E-viri
Recenzirano
Odprti dostop
-
Abratenko, P.; Alrashed, M.; Anthony, J.; Asaadi, J.; Ashkenazi, A.; Balasubramanian, S.; Baller, B.; Barnes, C.; Bathe-Peters, L.; Berkman, S.; Bhat, A.; Blake, A.; Caratelli, D.; Castillo Fernandez, R.; Cavanna, F.; Cerati, G.; Chen, Y.; Church, E.; Conrad, J. M.; Convery, M.; Cooper-Troendle, L.; Crespo-Anadón, J. I.; Dennis, S. R.; Devitt, D.; Diurba, R.; Duffy, K.; Dytman, S.; Eberly, B.; Ereditato, A.; Fiorentini Aguirre, G. A.; Fitzpatrick, R. S.; Franco, D.; Furmanski, A. P.; Goodwin, O.; Gramellini, E.; Gu, W.; Hagaman, L.; Itay, R.; Jan de Vries, J.; Ji, X.; Jo, J. H.; Kamp, N.; Karagiorgi, G.; Ketchum, W.; Kirby, B.; Kobilarcik, T.; Li, K.; Li, Y.; Luo, X.; Marchionni, A.; Martin-Albo, J.; Martinez Caicedo, D. A.; McConkey, N.; Mettler, T.; Mills, J.; Mistry, K.; Mohayai, T.; Moor, A. F.; Navrer-Agasson, A.; Neely, R. K.; Nienaber, P.; Nowak, J.; Palamara, O.; Papavassiliou, V.; Pate, S. F.; Prince, S.; Raaf, J. L.; Rafique, A.; Ren, L.; Rochester, L.; Ross-Lonergan, M.; Schukraft, A.; Seligman, W.; Shaevitz, M. H.; Sharankova, R.; Sinclair, J.; Smith, A.; Snider, E. L.; Soderberg, M.; Söldner-Rembold, S.; Soleti, S. R.; Spitz, J.; Stancari, M.; John, J. St; Strauss, T.; Szelc, A. M.; Tagg, N.; Tang, W.; Terao, K.; Tsai, Y. -T.; Uchida, M. A.; Usher, T.; Van De Pontseele, W.; Williams, Z.; Wospakrik, M.; Yandel, E.; Yarbrough, G.; Yates, L. E.; Zeller, G. P.; Zhang, C.
Physical review. D, 03/2021, Letnik: 103, Številka: 5Journal Article
We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino properties and interactions. SparseSSNet is a submanifold sparse convolutional neural network, which provides the initial machine learning based algorithm utilized in one of MicroBooNE's ν_e-appearance oscillation analyses. The network is trained to categorize pixels into five classes, which are re-classified into two classes more relevant to the current analysis. The output of SparseSSNet is a key input in further analysis steps. This technique, used for the first time in liquid argon time projection chambers data and is an improvement compared to a previously used convolutional neural network, both in accuracy and computing resource utilization. The accuracy achieved on the test sample is ≥99%. For full neutrino interaction simulations, the time for processing one image is ≈ 0.5 sec, the memory usage is at 1 GB level, which allows utilization of most typical CPU worker machine.
