Mohamed Hussein Rehan Habeb

Dr. Mohamed Hussein Rehan Habeb

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 July 2024 in Algorithms
Verified
Journal Article
Open access
PDF file
MHMohamed Hussein Rehan Habeb
Mohamed Hussein Rehan Habeb
MSMay Ahmed Salama
May Ahmed Salama
Lamiaa ElrefaeiLamiaa Elrefaei
Lamiaa Elrefaei
This work introduces an unsupervised framework for video anomaly detection, leveraging a hybrid deep learning model that combines a vision transformer (ViT) with a convolutional spatiotemporal relationship (STR) attention block. The proposed model addresses the challenges of anomaly detection in video surveillance by capturing both local and global relationships within video frames, a task that traditional convolutional neural networks (CNNs) often struggle with due to their localized field of view. We have utilized a pre-trained ViT as an encoder for feature extraction, which is then processed by the STR attention block to enhance the detection of spatiotemporal relationships among objects in videos. The novelty of this work is utilizing the ViT with the STR attention to detect video anomalies effectively in large and heterogeneous datasets, an important thing given the diverse environments and scenarios encountered in real-world surveillance. The framework was evaluated on three benchmark datasets, i.e., the UCSD-Ped2, CHUCK Avenue, and ShanghaiTech. This demonstrates the model’s superior performance in detecting anomalies compared to state-of-the-art methods, showcasing its potential to significantly enhance automated video surveillance systems by achieving area under the receiver operating characteristic curve (AUC ROC) values of 95.6, 86.8, and 82.1. To show the effectiveness of the proposed framework in detecting anomalies in extra-large datasets, we trained the model on a subset of the huge contemporary CHAD dataset that contains over 1 million frames, achieving AUC ROC values of 71.8 and 64.2 for CHAD-Cam 1 and CHAD-Cam 2, respectively, which outperforms the state-of-the-art techniques.

1 January 2023 in Mansoura Engineering Journal
Verified
Journal Article
Open access
PDF file
MHMohamed Hussein Rehan Habeb
Mohamed Hussein Rehan Habeb
MSMay Ahmed Salama
May Ahmed Salama
LELamiaa A. Elrefaei
Lamiaa A. Elrefaei
This paper proposes an efficient lightweight deep spatial residual autoencoder (SRAE) model to detect anomalous events in video surveillance systems. A lightweight network is essential in real-time situations where time is critical. Moreover, it could be deployed on low-resource devices like embedded systems or mobile devices. This makes it a very useful option for real-world situations where there may be a shortage of resources. The proposed network is composed of a 3-layer residual encoder-decoder architecture that is adopted to acquire the salient spatial characteristics representative of normal events in videos. Then, the reconstruction loss is used to find abnormalities, where normal frames are recreated well with a low reconstruction loss, and abnormal ones are found as the opposite. The model's efficiency is tested by two benchmark datasets, the UCSD Pedestrian2 and the CUHK Avenue, achieving AUC ≈ 95% and 81% for the two datasets, respectively. Hence, its performance proves to be comparable with the state-of-the-art models.

8 June 2026 in Bioengineering
Verified
Journal Article
Open access
PDF file
MHMohamed Hussein Rehan Habeb
Mohamed Hussein Rehan Habeb
RAReem Alnanih
Reem Alnanih
Lamiaa ElrefaeiLamiaa Elrefaei
Lamiaa Elrefaei
Alzheimer’s disease (AD) is a global health challenge requiring early and accurate diagnosis, yet current clinical methods struggle with early stages. Deep learning approaches for MRI-based diagnosis face persistent challenges related to image quality issues, limited model generalization, and subtle inter-class variations. To address these limitations, this paper proposes a robust, end-to-end brain MRI-based framework for multi-class classification of AD stages. Positioned within the broader research priority of artificial intelligence and intelligent healthcare technologies, the proposed methodology incorporates an attention-based ensemble of deep learning models alongside an enhanced image preprocessing that uses Real-ESRGAN to mitigate common compression and resolution degradations in 2-D MRI slices. The ensemble makes use of the superior capabilities of the Swin Transformer to capture global contextual dependencies and EfficientNet-B3/MobileNetV2 for effective multi-scale feature extraction, with feature fusion performed using a Squeeze-and-Excitation attention mechanism. The experiments were performed on a publicly available Alzheimer’s MRI dataset, resulting in classification accuracy of 94.47% and 92.28% for the two proposed frameworks. The robustness and clinical interpretability of the framework are emphasized through comprehensive metrics and qualitative analysis. This framework demonstrates promising benchmark performance on a standardized public dataset, highlighting the potential of cross-paradigm ensembles combined with super-resolution preprocessing.