جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

112 مُخرَج نتائج البحث عن «deep learning»

مقالوصول مفتوح20266استشهاد· Semantic Scholar

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

Scientific Reports · مجلد 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
مقالوصول مفتوح20261استشهاد· Semantic Scholar

Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network

Frontiers in Medicine · مجلد 13 · 1709872-1709872

Introduction: Diabetic retinopathy (DR) is an inflammatory condition affecting the retina caused by elevated and unregulated blood glucose levels. On a global scale, it is a contributing factor to vision impairment. Several deep learning (DL) methods use retinal images to identify DR severity. However, a significant improvement is required to assist medical professionals in recognizing DR in its early phases. Methods: Thus, the author introduced a method based on the DL technique to determine the DR severity grades using retinal images. A ShuffleNet V2 model with vision transformers' (ViT) attention mechanism was used to extract the features. An improved Whale optimization method (IWO) was used to fine-tune the feature extraction model. We employed a convolutional Kolmogorov-Arnold Network to categorize the DR severity using the extracted features. The EyePACS dataset was utilized to train the proposed DR severity grading model using a five-fold cross-validation strategy. We generalized the model on the Messidor-2 dataset. Results: The findings revealed an average accuracy of 93.84% on the MESSIDOR-2 dataset, demonstrating a substantial improvement in detecting DR using the fundus images. Discussion: Furthermore, the model demands minimal processing resources to generate the outcomes, leading to the deployment of the proposed DR severity detection model in healthcare facilities with limited computational resources.

diabetic retinopathyseverity classificationfundus imageswhale optimization algorithm
مقالوصول مفتوح20261استشهاد· Semantic Scholar

A hybrid deep learning framework for early detection of developmental disabilities using speech and behavioral biomarkers

Array · مجلد 29 · 100691-100691

Early and precise recognition of developmental disabilities (DDs) is essential for the timely intervention of preschool-age children. Although various predictive models have been developed in the past, they cannot provide accurate detections and face challenges like high false prediction, limited generalization, etc. To address these issues, a novel artificial intelligence (AI)-based algorithm was proposed for accurate DD detection. The proposed system integrates digital biomarkers from speech and behavioral domains for predicting DDs. Consequently, an Enhanced Gaussian-Based Noise Filtering (EGNF) is applied to speech data, and Z-score normalization is applied to behavioral data for preprocessing, which makes the raw data reliable for subsequent analysis. Further, feature extraction is performed using Convolutional-Bidirectional Long Short-Term Memory (Conv-BiLSTM) for speech data and Graph Attention Network (GAT) for behavioral data. Subsequently, a Hybrid Feature Selection (HFS) method was developed by combining the Harmony Search Algorithm (HSA) and ReliefF ranking for selecting informative and relevant attributes for model training. Finally, a hybrid classification model named DeepSTNet has been developed by integrating MnasNet and Independently Recurrent Neural Networks (IndRNN), which allows the capture of spatial and temporal long-term dependencies within the data, resulting in high detection performances. The proposed framework was implemented in Python and validated using comprehensive data formed by combining the Dysarthria Detection dataset and the Autism Dataset for Toddlers. The execution outcomes highlighted that the developed framework achieved an accuracy of 99.46%, a precision of 97.74%, and a recall of 98.05%, illustrating that this AI-centric system can be equipped by end users, including healthcare professionals and caregivers, with tools for early screening and detection of DDs.

developmental disabilitiesearly detectionspeech biomarkersbehavioral biomarkers
مقالوصول مغلق2026

Diagnostic Accuracy of Artificial Intelligence versus Clinical Diagnosis in Detecting Acute Otitis Media: A Systematic Review and Meta-analysis

