Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.

المخرجات

Research outputs

Articles, reviews, conference papers and book chapters, indexed by DOI and linked to University researchers.

13 output Results for «ResNet»

ArticleOpen access20266citation· Semantic Scholar

Personalized multi-agent reinforcement learning framework for adaptive chronic disease therapy management

Scientific Reports · vol. 16 (1)

Long-term, flexible therapy strategies are needed for chronic diseases like cardiovascular ailments, diabetes, and chronic kidney disease and they have to deal with patient heterogeneity, changing physiological states and privacy constraints. This research suggests a framework for privacy-preserving and personalized artificial intelligence that combines Federated Learning (FL), a Res-HyperTransformerNet deep prediction model, Personalized Multi-Agent Reinforcement Learning (PMARL) and Explainable Artificial Intelligence (XAI) for adaptive chronic disease management. The framework is structured with two main aims: (i) to create an accurate and privacy-aware predictive model for chronic disease risk using diverse data sources, and (ii) to permit adaptive, individual therapy optimization through multi-agent reinforcement learning. Federated learning is utilized to conduct the training of Res-HyperTransformerNet over distributed Internet of Medical Things (IoMT) nodes without the requirement of transferring raw patient data. The embeddings that are created from patient data are then passed on to a PMARL module, where several agents optimize therapy dimensions like medications, diet, physical activity, and mental health interventions independently. To make the clinical support more understandable, the SHAP-based explainability method is used for both predictive and decision-making parts. The framework is tested using two public datasets—the CDC Chronic Disease dataset and the UCI Chronic Kidney Disease Risk Factor dataset. The performance is measured by employing classification metrics (accuracy, precision, recall, F1-score, MCC) as well as reinforcement learning metrics (reward score, convergence steps, episode return) and federated system metrics (communication overhead, convergence rounds, and training time). The experiments indicate that the proposed framework demonstrated improved performance in terms of predictive accuracy and policy convergence speed compared to the baseline deep learning and reinforcement learning models, and at the same time it is more cost-effective when it comes to communication in a federated setting. This means that the proposed method suggests the potential of being a reproducible and open AI framework for adaptive chronic disease therapy management. The combination of ResNet and Transformer blocks, i.e., Federated Res-HyperTransformerNet, achieved strong performance in both datasets, namely CDC Chronic Disease (Dataset 1) and UCI CKD Risk Factor (Dataset 2). The obtained accuracy for Dataset 1 was 98.61% and for Dataset 2, it was 97.75%, under the conducted experimental settings.

chronic disease managementfederated learningprivacy-preserving healthcarechronic disease risk prediction
ArticleOpen access2026

NeuroTLEDNet: a novel artificial intelligence with squirrel reptilian optimization (SRO) and TLE-SegNet+ for early detection of temporal lobe epilepsy from medical imaging

Journal Of Big Data · vol. 13 (1)

