العدد الحالي

Sana'a University Journal of Applied Sciences and Technology

مجلد 4 عدد 1 (2026)

2026-01-29

10 مقال

The fourth volume – the first issue in the Sana'a University Journal of Applied Sciences and Technology

المقالات

6 مقالات

Mobile cellular subscriptions - Rep. Yemen

KEY INTERNAL FACTORS CAUSING SCHEDULE DELAYS IN YEMEN-MOBILE TELECOM TRANSCEIVER SITES PROJECTS

Mohammed Ahmed M. Aqlan، Wael Alaghbari، Farouk A. Al-Fahaidy (المؤلف)

1481-1495

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2292

الملخص

In Yemen, telecom projects frequently experience schedule delays, which in turn impede the successful execution of strategic initiatives and the effective deployment of new public services. This study aims to investigate the internal factors causing schedule delays in Yemen-Mobile’s transceiver sites projects. A re-structured questionnaire was distributed to employees involved in the implementation of transceiver sits projects in Yemen Mobile. Of the 191 questionnaires distributed, 154 valid responses were collected and used for analysis. The study identified ten major factors that have a significant detrimental influence on project schedules and caused delay. Procurement phase - related issues emerged as the most influential. These factors included a lack of technical equipment, supplier-related delays, lengthy purchasing procedures and unqualified technical equipment suppliers. Furthermore, Delays in the implementation phase also include delays in fiber optic network connection, security-related material and equipment delays to the project site and implementation start barriers. In addition to, the lack of comprehensive procurement planning, ineffective the strategy of addressing challenges of sites acquisition and lack of monitoring and control plans were identified as a critical planning issue. The study provided practical recommendations for improving procurement management, boosting the efficiency of the implementation phase, and addressing planning issues.

الكلمات المفتاحية

Projects Transceiver Sites Schedule Yemen-Mobile Telecom Projects Delay

AI-Driven Self-Organizing Networks (SON) for 5G OPEX Reduction: A Comprehensive Survey and Conceptual Framework

Mohamed Hankal (المؤلف)

1496-1506

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2291

The proposed Arabic-to-SQL system framework

Enabling Arabic Database Querying via Parameter-Efficient Fine-Tuning of Large Language Models

Mohammed Taj، Mohammed Zayed، Abdulwahid Alhetar، Mohammed Rajeh، Mohammed Abbas Al-Sharafi، Basem Abdulrhman Munassar (المؤلف)

1507-1519

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2248

الملخص

Recent advancements in Natural Language Processing (NLP) and Text-to-SQL systems have enabled easier interaction with relational databases. However, most solutions focus on English, leaving Arabic underrepresented. This study addresses that gap by fine-tuning the Llama-3-SQLCoder model to convert Arabic text into correct and executable SQL, enabling non-technical users to work with databases without learning SQL syntax. We enhanced the model using Low-Rank Adaptation (LoRA) and Unsloth, training it on Arabic questions paired with SQL queries from the Northwind database. To support low-resource environments, the model was converted to the GGUF format, reducing computational requirements while preserving performance. Evaluation results showed an execution accuracy of 90.24% and a validity rate of 97.56%, outperforming the zero-shot baseline (44% and 80%). The model also achieved an Exact Match score of 32% and an F1 score of 0.83, compared to 12% and 0.61 for the baseline. These findings demonstrate that LoRA and Unsloth are effective for adapting SQL-specialized models to Arabic. Despite these improvements, the system still struggles with complex nested queries and dialectal variations, indicating areas for future work. Overall, this study contributes to narrowing the gap between Arabic and other languages in Text-to-SQL research and improves database accessibility for non-technical users.

الكلمات المفتاحية

Text-to-SQL Large Language Models (LLMs) Natural Language Processing (NLP) Parameter-Efficient Fine-Tuning (PEFT) Low-Rank Adaptation (LoRA) GGUF Quantization Unsloth

Phenotypic characterization of Bacillus spp. a. Bacillus sp. growth on NA b. Gram stain (100× magnification), c. Malachite green staining shows endospore.