Saudi Journal of Otorhinolaryngology Head and Neck Surgery

Abstract Acute otitis media (AOM) represents a prevalent infection in children globally, leading to considerable morbidity and imposing a substantial burden on healthcare systems. Prompt and precise diagnosis is critical to reducing complications, such as tympanic membrane perforation, hearing impairment, and excessive antibiotic prescribing. Advances in artificial intelligence (AI), particularly deep learning, have created opportunities to enhance diagnostic accuracy and broaden access to care, especially in low-resource settings. This systematic review and meta-analysis aimed to evaluate the diagnostic performance of AI-based systems for detecting AOM compared with conventional clinical diagnosis and to analyze their accuracy relative to human clinicians across different model architectures and diagnostic methods. Following PRISMA-DTA standards and PROSPERO registration, systematic searches were conducted in PubMed, Web of Science, and IEEE Xplore up to July 30, 2025. Eligible studies included human participants with suspected AOM, employed AI-driven diagnostic approaches, and used a clinical reference standard. The Quality Assessment of Diagnostic Accuracy Studies-2 tool assessed bias, and pooled sensitivity and specificity were estimated using a bivariate random-effects model. Nine studies published between 2020 and 2025 met the inclusion criteria. The pooled sensitivity and specificity were 91% (95% confidence interval [CI]: 77%–97%) and 99% (95% CI: 94%–100%), respectively. AI models overall matched or outperformed general practitioners and pediatricians, approaching otolaryngologist-level accuracy. AI-based tools have the potential to improve AOM detection, mitigate inequalities in healthcare access, and promote more effective diagnosis, particularly in underserved regions.

acute otitis mediaartificial intelligencedeep learningdiagnostic accuracy
مقالوصول مفتوح2026

VG-RETFound: a hybrid retinal AI framework for early vision impairment screening through vessel-graph learning and cross-modal fusion

Frontiers in Medicine · مجلد 13 · 1905129-1905129

Introduction: Vision impairment caused by retinal diseases stands out as one of the significant sources of irreversible blindness, highlighting the importance of developing robust automated screening tools to detect eye diseases at an early stage. Despite the promising results of recent deep learning approaches to the automatic classification of retinal images, most existing solutions focus on image-based representations and do not consider the importance of vascular topology. To overcome the limitations, this study proposes VG-RETFound - a hybrid framework based on a retinal foundation model and graph-based vascular-topology modeling that can be used to classify multiple retinal categories and detect vision impairment. Methods: The authors use RETFound-a retinal foundation model-pretrained on a vast number of retinal images, as well as the Graph Attention Network (GAT), to learn vascular topology features by representing retinal vessels as graphs. The presented approach employs a cross-modal multi-head attention fusion method to integrate features from both modalities in real time. To evaluate the efficiency of VG-RETFound, experiments were conducted using the RFMiD and ODIR-5 K datasets for model training and testing across six retinal categories: Normal, Diabetic Retinopathy, Pathological Myopia, Age-related Macular Degeneration, Hypertensive Retinopathy, and Other Retinal Diseases. Results: The accuracy of 96.39%, F1-score of 95.84%, MCC of 94.87%, and Kappa of 94.71% were attained on an internal test dataset, while cross-dataset external validation on the BRSET dataset revealed accuracy of 94.81%, F1-score of 94.25%, MCC of 93.09%, and Kappa of 92.94%. Discussion: These findings demonstrate that integrating retinal foundation models with anatomically informed vessel-topology learning significantly improves classification accuracy, interpretability, and generalization, highlighting the potential of VG-RETFound as a tool for large-scale vision impairment. screening and retinal disease diagnosis.

retinal disease classificationRETFoundgraph attention networksvascular topology
مقالوصول مغلق2026

Artificial Intelligence in Anatomical Education and Clinical Anatomy: Current Applications and Future Directions

