Skip to content
AI Sec Watch

The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.

InfoResearchPeer-reviewed

TrustTiny-HAR: Selective, Open-Set, and Calibrated Activity Recognition on Microcontrollers

Source
IEEE Xplore (Security & AI Journals)(opens in a new tab)
Published
Record updated

Summary

TrustTiny-HAR is a pipeline for on-device human activity recognition on microcontrollers that pairs an int8 time-series backbone with a distilled trust head and a streaming conformal layer. Evaluated with leave-one-subject-out protocols on UCI HAR, PAMAP2 and WISDM, it matches int8 baselines on in-distribution macro-F1 (93.8 on UCI HAR) while improving calibration (ECE 2.4%) and out-of-distribution robustness (AUROC 0.96 for unseen classes). On nRF52840 and STM32L4 it adds under 10% energy overhead versus a TinyCNN baseline.