AMAyad Hameed Mousa

Ayad Hameed Mousa

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ayad Hameed Mousa has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Diabetes at a Glance: Assessing AI Strategies for Early Diabetes Detection and Intervention via a Mobile App

    by Ayad Hameed Mousa, Ibrahim Oday Alrubaye, Mayameen S. Kadhim, Ahmed Dheyaa Radhi, Mudatheer M. Al-Slivani, Rusul Mansoor Al-Amri, Liaw Geok Pheng

    Diabetes is a widespread disease worldwide that does not differentiate between children and adults. It also affects the elderly and pregnant women. However, early detection of the disease facilitates its control to avoid the effects resulting from delayed diagnosis. With the emergence of artificial intelligence represented by machine learning techniques and its use in most sectors, accordingly, the adoption of machine learning techniques to help in disease prediction has become a necessity. This study proposes a machine learning algorithm-based approach for diabetes prediction. This study uses three datasets, two of which are private and the other includes the Pima Indians dataset. Six machine-learning models have been used and evaluated in this study including Gaussian Naive Bayes model. Bernoulli Naive Bayes Model, Bagging Regressor Model, Neural Network Architecture, Multilayer perceptron, and SVR. To address the imbalance in classes of the private datasets, the SMOTE technique has been utilized. To analyze the state of the arts, a systematic literature review was conducted. The results showed that the Bagging Regressor algorithm is the best among the used algorithms in terms of the accuracy of the derived results. It achieved an accuracy of 99.79 with SMOTE included and 97.95 without SMOTE. A smart mobile application was developed based on the proposed approach that facilitates clinicians to predict diabetes. This study strengthens the theoretical foundations of machine learning in healthcare by presenting a robust and empirically validated approach for early detection and prediction of diabetes. The findings not only advance academic knowledge but also provide practical guidance for developing AI-based diagnostic tools in clinical settings.


  • Open Access

    Investigating the Differential Effects of SMOTE Variants on Class Imbalance and Exploring Their Applicability to a Thalassemia Prediction Model

    by Hussam Mezher Merdas, Ayad Hameed Mousa

    Researchers work around the clock on many datasets provided by various institutions. These researchers strive to come up with highly efficient Artificial Intelligence models. Often, researchers face the problem of imbalance in the distribution of classes in a particular feature in the selected dataset, which creates an Artificial Intelligence model biased towards one class at the expense of another class that is no less important than the first. On the other hand, thalassemia is a disease that affects people of different ages. The degree of disease varies according to the thalassemia class. This study proposes an improved Machine Learning model that aims to provide a comprehensive comparison of different SMOTE techniques to enhance class balance in thalassemia prediction. And create a Machine Learning model that predicts the possibility of an individual suffering from thalassemia based on the data modified by the proposed SMOTE technology. This study concluded, according to the proposed model, that the best SMOTE technique that can be used in such datasets with clear imbalance is the SMOTE-ENN technique, as the model achieved high-accuracy prediction results, as the model's accuracy was 99% and the F1-score was 97%. This study provides software developers with the steps and source code to develop it as a mobile or computer application to help people know the probability of their infection with thalassemia. The study also helps researchers determine the best SMOTE technique that is compatible with imbalanced datasets.


  • Open Access

    Construction a virtual central network for all Iraq's fire station

    by Wasnaa Hadi Ghasab, Ahmed Adnan Hadi, Alaa.G.K. Alshami, Ahmed Dheyaa Radhi, Rusul Mansoor Al-Amri, Ayad Hameed Mousa

    Fire stations are crucial in Iraq for protecting human life, property, and vital economic and religious infrastructure. In this paper, a design for a centralized virtual network that brings together all fire stations in Iraq is proposed. The network consists of 18 stations, with each station representing a governorate in Iraq. When a fire occurs in a certain area, citizens can request the service by entering their personal information and the location of the event, which is sent to the centralized network that transfers it to the appropriate station in the area. If the station is not available in the area, the request is sent to the nearest other station to fulfil the request as quickly as possible. This virtual communication network allows for better coordination and simplifies data sharing and communication between different stations. The results showed that the centralized network design contributes to fast response times, rapid response to requests and rapid deployment of fire engines to the incident site. Fire stations can also increase overall efficiency by improving coordination, allocating resources more effectively and monitoring situations in real time. Thanks to the centralization of data, all stations have access to the same set of information, enhancing decision-making, especially in the case of large-scale incidents. Also, the network design is characterized by a high level of security.


