PCA-Driven Adaptive Sensor Triage for Edge AI Inference

TL;DR

PCA-Triage is a fast, unsupervised streaming algorithm that adaptively allocates sensor sampling rates in industrial IoT networks to optimize bandwidth usage while maintaining high inference accuracy.

Contribution

The paper introduces PCA-Triage, a novel zero-parameter, real-time method for sensor triage that outperforms existing baselines across multiple benchmarks.

Findings

PCA-Triage achieves near full-data F1 scores at 50% bandwidth.

It outperforms 9 baselines on 6 datasets with large effect sizes.

The algorithm is robust to packet loss and sensor noise.

Abstract

Multi-channel sensor networks in industrial IoT often exceed available bandwidth. We propose PCA-Triage, a streaming algorithm that converts incremental PCA loadings into proportional per-channel sampling rates under a bandwidth budget. PCA-Triage runs in O(wdk) time with zero trainable parameters (0.67 ms per decision). We evaluate on 7 benchmarks (8--82 channels) against 9 baselines. PCA-Triage is the best unsupervised method on 3 of 6 datasets at 50% bandwidth, winning 5 of 6 against every baseline with large effect sizes (r = 0.71--0.91). On TEP, it achieves F1 = 0.961 +/- 0.001 -- within 0.1% of full-data performance -- while maintaining F1 > 0.90 at 30% budget. Targeted extensions push F1 to 0.970. The algorithm is robust to packet loss and sensor noise (3.7--4.8% degradation under combined worst-case).