Embedding Principal Component Analysis for Data Reductionin Structural Health Monitoring on Low-Cost IoT Gateways

TL;DR

This paper introduces a memory-efficient, parallel streaming PCA algorithm tailored for low-cost IoT gateways, significantly reducing data size and memory usage while maintaining signal quality, enabling effective structural health monitoring on embedded platforms.

Contribution

It presents a novel parallel streaming PCA implementation optimized for embedded IoT devices, achieving high compression and memory reduction with minimal signal degradation.

Findings

10x data compression factor

59x memory reduction

4.8x speedup on multi-core platform

Abstract

Principal component analysis (PCA) is a powerful data reductionmethod for Structural Health Monitoring. However, its computa-tional cost and data memory footprint pose a significant challengewhen PCA has to run on limited capability embedded platformsin low-cost IoT gateways. This paper presents a memory-efficientparallel implementation of the streaming History PCA algorithm.On our dataset, it achieves 10x compression factor and 59x memoryreduction with less than 0.15 dB degradation in the reconstructedsignal-to-noise ratio (RSNR) compared to standard PCA. More-over, the algorithm benefits from parallelization on multiple cores,achieving a maximum speedup of 4.8x on Samsung ARTIK 710.