Physics Augmented Tuple Transformer for Autism Severity Level Detection

TL;DR

This paper introduces a physics-informed neural network framework that leverages skeleton motion trajectories to improve autism severity detection, achieving state-of-the-art results and demonstrating versatility in fall prediction tasks.

Contribution

It presents a novel physics-augmented neural network architecture that encodes physical laws into ASD severity recognition from motion data, outperforming existing methods.

Findings

Achieved state-of-the-art performance on ASD diagnosis benchmarks.

Demonstrated effectiveness in fall prediction using the proposed framework.

Validated the model's versatility across different motion analysis tasks.

Abstract

Early diagnosis of Autism Spectrum Disorder (ASD) is an effective and favorable step towards enhancing the health and well-being of children with ASD. Manual ASD diagnosis testing is labor-intensive, complex, and prone to human error due to several factors contaminating the results. This paper proposes a novel framework that exploits the laws of physics for ASD severity recognition. The proposed physics-informed neural network architecture encodes the behaviour of the subject extracted by observing a part of the skeleton-based motion trajectory in a higher dimensional latent space. Two decoders, namely physics-based and non-physics-based decoder, use this latent embedding and predict the future motion patterns. The physics branch leverages the laws of physics that apply to a skeleton sequence in the prediction process while the non-physics-based branch is optimised to minimise the difference between the predicted and actual motion of the subject. A classifier also leverages the same latent space embeddings to recognise the ASD severity. This dual generative objective explicitly forces the network to compare the actual behaviour of the subject with the general normal behaviour of children that are governed by the laws of physics, aiding the ASD recognition task. The proposed method attains state-of-the-art performance on multiple ASD diagnosis benchmarks. To illustrate the utility of the proposed framework beyond the task ASD diagnosis, we conduct a third experiment using a publicly available benchmark for the task of fall prediction and demonstrate the superiority of our model.