— · مجلد 5 (1) · 97-103

Artificial intelligence (AI) is increasingly influencing medical education and clinical practice by providing new approaches to learning, visualization, diagnosis, decision-making, and personalized training. Anatomical education represents an important area for AI integration because conventional teaching methods often depend on cadaveric dissection, two-dimensional illustrations, atlases, and static imaging resources. Recent advances in machine learning, deep learning, computer vision, natural language processing, generative AI, and three-dimensional reconstruction have created opportunities to enhance the teaching and understanding of human anatomy. AI-supported anatomical education can facilitate automated identification of anatomical structures, generation of personalized learning materials, interactive three-dimensional models, intelligent tutoring, image-based assessment, and adaptive learning environments. In clinical anatomy, AI can assist with anatomical segmentation, interpretation of medical images, surgical planning, identification of anatomical variations, and simulation-based training. Nevertheless, the implementation of AI also presents challenges related to accuracy, bias, data privacy, explainability, cost, technological infrastructure, academic integrity, and the potential overreliance of students on automated systems. This review discusses the current applications of AI in anatomical education and clinical anatomy, examines its potential advantages and limitations, and considers future directions for responsible integration into anatomy curricula and healthcare practice. The future of AI-assisted anatomy is likely to involve multimodal learning environments combining three-dimensional visualization, augmented and virtual reality, intelligent tutoring systems, medical imaging, and generative AI. Rather than replacing anatomists and educators, AI is expected to function as an augmentative technology that supports deeper anatomical understanding, individualized learning, and clinically oriented education.

artificial intelligenceanatomy educationclinical anatomygenerative AI
مقالوصول مفتوح2026

RAD-OAEnsemble: Residual attention DenseNet with radiograph-EHR fusion and dual-stream deep feature embedding for knee osteoarthritis risk prediction

Egyptian Informatics Journal · مجلد 34 · 100929-100929

Knee osteoarthritis (OA) is a popular and progressive degenerate joint disease and require a predictor of risk at the primary stage to predict drug treatment and propose an early intervention. The current methods of deep learning are not sufficient enough to deal with integrating the heterogeneous modality component, modeling of irregular temporal follow ups, and capture of the fine grained variations of pathological types. In order to address such limitations, this paper suggests a new multimodal approach named, RAD-OAEnsemble which introduces three main innovations. First, a novel Cross Bi-modal Heterogeneous Graph Fusion Network (CBHGF-Net) is introduced for the multi-scale semantic fusion of Radiographs and Electronic Health Records (EHRs). Second, a Modified DenseNet with Multi-scale Attention Criss-Cross Blocks (MACC-Blocks) is presented to extract the anatomical features of knee OA patterns by utilizing dilated convolution, criss-cross attention, residual attention gating. Third, a Dual-Stream Tranfo-Convo (DTC) Deep Temporal Embedding module is proposed that consists of a Time-Warped Convolutional Blocks and a Temporal Decay Encoded Informer for the knee OA risk prediction. The suggested approach delivered better outcomes with accuracy of 99.275%, precision of 98.175%, specificity of 99.165%, sensitivity of 98.95%, and F1-score of 98.175% in having considerably a low rate of false positives (1.875%) and false negatives (2.175%). The findings support the relevance of the suggested framework in providing resilient, time-sensitive, and explainable OA progression predictions by multimodal combination and high-fidelity feature learning.

knee osteoarthritismultimodal fusionDenseNetattention mechanism
مقالمفتوح (مستودع)2026

Optimized Deep Learning Techniques for Enhanced Epilepsy Prediction from Electroencephalogram Signals

Advanced Health Science and Technology Journal · مجلد 2 (1) · 63-72

Abstract Background: Well over 65 million people throughout the world suffered from epilepsy, a common neurological illness. The success rate of standard medical interventions, including medication and surgery, is <30%. On the other hand, seizure prevention methods involving prompt therapeutic interventions are possible with early seizure prediction. Effective and highly accurate epilepsy prediction is still a challenge, despite experts’ best efforts. Aims and Objectives: We present the Particle Swarm Optimized–Convolutional Neural Network and Long Short Term Memory (PSO CNN LSTM) model for electroencephalogram (EEG) signal categorization to support epilepsy diagnosis. Materials and Methods: For EEG classification, we acquire EEG samples from the Bonn dataset that has been used in many reliable studies, which contains five categories of EEG signals, including both normal and epileptic samples. The dataset is preprocessed by removing artifacts and noise. The Short Time Fourier Transform method is subsequently employed for converting the EEG signals into spectrogram images. The postulated PSO CNN LSTM model and other deep learning models, such as CNN and CNN LSTM, employed these spectrogram images as inputs. MATLAB software was implemented for training and verifying models. Results and Conclusions: The studies’ findings revealed that the suggested PSO CNN LSTM model performs better than the other models, with an accuracy of 96% as opposed to 84% and 94%, respectively.

