eng Ansari Education and Research Society Journal of Ultra Scientist of Physical Sciences October 2025 37 6 50 70 http://dx.doi.org/10.22147/jusps-B/370601 1549 article SUMAIYYA YASMEEN MUSTAFA KHAN 1 ARPANA CHOURASIYA 1 GHIZAL F. ANSARI 2 1Department of Computer Science, Madhyanchal Professional University Bhopal 2Department of Physics, Madhyanchal Professional University Bhopal <p style="text-align:justify">The goal of this study entails the design of a high-fidelity predictive model for Autism Spectrum Disorder (ASD), combining multi-modal behavioural, developmental, and interactional data with the aim offostering early diagnosis and intervention planning. This methodology takes advantage of a novel multimoduledeep learning pipeline, namely temporal modelling, multi-modal fusion (MMF), and causal inferencebasedlearning. These components are fully designed with the peculiar heterogeneous traits of ASD in mind.Five different specialized modules are introduced: (1) Dynamic Time Warping Auto-Encoder (DTW-AE), wheredynamic temporal alignment and compression of longitudinal developmental features are performed usingDTW-embedded LSTM autoencoder capturing individualized developmental trajectories; (2) Cross-Modal GraphConvolutional Network (CM-GCN): a Cross-Modal Graph Convolutional Network&mdash;that jointly learns intermodalityrelationships and fuses behavioural modalities together for eye gaze, facial dynamics, and prosody;(3) LSCE-CL: contrastive learning-based for the extraction of latent representation of social reciprocity from unstructured video/audio data; (4) BSTN: Bayesian Structural Time-Series Network for estimating causal impacts of interventions on behavioural outcome and, thus, conducting counterfactual simulations; (5) AAM-RIS: An adaptive attention-based module for real-time scoring of social engagement signals within downstream diagnostic classifications. The data inputs are developmental logs, behavioural sensor data, and interaction videos recorded&nbsp;by clinicians. The integrated pipeline substantiates gains over the baselines, with diagnostic accuracy of 93-95%, AUC-ROC of 0.95-0.97, and early ASD detection (&gt;3 years) accuracy of 88-90%. Furthermore, it was found that DTW-AE increases temporal representation accuracy by ~15%, CM-GCN improves the classification accuracyby ~12%, and BSTN reduces the error in the intervention forecasting process by ~15% RMSE. The study adds neural alignment of developmental timestamp series, real-time graph fusion of behavioural signals, and counterfactual modelling for ASD prediction. Future work will include scaling to become systems for personalizedtherapy recommendation and real-time clinical deployment for neurodevelopmental monitoring purposes.</p> https://ultraphysicalsciences.org/paper/1549/ Autism Prediction Temporal Alignment Multi-Modal Fusion