# Detecting Agitation Before Behavioral Escalation in Autistic Youth Through Multimodal Wearable Sensing

arXiv: https://arxiv.org/abs/2609.24791 · HTML: https://mlsanity.com/paper/2609.24791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 56 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [PaPaGei: Open Foundation Models for Optical Physiological Signals](https://mlsanity.com/paper/2410.20542/) (2024)
- [Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation](https://mlsanity.com/paper/2211.04772/) (2022)
- [UniMTS: Unified Pre-training for Motion Time Series](https://mlsanity.com/paper/2410.19818/) (2024)
- [Activity Recognition with Moving Cameras and Few Training Examples: Applications for Detection of Autism-Related Headbanging](https://mlsanity.com/paper/2101.03478/) (2021)
- [A Survey on Physiological Signal Based Emotion Recognition](https://mlsanity.com/paper/2205.10466/) (2022)
- [A foundation model for electrodermal activity data](https://mlsanity.com/paper/2603.16878/) (2026)
- [Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensors](https://mlsanity.com/paper/2605.17618/) (2026)

## Abstract (arXiv)

Challenging behaviors including aggression, self-injury, and property destruction are observed in 68% of autistic youth and pose risks to youth and caregivers. These episodes are preceded by agitation, a rising state of distress expressed through movement, vocalization, and autonomic arousal. Its signs are subtle and individualized, and its autonomic components are invisible without instrumentation. We collected upper-body movement from inertial measurement units, physiology from a wrist-worn device, and vocalizations from lapel microphones across 30 clinician-led sessions with 15 autistic youth, paired with expert behavioral annotations. We adapt four pretrained foundation models, one per modality, project each to a shared 128-dimensional space, and fuse them into a single group model. The model detected agitation with an area under the ROC curve of 0.724 at the clinician-annotated onset (within-participant permutation p=0.0005), declining to 0.608 at 30,s before onset. Thirteen of fifteen participants were above chance. A from-scratch configuration reached only 0.58, while frozen and fine-tuned features performed comparably (0.71 and 0.72). Audio contributed most of the signal, and a watch-only configuration stayed near chance. Individualized agitation is therefore detectable, including in unannotated windows preceding the annotated onset, using foundation-model transfer with one shared model rather than one per child.