Antimicrobial activity of Bacillus species isolated from Yemeni soils against some human pathogens

Nesrain A. Al-Mekhlafi، Kholoud G. Badi، Roua A. Al-Refai، Sara M. Al-bana’a (المؤلف)

1520-1527

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2137

متوسط اللمكانات العملية الشهرية بالمستوى 1 في الجمهورية اليمنية

Assessment of the Potential Photovoltaic Power in Yemen Using Satellite Data and GIS

Adel M. Al-Weshali، Abdullah M. Yaya (المؤلف)

1528-1544

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2155

الملخص

يتناول هذا البحث تقييماً شاملاً للإمكانات النظرية والعملية للطاقة الشمسية في الجمهورية اليمنية، بالاعتماد على بيانات الأقمار الصناعية الصادرة عن منصة "سولار جيس" (SolarGIS) المتاحة عبر "أطلس الطاقة الشمسية العالمي". تم تحليل عدة مؤشرات رئيسية، شملت الإشعاع الشمسي المباشر (DNI)، الإشعاع المنتشر (DIF)، الإشعاع الأفقي الشامل (GHI)، والإشعاع على السطح المائل بالإمالة المثلى (GTI)، إلى جانب عوامل مساعدة مثل زاوية الميل المثلى، درجة حرارة الهواء، والارتفاع عن مستوى سطح البحر. أظهرت نتائج الإشعاع الشمسي الأفقي (GHI) أن القيم تراوحت بين 5.46 و6.88 كيلوواط ساعي لكل متر مربع يوميًا، حيث تمتلك 7.62% من مساحة اليمن أعلى إمكانات نظرية (6.8–7.05)، بينما تمتلك 47.27% إمكانات عالية جداً (6.6–6.8). أما الإشعاع المباشر (DNI)، فقد بلغ أقصاه 7.29 وأدناه 3.76، مع تميّز 1.45% من المساحة بأعلى الإمكانات عالميًا (7.2–7.75)، و15.38% ضمن فئة مرتفعة. (6.7–7.2) وفيما يخص الإشعاع المنتشر (DIF)، تراوحت القيم بين 1.83 و2.76، حيث تقع 38.5% من المساحة ضمن الفئة (2.1–2.2). أما الإشعاع المائل (GTI)، فقد بلغ أعلى قيمة 7.27 وأدناها 5.66، مع 13.64% من المساحة ضمن فئة عالية (7.1–7.3). وفيما يتعلق بالإمكانات الكهروضوئية العملية (PVOUT)، بينت النتائج أن 2.35% من المساحة تمتلك أعلى كفاءة إنتاج (5.6–5.9 كيلوواط ساعي لكل كيلوواط مثبت يوميًا)، و24.41% ضمن فئة عالية جداً (5.4–5.6)، بينما لا تقل الإمكانات في 90.09% من المساحة عن 5. وفقًا لمستويات التقييم الثلاثة (0، 1، 2)، بلغت المساحات 455,112 كم²، 235,748 كم²، و219,364 كم² على التوالي، ما يعادل 86.2%، 44.65%، و41.54% من إجمالي مساحة اليمن. بينما غطّت المناطق ذات الإمكانات الأعلى من 5.6 نحو 1.7–2% من المساحة، وبلغت المساحة التي تفوق الإمكانات فيها المتوسط الوطني (5.2) حوالي 152,007 كم². تؤكد هذه النتائج توفر موارد شمسية واعدة في اليمن، ما يعزز إمكانية الاعتماد على الطاقة الشمسية كخيار استراتيجي مستدام لإنتاج الكهرباء وتحقيق التنمية.

الكلمات المفتاحية

الطاقة الشمسية بيانات الاقمار الصناعية القدرة الكهروضوئية الطاقة المتجددة (Solar GIS) سولار جيس

Number of Bacterial isolates recovered from 10 Soil samples

Antibacterial Activity of Soil Bacteria against Escherichia coli and GC-MS Analysis of their Organic Compounds

Miadah M. Mojahed، Abdulrahman A. Humaid (المؤلف)

