Machine learning for radioxenon event classification for the Comprehensive Nuclear-Test-Ban Treaty

Stocki, T. J.; Li, Guichong; Japkowicz, Nathalie; Ungar, R. Kurt

doi:10.1016/j.jenvrad.2009.08.015

Cited by 8 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, because there were no available explosion data, they provided synthesized explosion data. Stocki et al used several binary classifiers to discriminate between the background and synthesized explosion data and demonstrated that these methods outperformed simple linear discriminators. Following this study, Bellinger et al noted the “unnatural” a priori class probabilities that were inherent in the publicly available Health Canada CTBT data set, highlighting that the domain clearly fits into a 1‐class classification problem.…”

Section: Practical Case Studiesmentioning

confidence: 99%

“…Our work was inspired by research conducted over 3 real‐world domains. The first domain comprised data representing Xenon isotopes and dealt with the compliance verification of the Comprehensive Test Ban Treaty (CTBT); we were tasked with investigating whether machine learning could be applied so as to automate the detection of clandestine nuclear tests by nations. The second domain comprised gamma ray spectra and involved investigating the applicability of machine learning for the purposes of detecting gamma ray signatures emitted from dangerous isotopes, for example, uranium or plutonium.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning over subconcepts: Strategies for 1‐class classification

Sharma

Somayaji

Japkowicz

2017

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

In machine learning research and application, multiclass classification algorithms reign supreme. Their fundamental property is the reliance on the availability of data from all known categories to induce effective classifiers. Unfortunately, data from so‐called real‐world domains sometimes do not satisfy this property, and researchers use methods such as sampling to make the data more conducive for classification. However, there are scenarios in which even such explicit methods to rectify distributions fail. In such cases, 1‐class classification algorithms become the practical alternative. Unfortunately, domain complexity severely impacts their ability to produce effective classifiers. The work in this article addresses this issue and develops a strategy that allows for 1‐class classification over complex domains. In particular, we introduce the notion of learning along the lines of underlying domain concepts; an important source of complexity in domains is the presence of subconcepts, and by learning over them explicitly rather than on the entire domain as a whole, we can produce powerful 1‐class classification systems. The level of knowledge regarding these subconcepts will naturally vary by domain, and thus, we develop 3 distinct methodologies that take the amount of domain knowledge available into account. We demonstrate these over 3 real‐world domains.

show abstract

Section: Practical Case Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning over subconcepts: Strategies for 1‐class classification

Sharma

Somayaji

Japkowicz

2017

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

AI, WMD and Arms Control: The Case of Nuclear Testing

Heise¹

2022

Armament, Arms Control and Artificial Intelligence

View full text Add to dashboard Cite

Clustering Based One-Class Classification for Compliance Verification of the Comprehensive Nuclear-Test-Ban Treaty

Sharma

Bellinger

Japkowicz

2012

Advances in Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Monitoring the levels of radioxenon isotopes in the atmosphere has been proposed as a means of verifying the Comprehensive Nuclear-Test-Ban Treaty (CTBT). This translates into a classification problem, whereby the measured concentrations either belong to an explosion class or a background class. Instances drawn from the explosions class are extremely rare, if not non-existent. Therefore, the resulting dataset is extremely imbalanced, and inherently suited for one-class classification. Further exacerbating the problem is the fact that the background distribution can be extremely complex, and thus, modelling it using one-class learning is difficult. In order to improve upon the previous classification results, we investigate the augmentation of one-class learning methods with clustering. The purpose of clustering is to convert a complex distribution into simpler distributions, the clusters, over which more effective models can be built. The resulting model, built from oneclass learners trained over the clusters, performs more effectively than a model that is built over the original distribution. This thesis is empirically tested on three different data domains; in particular, a number of artificial datasets, datasets from the UCI repository, and data modelled after the extremely challenging CTBT. The results offer credence to the fact that there is an improvement in performance when clustering is used with one-class classification on complex distributions.

show abstract

Machine learning for radioxenon event classification for the Comprehensive Nuclear-Test-Ban Treaty

Cited by 8 publications

References 8 publications

Learning over subconcepts: Strategies for 1‐class classification

Learning over subconcepts: Strategies for 1‐class classification

AI, WMD and Arms Control: The Case of Nuclear Testing

Clustering Based One-Class Classification for Compliance Verification of the Comprehensive Nuclear-Test-Ban Treaty

Contact Info

Product

Resources

About