Alternate methods for anomaly detection in high-energy physics via semi-supervised learning

Recently, the concept of weakly supervised learning has gained popularity in the high-energy physics community due to its ability to learn even with a noisy and impure dataset. This method is valuable in the quest to discover the elusive beyond Standard Model (BSM) particle. Nevertheless, the weakly...

Full description

Bibliographic Details
Main Authors: Md. Ali, Mohd. Adli, Badrud’din, Nu’man, Abdullah, Hafidzul, Kemi, Faiz
Format: Article
Language:English
Published: World Scientific Publishing Co Pte Ltd 2020
Subjects:
Online Access:http://irep.iium.edu.my/82384/
http://irep.iium.edu.my/82384/1/Final-WS-IJMPA%20Sepohon.pdf
_version_ 1848789289441165312
author Md. Ali, Mohd. Adli
Badrud’din, Nu’man
Abdullah, Hafidzul
Kemi, Faiz
author_facet Md. Ali, Mohd. Adli
Badrud’din, Nu’man
Abdullah, Hafidzul
Kemi, Faiz
author_sort Md. Ali, Mohd. Adli
building IIUM Repository
collection Online Access
description Recently, the concept of weakly supervised learning has gained popularity in the high-energy physics community due to its ability to learn even with a noisy and impure dataset. This method is valuable in the quest to discover the elusive beyond Standard Model (BSM) particle. Nevertheless, the weakly supervised learning method still requires a learning sample that describes the features of the BSM particle truthfully to the classification model. Even with the various theoretical framework such as supersymmetry and the quantum black hole, creating a BSM sample is not a trivial task since the exact feature of the particle is unknown. Due to these difficulties, we propose an alternative classifier type called the one-class classification (OCC). OCC algorithms require only background or noise samples in its training dataset, which is already abundant in the high-energy physics community. The algorithm will flag any sample that does not fit the background feature as an abnormality. In this paper, we introduce two new algorithms called EHRA and C-EHRA, which use machine learning regression and clustering to detect anomalies in samples. We tested the algorithms’ capability to create distinct anomalous patterns in the presence of BSM samples and also compare their classification output metrics to the Isolation Forest (ISF), a well-known anomaly detection algorithm. Five Monte Carlo supersymmetry datasets with the signal to noise ratio equal to 1, 0.1, 0.01, 0.001, and 0.0001 were used to test EHRA, C-EHRA and ISF algorithm. In our study, we found that the EHRA with an artificial neural network regression has the highest ROC-AUC score at 0.7882 for the balanced dataset, while the C-EHRA has the highest precision-sensitivity score for the majority of the imbalanced datasets. These findings highlight the potential use of the EHRA, C-EHRA, and other OCC algorithms in the quest to discover BSM particles.
first_indexed 2025-11-14T17:54:21Z
format Article
id iium-82384
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T17:54:21Z
publishDate 2020
publisher World Scientific Publishing Co Pte Ltd
recordtype eprints
repository_type Digital Repository
spelling iium-823842022-07-15T03:24:19Z http://irep.iium.edu.my/82384/ Alternate methods for anomaly detection in high-energy physics via semi-supervised learning Md. Ali, Mohd. Adli Badrud’din, Nu’man Abdullah, Hafidzul Kemi, Faiz QA76 Computer software QC Physics Recently, the concept of weakly supervised learning has gained popularity in the high-energy physics community due to its ability to learn even with a noisy and impure dataset. This method is valuable in the quest to discover the elusive beyond Standard Model (BSM) particle. Nevertheless, the weakly supervised learning method still requires a learning sample that describes the features of the BSM particle truthfully to the classification model. Even with the various theoretical framework such as supersymmetry and the quantum black hole, creating a BSM sample is not a trivial task since the exact feature of the particle is unknown. Due to these difficulties, we propose an alternative classifier type called the one-class classification (OCC). OCC algorithms require only background or noise samples in its training dataset, which is already abundant in the high-energy physics community. The algorithm will flag any sample that does not fit the background feature as an abnormality. In this paper, we introduce two new algorithms called EHRA and C-EHRA, which use machine learning regression and clustering to detect anomalies in samples. We tested the algorithms’ capability to create distinct anomalous patterns in the presence of BSM samples and also compare their classification output metrics to the Isolation Forest (ISF), a well-known anomaly detection algorithm. Five Monte Carlo supersymmetry datasets with the signal to noise ratio equal to 1, 0.1, 0.01, 0.001, and 0.0001 were used to test EHRA, C-EHRA and ISF algorithm. In our study, we found that the EHRA with an artificial neural network regression has the highest ROC-AUC score at 0.7882 for the balanced dataset, while the C-EHRA has the highest precision-sensitivity score for the majority of the imbalanced datasets. These findings highlight the potential use of the EHRA, C-EHRA, and other OCC algorithms in the quest to discover BSM particles. World Scientific Publishing Co Pte Ltd 2020-07-13 Article PeerReviewed application/pdf en http://irep.iium.edu.my/82384/1/Final-WS-IJMPA%20Sepohon.pdf Md. Ali, Mohd. Adli and Badrud’din, Nu’man and Abdullah, Hafidzul and Kemi, Faiz (2020) Alternate methods for anomaly detection in high-energy physics via semi-supervised learning. International Journal of Modern Physics A. ISSN 0217-751X E-ISSN 1793-656X https://www.worldscientific.com/worldscinet/ijmpa
spellingShingle QA76 Computer software
QC Physics
Md. Ali, Mohd. Adli
Badrud’din, Nu’man
Abdullah, Hafidzul
Kemi, Faiz
Alternate methods for anomaly detection in high-energy physics via semi-supervised learning
title Alternate methods for anomaly detection in high-energy physics via semi-supervised learning
title_full Alternate methods for anomaly detection in high-energy physics via semi-supervised learning
title_fullStr Alternate methods for anomaly detection in high-energy physics via semi-supervised learning
title_full_unstemmed Alternate methods for anomaly detection in high-energy physics via semi-supervised learning
title_short Alternate methods for anomaly detection in high-energy physics via semi-supervised learning
title_sort alternate methods for anomaly detection in high-energy physics via semi-supervised learning
topic QA76 Computer software
QC Physics
url http://irep.iium.edu.my/82384/
http://irep.iium.edu.my/82384/
http://irep.iium.edu.my/82384/1/Final-WS-IJMPA%20Sepohon.pdf