2026· Communication in Physical Sciences· 0 citations
TL;DR
A Hybrid Intelligent Model designed to predict ASD in pediatric cases, leveraging adaptive neuro-fuzzy systems integrates artificial neural network capabilities with fuzzy logic, offering a comprehensive approach to ASD prediction.
Abstract
Autism Spectrum Disorder (ASD) presents a significant challenge in early diagnosis and intervention due to its complexand varied symptomatology. ASD poses significant challenges in early detection and intervention due to its multifaceted nature. This study presents a Hybrid Intelligent Model designed to predict ASD in pediatric cases, leveraging adaptive neuro-fuzzy systems. The model integrates artificial neural network capabilities with fuzzy logic, offering acomprehensive approach to ASD prediction. A diverse dataset comprising behavioral observations, developmental milestones, and clinical assessments is utilized to identify key features relevant to ASD diagnosis. These features include eye contact, gesture use, language skills, sensitivity to pain, communication abilities, and social interaction. Through fuzzy logic-based soft computing techniques, the model achieves enhanced accuracy in predicting ASD and assessing its severity in children. Sensitivity analysis highlights the significant contributions of input variables to ASD prediction, withsensitivity to pain, eye contact level, and social interaction emerging as crucial factors. Comparative analysis with the Back Propagation Algorithm underscores the superiority of the proposed Hybrid Algorithm in error minimization across various phases of model training and evaluation. The findings underscore the potential of adaptive neurofuzzy systems in facilitating early ASD diagnosis, enabling timely intervention and support for affected children and their families.This research contributes to advancing the understanding and management of ASD, offering valuable insights for clinical practice and research in pediatric neurodevelopmental disorders.
Autism Spectrum Disorder (ASD) is a neurological and developmental condition characterized by challenges in social interaction, communication (both verbal and non-verbal), and repetitive behaviours. While genetics play a key role in its onset, early diagnosis remains essential for effective intervention. Machine learning (ML) offers a promising approach to streamline and accelerate ASD detection, making it faster and more cost-effective than traditional methods. This paper evaluates eight classification models to identify key ASD features and automate diagnosis. We compare their performance on large datasets to enhance predictive accuracy. ML has transformed healthcare by leveraging vast data volumes for analysis, with technological advances over the past decade improving diagnostic tools now standard in medical settings. ASD affects individuals variably, with symptoms typically appearing between 18 months and 3 years. Although genetic and environmental factors contribute, no single cause is confirmed. Traditional screenings rely heavily on clinician expertise, involving manual assessments and scoring, which can be subjective and time-consuming—even experts face uncertainties in predicting onset or severity. Parents seek rapid, reliable results. ML and deep learning (DL) address these gaps by analyzing complex patterns in data, enabling early prediction of ASD and its severity. This study implements diverse algorithms to support precise, automated screening, reducing diagnostic delays and improving outcomes.
Devireddy Mamatha, K. Maheswari· 2026 6th International Confe...· 0 citations
The proposed ensemble-based machine learning classifier methodology presented in this study seeks to revolutionize the diagnosis of ASD by harnessing the collective power of various machine learning algorithms to enhance diagnostic precision, mitigate the subjectivity associated with traditional diagnostic methods, and accelerate the detection process.
Shabeena Lylath, Laxmi B. Rananavare· IAES International Journal o...· 0 citations
Autism Spectrum Disorder (ASD) is associated with a nervous system development condition identified by persistent challenges in social communication and behavior, typically identified in the formative years. It is associated with repetitive behaviours and difficulties in social interaction among affected beings. Various approaches to autism spectrum disorder classification have been developed, comprising emotional tests, facial image analysis, and neuroimaging techniques. ASD is a challenging task to diagnose through medical analysis, and some tests are time-consuming and more expensive. In this research article, a novel approach with an Optimized Pre-Trained Feature Selection With Support Vector Machine (OPFSVM) detection model for ASD is proposed to overcome the existing challenges and problems. The novel method accurately identifies Autism in children; this study employed a pre-trained ResNet50 feature extraction method. The feature selection process is performed using a Particle Swarm Optimization (PSO)approach that helps improve system performance by eliminating irrelevant feature sets while retaining the most significant ones. Subsequently, the Support Vector Machine (SVM) model is applied to perform two-class classification of ASD. The proposed (OPFSVM) model integrates pretrained feature extraction and optimized feature processing in the SVM model with binary classification to accurately detect Autism in children. For training the proposed model, an online accessible dataset is used, including facial images for kids, analyzed with Autism, and control subjects categorized as either autistic or non-autistic. According to the outcomes, the suggested OPFSVM model is achieving 97% accuracy, 97% precision, and reducing the 3% error rate, compared with other methods (Vgg19, ResNet50, MobileNet, etc.). These findings highlight the implemented method's high effectiveness in early ASD detection and position it as an effective tool for timely and rapid analysis.
