Mustafa Ali Abuzaraida
@misuratau.edu.ly
Department of Computer Science/ Faculty of Information Technology
Misurata University
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Science, Computer Science Applications, Artificial Intelligence
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Adib Habbal, Mohamed Khalif Ali, and Mustafa Ali Abuzaraida
Elsevier BV
Abdullah Habberrih and Mustafa Ali Abuzaraida
Springer Nature Singapore
Abdulrahman Alkandari, Adel Alfoudery, Mustafa Ali Abuzaraida, and Abdullah Alshehab
Seventh Sense Research Group Journals
Drivers of cars always face issues and some difficulties during driving the car on the road with their car’s tires. Puncture of tires, tube burst, or bends in rims of tires are actions or events surely lead to complete stop moving the car, and usually without earlier notification. The main idea of doing this study is to design a robot which acts as a mechanic to facilitate change tires and to avoid any issues with the removal or replacement problem of the tire. Plus, that many people don’t have the required skills to change the tire easily and fast, which indeed may cause more problems and time-consuming. The Robot will be able to carry up the car exactly like the jack, small motor to remove the old tire and install the new tire. The robot will be developed to replace the mechanic in changing tires, and to solve this problem which considered as a real problem for many people.
Mohamad Asyraf Noorza Bin Mohd Tamron, Zainab S. Attarbashi, Mustafa Ali Abuzaraida, Nesrine Atitallah, Saman Iftikhar, Dini Oktarina Dwi Handayani, and Atikah Balqis Binti Basri
IEEE
The advent of the Internet of Things (loT) has opened up a realm of possibilities in developing globally accessible systems and devices. With the current state of internet speeds, these systems offer real-time control, making them more powerful than ever. Simultaneously, the healthcare sector has been witnessing notable advancements, but it also grapples with an increasing number of health issues, with heart problems standing out as a prominent concern in many countries. These problems manifest in various symptoms, some of which can lead to more serious conditions, such as irregular heartbeats. In response to these challenges and leveraging cutting-edge technology, researchers have embarked on endeavors to enhance healthcare devices and render them more readily available to medical professionals. This paper explores the merging of loT technology with healthcare, specifically focusing on the development of a system designed to monitor and record a patient’s heartbeat. This is achieved through the deployment of a Heartbeat/SpO2 Sensor, and the data is seamlessly transmitted to a mobile application accessible remotely. The outcomes of this study demonstrate that the heartbeat data captured by Arduino is effectively transmitted to the cloud, meeting the system’s predefined objectives. This represents a significant stride in harnessing loT’s potential to enhance healthcare practices and patient monitoring.
Zainab S. Attarbashi, Tharshaan A-L Thamodharan, Mustafa Ali Abuzaraida, Saman Iftikhar, Noof Abdulaziz Alansari, Atikah Balqis Binti Basri, and Dini Oktarina Dwi Handayani
IEEE
The idea of using the current technologies to build more sustainable smart cities has gained great popularity. One of attractive fields is Internet of Things applications to control vehicle traffic and parking which reduce energy consumption in smart cities. This paper presents an android mobile application system that allows users to check the availability and location of parking spots by using their smartphones. Main tools used for this project are the Arduino UNO and mobile application running with Android. Sensors were used to sense if the spot is empty, and then send that info to the mobile application. As the empty place is discovered to be vacant it is distinguished utilizing ultrasonic sensors which report it further. The system would not help the user to book parking spot but would show the availability of parking spot to reduce the searching time. This Smart Parking System is a basic prototype which can be improved later for real system by connecting the system to a GPS-based application which will direct the user to the spot itself and it can further be improved by using artificial intelligence to highlight different spots to different users.
