Jul 2026· International Conference Computing Methodologies and Communication· pp. 1297-1304· 0 citations· 17 references
Abstract
Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that manifests itself through unusual social interactions and visual attention. Thus, it is of prime importance to diagnose the condition correctly. In this context, this paper proposes a deep learning-based framework for the detection of Autism Spectrum Disorder by utilizing eye-tracking images. The structured framework of the paper is as follows: the images are first preprocessed through a structured framework involving resizing, min-max normalization, and Otsu threshold-based segmentation. Then, rotation-based data augmentation is performed on the images. Finally, the EfficientNet-B4 network is used in combination with Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) for the detection of ASD. The experimental results of the framework have shown that the framework has achieved a classification accuracy of 98.1%, thereby outperforming than other state-of-the-art techniques.
This study investigates the utilization of deep learning models to recognize ASD among 13-year-old children based on eye movement data collected as participants observed static images and short video sequences, highlighting the potential of deep learning frameworks as objective, data-driven tools for ASD detection in both clinical and research contexts.
Muhamad Syukron, R. Faresta· Jurnal Ilmiah Kursor· 0 citations
Autism Spectrum Disorder (ASD) is a prevalent neurodevelopmental condition for which early screening is essential to support timely intervention. Conventional diagnostic procedures are often time-consuming and resource-intensive, highlighting the need for accessible and cost-effective screening approaches. This study investigates the use of deep learning–based facial image analysis as a supportive tool for ASD screening rather than as a diagnostic solution. A comparative evaluation of three state-of-the-art convolutional neural network architectures EfficientNetB0, MobileNetV2, and ResNet50 is conducted using a unified experimental framework based on transfer learning and fine-tuning. Experiments are performed on a publicly available Autistic Children Facial Image Dataset, with an additional verification step to prevent duplicate images in order to enhance generalization and reduce potential bias. All models are trained and evaluated under identical conditions to ensure a fair comparison. Experimental results indicate that EfficientNetB0 achieves the best overall performance, reaching a test accuracy of 88%, while maintaining a favorable balance between model complexity and generalization ability.
Autism, or autism spectrum disorder (ASD), is a neurodevelopmental condition characterized by atypical development of neurons in the brain. Diagnosing ASD remains a major challenge due to the complexity and heterogeneity of the symptoms associated with this disorder. Early detection is essential, as rapid treatment significantly improves patients’ quality of life. However, traditional diagnostic methods are often subjective, time-consuming, and resource-intensive. To defeat these limitations, this study proposes an improved deep learning-based framework for the early detection of ASD from functional magnetic resonance imaging (fMRI) data. For this study, a pretrained Convolutional Neural Network (CNN) model EfficientNetB2 and a pretrained Vision Transformer (ViT) model ViT-B16 have been fine-tuned and then get combined to an hybrid model. All these models will be evaluated its performance on the pre-processed ABIDE dataset. Data augmentation techniques were also implemented to overcome the limitations of the dataset and improve the model’s generalization ability. The experimental results show that the fine-tuned EfficientNetB2 model achieves 96% accuracy, while the fine-tuned ViT-B16 model realises 95% and the hybrid model reaches 97%. These results were promising, highlight the potential of transfer learning models optimized for clinical applications, demonstrating their effectiveness to aid in the early and accurate diagnosis of ASD. This study thus contributes to the development of diagnostic systems compatible with the state of the art, paving the way for better management of neurodevelopmental disorders.
Fedia Bahloul, Raouia Mokni, M. Kherallah· International Conference on...· 0 citations
The proposed VGG16-based approach has potential as a supportive, non-invasive tool for early ASD screening and is deployed as an interactive, Streamlit-based web application that allows users to upload facial images and receive real-time predictions.
The growing prevalence of Autism Spectrum Disorder (ASD) highlights the need for accurate and reliable intelligent screening systems for early behavioral assessment. However, ASD-related behaviors vary significantly across individuals, making diagnosis based on a single modality or subjective evaluation unreliable. Moreover, existing computational approaches often struggle to effectively model complex spatial and temporal dependencies in behavioral video data, leading to limited feature representation. To address these challenges, this study proposes a Multi-head Attention-driven Multimodal Feature Integration Network (MAtMFIN) that jointly analyzes Eye-Tracking (ET) scanpath data and behavioral video data to improve the robustness of ASD screening. The framework employs a Hierarchical Attention Refinement block (HARb) and a Spatial Enhancement Module (SEM) for effective feature refinement, along with a cross-modal cross-attention mechanism to capture complementary relationships between modalities. Experimental evaluation on the proposed multimodal ASD dataset demonstrates that the proposed MAtMFIN framework consistently outperforms state-of-the-art transfer learning and Deep Learning (DL) models, including a hybrid Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) model, 2D-CNN with attention, LSTM-attention, Inflated 3D CNN, and Spatio-Temporal Graph Neural Networks (STGNN). The proposed method achieves a training accuracy of 94.6%, a testing accuracy of 93.2%, and an F1 score of 93.5%. These results indicate that effective cross-modal feature integration and attention-based modelling of spatio-temporal dependencies significantly enhance the ASD behavioral analysis, highlighting the potential of the proposed framework for intelligent healthcare applications.
A. R., Radha Senthilkumar· Discover Artificial Intellig...· 0 citations
These findings demonstrate the potential of computer vision-based analysis of children’s expressive activities as an effective, non-invasive ASD pre-screening tool and will focus on expanding dataset diversity and integrating multimodal behavioral cues to improve model generalization and clinical applicability.
Aina Khairina Ahmad Khair, Wan Mohd Yaakob Wan Bejuri, Mohd Murtadha Mohamad et al.· Bulletin of Electrical Engin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
