Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Developing a Bubble Chamber Particle Discriminator Using Semi-Supervised Learning
arXiv.org
27 Nov 2018
Abstract
The identification of non-signal events is a major hurdle to overcome for
bubble chamber dark matter experiments such as PICO-60. The current practice of
manually developing a discriminator function to eliminate background events is
difficult when available calibration data is frequently impure and present only
in small quantities. In this study, several different discriminator
input/preprocessing formats and neural network architectures are applied to the
task. First, they are optimized in a supervised learning context. Next, two
novel semi-supervised learning algorithms are trained, and found to replicate
the Acoustic Parameter (AP) discriminator previously used in PICO-60 with a
mean of 97% accuracy.
Metrics
6 Record Views
Details
- Title
- Developing a Bubble Chamber Particle Discriminator Using Semi-Supervised Learning
- Creators
- B MatuschC AmoleM ArdidI. J ArnquistD. M AsnerD BaxterE BehnkeM BresslerB BroermanG CaoC. J ChenU ChowdhuryK ClarkJ. I CollarP. S CooperC. B CoutuC CowlesM CrislerG CrowderN. A Cruz-VenegasC. E DahlM DasS FallowsJ FarineI FelisR FilgasF GirardG GirouxJ HallC HardyO HarrisT HillierE. W HoppeC. M JacksonM JinL KlopfensteinC. B KraussM LaurinI LawsonA LeblancI LevineC LicciardiW. H LippincottB LoerF MamedovP MitraC MooreT NaniaR NeilsonA. J NobleP OedekerkA OrtegaM. -C PiroA PlanteR PodviyanukS PriyaA. E RobinsonS SahooO ScallonS SethA SonnenscheinN StarinskiI ŠteklT SullivanF TardifE Vázquez-JáureguiN WalkowskiE WeimaU WichoskiK WiermanY YanV ZacekJ Zhang
- Publication Details
- arXiv.org
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Accelerated Career Entry Bachelor of Science in Nursing (BSN); Physics
- Other Identifier
- 991021863139904721