# Introducing 3DCNN ResNets for ASD full-body kinematic assessment: a comparison with hand-crafted features

arXiv: https://arxiv.org/abs/2311.14533 · HTML: https://mlsanity.com/paper/2311.14533/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 61 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Builds on (most cited first, 3 of 3)

- [Feature Selection: A Data Perspective](https://mlsanity.com/paper/1601.07996/) (2016)
- [Cross-validation failure: small sample sizes lead to large error bars](https://mlsanity.com/paper/1706.07581/) (2017)
- [Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification](https://mlsanity.com/paper/2109.07604/) (2021)

## Built on by (most cited first, 1 of 1)

- [Analysis of Motor Signatures of Social Adaptation in Autism for Efficient Human-Centric Systems](https://mlsanity.com/paper/2608.12548/) (2026)

## Abstract (arXiv)

Autism Spectrum Disorder (ASD) is characterized by challenges in social communication and restricted patterns, with motor abnormalities gaining traction for early detection. However, kinematic analysis in ASD is limited, often lacking robust validation and relying on hand-crafted features for single tasks, leading to inconsistencies across studies. End-to-end models have emerged as promising methods to overcome the need for feature engineering. Our aim is to propose a newly adapted 3DCNN ResNet from and compare it to widely used hand-crafted features for motor ASD assessment. Specifically, we developed a virtual reality environment with multiple motor tasks and trained models using both approaches. We prioritized a reliable validation framework with repeated cross-validation. Results show the proposed model achieves a maximum accuracy of 85±3%, outperforming state-of-the-art end-to-end models with short 1-to-3 minute samples. Our comparative analysis with hand-crafted features shows feature-engineered models outperformed our end-to-end model in certain tasks. However, our end-to-end model achieved a higher mean AUC of 0.80±0.03. Additionally, statistical differences were found in model variance, with our end-to-end model providing more consistent results with less variability across all VR tasks, demonstrating domain generalization and reliability. These findings show that end-to-end models enable less variable and context-independent ASD classification without requiring domain knowledge or task specificity. However, they also recognize the effectiveness of hand-crafted features in specific task scenarios.