epileptic seizure predictionseizure predictionEEGEEG classification
مقالوصول مفتوح202532استشهاد· Semantic Scholar

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

Scientific Reports · مجلد 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
مقالوصول مفتوح202529استشهاد· Semantic Scholar

Optimizing IoT intrusion detection with cosine similarity based dataset balancing and hybrid deep learning

Scientific Reports · مجلد 15 (1) · 30939-30939

With IoT networks expected to exceed 29 billion connected devices by 2030, the risk of cyberattacks has never been higher. As more devices come online, the attack surface for hackers continues to expand, making cybersecurity a pressing concern. Intrusion Detection Systems (IDS) are essential for identifying and mitigating these threats in real-time. However, a significant challenge IDS faces is dealing with imbalanced datasets, where attack instances are significantly underrepresented compared to normal traffic. Training models on such skewed data leads to a bias toward majority-class patterns, reducing their ability to detect intrusions effectively. To address this issue, this work introduces CSMCR (Cosine Similarity-based Majority Class Reduction), a novel technique that selectively removes redundant majority-class samples while preserving dataset integrity. Unlike traditional approaches like SMOTE (oversampling) or random undersampling, CSMCR ensures that the retained majority instances remain diverse by analyzing feature-wise similarity. This prevents unnecessary data duplication and minimizes information loss. Additionally, we developed a hybrid deep learning model integrating RegNet and FBNet architectures to enhance feature extraction and classification performance. Experimental results on multiple IDS datasets confirm that balancing the dataset to a 1:1 ratio optimally prevents overfitting and improves model interpretability. The proposed model achieved an F1-score of 0.9758 on RT-IoT2022 and 0.9275 on UNSW Bot-IoT, outperforming SMOTE-based methods in accuracy and computational efficiency. Notably, CSMCR reduced training time by 53% compared to conventional oversampling techniques. Incremental training evaluations reveal that bias formation reduces performance beyond a 1:2 majority-to-minority ratio. These findings establish CSMCR as a robust, scalable, and computationally efficient IDS balancing strategy tailored for IoT network security.

IoT intrusion detectionclass imbalancecosine similaritydata balancing
مقالوصول مفتوح202524استشهاد· Semantic Scholar

Early attention-deficit/hyperactivity disorder (ADHD) with NeuroDCT-ICA and rhinofish optimization (RFO) algorithm based optimized ADHD-AttentionNet

Scientific Reports · مجلد 15 (1) · 6967-6967

The ADHD detector analyzes behavioral, cognitive, or physiological data (e.g., EEG, eye-tracking, or surveys) to identify patterns associated with ADHD symptoms. This work offers a more sophisticated method of detecting ADHD by overcoming the main drawbacks of existing approaches in terms of data processing, detection accuracy, and computational time. The work is inspired by the fact that Deep Learning (DL) frameworks could transform the existing detection systems of ADHD. In the proposed framework, there is a new NeuroDCT-ICA module for the preprocessing of raw EEG data, which guarantees the elimination of noise and extraction of informative features. Moreover, the method introduces a novel RhinoFish Optimization (RFO) algorithm for selecting optimal features, which enhance the data processing capacity and the stability of the system. As a core of the approach, there is the ADHD-AttentionNet - the deep learning-based model aimed at improving the accuracy and confidence of ADHD identification. The model is validated with the standard metrics, and the performance of the model is outstanding as it has high accuracy of 98.52%, F-score of 98.26% and specificity of 98.16%. These outcomes show that the proposed model yields better accuracy in detecting ADHD related patterns.

attention deficit hyperactivity disorderADHD detectionEEG preprocessingdiscrete cosine transform
مقالوصول مفتوح202518استشهاد· Semantic Scholar

