Calò, Alessandro
(2023)
Applying Deep Learning methods on Particle Detector Data for Radioactive Beta Decay Analysis.
[Laurea magistrale], Università di Bologna, Corso di Studio in
Artificial intelligence [LM-DM270], Documento ad accesso riservato.
Documenti full-text disponibili:
![[img]](http://amslaurea.unibo.it/style/images/fileicons/application_pdf.png) |
Documento PDF (Thesis)
Full-text accessibile solo agli utenti istituzionali dell'Ateneo
Disponibile con Licenza: Salvo eventuali più ampie autorizzazioni dell'autore, la tesi può essere liberamente consultata e può essere effettuato il salvataggio e la stampa di una copia per fini strettamente personali di studio, di ricerca e di insegnamento, con espresso divieto di qualunque utilizzo direttamente o indirettamente commerciale. Ogni altro diritto sul materiale è riservato
Download (3MB)
| Contatta l'autore
|
Abstract
The objective of this thesis is to thoroughly portray the work done during a twelve week-long internship that revolved around one of the many projects that are currently active at GSI/FAIR, a research facility that hosts hundreds of scientist from all over the world, located in Germany. One of the main goals of this project was to better understand how methods based on Artificial Intelligence (AI) can be integrated in the field of Nuclear Physics research in order to achieve superior results compared to current analysis procedures. As such, this work represents a proof of principle, investigating the potential of AI and its applications in this domain. This project took place in the Nuclear Spectroscopy Group environment (under the supervision of Dr. Helena May Albers) and concerned AIDA (the Advanced Implantation Detector Array), a state-of-the-art detector system for the measurement of decay properties of exotic nuclei. In this work, AI was used in the form of Deep Neural Networks to tackle two different aspects of the problem: (i) being able to accurately identify the correct origin of decay traces and (ii) filter out the noise contribution measured by the detector. For task (i), hereafter referred to as the ``correlation" task, it was possible to obtain robust results when compared to algorithmical (non-AI) solutions by exploiting the features of convolutional layers. A successful proof of principle was also achieved in the noise filtering task (ii).
Abstract
The objective of this thesis is to thoroughly portray the work done during a twelve week-long internship that revolved around one of the many projects that are currently active at GSI/FAIR, a research facility that hosts hundreds of scientist from all over the world, located in Germany. One of the main goals of this project was to better understand how methods based on Artificial Intelligence (AI) can be integrated in the field of Nuclear Physics research in order to achieve superior results compared to current analysis procedures. As such, this work represents a proof of principle, investigating the potential of AI and its applications in this domain. This project took place in the Nuclear Spectroscopy Group environment (under the supervision of Dr. Helena May Albers) and concerned AIDA (the Advanced Implantation Detector Array), a state-of-the-art detector system for the measurement of decay properties of exotic nuclei. In this work, AI was used in the form of Deep Neural Networks to tackle two different aspects of the problem: (i) being able to accurately identify the correct origin of decay traces and (ii) filter out the noise contribution measured by the detector. For task (i), hereafter referred to as the ``correlation" task, it was possible to obtain robust results when compared to algorithmical (non-AI) solutions by exploiting the features of convolutional layers. A successful proof of principle was also achieved in the noise filtering task (ii).
Tipologia del documento
Tesi di laurea
(Laurea magistrale)
Autore della tesi
Calò, Alessandro
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
AI,Artificial Intelligence,Deep Learning,UNet,Convolutional Neural Networks,Particle Detector,GSI/FAIR,Beta Decay
Data di discussione della Tesi
16 Dicembre 2023
URI
Altri metadati
Tipologia del documento
Tesi di laurea
(NON SPECIFICATO)
Autore della tesi
Calò, Alessandro
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
AI,Artificial Intelligence,Deep Learning,UNet,Convolutional Neural Networks,Particle Detector,GSI/FAIR,Beta Decay
Data di discussione della Tesi
16 Dicembre 2023
URI
Statistica sui download
Gestione del documento: