurofeedback training can capture cognitiv...
Article
Full-text available
Student admission problem is very important in educational institutions. This paper addresses machine learning models to predict the chance of a student to be admitted to a master's program. This will assist students to know in advance if they have a chance to get accepted. The machine learning models are multiple linear regression, k-nearest neigh...
Article
Full-text available
The automatic identification and verification of speakers through representative audio continue to gain the attention of many researchers with diverse domains of applications. Despite this diversity, the availability of classified and categorized multi-purpose Arabic audio libraries is scarce. Therefore, we introduce a large Arabic-based audio clip...
Conference Paper
Full-text available
In this paper, an Arabic dataset known as ANERCorp is classified into three name entities: Person, Location, and Organization. This classification process aims to design a model that used to facilitate the searching tasks of the Arabic named entities. The classification process was done by proposing a hybrid model which consists of Radial Basis Fun...
Conference Paper
Full-text available
The gas turbine is the most important part of the combined cycle power plant that generates the total electric power from the fuel to provide it to the houses, schools, and other facilities in the country. Thus, it is important to predict the power to increase and maximize profit. This paper compares four machine learning algorithms which are Multi...
Article
Full-text available
The fields of machine learning and Web technologies have witnessed significant development in the last years. This caused a ceaseless and rapid growth in sharing of the views and experience regarding services or products over the Internet in different domains. Therefore, a torrential flow of online data is available for analytical studies. Sentimen...
Article
Full-text available
This paper introduces a thorough study of classical and deep learning algorithms implemented for multi-class speaker identification and verification of Qur’anic audio clips. Thirty different reciters and twelve imitators, of top reciters, were evaluated in the study. In addition to identifying the reciter, our objective is to first evaluate differe...
Chapter
Full-text available
In this review, significant literature surveys on machine learning (ML) and deep learning (DL) techniques for network analysis of intrusion detection are explained. In addition, it presents a short tutorial explanation on every ML/DL method. Data holds a significant position in ML/DL methods; hence this paper highlights the datasets used in machine...
Chapter
Full-text available
One of the developing fields of the present times is educational data mining that pertains to developing methods that help in examining various kinds of data obtained from the educational field. A vital part is played by data mining in the education field, particularly when behavior is being assessed in an online learning setting. This is because d...
Chapter
Full-text available
This paper introduces a comparative analysis for a supervised classification system of Quranic audio clips of several reciters. Other than identifying the reciter or the closest reciter to an input audio clip, the study objective is to evaluate and compare different classifiers performing the stated recognition. With the widespread of multimedia ca...
Article
Text classification or categorization is the process of automatically tagging a textual document with most relevant labels or categories. When the number of labels is restricted to one, the task becomes single-label text categorization. However, the multi-label version is challenging. For Arabic language, both tasks (especially the latter one) beco...
Article
Full-text available
Text Classification is one of the most popular Natural Language Processing (NLP) tasks. Text classification (aka categorization) is an active research topic in recent years. However, much less attention was directed towards this task in Arabic, due to the lack of rich representative resources for training an Arabic text classifier. Therefore, we in...
Chapter
Arabic language suffers from the lack of available large datasets for machine learning and sentiment analysis applications. This work adds to the recently reported large dataset BRAD, which is the largest Book Reviews in Arabic Dataset. In this paper, we introduce HARD (Hotel Arabic-Reviews Dataset), the largest Book Reviews in Arabic Dataset for s...
Article
Full-text available
Recently, the vast use of social media and the high availability of internet access have produced a considerably different textual data from the formal and standard data on the Web. This includes various Arabic dialectal languages, which are the native spoken languages of Arabic speakers. The presence of textual Arabic dialectal languages on the We...
Conference Paper
Smart robotics platforms in human environments usually develop a complete model of the surrounding environment. Exploring and modeling the environment required planning of best view positions as well as a navigation strategy that assures the completeness and high quality of the construed model. In this paper, we describe a next-best-view planning f...
Article
Full-text available
The incidence of esophageal cancer varies widely in the world. In the Middle East, Africa, and Asia and parts of Europe, squamous cell carcinoma of the esophagus dominates the esophageal cancer landscape. Worldwide the rates are highest in Northern China, South Africa, Turkey and Iran. In the United States, the black population has a five-fold high...
Article
Full-text available
Introduction Helicobacter pylori is an important causative factor in gastric carcinogenesis; its role in extra-gastric gastrointestinal malignancies such as oesophageal cancer is controversial. H. pylori is thought to cause extensive gastric atrophy associated with squamous cell carcinoma of the oesophagus. We conducted a study to determine the pre...
Article
Full-text available
Patients with cirrhosis of the liver usually present with a small shrunken liver and a large spleen. The presence of an unusually huge liver should prompt the treating doctor to look for another cause, as this may be treatable and improve the patient's outcome. In South Africa tuberculosis and lymphoma in the presence of HIV infection should be exc...
Article
Helicobacter pylori is an important causative factor in gastric carcinogenesis, its role in extra-gastric gastrointestinal malignancies such as oesophageal cancer, is controversial. H. pylori is thought to be associated with an increased risk of squamous cell carcinoma of the oesophagus. We conducted a case control study to determine the prevalence...
Conference Paper
Tele-robotic localization systems vary in implementation, but the cost of building such solutions is high. Therefore, utilizing such solutions in complex areas becomes a very difficult choice. Can we send a high-end costly solution to a hazardous or military location where it can be destroyed or lost? Or is it feasible to use such solution in routi...
Article
Full-text available
In this study, we focus on two objectives: (1) To raise awareness of the computing field in three groups of students-high school, freshmen in their first term of university (i.e., students taking the Introduction to IT course) and freshmen in their second term of university (i.e., students taking the Programming I course); and (2) to organize visib...
Article
Full-text available
We propose a motion planning gap-based algorithms for mobile robots in an unknown environment for exploration purposes. The results are locally optimal and sufficient to navigate and explore the environment. In contrast with the traditional roadmap-based algorithms, our proposed algorithm is designed to use minimal sensory data instead of costly on...
Conference Paper
In robotics, Bug/Gap algorithms have shown good results as an alternative for traditional roadmap techniques, with a promising future, these results were locally optimal and sufficient to navigate and achieve goals. However, such algorithms have not been applied, or tested, on all types of environments. This work is aiming at improving and adding t...
Conference Paper
Multi-robots coordinated motion is gaining more attention in the robotics research community because of its significance to a variety of applications such as formation control, evacuation and object transformation. Even in situations where a single robot may accomplish the task required, the use of multiple robots offers the ability to parallelize...
Conference Paper
Active learning methodologies have evolved over the years in order to increase student input in the learning process. One example is Team-Based Learning (TBL), which fosters active learning and has become increasingly popular in modern curricula. However, in developing nations, the well-established lecture-based teaching paradigm is the prominent m...
Conference Paper
This paper sheds the light on an attempt to use a pedagogy integrating Team-Based Learning (TBL) for effective learning and hands-on experience in an introductory programming course. We have adopted a modified version of TBL to study its effect on students learning and to examine how teams intra- and inter-team active interactions influence student...
Article
This paper presents a novel plagiarism detection system for Arabic text-based documents, Iqtebas 1.0. This is a primary work dedicated for plagiarism of Arabic based documents. Arabic is a rich morphological language that is among the top used languages in the world and in the Internet as well. Given a document and a set of suspected files, our goa...
Conference Paper
This paper presents a novel plagiarism detection system for Arabic text-based documents, Iqtebas 1.0. This is a primary work dedicated for plagiarism of Arabic based documents. Arabic is a rich morphological language that is among the top used languages in the world and in the Internet as well. Given a document and a set of suspected files, our goa...
Article
Full-text available
The segmentation of individual words into characters is a vital process in handwritten character recognition systems. In this paper, a novel approach is proposed to segment handwritten Arabic text (words). We consider the "Naskh" font style. The segmentation algorithm employs seven agents in order to detect regions where segmentation is illegal. Fe...
Article
This paper presents a graph-based grading system for Java introductory programming courses, eGrader. The as- sessment process undergoes two stages in succession. Namely, dynamically and statically. This analysis leads to producing detailed feedback reports to both students and instructors. The student report provides a detailed feedback on the subm...
Conference Paper
This paper presents a graph-based grading system for Java introductory programming courses, eGrader. This system grades submission both dynamically and statically to ensure a complete and through grading job. While dynamic analysis is based on JUnit framework, the static analysis is based on the graph representation of the program and its quality w...
Article
Full-text available
In this paper, we describe an algorithm for predicting future positions and orientation of a moving object in a time-varying environment using an autoregressive model (ARM). No constraint is placed on the obstacles motion. The model addresses prediction of translational and rotational motions. Rotational motion is repre-sented using quaternions rat...
Conference Paper
This paper presents a novel approach for the problem of tracking a moving target in a global dynamic environment. The robot has to move such that it keeps the target visible for the longest time possible, and at the same time, avoid colliding with any of the moving obstacles. This paper presents a solution that is based on the idea of three interac...
Conference Paper
This paper presents a novel approach for the problem of tracking a moving target in a dynamic environment. The robot has to move such that it keeps the target visible for the longest time possible, and at the same time, avoid colliding with any of the moving obstacles. This paper presents a solution that is based on the idea of three interacting co...
Conference Paper
Learning how to program is a universal problem that is facing many students in introductory programming courses. This multinational problem created the need for an effective and easy to use learning system. The system introduced in this paper, Java Learning System using Dependence Graphs (JLearn-DG), teaches students the basic concepts of programmi...
Conference Paper
The segmentation of words into characters is a main stage in character recognition systems. In this paper, a novel approach is proposed to segment Arabic words, written in Naskh handwriting style. The segmentation algorithm is based on seven agents which cooperate to detect regions where segmentation is illegal. Then, end point features are extract...
Article
Full-text available
The educational community across the world is facing the increasing problem of plagiarism. The proposed Plagiarism Detection Engine for Java (PDE4Java) detects code-plagiarism by applying data mining techniques. The engine consists of three main phases; Java tokenisation, similarity measurement and clustering. It has an optional default tokeniser t...
Article
We introduce an effective computer aided learning visual tool (CALVT) to teach graph-based applications. We present the robot motion planning problem as an example of such applications. The proposed tool can be used to simulate and/or further to implement practical systems in different areas of computer science such as graphics, computational geome...
Conference Paper
This paper presents a practical algorithm for evader detection and tracking using one or more pursuers. The solution employs two advanced data structures. The first one is the rapidly-exploring random tree (RRT). It is constructed randomly but evenly distributed to generate a roadmap that captures the connectivity of the free space. The second data...
Article
In this paper, we present a novel near-optimal art gallery-based algorithm for placing a small (but sufficient) number of robot configurations to plan its path in a 2D environment cluttered with obstacles. The solution of the problem is inspired from the well-known art gallery problem (AGP) which asks to position the minimum number of guards requir...