Mustafa Hussein Mohammed

Mr. Mustafa Hussein Mohammed

Al-Mustaqbal University College, Al Ḩillah, Bābil, Iraq
orcid
programmer

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2025 in IEEE Access
Verified
Journal Article
Open access
Mustafa Hussein MohammedMustafa Hussein Mohammed
Mustafa Hussein Mohammed
MKMustafa Noaman Kadhim
Mustafa Noaman Kadhim
DADhiah Al-Shammary
Dhiah Al-Shammary
AIAyman Ibaida
Ayman Ibaida
In this paper, a novel classifier based on Robert’s similarity measure is introduced for emotion detection using electroencephalogram (EEG) signals. Traditional machine learning classifiers machine learning such as k-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), and Random Forest (RF), often struggle to accurately capture both linear and nonlinear patterns in EEG signals and face limitations in handling high-dimensional datasets. The proposed classifier addresses these challenges by segmenting EEG signals into block sizes categorized as small (1 to 10 samples), medium (20 to 100 samples), and large (200 to 1,000 samples), demonstrating particularly strong performance with medium and large block sizes to capture essential features. Integration of Particle Swarm Optimization (PSO) for feature selection, with Robert’s similarity as the fitness function, effectively refines the feature set, boosting classification accuracy and computational efficiency. Evaluation on an EEG brainwave dataset demonstrated that the method achieved an accuracy of 98.75% with feature selection, compared to 94.04% without it in emotional state detection. The results demonstrate that the proposed classifier is a valuable tool for diverse fields, including healthcare by detecting patient stress, education by assessing student engagement, customer service by monitoring satisfaction, and smart environments by enabling adaptive responses. Furthermore, the classifier has potential for broader industrial applications, such as improving workplace productivity by monitoring employee stress and enhancing safety in autonomous vehicle systems, making it a versatile solution for emotionally-aware systems across multiple domains.
1

22 May 2025 in Journal of Voice
Verified
Journal Article
Open access
Mustafa Hussein MohammedMustafa Hussein Mohammed
Mustafa Hussein Mohammed
MKMustafa Noaman Kadhim
Mustafa Noaman Kadhim
DADhiah Al-Shammary
Dhiah Al-Shammary
AIAyman Ibaida
Ayman Ibaida
This paper presents a novel classifier based on the Clark distance for early detection of Parkinson's disease (PD) using voice data. The nonlinear nature of human voice signals and their inherent fluctuations pose significant challenges for traditional machine learning classifiers such as Random Forest (RF), Support Vector Machines (SVM), Decision Trees (DT), K-Nearest Neighbors (KNN), and Logistic Regression (LR), which struggle to capture meaningful relationships within the voice data for accurate classification. The proposed classifier addresses these limitations by segmenting the data features of each voice sample into smaller blocks (ranging in size from 2 to 10 features per block), to better capture relationships and minimize fluctuations that negatively impact classification accuracy. To further enhance the performance of the classifier, Grey Wolf Optimization (GWO) was integrated to select high-harmony (convergent) features while removing irrelevant and redundant (divergent) features. The proposed approach achieved an accuracy of 94.6% without GWO and an impressive 98.305% accuracy with GWO, using only 12 selected features. Additionally, the classifier demonstrates efficient execution time, making it well-suited for real-time applications in medical organizations. The combination of the Clark distance classifier with GWO not only improves classification accuracy but also ensures computational efficiency, enabling its deployment in diverse settings such as hospitals and home monitoring systems for early detection and continuous monitoring of PD patients. This study highlights the potential of the proposed approach as a reliable, cost-effective, and scalable solution for voice-based PD detection.

1 August 2025
Verified
Conference Paper
Closed access
RNRajit Nair
Rajit Nair
Mustafa Hussein MohammedMustafa Hussein Mohammed
Mustafa Hussein Mohammed
MSMayank Sharma
Mayank Sharma
JBJyoti Badge
Jyoti Badge
SDShivendra Dubey
Shivendra Dubey
PHPon Harshavardhanan
Pon Harshavardhanan
This paper describes a novel brain and cellular data analysis. Bayesian reasoning and hierarchical models provide important information. Bayesian principles continually anticipate model parameters in the offered strategy. This updates previous perspectives based on observations. The approach employs sophisticated sampling methods like Markov Chain Monte Carlo (MCMC) to ensure accurate parameter estimations. It also examines future data using the posterior prediction distribution. We discuss how a hierarchical Bayesian model with hyperpriors enhances research and flexibility. We utilize the Deviance Information Criterion (DIC) to assess the model's usefulness. Other approaches, like SVM and Random Forest, are used to evaluate the model's performance. Investigating the recommended approach indicates that it has excellent sensitivity and specificity, 95% accuracy, and 0.97 AUC. The recommended approach has a 98% closure rate and is noise-free, making it a trustworthy clinical tool. Reduced model complexity and ease of understanding make the technique helpful in the field. With everything considered, this Bayesian strategy changes patient care choices and brain understanding.

30 June 2024 in Journal of Al-Qadisiyah for Computer Science and Mathematics
Verified
Journal Article
Open access
PDF file
Mustafa Hussein MohammedMustafa Hussein Mohammed
Mustafa Hussein Mohammed
The use of wireless sensor networks (WSNs) in tracking moving objects has increased significantly in recent years. Target node coverage, a criterion for choosing the right node or nodes for monitoring moving targets, is described in this research utilizing the proposed algorithm that is based on the combined genetic algorithm and MTR (Multiple Target Research). The suggested approach combines factors according to a basic strategy, and while choosing the right node, better attributes are taken into account. The suggested approach determines which node or nodes are suitable for covering and tracking network objectives based on their degree of overlap, distance to the well, and best remaining energy. Criterion for selecting the appropriate node or nodes for tracking moving targets are presented in the form of target node coverage. In the proposed method, parameters are combined based on a fundamental strategy, and superior characteristics are regarded when selecting the appropriate node. Fewer nodes are positioned in the appropriate coverage region, according to the results. Furthermore, given that the communication

30 March 2026 in Journal of Biomedicine and Biochemistry
Verified
Journal Article
Open access
PDF file
RMRusul Ahmed Mohammed
Rusul Ahmed Mohammed
NHNada Khazal K. Hindi
Nada Khazal K. Hindi
Mustafa Hussein MohammedMustafa Hussein Mohammed
Mustafa Hussein Mohammed
ZSZahraa I. J. Shubber
Zahraa I. J. Shubber
AGAbdolmajid Ghasemian
Abdolmajid Ghasemian
Acute Myeloid Leukemia comprises a heterogeneous group of clonal disorders that result from the abnormal accumulation of immature myeloid cells within the bone marrow and peripheral blood. This study aims to detect Advances in the Molecular Pathogenesis of Acute Myeloid Leukemia. This has been elucidated by recent molecular studies that identified crucial mutations in FLT3, NPM1, and DNMT3A genes and epigenetic changes that contribute to leukemogenesis. Deregulated pathways besides PI3K/AKT and MAPK have also asserted themselves in disease progression and resistance to therapy. Hence, the review presents an extensive discussion of contemporary molecular perspectives of AML pathogenesis and their relevance to diagnosis and treatment. The rise in targeted therapies and precision medicine thus paints a promising clinical picture for a better prognosis. Knowledge of the biological compromise unleashed by mutations in genes and their interplay with the bone marrow microenvironment is key to forging newer therapies.