Abdulrahman Alkandari, Mohammed Alahmad, Nayfa almutairi, Mustafa Ali Abuzaraida, and Danah AlMansou
Seventh Sense Research Group Journals
Ibrahim Nasir Mahmood and Mustafa Ali Abuzaraida
International Association of Online Engineering (IAOE)
E-learning became the main medium of education in the world for the past two years. COVID-19 virus has pushed all the universities and academic institutions to utilize and activate E-learning platforms and systems. The sudden and urgent transformation from the regular traditional learning system to E-learning system has involved many challenges and limitations. Therefore, the need to evaluate and enhance the current E-learning mechanism in Iraq became very urgent and critical need. The target level was students at higher education institutes which include university students in Basra city. The data collected based on students’ evaluation and opinions about E-learning based on their interaction and usage during two years under COVID-19 spread era. This research involved applying data mining techniques to sample dataset and utilizing the obtained results as feedback for a proposed model suggested by the authors to measure adaptability. The proposed model is derived from the idea of the Technology Acceptance Model (TAM) with focus on the positivity as the main factor to measure adaptability. The results of the research showed approximate adaptation level of 52% which is very close compared to the actual situation in real life which involve limitations and challenges faced by Iraqi students.
Nur Anisah Binti Ramli, Maria Jasmin Binti Mohamed Jamil, Nur Nazifa Binti Zhamri, and Mustafa Ali Abuzaraida
IOP Publishing
Abstract In this paper, we measure the performance of supervised learning algorithms on imbalanced class datasets. Supervised learning is considered to be the most advanced and mature from other types of learning in machine learning. On the other hand, imbalanced class data sets refer to an unequal amount of data for each class in the data sets. Many real-world datasets exhibit an imbalanced class distribution. Hence, this paper aims to compare the supervised learning algorithms in classifying the output for imbalanced dataset. This paper also focused on finding the significance of balancing the dataset to the results. This study is conducted by using three different datasets and made a comparison with three supervised learning algorithms chosen which are Logistic Regression, Random Forest and k-Nearest Neighbours. In the experiments, all three datasets used are labelled data with imbalanced class. Due to the imbalanced class for all datasets chosen, a sampling technique with combination of under-sampling and oversampling is implemented to all datasets in data preparation steps. The performance of the algorithms is measured through Classification Accuracy (CA) value. From the experiments, it is proven that Random Forest shown the best results, for both imbalanced and balanced datasets.
Mustafa Ali Abuzaraida, Mohammed Elmehrek, and Esam Elsomadi
Institute of Advanced Engineering and Science
With advances in machine learning techniques, handwriting recognition systems have gained a great deal of importance. Lately, the increasing popularity of handheld computers, digital notebooks, and smartphones give the field of online handwriting recognition more interest. In this paper, we propose an enhanced method for the recognition of Arabic handwriting words using a directions-based segmentation technique and discrete cosine transform (DCT) coefficients as structural features. The main contribution of this research was combining a total of 18 structural features which were extracted by DCT coefficients and using the k-nearest neighbors (KNN) classifier to classify the segmented characters based on the extracted features. A dataset is used to validate the proposed method consisting of 2500 words in total. The obtained average 99.10% accuracy in recognition of handwritten characters shows that the proposed approach, through its multiple phases, is efficient in separating, distinguishing, and classifying Arabic handwritten characters using the KNN classifier. The availability of an online dataset of Arabic handwriting words is the main issue in this field. However, the dataset used will be available for research via the website.
Ibrahim Nasir Mahmood, Hussein Ali Aliedane, and Mustafa Ali Abuzaraida
International Association of Online Engineering (IAOE)
<p class="0abstract">Due to the increased rate of fire accidents which cause many damages and losses to people souls, material, and property in Basra city. The necessity of analyzing and mining the data of the fire accidents became an urgent need to find a solution. The need increased for a solution that helps to mitigate and reduce the number of accidents. In this paper, data mining techniques and applications including data preprocessing, data cleaning, and data exploration have been applied. Data mining applications is performed to analyze and discover the hidden knowledge in ten years of data (fire accidents happened from 2010 – 2019) which is approximately 20k record of accidents. These data mining techniques along with the association rules algorithm is applied on the dataset. The applied approach and techniques resulted in discovering the patterns and the nature of the fire accidents in Basra city. It also helped to reach to recommendations and resolutions for mitigating the fire accidents and its occurrence rate.</p>
Mustafa Ali Abuzaraida, , Osama Mohamed Elrajubi, and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Recently, deep learning approaches have been getting more attention in many research fields. Medical imaging field has been attracting widely by deep learning techniques. An example of this field categories are images segmentations, images registration, images classification and retrieval of images database. This paper is presenting a number of experiments to classify rental images using Convolutional Neural Networks (CNN). These images of retinal could contain laser marks which left by the action of the laser on the surface of the retina. (CNN) is defined as trainable multi-stages architecture composed of multiple stages. The inputs and outputs of each stage are a set of arrays which called the feature maps. For the outputs, every feature map is representing a unique feature which extracted from all the regions which located on the input. Basically, every stage is consisted of three layers which are: a filter bank, a non linearity, and a layer of feature pooling. However, the classic (CNN) is normally consisting of three or less number of layers. The results accuracy were appropriate of more than 90%. As a summary of this paper, a number of considerations are listed for possible improvements and future developments.
