English

Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge

Machine Learning 2025-07-08 v1

Abstract

A lightweight, edge-deployable pipeline is proposed for detecting sensor anomalies in chemistry and biology laboratories. A custom PCB captures seven sensor channels and streams them over the local network. An Attention-based One-Class Autoencoder reaches a usable state after training on only thirty minutes of normal data. Despite the small data set, the model already attains an F1 score of 0.72, a precision of 0.89, and a recall of 0.61 when tested on synthetic micro-anomalies. The trained network is converted into a TensorFlow-Lite binary of about 31 kB and runs on an Advantech ARK-1221L, a fan-less x86 edge device without AVX instructions; end-to-end inference latency stays below two seconds. The entire collect-train-deploy workflow finishes within one hour, which demonstrates that the pipeline adapts quickly whenever a new liquid or sensor is introduced.

Keywords

Cite

@article{arxiv.2507.03995,
  title  = {Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge},
  author = {Seongyun Choi},
  journal= {arXiv preprint arXiv:2507.03995},
  year   = {2025}
}

Comments

11 pages, 2 figure

R2 v1 2026-07-01T03:47:37.348Z