analiza aiqbench
This research applies attention-enhanced Transformer models to 3D gait data for automated Autism Spectrum Disorder screening, addressing limitations in subjective clinical assessments. By rigorously evaluating fold-to-fold statistical stability across distinct datasets, the study demonstrates high accuracy using non-invasive biomechanical biomarkers rather than raw video or generic computer vision tasks. The work represents a significant methodological advance in applying deep learning to neurodevelopmental diagnostics, though its primary focus remains on the machine learning architecture and application domain rather than core AI infrastructure or quantum mechanics.
3D Gait-Based Autism Classification Using Attention-Enhanced Deep Learning with Cross-Fold Statistical Stability Analysis
arXiv:2609.14159v1 Announce Type: cross Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose early diagnosis remains challenging because conventional clinical assessments are often subjective, time-consuming, and require expert evaluation. Gait provides a promising non-invasive behavioral biomarker for auto- mated ASD screening; however, existing studies have primarily relied on single-dataset evaluations, convolutional architectures, and descriptive summaries of cross-validation performance without formally assessing fold-to-fold stability. This study addresses these gaps with an attention-enhanced Transformer framework for ASD classification, evaluated on two structurally different 3D gait feature representations: precomputed statistical gait descriptors and raw biomechanical ground-reaction- force measurements. Under five-fold cross-validation, the proposed framework achieved 99.00% accuracy, 99.02% precision, 99.00% recall, 99.00% F1-score, and 99.00% specificity on the public Kinect-based benchmark, exceeding the performance of the compared state-of-the-art methods. On the independent private force-plate dataset, it achieved mean values of 95.00% accuracy, 93.81% precision, 96.67% recall, 95.13% F1-score, and 93.33% specificity.
Abstract:Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose early diagnosis remains challenging because conventional clinical assessments are often subjective, time-consuming, and require expert evaluation. Gait provides a promising non-invasive behavioral biomarker for auto- mated ASD screening; however, existing studies have primarily relied on single-dataset evaluations, convolutional architectures, and descriptive summaries of cross-validation performance without formally assessing fold-to-fold stability. This study addresses these gaps with an attention-enhanced Transformer framework for ASD classification, evaluated on two structurally different 3D gait feature representations: precomputed statistical gait descriptors and raw biomechanical ground-reaction- force measurements. Under five-fold cross-validation, the proposed framework achieved 99.00% accuracy, 99.02% precision, 99.00% recall, 99.00% F1-score, and 99.00% specificity on the public Kinect-based benchmark, exceeding the performance of the compared state-of-the-art methods. On the independent private force-plate dataset, it achieved mean values of 95.00% accuracy, 93.81% precision, 96.67% recall, 95.13% F1-score, and 93.33% specificity.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2609.14159 [cs.CV]
(or arXiv:2609.14159v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.14159 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 244 cuvinte
Subiecte conexe
Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection
arXiv · 9 sept. 2026
Leakage-Robust Evaluation and Data-Scale Sensitivity of Attention-Enhanced Multi-Task Learning for Joint Fault Diagnosis and Remaining Useful Life Estimation
arXiv · 21 iul. 2026
HyperAMS-Net: Adaptive Multi-Scale Spatial Hypergraph Network for Brain Disorder Classification
arXiv · 18 sept. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026