Dini Handayani, Normi Sham Awang Abu Bakar, Hamwira Yaacob, and Mustafa Ali Abuzaraida
IEEE
Recent research and developments in Sentiment Analysis (SA) have simplified sentiment detection and classification from textual content. The related domains for these studies are diverse and comprise fields such as tourism, costumer review, finance, software engineering, speech conversation, social media content, news and so on. SA research and developments field have been done on various languages such as Chinese and English language. However, SA research on other languages such as Malay language is still scarce. Thus, there is a need for constructing SA research specifically for Malay language. To understand trends and to support practitioners and researchers with comprehension information with regard to SA for Malay language, this study exhibit to review published articles on SA for Malay language. From five online databases including ACM, Emerald insight, IEEE Xplore, Science Direct, and Scopus, 2433 scientific articles were obtained. Moreover, through the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) Statement, 10 articles have been chosen for the review process. Those articles have been reviewed depend on a few categories consisting of the aim of the study, SA classification techniques, as well as the domain and source of content. As a result, the conducted systematic literature review shed some light about the starting point to research in term of SA for Malay language.
Normi Sham Awang Abu Bakar, Hamwira Yaacob, Dini Handayani, and Mustafa Ali Abuzaraida
IEEE
The development of the various Malay corpora have given the opportunities to many researchers to explore their usage in diverse contexts. However, the corpora were distributed in various locations, and for the ease of access for users, a system called Malay Online Virtual Integrated Corpus (MOVIC) is proposed. This paper focuses on applying the systematic literature review (SLR) on the Malay corpus research to find out the recent development in the area. From the initial search, 3231 articles were extracted from five online databases, such as, IEEE Xplore, Scopus, ProQuest, Springer Link, and ACM. After several rounds of filtering, 11 papers were selected for review.
Osama Mohamed Elrajubi, Mustafa Ali Abuzaraida, and Akram M. Zeki
IEEE
This paper presents a retinal image classifier based on Convolutional Neural Networks which are commonly deep learning used tool. This classifier uses some texture based features to decide if an input image shows evidence of previous photocoagulation laser treatments. However, this classifier could help the expert human to examine the case which make the process easier and spend less time. The solution proposed as well as the datasets used in the training and performance evaluation are presented in detail. The results obtained are described and analyzed. The accuracy obtained was above 90%. Finally, some considerations on possible improvements and future developments are made to close the article.
Mustafa Ali Abuzaraida and Amel Faraj Elramalli
IEEE
In real world, organizations often have large amount of data that are stored in databases. The large size of data makes data analysis difficult as data are more complex in terms of number of attributes and number of objects. The use of a sufficient number of attributes and objects are one way to overcome the problem. There are many techniques that can be used to minimize the number of attributes in data mining. In this paper, three reduction techniques namely Genetic Algorithm (GA), Principal Component Analysis (PCA), and Johnson have been tested on medical domain using 5 datasets which obtained from UCI machine learning archive. The study examines which reduction technique is most suitable for medical datasets. In addition, the study also identifies the ranking of the three techniques based on percentage accuracy and number of selected attributes.
Osama Mohamed Elrajubi, Ali Mustafa Elshawesh, and Mustafa Ali Abuzaraida
IEEE
In telecommunication industry, fraud becomes a serious problem that affects telecommunications service providers all around the world. As a significant amount of revenue losses to fraud every year, so an efficient system to detect fraud activities is greatly required. A well-known fraud which affects GSM and PSTN service providers is Bypass fraud. It is used to avoid a charge of international calls. However, a fraud cannot be completely eradicated, an early detection of a fraud will minimize the loss in revenue. In this paper a new approach of detection system of Bypass Fraud is proposed. The proposed system based on the speaker recognition techniques to detect any fraud based on the user profiling.
