Skip to main navigation Skip to search Skip to main content

Task-Difficulty Aware Meta-Learning for Adaptive Few-Shot Human Activity Recognition Using UWB Sensors

  • Seoul National University of Science and Technology (SNUST)
  • Grit Custom-IC Corp.
  • National NanoFab Center

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study presents the Difficulty-Adaptive Strategy Selector for Learning (DASSL), a task-aware metalearning framework designed for adaptive few-shot human activity recognition (HAR) with ultra-wideband (UWB) sensors. To validate the proposed system, we evaluated DASSL using data acquired with our self-developed UWB sensor. DASSL dynamically adjusts key training parameters-learning rate, regularization, and inner-loop update steps-based on taskspecific statistical difficulty indicators, including intra-class variance, inter-class similarity, and query-support alignment. Experimental results show that DASSL achieves 90.2% accuracy, outperforming fixed-strategy and task-agnostic metalearning baselines by 6.5% and 4.9%, respectively. Furthermore, the adaptive selection of hyperparameters enhances interpretability and computational efficiency, making the framework well-suited for deployment in resourceconstrained elderly health assistance systems.

Original languageEnglish
Title of host publicationIEEE SENSORS 2025 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331544676
DOIs
StatePublished - 2025
Event2025 IEEE SENSORS - Vancouver, Canada
Duration: 19 Oct 202522 Oct 2025

Publication series

NameProceedings of IEEE Sensors
ISSN (Print)1930-0395
ISSN (Electronic)2168-9229

Conference

Conference2025 IEEE SENSORS
Country/TerritoryCanada
CityVancouver
Period19/10/2522/10/25

Keywords

  • Elderly health assistance system
  • Few-shot learning
  • Human activity recognition
  • Meta-learning
  • Task difficultyaware adaptation
  • UWB sensors

Fingerprint

Dive into the research topics of 'Task-Difficulty Aware Meta-Learning for Adaptive Few-Shot Human Activity Recognition Using UWB Sensors'. Together they form a unique fingerprint.

Cite this