1545-1551

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.1931

الملخص

Antimicrobial agents encompass a wide range of compounds, including antibiotics, bacteriocins, and lipopeptides, which play a crucial role in combating infectious diseases. Antibiotics, in particular, are secondary metabolites of low molecular weight predominantly synthesized by soil dwelling microorganisms. These microbial metabolites have long served as a vital source of clinically important therapeutic agents. Members of the genus Bacillus and other rhizosphere-associated bacteria are especially known for producing diverse antimicrobial substances. In this study, ten rhizosphere soil samples were collected from different sites in Sana’a city, Yemen. From these samples, 50 antibiotic-producing soil bacteria were isolated. Bioactive metabolites were extracted using the solvent extraction method with chloroform and Ethanol. The crude extracts were analyzed by Gas Chromatography–Mass Spectrometry (GC–MS) to identify their organic composition. Among the 50 bacterial isolates, 14 showed antibacterial activity against resistant Escherichia coli using the agar well diffusion method. Further secondary screening revealed that the filtrates of four isolates Pseudomonas fluorescens, Bacillus subtilis, Acinetobacter baylyi, and Azotobacter vinelandii exhibited the strongest antibacterial effects. GC–MS analysis showed that each isolate produced more than eighty organic compounds; however, only a subset demonstrated antibacterial activity. The most notable bioactive compounds detected included Phenol, 4-(2-aminoethyl)- (CAS: tyramine), 2,4-di-tert-butylphenol, and n-hexadecanoic acid. This study highlights the potential of rhizosphere soil bacteria as promising sources of novel bioactive compounds. The identification of active metabolites and their antibacterial properties against resistant E. coli underscores their possible application in the development of alternative therapeutic strategiesto address antibiotic resistance.

الكلمات المفتاحية

Secondary metabolites GC-MS spectrophotometer Escherichia coli Soil bacteria Organic compounds Chloroform Ethanol

مراجعة

4 مقالات

Generative Adversarial Networks for Visual Content: A Comprehensive Review of Image and Video Synthesis, Challenges, and Ethical Implications

Samah Ahmed Mohammed AlSarori، Ammar T. Zahary (المؤلف)

1552-1579

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2100

الملخص

Generative adversarial networks (GANs) represent a ground-breaking advancement in artificial intelligence, revolutionizing data generation and content creation. This systematic review critically analyses literature from 2019-2024, sourced from major databases like IEEE Xplore and Scopus, to go beyond descriptive surveys and provide a synthesized, critical evaluation. We identify a pivotal gap in the existing literature: a frequent disconnect between reporting technical advancements and examining their profound ethical and societal implications. Our analysis yields several integrated insights. First, while GAN applications predominantly excel in visual content generation with architectures like StyleGAN and BigGAN achieving remarkable progress in photorealistic image and video synthesis their efficacy is highly application-specific, revealing significant trade-offs in stability and diversity in domains such as medical imaging and real-time video processing. Second, persistent core challenges like training instability and mode collapse continue to drive architectural innovations; however, we critically examine how solutions like Wasserstein loss or minibatch discrimination demonstrate varying effectiveness and limitations across different tasks and datasets. Third, and most critically, we argue that ethical concerns, particularly regarding deepfakes and data bias, are not peripheral issues but are intrinsically linked to architectural choices and the quality of training data. The key contribution of this review is its novel, integrated framework for evaluating GANs, which concurrently assesses architectural efficacy, application-specific maturity, and associated ethical risks. This holistic and critical synthesis provides researchers with a nuanced reference and outlines clear, responsible directions for future GAN development, emphasizing the need for models that are not only more powerful but also more robust, fair, and accountable.

الكلمات المفتاحية

التعلم الآلي التعلم العميق الشبكة التوليدية التنافسية الذكاء الإصطناعي

Machine Learning Algorithms for Customer Churn Prediction in the Banking Sector: A Comparative Study

Ibrahim Ahmed Al-Baltah، Sultan Yahya Al-Sultan (المؤلف)

1580-1595

2026-01-29

PDF

DOI: 10.59628/jast.v4i1.2302

الملخص

Predicting customer churn in retail banking is essential for sustaining profitability. This study compares four supervised machine-learning models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN)—using the publicly available bank customer churn dataset from Kaggle (10,000 records, 18 attributes; publicly available at Kaggle repository. Data preprocessing included one-hot encoding for categorical variables, label encoding for gender, and feature selection via an ExtraTreesClassifier retaining nine informative predictors (e.g., age, credit score, balance). To address class imbalance (≈80% nonchurners vs. 20% churners), models were trained and evaluated with and without the Synthetic Minority Oversampling Technique (SMOTE), which was applied only to the training folds under stratified 5-fold cross-validation. Evaluation metrics comprised accuracy, precision, recall (for churn class), F1-score, ROC–AUC, and PR–AUC. RF achieved the best balance between recall (0.484 imbalanced; 0.619 balanced) and accuracy (0.867 imbalanced), while LR with SMOTE attained the highest recall (0.715) at the cost of reduced accuracy (0.718). Overall, the results highlight RF as the most robust model across both distributions and emphasize the importance of imbalance-aware evaluation in bank churn prediction.