Mustafa Ali Abuzaraida and Salem Meftah Jebriel
IEEE
The typical Online Handwritten Text Recognition System contains four main phases which are: preprocessing, feature extraction, recognition, and post-processing phases. Preprocessing phase aims to reduce or remove imperfections caused during acquisition step. This phase is also used to minimize handwriting variations irrelevant for pattern classification which may exist in the text acquisition. The preprocessing phase has a great influence on subsequent processing, and a real impact on the recognition rate. This phase could include a number of steps like resizing, centering, simplifying, and smoothing the text. This paper presents an experimental study of using a simplification technique which is used in the preprocessing phase in Online Handwritten Text Recognition systems. The proposed system is designed to deal with any type of text. However, the study is limited to deal with acquired digits which will give a deep understanding of using preprocessing steps in this field.
Salem Meftah Jebriel, Haitham Alali, and Mustafa Ali Abuzaraida
IEEE
Online applications and computer applications software are increasingly grown and one of the most cornerstone issues of these applications is the usability issue. Investigating the usability of using any technique is very important before distributing that technique. In this paper, we investigate an authentication systems based on recognition graphical password using Doodles Scan System (DSS) were used to investigate the usability of using doodles on web authentication. The DSS system needs very simple equipment: printer and scanner. Indeed, results showed that such equipment are often not available in Misurata University which affects the usability of the proposed technique. Moreover, the efficiency of using DSS with 41 participants was only usable for five participants. As consequence, the doodles scan system DSS might have some difficulties to be used in Libya or can be applied in proper places.
Mustafa Ali Abuzaraida, Akram M. Zeki, Ahmed M. Zeki, and Nor Farahidah Za'bah
IEEE
Arabic chemical symbols are remarkably different from Latin chemical symbols which written by Arabic characters. On the other hand, Arabic chemical symbols follow Latin chemical symbols from the structure of writing the symbols. Although, Arabic symbols have special way of the writing like writing direction, cursive style, and written by Arabic characters. In fact, these symbols are being used in schools and high education level around many Arabic countries. In this paper an online system for recognizing handwritten Arabic chemical symbols is presented. The paper illustrates each phase of the system in details. The system is dealing with some Arabic chemical symbols as initial study and to be updated with more symbols later.
Mustafa Ali Abuzaraida, Akram M. Zeki, and Ahmed M. Zeki
IEEE
Recently, online character recognition approaches are gotten attention everywhere due to the raped growing of touch screen devices industry. Furthermore, keyboards and mice devises become inapplicable to be included in small devises. These reasons would open the gate for discovering new techniques which can enrich and enhance this kind of approaches. These online approaches can be used for recognizing different texts like letters, digits, or symbols. In this paper, an online system for recognizing handwritten Hindi digits is highlighted based on matching alignment algorithm. It illustrates every phase of the system in details which are: digits acquisition, preprocessing, features extraction, and recognition phase. The dataset of the system were collected by 50 writers using a touch screen laptop with 50 sample of each digit. The results of testing the proposed system showed a high accuracy rate with an average of 96%.
M. A. Abuzaraida, A. M. Zeki, and A. M. Zeki
IEEE
Online recognition of Arabic handwritten text has been an ongoing research problem for many years. Generally, online text recognition field has been gaining more interest lately due to the increasing popularity of hand-held computers, digital notebooks and advanced cellular phones. Most of the online text recognition systems consist of three main phases which are preprocessing, feature extraction, and recognition phase. This paper compares between different techniques that have been used to extract the features of Arabic handwriting scripts in online recognition systems. Those techniques attempt to extract the feature vector of Arabic handwritten words, characters, numbers or strokes. This vector then will be fed into the recognition engine to recognize the pattern using the feature vector. The structure and strategy of those reviewed techniques are explained in this article. The strengths and weaknesses of using these techniques will also be discussed.