...
| marco.letizia@edu.unige.it | ||
| Social | N/A | Jira |
General Information
| ML/DL Technologies | Classification, Logistic Regression, Kernel Methods |
|---|---|
| Science Fields | High Energy Physics |
| Difficulty | Medium |
| Language | English |
| Type | Fully annotated, runnable |
...
Needed datasets
| Data Creator | INFN Legnaro laboratories |
|---|---|
| Data Type | Real acquisition |
| Data Size | 12 39 MB |
| Data Source | https://doi.org/10.5281/zenodo.7128223 |
...
A machine learning approach for monitoring particle detectors in real-time. The goal is to assess the compatibility of incoming experimental data with a reference dataset, characterising the data behaviour under normal circumstances, via a likelihood-ratio hypothesis test. The model is based on a modern implementation of kernel methods, nonparametric algorithms that can learn any continuous function given enough data. The resulting approach is efficient and agnostic to the type of anomaly that may be present in the data. Our study demonstrates the effectiveness of this strategy on multivariate data from drift tube chamber muon detectors.
How to execute it
Python environment, code and a fully annotated Code to reproduce the experiments in [1] with an illustrative Jupyter notebook are available at https://github.com/FalkonHEP/DQM.
References
[1] G. Grosso, N. Lai, M. Letizia, J. Pazzini, M. Rando, L. Rosasco, A. Wulzer, M. Zanetti, Fast kernel methods for Data Quality Monitoring as a goodness-of-fit test,[2303.05413].
[2] M. Letizia, G. Losapio, M. Rando, G. Grosso, A. Wulzer, M. Pierini, M. Zanetti, L. Rosasco,Learning new physics efficiently with nonparametric methods, Eur. Phys. J. C 82 (2022) 879 [2204.02317].
| Info |
|---|
| Presentation made on : https://agenda.infn.it/event/35822/contributions/198103/attachments/105222/147811/MarcoLetizia_MLINFN_May2023.pdf |