Efficient uncertainty aware human activity recognition on microcontrollers using hyperdimensional computing and conformal prediction.

In this paper, we tackle a core challenge for wearable human activity recognition (HAR), namely the recognition of daily-living and locomotion activities from inertial sensor windows: delivering reliable, interpretable uncertainty on tiny microcontrollers where latency, RAM, and energy are tightly constrained. Existing embedded approaches either calibrate softmax confidences, which are cheap but brittle under sensor placement or tempo shifts, or rely on generative or posterior-sampling schemes that exceed TinyML budgets. We propose hyperdimensional distance- and uncertainty-aware human activity recognition (HDUQ-HAR), an on-device hyperdimensional computing (HDC) framework that encodes each IMU window into a bipolar hypervector, classifies via prototype similarity, and derives three complementary, lightweight uncertainty signals from the same representation: (1) distance to the class prototype, (2) similarity gap to the runner-up, and (3) vote-dispersion capturing n-gram consensus. A label-conditional conformal layer converts these scores into set-valued predictions with finite-sample coverage guarantees and exposes a human-readable reason code indicating why uncertainty increased. Across UCI HAR, WISDM, PAMAP2, and OPPORTUNITY with subject-out splits and realistic shifts (orientation, gain, time-warp, missing axis, cross-placement), HDUQ-HAR achieves near-target coverage at [Formula: see text] with near-singleton sets on i.i.d. data (average size 1.18-1.25) and robust shift/OOD detection (AUROC 0.92-0.96), while running in 3-5 ms/window on Cortex-M4 with ∼6-9 KB RAM and ∼5-7 KB Flash. By unifying HDC geometry with label-conditional conformal prediction, our method shows that efficiency and reliability can co-exist in wearables, yielding small, calibrated sets that expand gracefully under shift and actionable explanations practitioners can trust.