Temporal Lobe Epilepsy (TLE), a very common type of focal epilepsy, requires early and precise identification to enable prompt treatment and enhance patient outcomes. Traditional methods of detection, most notably manual MRI interpretation, tend to be time-consuming, subjective, and dependent on expert specialists, hindering their scalability and reliability. Due to the limitations of conventional and current automated systems—e.g., poor feature extraction, poor segmentation, and low accuracy in classification—this work presents NeuroTLEDNet, a new end-to-end artificial intelligence model for early TLE detection from medical images. The new methodology integrates multiple series of innovations across every processing phase. In preprocessing, skull stripping, Gaussian blurring, and color normalization are used to improve image uniformity and suppress irrelevant structures. In segmentation, the improved TLE-SegNet + is suggested—based on Mask R-CNN and supplemented with DarkNet-53, DenseNet, HetConv layers, and Attention Feature Pyramid Networks (FPN)—to facilitate highly accurate delineation of epileptogenic areas. For further describing the segmented areas, a rich feature space encompassing color histograms, Local Binary Patterns (LBP), and geometric features (eccentricity, area, perimeter) is developed. To resolve inefficiencies in feature selection, this paper presents the Squirrel Reptilian Optimization (SRO) algorithm, a new hybrid metaheuristic that incorporates both the Squirrel Search Algorithm (SSA) and the Reptile Search Algorithm (RSA). The hybrid enhances discriminative feature selection by handling exploration and exploitation dynamics better compared to individual methods. For categorization, NeuroTLEDNet utilizes an in-depth hybrid ensemble of 3D Convolutional Neural Networks (3D-CNN), Recurrent Neural Networks (RNN), Radial Basis Function Networks (RBFN), and SqueezeNet, facilitating powerful modeling of spatial-temporal relationships in brain MRI scans. Tested on an 80/30 split MRI dataset, the designed model attains a remarkable accuracy of 98.6%, outperforming current methods like CNN-LSTM (94.2%), Mask R-CNN (92.7%), and ResNet-based architectures (93.1%). Indeed, NeuroTLEDNet provides an end-to-end solution for the shortcomings of existing TLE detection methods by utilizing advanced preprocessing, segmentation, feature optimization, and hybrid classification, with state-of-the-art performance in terms of both accuracy and explainability. The suggested model is a promising candidate for clinical application, and it has the potential to assist neurologists in faster and more accurate TLE diagnosis.

temporal lobe epilepsybrain MRIMask R-CNNDarknet-53
ArticleOpen access202532citation· Semantic Scholar

Multi-scale feature fusion of deep convolutional neural networks on cancerous tumor detection and classification using biomedical images

Scientific Reports · vol. 15 (1) · 1105-1105

In the present scenario, cancerous tumours are common in humans due to major changes in nearby environments. Skin cancer is a considerable disease detected among people. This cancer is the uncontrolled evolution of atypical skin cells. It occurs when DNA injury to skin cells, or a genetic defect, leads to an increase quickly and establishes malignant tumors. However, in rare instances, many types of skin cancer occur from DNA changes tempted by infrared light affecting skin cells. This disease is a worldwide health problem, so an accurate and appropriate diagnosis is needed for efficient treatment. Current developments in medical technology, like smart recognition and analysis utilizing machine learning (ML) and deep learning (DL) techniques, have transformed the analysis and treatment of these conditions. These approaches will be highly effective for the recognition of skin cancer utilizing biomedical imaging. This study develops a Multi-scale Feature Fusion of Deep Convolutional Neural Networks on Cancerous Tumor Detection and Classification (MFFDCNN-CTDC) model. The main aim of the MFFDCNN-CTDC model is to detect and classify cancerous tumours using biomedical imaging. To eliminate unwanted noise, the MFFDCNN-CTDC method initially utilizes a sobel filter (SF) for the image preprocessing stage. For the segmentation process, Unet3+ is employed, providing precise localization of tumour regions. Next, the MFFDCNN-CTDC model incorporates multi-scale feature fusion by combining ResNet50 and EfficientNet architectures, capitalizing on their complementary strengths in feature extraction from varying depths and scales of the input images. The convolutional autoencoder (CAE) model is utilized for the classification method. Finally, the parameter tuning process is performed through a hybrid fireworks whale optimization algorithm (FWWOA) to enhance the classification performance of the CAE model. A wide range of experiments is performed to authorize the performance of the MFFDCNN-CTDC approach. The experimental validation of the MFFDCNN-CTDC approach exhibited a superior accuracy value of 98.78% and 99.02% over existing techniques under ISIC 2017 and HAM10000 datasets.

skin cancer detectionskin lesion classificationmulti-scale feature fusionconvolutional neural networks
ArticleOpen access20258citation· Semantic Scholar

Explainable multi-view transformer framework with mutual learning for precision breast cancer pathology image classification

