Saved in:
Bibliographic Details
Main Authors: Nirmal, Isura, Hu, Wen, Hassan, Mahbub, Aboutanios, Elias, Khamis, Abdelwahed
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.16764
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909547135762432
author Nirmal, Isura
Hu, Wen
Hassan, Mahbub
Aboutanios, Elias
Khamis, Abdelwahed
author_facet Nirmal, Isura
Hu, Wen
Hassan, Mahbub
Aboutanios, Elias
Khamis, Abdelwahed
contents We introduce BeaMsteerX (BMX), a novel mmWave hand hygiene gesture recognition technique that improves accuracy in longer ranges (1.5m). BMX steers a mmWave beam towards multiple directions around the subject, generating multiple views of the gesture that are then intelligently combined using deep learning to enhance gesture classification. We evaluated BMX using off-the-shelf mmWave radars and collected a total of 7,200 hand hygiene gesture data from 10 subjects performing a six-step hand-rubbing procedure, as recommended by the World Health Organization, using sanitizer, at 1.5m -- over five times longer than in prior works. BMX outperforms state-of-the-art approaches by 31--43% and achieves 91% accuracy at boresight by combining only two beams, demonstrating superior gesture classification in low SNR scenarios. BMX maintained its effectiveness even when the subject was positioned 30 degrees away from the boresight, exhibiting a modest 5% drop in accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16764
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving mmWave based Hand Hygiene Monitoring through Beam Steering and Combining Techniques
Nirmal, Isura
Hu, Wen
Hassan, Mahbub
Aboutanios, Elias
Khamis, Abdelwahed
Human-Computer Interaction
We introduce BeaMsteerX (BMX), a novel mmWave hand hygiene gesture recognition technique that improves accuracy in longer ranges (1.5m). BMX steers a mmWave beam towards multiple directions around the subject, generating multiple views of the gesture that are then intelligently combined using deep learning to enhance gesture classification. We evaluated BMX using off-the-shelf mmWave radars and collected a total of 7,200 hand hygiene gesture data from 10 subjects performing a six-step hand-rubbing procedure, as recommended by the World Health Organization, using sanitizer, at 1.5m -- over five times longer than in prior works. BMX outperforms state-of-the-art approaches by 31--43% and achieves 91% accuracy at boresight by combining only two beams, demonstrating superior gesture classification in low SNR scenarios. BMX maintained its effectiveness even when the subject was positioned 30 degrees away from the boresight, exhibiting a modest 5% drop in accuracy.
title Improving mmWave based Hand Hygiene Monitoring through Beam Steering and Combining Techniques
topic Human-Computer Interaction
url https://arxiv.org/abs/2503.16764