Saved in:
Bibliographic Details
Main Authors: Yue, Alexander, Jia, Haoyi, Gonski, Julia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.01118
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916900466851840
author Yue, Alexander
Jia, Haoyi
Gonski, Julia
author_facet Yue, Alexander
Jia, Haoyi
Gonski, Julia
contents Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges, machine learning in readout electronics can be leveraged for smart detector designs, enabling intelligent inference and data reduction at-source. Variational autoencoders (VAEs) offer a variety of benefits for front-end readout; an on-sensor encoder can perform efficient lossy data compression while simultaneously providing a latent space representation that can be used for anomaly detection. Results are presented from low-latency and resource-efficient VAEs for front-end data processing in a futuristic silicon pixel detector. Encoder-based data compression is found to preserve good performance of off-detector analysis while significantly reducing the off-detector data rate as compared to a similarly sized data filtering approach. Furthermore, the latent space information is found to be a useful discriminator in the context of real-time sensor defect monitoring. Together, these results highlight the multifaceted utility of autoencoder-based front-end readout schemes and motivate their consideration in future detector designs.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01118
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variational Autoencoders for At-Source Data Reduction and Anomaly Detection in High Energy Particle Detectors
Yue, Alexander
Jia, Haoyi
Gonski, Julia
Data Analysis, Statistics and Probability
High Energy Physics - Experiment
Instrumentation and Detectors
Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges, machine learning in readout electronics can be leveraged for smart detector designs, enabling intelligent inference and data reduction at-source. Variational autoencoders (VAEs) offer a variety of benefits for front-end readout; an on-sensor encoder can perform efficient lossy data compression while simultaneously providing a latent space representation that can be used for anomaly detection. Results are presented from low-latency and resource-efficient VAEs for front-end data processing in a futuristic silicon pixel detector. Encoder-based data compression is found to preserve good performance of off-detector analysis while significantly reducing the off-detector data rate as compared to a similarly sized data filtering approach. Furthermore, the latent space information is found to be a useful discriminator in the context of real-time sensor defect monitoring. Together, these results highlight the multifaceted utility of autoencoder-based front-end readout schemes and motivate their consideration in future detector designs.
title Variational Autoencoders for At-Source Data Reduction and Anomaly Detection in High Energy Particle Detectors
topic Data Analysis, Statistics and Probability
High Energy Physics - Experiment
Instrumentation and Detectors
url https://arxiv.org/abs/2411.01118