EUVIMEDFaigh amach EUVIMED
Open access · CC BY 4.0

Deployable Stimming Classification From Wrist‐Worn 9 Degrees of Freedom Inertial Sensing: Accuracy, Memory, and Latency Trade‐Offs

Montserrat Ramirez‐De Angel, Neil Joshua Limbaga, Eckaard le Roux, Kareem Hamdan, Samanta Castro Rodriguez, Ahmed M. Eltawil, Khaled N. Salama

Advanced Intelligent Systems · 2026-11-15

DOI: 10.1002/aisy.70653 ↗

At a glance

Journal article in Advanced Intelligent Systems, published online on 2026-11-15. Written by Montserrat Ramirez‐De Angel and 6 co-authors. 38 references. The full text is freely available (open access, CC BY 4.0). Funded by: King Abdullah University of Science and Technology.

AchoimreSonraí leabharliostaCiteRelated studies

Abstract (original language)

Objective monitoring of repetitive motor behaviors, or stimming, could support quantitative assessment in autism research and assistive technology, but wearable systems reported to date are typically validated on very few participants and benchmarked on desktop hardware, leaving their actual deployability unresolved. Here, a compact wrist‐worn nine‐degree‐of‐freedom (9DoF) inertial sensing node is presented together with a deployment‐oriented rule for selecting a wearable classifier. Recordings from participants performing four stimming behaviors and two nonstimming control activities are used to compare three feature‐based classifiers and four deep‐learning architectures across four sensing configurations under fully subject‐independent validation. Accuracy is found not to be the limiting factor: across the feature‐based classifiers, macro‐ F 1 exceeds 0.97 for every model and sensing configuration, and stimming is separated from nonstimming activity with an F 1 above 0.998 using the accelerometer alone. Deployment cost, by contrast, varies by more than an order of magnitude, and porting the networks to the target microcontroller reveals on‐device inference spanning 3.7–631 ms, modifying the ranking obtained on a workstation. Model selection for wearable stimming monitoring is therefore governed by memory and latency rather than by accuracy, and on‐device measurement is shown to be a prerequisite rather than a refinement.

Funding

  • King Abdullah University of Science and Technology

Cite

APA

Angel, M. R., Limbaga, N. J., Roux, E. L., Hamdan, K., Rodriguez, S. C., Eltawil, A. M., & Salama, K. N. (2026). Deployable Stimming Classification From Wrist‐Worn 9 Degrees of Freedom Inertial Sensing: Accuracy, Memory, and Latency Trade‐Offs. Advanced Intelligent Systems. https://doi.org/10.1002/aisy.70653

Vancouver

Angel MR, Limbaga NJ, Roux EL, Hamdan K, Rodriguez SC, Eltawil AM, et al. Deployable Stimming Classification From Wrist‐Worn 9 Degrees of Freedom Inertial Sensing: Accuracy, Memory, and Latency Trade‐Offs. Advanced Intelligent Systems. 2026. doi:10.1002/aisy.70653

BibTeX
@article{Angel2026,
  author = {Angel, Montserrat Ramirez‐De and Limbaga, Neil Joshua and Roux, Eckaard le and Hamdan, Kareem and Rodriguez, Samanta Castro and Eltawil, Ahmed M. and Salama, Khaled N.},
  title = {Deployable Stimming Classification From Wrist‐Worn 9 Degrees of Freedom Inertial Sensing: Accuracy, Memory, and Latency Trade‐Offs},
  journal = {Advanced Intelligent Systems},
  year = {2026},
  doi = {10.1002/aisy.70653}
}
Start for free →