Article

Efficient Uncertainty Aware Human Activity Recognition On Microcontrollers Using Hyperdimensional Computing And Conformal Prediction

2025-10-31

Abstract excerpt

<title>Abstract</title> <p>In this paper, we tackle a core challenge for wearable human activity recognition (HAR): delivering reliable, interpretable uncertainty on tiny microcontrollers where latency, RAM, and energy are tightly constrained. Existing embedded approaches either calibrate softmax confidences—cheap but brittle under sensor placement or tempo shifts—or rely on generative or posterior-sampling schem...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9cfbe888-f0e2-5248-adbd-d608d6fcfa44
DOI: 10.21203/rs.3.rs-7728157/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Efficient Uncertainty Aware Human Activity Recognition On Microcontrollers Using Hyperdimensional Computing And Conformal PredictionDOI 10.21203/rs.3.rs-7728157/v1Read

XTinyHAR: A Tiny Inertial Transformer for Human Activity Recognition via Multimodal Knowledge Distillation and Explainable AISemantic proximity Read

Generative AI-Driven Sensor Fusion forMissing-Modality and Open-Set SmartphoneActivity RecognitionSemantic proximity Read

A Real-Time Communication Framework for Distributed Wearable Human Activity RecognitionSemantic proximity Read

NDPAI: Neuroscience-Derived Predictive Active Inference for Calibrated Cross-Subject Wearable Stress DetectionSemantic proximity Read

Unsupervised Cross-Domain Adaptation for Wearable-based Human Activity RecognitionSemantic proximity Read

Hierarchical Fusion with Decision Enhancement for Human Activity Recognition Using Deep Learning FrameworkSemantic proximity Read

Large Language Models for Wearable Sensor-Based Human Activity Recognition, Health Monitoring, and Behavioral Modeling: A Survey of Early Trends, Datasets, and ChallengesSemantic proximity Read

From Offline Accuracy to Deployed Performance: A Four-Phase Evaluation of an Edge-Hosted Wearable Stress-Monitoring PlatformSemantic proximity Read

Cross-Domain Complementary Dual-Stream Deep Self-Supervised Learning Framework for Human Activity Recognition on Wearable DevicesSemantic proximity Read

STAR-RL: Stealth-Aware Targeted Adversarial Attack on Multimodal Sensors in Human Activity Recognition via Reinforcement LearningSemantic proximity Read

Self-Supervised Gait Event Detection from Smartphone IMUs for Human Performance and Sports MedicineSemantic proximity Read

A Unified Approach for Real-Time Human Activity Recognition in Wearable Devices Using Attention-Gated Spatiotemporal Fusion Networks and Optimized Sensor Data ProcessingSemantic proximity Read