Robin Khurana, Satyaveer Singh· international journal of eng...· 0 citations
Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by persistent deficits in social communication, interaction, and behavioral patterns. Early screening is essential for timely intervention; however, conventional diagnostic procedures are often resource-intensive, subjective, and dependent on clinical expertise. This study proposes an integrated hybrid artificial intelligence framework for preliminary ASD screening by combining machine learning and deep learning techniques using structured behavioral data and facial image analysis. The first module employs a Random Forest classifier to analyze Autism Quotient-10 (AQ-10) questionnaire responses together with demographic and medical history attributes, including age, gender, ethnicity, family history, and developmental factors. The second module utilizes ResNet18 with transfer learning to classify facial images after preprocessing and data augmentation, enabling non-invasive image-based screening. Both predictive models are integrated into a user-friendly screening application developed using CustomTkinter, allowing independent questionnaire-based and image-based assessments through a unified graphical interface. Model training incorporates feature preprocessing, hyperparameter optimization using Grid Search with cross-validation, and performance evaluation using accuracy, precision, recall, F1-score, specificity, and area under the receiver operating characteristic curve (ROC-AUC). Experimental results demonstrate that the Random Forest model achieved an accuracy of 96.8%, while the ResNet18 model attained 94.2% accuracy, indicating the effectiveness of combining behavioral and facial information for preliminary ASD screening. The proposed framework is intended as a clinical decision-support tool to facilitate accessible and timely screening and is not designed to replace comprehensive clinical diagnosis.
Neha A. Kandalkar, R. Jogekar· Adolescência e Saúde· 0 citations
With Early detection of Autism Spectrum Disorder (ASD) can make a life-changing difference in a child’s journey,
helping them receive the right support at the right time. This project introduces a smart, hybrid system that combines advanced
deep learning technology with proven treatment methods, aiming to close the gap between diagnosis and meaningful help. It
examines various types of information such as behavioural assessments and sensory response patterns to train a model that can
identify early signs of autism with high accuracy and consistency. When the system detects a possible case, it provides structured,
theory-based activities designed to develop cognitive, social, emotional, and communication skills in young children. These
activities are based on widely accepted approaches and are intended to encourage steady developmental growth. A major strength
of this system is its automated reporting feature, which gathers diagnostic insights, structured treatment recommendations, and
predicted progress into a clear, easy-to-read report for parents, therapists, and healthcare professionals, ensuring everyone stays
informed and aligned. By blending advanced computational analysis with trusted treatment practices, the system ensures both
accurate detection and a smooth path to intervention. It supports early diagnosis, ongoing guidance, and continuous monitoring,
helping reduce delays and improving engagement in a child’s developmental plan. This combined approach demonstrates how
technology and professional expertise can work together to create an accessible, practical tool for ASD management. Its goal is
to transform early detection into immediate, meaningful action that nurtures potential, builds confidence, and helps shape a
brighter future for every child.
S. Ahmed, Shaikh Faeik, Shaikh Israhil et al.· International Journal for Re...· 0 citations
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by significant heterogeneity, making the accurate classification of its severity levels crucial for effective intervention. This study develops and validates a comprehensive machine learning framework to classify ASD severity (mild, moderate, severe) by investigating the differential impact of feature engineering and selection. A dataset of 340 individuals was analyzed using a dual-framework approach, integrating supervised classification (SVM, Random Forest, XGBoost) and unsupervised clustering (K-Means, Hierarchical, GMM). The methodology centered on comparing a feature-centric approach, using a hybrid selection strategy on 60 engineered and original features, against a baseline approach using only 33 original features. The feature-centric approach yielded markedly superior results; a Random Forest classifier, trained on a minimal subset of just nine engineered features, achieved a test accuracy of 76.5%, significantly outperforming all other models, including an SVM trained on 22 original features (70.6% accuracy). This highlights that feature quality is more critical than quantity. The unsupervised analysis revealed a critical “evaluation paradox,” where radical, unguided feature reduction improved geometric cluster cohesion but degraded clinical accuracy. Conversely, a guided, domain-informed selection improved both internal and external metrics.
Arazo Mohammed Mustafa· ARID International Journal f...· 0 citations