Frontiers in Oncology · vol. 15 · 1626785-1626785

Breast cancer remains the most prevalent cancer among women, where accurate and interpretable analysis of pathology images is vital for early diagnosis and personalized treatment planning. However, conventional single-network models fall short in balancing both performance and explainability—Convolutional Neural Networks (CNNs) lack the capacity to capture global contextual information, while Transformers are limited in modeling fine-grained local details. To overcome these challenges and contribute to the advancement of Explainable AI (XAI) in precision cancer diagnosis, this paper proposes MVT-OFML (Multi-View Transformer Online Fusion Mutual Learning), a novel and interpretable classification framework for breast cancer pathology images. MVT-OFML combines ResNet-50 for extracting detailed local features and a multi-view Transformer encoding module for capturing comprehensive global context across multiple perspectives. A key innovation is the Online Fusion Mutual Learning (OFML) mechanism, which enables bidirectional knowledge sharing between the CNN and Transformer branches by aligning both intermediate feature representations and prediction logits. This mutual learning framework enhances performance while also producing interpretable attention maps and feature-level visualizations that reveal the decision-making process of the model—promoting transparency, trust, and clinical usability. Extensive experiments on the BreakHis and BACH datasets demonstrate that MVT-OFML significantly outperforms the strongest baseline models, achieving accuracy improvements of 0.90% and 2.26%, and F 1 -score gains of 4.75% and 3.21%, respectively. By integrating complementary modeling paradigms with explainable learning strategies, MVT-OFML offers a promising AI solution for precise and interpretable breast cancer diagnosis and prognosis, supporting informed decision-making in clinical settings.

breast cancerhistopathological image classificationexplainable AICNN-Transformer hybrid
ArticleOpen access202454citation· Semantic Scholar

Efficient identification and classification of apple leaf diseases using lightweight vision transformer (ViT)

Discover Sustainability · vol. 5 (1)

Abstract The timely diagnosis and identification of apple leaf diseases is essential to prevent the spread of diseases and ensure the sound development of the apple industry. Convolutional neural networks (CNNs) have achieved phenomenal success in the area of leaf disease detection, which can greatly benefit the agriculture industry. However, their large size and intricate design continue to pose a challenge when it comes to deploying these models on lightweight devices. Although several successful models (e.g., EfficientNets and MobileNets) have been designed to adapt to resource-constrained devices, these models have not been able to achieve significant results in leaf disease detection tasks and leave a performance gap behind. This research gap has motivated us to develop an apple leaf disease detection model that can not only be deployed on lightweight devices but also outperform existing models. In this work, we propose AppViT, a hybrid vision model, combining the features of convolution blocks and multi-head self-attention, to compete with the best-performing models. Specifically, we begin by introducing the convolution blocks that narrow down the size of the feature maps and help the model encode local features progressively. Then, we stack ViT blocks in combination with convolution blocks, allowing the network to capture non-local dependencies and spatial patterns. Embodied with these designs and a hierarchical structure, AppViT demonstrates excellent performance in apple leaf disease detection tasks. Specifically, it achieves 96.38% precision on Plant Pathology 2021—FGVC8 with about 1.3 million parameters, which is 11.3% and 4.3% more accurate than ResNet-50 and EfficientNet-B3. The precision, recall and F score of our proposed model on Plant Pathology 2021—FGVC8 are 0.967, 0.959, and 0.963 respectively.

apple leaf disease detectionlightweight vision transformerplant disease classificationmulti-head self-attention
ArticleOpen access202419citation· Semantic Scholar

Detection of renal cell hydronephrosis in ultrasound kidney images: a study on the efficacy of deep convolutional neural networks

