Hybrid CNN-LSTM Framework for Spatiotemporal Detection of Autism Based on Facial and Motor Behavior Analysis
Amirbay A. Mukhanova A. Abdikerimova G.
2025Institute of Electrical and Electronics Engineers Inc.
International Conference on Computer Science and Engineering, UBMK
2025Issue 20251070 - 1075 pp.
Early detection of autism spectrum disorder (ASD) remains a critical challenge in pediatric neurodevelopment. This study introduces a hybrid CNN-LSTM framework for automated ASD detection by analyzing spatiotemporal patterns in facial expressions, hand gestures, and body postures extracted from video recordings. Using the MediaPipe framework, 2D anatomical landmarks and dynamic motion energy metrics were computed to form a 1,639-dimensional feature vector per frame. The proposed model was benchmarked against three other architectures - CNN- BiLSTM, Conv1D-GRU, and CNN-Transformer - on a custom dataset of childrens behavioral recordings. Evaluation metrics demonstrated strong classification performance for the CNN- LSTM model (accuracy = 91.0%, AUC = 0.931), with statistical analysis confirming its robustness and stability. The findings suggest that the CNN-LSTM framework offers a reliable, interpretable, and scalable approach for real-time ASD screening.
ASD , computer vision , convolutional neural network (CNN) , deep learning , MediaPipe , spatiotemporal analysis
Text of the article Перейти на текст статьи
L. N. Gumilyov Eurasian National University, Faculty of Information Technology, Astana, Kazakhstan
L. N. Gumilyov Eurasian National University
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026