College of Science and Mathematics
BS in Physics
Many of the various properties of neutrinos are still a mystery. One unknown is whether neutrinos are Majorana fermions or Dirac fermions. Cuoricino and CUORE are experiments that aim to solve this mystery. Noise reduction in these experiments hinges on the ability to discern among alpha, beta and gamma particle detections using the thermal pulses they create. In this paper, we look at Cuoricino data and attempt to classify pulses, not as alpha, beta or gamma particles, but rather as signal, noise or calibration data. We will use this preliminary testing ground to examine various machine learning algorithms' abilities in this dataset. We will consider and discuss the details of the Support Vector Classifier, Random Forest Classifier, Deep Neural Network, Convolutional Neural Network, and Mini Batch K-Means learning algorithms. Then, we will test the non-neural network algorithms on the data and discuss the results. Finally, we will propose future analysis and work that could be done to improve current results and to begin with particle classification.