PeerJ Computer Science · vol. 10 · e1797-e1797

In the realm of medical imaging, the early detection of kidney issues, particularly renal cell hydronephrosis, holds immense importance. Traditionally, the identification of such conditions within ultrasound images has relied on manual analysis, a labor-intensive and error-prone process. However, in recent years, the emergence of deep learning-based algorithms has paved the way for automation in this domain. This study aims to harness the power of deep learning models to autonomously detect renal cell hydronephrosis in ultrasound images taken in close proximity to the kidneys. State-of-the-art architectures, including VGG16, ResNet50, InceptionV3, and the innovative Novel DCNN, were put to the test and subjected to rigorous comparisons. The performance of each model was meticulously evaluated, employing metrics such as F1 score, accuracy, precision, and recall. The results paint a compelling picture. The Novel DCNN model outshines its peers, boasting an impressive accuracy rate of 99.8%. In the same arena, InceptionV3 achieved a notable 90% accuracy, ResNet50 secured 89%, and VGG16 reached 85%. These outcomes underscore the Novel DCNN's prowess in the realm of renal cell hydronephrosis detection within ultrasound images. Moreover, this study offers a detailed view of each model's performance through confusion matrices, shedding light on their abilities to categorize true positives, true negatives, false positives, and false negatives. In this regard, the Novel DCNN model exhibits remarkable proficiency, minimizing both false positives and false negatives. In conclusion, this research underscores the Novel DCNN model's supremacy in automating the detection of renal cell hydronephrosis in ultrasound images. With its exceptional accuracy and minimal error rates, this model stands as a promising tool for healthcare professionals, facilitating early-stage diagnosis and treatment. Furthermore, the model's convergence rate and accuracy hold potential for enhancement through further exploration, including testing on larger and more diverse datasets and investigating diverse optimization strategies.

kidney ultrasound imagesdeep convolutional neural networksautomated disease detectionVGG16
ArticleOpen access20248citation· Semantic Scholar

A Speech Disorder Detection Model Using Ensemble Learning Approach

Journal of Disability Research · vol. 3 (3)

Speech disorder detection (SDD) models can assist speech therapists in providing personalized treatment to individuals with speech impairment. Speech disorders (SDs) comprise a broad spectrum of problems that affect the production, articulation, fluency, and quality of speech. Prompt identification and timely intervention are essential for efficient control and therapy of speech problems. However, current diagnostic techniques often depend on subjective evaluations by speech-language pathologists and may encounter challenges in terms of accessibility, scalability, and consistency. The limited dataset and substantial computational power reduce the efforts for developing automated SDD models. However, recent technology developments enable researchers to determine key factors to classify voice samples. The voice sample classification can identify the severity of the SD. Ensemble learning (EL) facilitates the integration of multiple models’ predictions to generate an optimal outcome. Hence, an EL-based SDD model is introduced in this study. A mel-spectrogram (MS) generator is built to produce images using the voice samples. The authors suggested a feature engineering based on the ResNet 18 model for extracting crucial features from the MS. CatBoost and XGBoost models are employed to classify the features. The outcomes of these models are used to train the support vector machine model to make a final prediction. The VOice ICarfEDerico II (VOICED) dataset is used to generalize the proposed model. The experimental findings indicate that the recommended SDD model outperforms the state-of-the-art models by yielding an outstanding performance. This suggests that the model can assist speech therapists in offering customized speech therapies based on the SD severity. The model performance can be improved using multilanguage voice samples.

ensemble learningMel spectrogramCatBoostXGBoost
ArticleOpen access20243citation· Semantic Scholar

TRI-POSE-Net: Adaptive 3D human pose estimation through selective kernel networks and self-supervision with trifocal tensors

PLoS ONE · vol. 19 (12) · e0310831-e0310831

Accurate and flexible 3D pose estimation for virtual entities is a strenuous task in computer vision applications. Conventional methods struggle to capture realistic movements; thus, creative solutions that can handle the complexities of genuine avatar interactions in dynamic virtual environments are imperative. In order to tackle the problem of precise 3D pose estimation, this work introduces TRI-POSE-Net, a model intended for scenarios with limited supervision. The proposed technique, which is based on ResNet-50 and includes integrated Selective Kernel Network (SKNet) blocks, has proven to be efficient for feature extraction customised specifically to pose estimation scenarios. Furthermore, trifocal tensors and their trio-view geometry allow us to generate 3D ground truth poses from 2D poses, resulting in more refined triangulations. Through the proposed approach, the 3D poses can be estimated from a single 2D RGB image. Moreover, the proposed approach was evaluated on the HumanEva-I dataset yielding a Mean-Per-Joint-Position-Error (MPJPE) of 47.6 under self-supervision and an MPJPE of 29.9 under full supervision. In comparison with the other works, the proposed work has performed well in the self-supervision paradigm.

