On the Limits of Lossy Compression for Human Activity Recognition in Sensor Networks

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Abstract

Human activity recognition is crucial for tactile internet, virtual reality, and digital-twin applications. Previous works have analyzed machine learning for this purpose but often need to pay more attention to typical challenges when deploying these machine learning models in production. First, data must be transmitted to the network node on which the machine-learning model is running. However, scaling human activity recognition by the number of devices and users puts additional constraints on the available transmission channel. While transmitting less data saves bandwidth, removing redundant information from the data can also benefit machine learning. This paper addresses the problem of transmitting wearable sensor data for human activity recognition. To this end, we analyze the extent to which wearable sensor data can be compressed via sparse coding without sacrificing loss in recognition performance. We empirically illustrate, on various datasets, that only a fraction of sensor information is relevant for human activity recognition.

Details

Original languageEnglish
Title of host publication2023 IEEE 48th Conference on Local Computer Networks (LCN)
EditorsEyuphan Bulut, Florian Tschorsch, Kanchana Thilakarathna
PublisherIEEE Computer Society
Pages1-4
ISBN (electronic)979-8-3503-0073-4
Publication statusPublished - 2023
Peer-reviewedYes

Publication series

SeriesConference on Local Computer Networks (LCN)

Conference

Title48th IEEE Conference on Local Computer Networks , LCN 2023
Duration2 - 5 October 2023
CityDaytona Beach
CountryUnited States of America

External IDs

ORCID /0000-0001-7008-1537/work/158767463
ORCID /0000-0001-8469-9573/work/161891155