Saved in:
Bibliographic Details
Main Author: Choi, Seongyun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.03995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911039786844160
author Choi, Seongyun
author_facet Choi, Seongyun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03995
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge
Choi, Seongyun
Machine Learning
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.
title Fast Re-Trainable Attention Autoencoder for Liquid Sensor Anomaly Detection at the Edge
topic Machine Learning
url https://arxiv.org/abs/2507.03995