This prestigious milestone reflects years of dedication, impactful research, and meaningful collaboration within the engineering and scientific communities. It stands as a recognition of professional excellence and a sustained contribution to the advancement of technology.

Congratulations to Prof. Tamer M. Nassef on this remarkable and well-deserved achievement!

Their paper titled ‘Abnormal Behavior Analysis for Surveillance in Poultry Farms using Deep Learning,’ introduces a groundbreaking computer-vision-based system. It utilizes deep learning and crowd behavior analysis techniques to identify and monitor abnormal behaviors among chickens in poultry farms, thereby ensuring the well-being and health of the birds.

You can read the paper through the following link:

Congratulations for your outstanding work

Their collaborative paper, titled ‘The Effect of Using Tangible User Interfaces Compared to Traditional Learning for Teaching Programming in Higher Education: An Experimental Study,’ has been successfully published under the invaluable guidance and collaboration of Dr. Ayman Ezzat, Vice Dean of the Faculty of Computer Science.

This groundbreaking research aimed to assess the effectiveness of Tangible User Interfaces (TUIs) in educational settings. They developed an innovative interface for teaching programming to higher education students. The study yielded impressive results, showcasing that the utilization of TUIs enhances information retention and improves comprehension of learning outcomes. Conducted on the MSA campus, this experimental study enlisted students from the Faculty of Computer Science as volunteer subjects.

You can read the paper through the following link:

Congratulations for your outstanding work

Their paper titled “Real-time Detection of Taikyoku Shodan Karate Kata Poses Using Classical Machine Learning and Deep Learning Models,” presents a system designed to detect specific karate poses in real-time. This innovative system aims to provide instant and precise feedback to practitioners, revolutionizing training methodologies and improving performance.

By integrating machine learning (ML) and deep learning (DL) models, the research addresses the need for accurate feedback in karate training. The system utilizes various ML and DL algorithms, achieving impressive accuracies of 98% with the Random Forest model and 97% with the Long-Short Term Memory model.

Through meticulous data collection, pre-processing, and model training, this system has the potential to expedite the identification and correction of technique flaws, facilitating faster and more effective learning while minimizing the risk of injuries.

You can read the paper through the following link:

Congratulations for your outstanding work

Their collaborative paper, titled A Robust Ensemble Deep Learning Approach for Breast Cancer Diagnosis,’ has been successfully published on the International Journal IEEE.

In their paper, they delved into a comprehensive exploration of ensemble deep learning techniques aimed at enhancing the performance of breast cancer classification models. Their primary goal is to harness the power of pre-trained models and elevate their capabilities through the application of ensemble and meta-learning techniques.

They began by utilizing the BCI dataset as the cornerstone of their research. Recognizing the potential value of pre-trained models in breast cancer detection and classification, they selected five prominent pre-trained models, including ResNet50, MobileNet, Inception, VGG-SVM, and Desnet, to establish their baseline models. These models serve as a robust foundation upon which they can build and refine their approach.

To further boost the predictive abilities of their models, they employed various ensemble techniques. They experimented with average weighted, soft voting, and hard voting ensembles, meticulously exploring different combinations to identify the optimal approach. By leveraging the collective intelligence of multiple models, they aimed to maximize strengths and compensate for individual limitations. This ensemble-based approach seeks to achieve superior performance compared to individual models. The outputs of their ensemble models, when presented to various machine learning classifiers, demonstrate the potential of their approach in the realm of meta-learning.

In conclusion, the authors’ research endeavors to capitalize on the utilization of pre-trained models in breast cancer detection and classification. By integrating ensemble and meta-learning techniques, they aimed to enhance the performance of these models. This approach holds significant promise for the field of breast cancer diagnosis, empowering healthcare professionals to make more informed decisions and facilitating early detection and intervention.

You can read the paper through the following link:

Congratulations for your outstanding work

Their collaborative paper, titled An enhanced Transformer-based Approach with Meta-Ensemble Learning for Arabic Sentiment Analysis” (Sep-2023)’ has been successfully published in the International Journal (IEEE) under the supervision of Professor Ammar Mohammed.

Their paper was published at IEEE at the 3rd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC-23). This research paper proposes an approach to address Arabic sentiment analysis by integrating ensemble learning with transformers. The fundamental goal of this work is to suggest an effective strategy for leveraging the potential of baseline transformer models, which are initially fine-tuned and rigorously evaluated for their performance.

Their approach achieved 95.2% accuracy, which is 2% higher than the best meta-ensemble deep learning model.

You can read the paper through the following link:

Congratulations for your outstanding work

MSA University and the Faculty of Computer Science in collaboration with the Faculty of Physical Therapy would like to congratulate Teaching Assistant Moamen Zaher, as he successfully published a scientific paper on IEEE Xplore as part of the 2023 Intelligent Methods, Systems, and Applications (IMSA) proceedings.

His paper, titled “A Framework for Assessing Physical Rehabilitation Exercises,” introduces an innovative framework for evaluating rehabilitation exercises and patient progress. Inspired by the WHO’s “Rehabilitation 2030” initiative and aligned with SDG 3 on Health and Wellbeing, his goal is to reduce rehabilitation costs while enabling personalized treatment plans through automated exercise assessment.

Using an RGB camera to capture patient movements and extract skeletal components for classification, his framework demonstrated impressive results as it achieved a remarkable 99.64% accuracy rate on a benchmarking dataset and a solid 90% accuracy rate on datasets from university clinics.

You can read the paper through the following link:

Congratulations Moamen for your outstanding work

MSA University and the Faculty of Computer Science would like to congratulate Teaching Assistant Ahmed Mostafa El-Kady as he successfully published a scientific paper on IEEE Xplore as part of the 2023 Intelligent Methods, Systems, and Applications (IMSA) proceedings.

His paper, titled “Comparative Analysis: Deep Learning vs. Machine Learning for Early DFU Detection in Medical Imaging,” highlights the significance of using machine learning and deep learning for early Diabetic Foot Ulcers (DFU) detection. The study introduces deep learning and machine learning models, with RESNET18 demonstrating an impressive 97.9% accuracy rate. This research has substantial implications for improving the quality of life for DM patients.

You can read the paper through following the button below:

Congratulations Ahmed for your outstanding work

MSA University and the Faculty of Computer Science would like to congratulate the Lecturer Assistant, Reem Kadry as she has successfully published two scientific papers on IEEE Xplore, both featured in the Intelligent Methods, Systems, and Applications (IMSA) publication.

The first paper, “Process Discovery Automation: Benefits and Limitations,” explores automation levels in process discovery for business processes, highlighting the advantages of semi-automated approaches and the superior performance of deep learning algorithms. You can view the paper through following the button below:

The second paper, “Prediction of Dental Fluorosis Infection based on Particle Optimized Scored KNN Approach,” introduces a novel technique for predicting dental fluorosis using real-world data. This approach outperforms traditional methods with an accuracy rate of 94.5% when the K value is 11. You can view the paper through following the button below:

Congratulations to Reem Kadry for your outstanding work

MSA University and the Faculty of Computer Science are delighted to share an exceptional achievement by our Computer Science Students Mohamed Ayman and Farah Darwish who published their paper “Deep Learning-Based Alzheimer’s Disease Classification: An Experimental Study” to IEEE Xplore.

Alzheimer’s disease poses a significant healthcare challenge, and timely diagnosis is crucial. Their study explores the power of image classification models in detecting Alzheimer’s using MRI images, covering four disease stages. They take great pride to report an impressive accuracy rate of 98.810%, highlighting the potential of AI in revolutionizing healthcare.

We invite you to explore the full paper by following the button below:

Congratulations to our remarkable students