Reproduce “AutoML for Multi-Class Anomaly Compensation of Sensor Drift” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Melanie Schaller, Mathis Kruse, Antonio Ortega, Marius Lindauer, Bodo Rosenhahn
The authors evaluate AutoML-DC for multi-class gas classification under sensor drift by training on five earlier chronological batches and testing on five later batches, while automatically selecting preprocessing, models, and ensembles. On one dataset, AutoML-DC reaches Precision 0.77, Recall 0.76, and F1 0.76, versus CNN’s 0.60 F1. The result does not establish generalization beyond this dataset or drift.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.