Novel deep reinforcement learning based collision avoidance approach for path planning of robots in unknown environment

PLoS ONE · مجلد 20 (1) · e0312559-e0312559

Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system's capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach's agent converged in 210th episodes in a cluttered environment and 400th episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.

collision avoidancerobot path planningdeep reinforcement learningQ-learning
مقالوصول مفتوح202516استشهاد· Semantic Scholar

Enhancing pediatric congenital heart disease detection using customized 1D CNN algorithm and phonocardiogram signals

Heliyon · مجلد 11 (3) · e42257-e42257

Congenital heart disease (CHD), impacting around 1 % of infants worldwide, constitutes a significant healthcare challenge. Early detection is crucial, however constrained by the intricacies of conventional diagnostic techniques such as auscultation and echocardiography. This research presents a tailored one-dimensional convolutional neural network (1D-CNN) for the classification of phonocardiogram (PCG) signals into normal or abnormal categories, providing an automated and efficient solution for congenital heart disease (CHD) diagnosis. The model was trained on a composite dataset consisting of local pediatric PCG signals and publicly accessible dataset. Preprocessing methods, such as low- and high-pass filtering (60-650 Hz), resampling, and noise reduction, were utilized to enhance signal quality. Data augmentation techniques, including chunking, padding, and pitch-shifting, were employed to rectify dataset imbalances and improve model efficacy. Experimental results indicate substantial enhancements, attaining an accuracy of 98.56 %, precision of 98.56 %, F1 score of 98.55 %, sensitivity of 0.98, and specificity of 0.99. The comparative analysis demonstrates the proposed approach's superiority over current methods regarding accuracy and reliability. The research highlights the promise of combining modern signal processing with deep learning for efficient CHD screening. The suggested model exhibits outstanding performance yet, issues like dataset variability and noise persist. Future endeavors involve extending to multiclass categorization and assessing performance across a wider range of medical problems. This study represents a significant advancement in accessible, automated CHD diagnoses, enhancing clinical competence to elevate pediatric treatment.

congenital heart diseasephonocardiogram1D convolutional neural networkpediatric cardiology
مقالوصول مفتوح202510استشهاد· Semantic Scholar

Image classification-driven speech disorder detection using deep learning technique

SLAS TECHNOLOGY · مجلد 32 · 100261-100261

Speech disorders affect an individual's ability to generate sounds or utilize the voice appropriately. Neurological, developmental, physical, and trauma may cause speech disorders. Speech impairments influence communication, social interaction, education, and quality of life. Successful intervention entails early and precise diagnosis to allow for prompt treatment of these conditions. However, clinical examinations by speech-language pathologists are time-consuming, subjective, and demand an automated speech disorder detection (SDD) model. Mel-spectrogram images present a visual representation of multiple speech disorders. By classifying Mel-Spectrogram, various speech disorders can be identified. In this study, the authors proposed an image classification-based automated SDD model to classify Mel-Spectrograms to identify multiple speech disorders. Initially, Wavelet Transform (WT) hybridization technique was employed to generate Mel-Spectrogram using the voice samples. A feature extraction approach was developed using an enhanced LEVIT transformer. Finally, the extracted features were classified using an ensemble learning (EL) approach, containing CatBoost and XGBoost as base learners, and Extremely Randomized Tree as a meta learner. To reduce the computational resources, the authors used quantization-aware training (QAT). They employed Shapley Additive Explanations (SHAP) values to offer model interpretability. The proposed model was generalized using Voice ICar fEDerico II (VOICED) and LANNA datasets. The exceptional accuracy of 99.1 with limited parameters of 8.2 million demonstrated the significance of the proposed approach. The proposed model enhances speech disorder classification and offers novel prospects for building accessible, accurate, and efficient diagnostic tools. Researchers may integrate multimodal data to increase the model's use across languages and dialects, refining the proposed model for real-time clinical and telehealth deployment.

Mel spectrogramwavelet transformfeature extractionensemble learning