  • Open Access

    Enhancement of The Performance of Machine Learning Algorithms to Rival Deep Learning Algorithms in Predicting Stock Prices.

    by Rusul Mansoor Al-Amri, Ahmed Adnan Hadi, Mayameen S. Kadhim, Ayad Hameed Mousa, Ali Z.K Matloob, Hasanain Flayyih Hasan

    This paper objectives to improve stock market prediction accuracy by training data on sentiment analysis of tweets, overcoming volatility and complexity. Utilizing the Use of natural language processing (NLP) algorithms, the tweet's sentiments were classified into (negative - neutral - and positive). The stock value price was predicted by implementing Machine learning algorithms (KNN, SVM, GBM, LR, DT, RF, EL). Among the techniques of ML, (GBM) achieved the greatest results in terms of accuracy (96%). Its results were compared with the results of a deep learning algorithm that uses the same data where GBM got better results, and other algorithms showed results (KNN = 55%, SVM=90%, LR=82%, DT=90%, RF=90%, EL = 88%). The results obtained were superior to previous studies.


  • Open Access

    Food sales prediction model using machine learning techniques

    by Hussam Mezher Merdas, Ayad Hameed Mousa

    Food sales prediction means how to obtain future results of sales of companies. The purpose of this step is to increase the profits of these companies by avoiding spoilage of food products and avoiding buying more quantities than the needs of these companies, which means the accumulation of these products in the warehouses without selling them. Stocked and expired products require a model that guesses the actual future need for these products. In this study, a model for food sales prediction using machine learning algorithms is proposed to achieve two objectives, first: make a comparison between two datasets, one dataset with a high correlation between its features, and another dataset has a low correlation between its features. The second objective is to use several machine learning algorithms for prediction and comparing between these algorithms to find the best three algorithms that give the best prediction. By using the most important metrics such as root mean square error (RMSE) and mean square error (MSE) found the best three algorithms by using the first dataset are support vector machines (SVMs), least absolute shrinkage and selection operator (LASSO), and bagging regressor) and the best three algorithms by using the second dataset are (gradient boosting, random forest regressor, and decision tree).


  • Open Access

    Virtual data integration for a clinical decision support systems

    by Intedhar Shakir Nasir, Ayad Hameed Mousa, Sakina M. Ali Alkhafaji, Wafia Shaker Abdul Hussein, Zahraa Razzaq Jasim, Saeed Qasim Ali

    Clinical decision support (CDS) supplies clinicians and their patients, and relevant staff with meaningful and timely information intelligently integrated or visualized to enhance health and the health sector. Data is the backbone of decision support systems, especially (clinical) ones. Data integration (either virtual or physical manner) is a powerful technique to manipulate a vast amount of heterogeneous data and prepare it as input for the decision-making process. The difficulties in manipulating data that have a physical data integration technique motivated the decision support developers to tend to data virtualization as a data integration technique. In this paper, a clinical decision support system was developed using the virtual data integration technique. The developed system was evaluated in terms of usability and its capability of providing clinical decision support. The evaluation findings indicate that the proposed system is highly usable and has a positive impact on supporting the clinical decision-making process.


  • Open Access

    The Development of a Deep Learning Model for Predicting Stock Prices

    by Rusul Mansoor Al-Amri, Ahmed Adnan Hadi, Ayad Hameed Mousa, Hasanain Flayyih Hasan, Mayameen S. Kadhim

    The volatility and complexity of the stock market make it difficult to predict stock values accurately. The primary goal of this paper is to overcome some of these difficulties by training the data to anticipate stock prices based on sentiment analysis of tweets. Using natural language processing (NLP) technology, the tweet sentiments were categorized into (positive - neutral - negative). The stock price was predicted using deep learning algorithms (CNNs, RNNs, LSTMs, BiLSTMs). Among the algorithms, (BiLSTM) achieved the best results in terms of accuracy (94%) and the others (CNN=90%, RNN=91%, LSTM=92%). The paper also confirms that the average MSE and RMSE (MSE=0.03552, RMSE=0.1882064) for the BiLSTM algorithm are achieved (MSE=0.03552, RMSE=0.1882064). As a result, the obtained results were better than previous studies.


  • Open Access

    Toward measuring the usability of decision support applications in fog computing environment

    by Oras Abdulkhdhur Hussein, Ayad Hameed Mousa

    Decision support systems are applications that provide meaningful information and help with decision support. To gain the benefits of these applications, they need to be used optimally. Thus, the optimal manner to utilize relies on several properties, such as usability. This research aims to investigate the decision support systems applications (DSS) in terms of usability evaluation and propose a usability instrument for DSS in a fog computing environment. Recently, complexity is a major problem with most software products. Hence, the way to ensure user satisfaction is by measuring its usability. The study is based on the research question: What dimensions and their elements that utilize to evaluate the usability of DSS applications. A systematic literature review (SLR) was conducted to understand and extract all the instrument’s dimensions and elements. To confirm the validity of the proposed instrument, Multi scientific methods were adapted such as face validity, a pilot study for testing the goodness of proposed instrument consistency, and factor analysis. Furthermore, Bartlett’s test was utilized to ensure the reliability of the developed instrument. Eventually, the validated instrument was used to evaluate DSS application in a fog computing environment. The findings show that the proposed instrument is workable in practice.


  • New design of low profile Uniform Substrate integrated waveguide antenna with square patch loaded

    by Mowafak K. Mohsen, Ayad Hameed Mousa, Rawya Read Jowad

    Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.