Al-Quds University Digital Repository service

The Digital Repository Service is a secure repository system, designed to store and share scholarly, administrative, and archival materials on behalf of Al-Quds University community.

Anyone is welcome to use the DRS to discover publicly available content. Members of Al-Quds University community are encouraged to sign in to access additional content that may not be publicly available.

 

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 10

Recent Submissions

No Thumbnail Available
Item
A Systematic Comparative Evaluation of Classical Machine Learning Algorithms for Liver Lesion Classification in Ultrasound Imaging
(Al- Quds University, 2026-01-14) Aesha Loay Ebrahim Enairat; عائشه لؤي ابراهيم انعيرات
Liver ultrasound is very popular as it is accessible, safe and inexpensive, but the distinction between benign and malignant liver lesions is still difficult to make, owing to the noise, low contrast, and the overlap of the lesions. The thesis is an evaluation of the performance and generalization of classical machine learning techniques in liver lesion classification with ultrasound images in 3 binary tasks, where one of them is benign-normal, another one is malignant-normal, and the last one is benign-malignant. We merged a localized clinical dataset with a publicly available dataset in Zenodo, which created an original set of 6,791 ultrasound images. By eliminating the duplicate and very similar images to avoid redundancy we were left with a curated set of unique images numbered 2,387. We compared the default preprocessing with contrast enhancement with Contrast Limited Adaptive Histogram Equalization (CLAHE) and tested various traditional classifiers, including ensemble model, support vector machines, linear model, instance-based model as well as probabilistic models. Stratified cross-validation, independent testing and a fully isolated holdout set were used in the evaluation of model performance. The best and consistent performance of the ensemble-based classifiers was observed especially when it came to malignant- normal and benign- normal classification. Conversely, benign-malignant classification was the hardest to carry out because the lesion types had large visual overlaps. The use of CLAHE resulted in better sensitivity and lesion separability of a number of models, and task-specific advantages. On the whole, the findings suggest that classical machine learning pipelines with the proper support of preprocessing and strict validation may be effective in terms of assisting the classification of ultrasound-based liver lesions and may serve as the basis of further advancement.
No Thumbnail Available
Item
Assessing Midwives' Perception and Knowledge Toward Disaster Emergency Management at Southern West Bank Hospitals
(AL-Quds University, 2025-12-23) Marah Jafar Hassan Humidat; مرح جعفر حميدات
Background: Disasters lead to a significant threat to maternal and neonatal health, despite skilled midwives' primary role in maternal and neonatal health, limited research in Palestine has examined midwives’ perception and knowledge regarding disaster emergency management. Aim: This study aims to assess the perception and knowledge of midwives towards disasters in emergency management in hospitals across Bethlehem and Hebron, and to explore factors associated with their preparing and hospital readiness. Methods: A descriptive, cross-sectional quantitative approach was employed among 195 midwives working in ten hospitals located in Bethlehem and Hebron in the West Bank. Data were gathered through a structured, self-administered questionnaire containing 61 items across five key domains: knowledge, roles, skills, preparedness, and hospital readiness. Results: Findings revealed that midwives had a moderate level of overall knowledge and perception, with an average score of 3.21. Levels of knowledge and role clarity were higher compared to preparedness and hospital readiness. Higher preparedness scores were significantly associated with advanced education, greater years of experience, and previous participation in disaster-related training (p < 0.05). Moreover, hospitals that regularly implemented drills or training programs demonstrated higher readiness outcomes. Conclusion: Midwives in Bethlehem and Hebron hospitals possess adequate awareness of their roles in disaster situations but remain insufficiently prepared to manage such events effectively. Institutional readiness and continuous training programs are urgently needed to enhance disaster preparedness and strengthen healthcare resilience in Palestine.
No Thumbnail Available
Item
Actual Blended Learning Among Graduate Students at Al-Quds University and Their Attitudes Toward It
(Al -Quds University, 2025-12-20) Leena Deeb Abeedallah Abu Zahra; لينا ديب عبيد الله أبو زهرة
This study aims to investigate graduate students’ perceptions of the application of blended learning at Al-Quds University and their attitudes toward it, as well as to examine potential differences according to gender, faculty, and age variables. A descriptive-analytical mixed-methods approach was employed in line with the study objectives. Quantitative data were collected using a structured questionnaire administered to a stratified sample of 278 graduate students during the second semester of the 2024/2025 academic year, ensuring representation across gender, faculty, and age categories. In addition, qualitative data were gathered through open-ended questions and semi-structured interviews with selected participants to gain deeper insights into students’ experiences and perceptions. The findings indicated that graduate students’ perceptions of blended learning were at a medium level (mean = 3.45), reflecting an acceptable degree of implementation with observable limitations in the dimensions of actual use and perceived impact. In contrast, students’ overall attitudes toward the blended learning process were high (mean = 3.83), indicating a generally positive orientation toward this instructional approach. No statistically significant differences in perceptions or attitudes were found based on gender or age, while students enrolled in scientific faculties reported significantly higher scores compared to those in humanities faculties. Based on these findings, the study recommends strengthening institutional infrastructure, enhancing faculty training in blended learning implementation, and improving the design and management of digital learning environments. The study further emphasizes the importance of clear institutional policies and sustained academic and technical support to ensure more effective and consistent application of blended learning at the postgraduate level.
Thumbnail Image
Item
Thumbnail Image
Item
OSMH: An Optimized Steganography Model for Healthcare CT Images Using AES Encryption and Adaptive Huffman Coding
(0025-09-25) Rushdi A. Hamamreh
Steganography provides a covert mechanism for embedding sensitive data within a carrier medium, such as a digital image, while maintaining its visual integrity. This paper proposes an advanced adaptive Steganography technique that combines AES-128 encryption for security,Adaptive Huffman compression for payload efficiency, and a progressive multi-bit embedding strategy to conceal text messages within RGB images. The method processes a cover image (e.g., a 512×512 RGB image) and a text message (up to 500 characters), encrypting it with AES-128 using a 16-byte key, compressing it with Adaptive Huffman coding, and embedding it into edge-detected "unimportant" pixels across red, green, and blue channels in steps from 1 to 8 bits per pixel. For each step, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR) are calculated, printed to the console, visualized in subplots, and logged to a text file, ensuring a detailed quality assessment. Experimental results demonstrate imperceptibility (PSNR > 40 dB) across all steps, with the progressive approach outperforming traditional LSB methods in flexibility, security, and capacity. This framework offers a robust, practical solution for secure communication, balancing distortion, payload size, and computational efficiency.