3D human pose estimationselective kernel networktrifocal tensorself-supervised learning
ArticleOpen access20243citation· Semantic Scholar

Deep learning-powered visual place recognition for enhanced mobile multimedia communication in autonomous transport systems

Alexandria Engineering Journal · vol. 109 · 950-962

The progress of autonomous transport systems (ATS) involves efficient multimedia communication for real-time data tradeoffs and environmental issues. Deep learning (DL) powered visual place recognition (VPR) was developed as an effective tool to improve mobile multimedia communication in ATS. VPR relates to the capability of a method or device to recognize and identify particular places or locations from the visual scene. This procedure involves inspecting visual data, like images or video frames, to control the unique features or features connected with diverse locations. By leveraging camera sensors, VPR allows vehicles to detect their surroundings, enabling context-aware communication and enhancing the entire system's performance. DL-empowered VPR offers a transformative manner to improve mobile multimedia communication in ATS. By identifying and understanding their situation, autonomous vehicles can communicate most effectively and operate reliably and safely, paving the way for a future characterized by seamless and intelligent transportation. This article develops a novel Deep Learning-Powered Visual Place Recognition for Enhanced Multimedia Communication in Autonomous Transport Systems (DLVPR-MCATS) methodology. The main aim of the DLVPR-MCATS methodology is to recognize visual places or not utilize optimal DL approaches. For this purpose, the DLVPR-MCATS approach utilizes a bilateral filtering (BF) based preprocessing model. For the feature fusion model, the DLVPR-MCATS approach follows three models: residual network (ResNet), EfficientNet, and MobileNetv2. Moreover, the hyperparameter tuning method uses the Harris Hawks Optimization (HHO) model. Finally, the bidirectional long short-term memory (BiLSTM) technique is implemented to recognize visual places. A wide range of simulations is executed to validate the solution of the DLVPR-MCATS method. The experimental validation of the DLVPR-MCATS method portrayed a superior performance over other models concerning various aspects.

visual place recognitionautonomous vehiclesmobile multimedia communicationautonomous transportation
ArticleClosed20225citation· Semantic Scholar

Intelligent Rider Optimization Algorithm with Deep Learning Enabled Hyperspectral Remote Sensing Imaging Classification

Canadian Journal of Remote Sensing · vol. 48 (5) · 649-662

Hyperspectral imaging (HSI) can be attained by the use of high resolution optical sensors and it comprises several spectral bands of the identical remote sensing target and is treated as a three-dimension (3D) dataset. Recently, deep learning (DL) techniques are gained important attention among research communities for image classification. In this aspect, this study develops an intelligent rider optimization algorithm with deep learning enabled HSI classification model, named IRODL-HSIC technique. The proposed IRODL-HSIC technique aims to categorize the different class labels of the multispectral images. Besides, the IRODL-HSIC technique applies singular value decomposition. Moreover, the ResNet-152 technique was executed as a feature extractor to generate a collection of features. Furthermore, the rider optimization algorithm with cascaded recurrent neural network (CRNN) approach is utilized for the classification process. For ensuring the enhanced performance of the IRODL-HSIC algorithm, a wide range of simulations take place utilizing the multispectral images and the outcomes are examined under different aspects. The extensive comparative study highlighted the better performance of the IRODL-HSIC technique over the recent methods.

hyperspectral image classificationrider optimization algorithmdeep learningsingular value decomposition