Point-cloud based machine learning for classifying rare events in the Active-Target Time Projection Chamber

被引：0

作者：

Dey, Poulomi ^{[1
,2
]}

Anthony, Adam K. ^{[1
,3
,4
]}

Hunt, Curtis ^{[1
]}

Kuchera, Michelle P. ^{[5
,6
]}

Ramanujan, Raghuram ^{[6
]}

Lynch, William G. ^{[1
,3
]}

Tsang, ManYee Betty ^{[1
,3
]}

Wieske, Joseph M. ^{[1
,3
]}

Ajongbah, Jessica W. ^{[1
,2
]}

Beceiro-Novo, Saul ^{[1
]}

Brown, Kyle W. ^{[1
,2
]}

Chajecki, Zbigniew ^{[7
]}

Cook, Kaitlin J. ^{[1
,8
]}

Gangestad, Skyler ^{[4
]}

Ginter, Tom ^{[1
]}

Kendziorski, Bergen ^{[1
]}

Teh, Fanurs Chi Eh ^{[1
]}

Wong, Hoting ^{[7
,9
]}

机构：

[1] Michigan State Univ, Facil Rare Isotope Beams, E Lansing, MI 48824 USA

[2] Michigan State Univ, Dept Elect & Comp Engn, E Lansing, MI 48824 USA

[3] Michigan State Univ, Dept Phys & Astron, E Lansing, MI 48824 USA

[4] High Point Univ, Dept Phys & Astron, High Point, NC 27268 USA

[5] Davidson Coll, Dept Phys, Davidson, NC 28035 USA

[6] Davidson Coll, Dept Math & Comp Sci, Davidson, NC 28035 USA

[7] Western Michigan Univ, Dept Phys, Kalamazoo, MI 49008 USA

[8] Australian Natl Univ, Res Sch Phys, Dept Nucl Phys & Accelerator Applicat, Canberra, Australia

[9] Chinese Univ Hong Kong, Dept Phys, Shatin, Hong Kong, Peoples R China

来源：

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT | 2025年 / 1072卷

关键词：

Time Projection Chambers; Fission; Machine learning; Event Classification; PointNet; Anomaly Detection; RANDOM SAMPLE CONSENSUS; CLASSIFICATION; MODEL;

D O I：

10.1016/j.nima.2024.170002

中图分类号：

TH7 [仪器、仪表];

学科分类号：

0804 ; 080401 ; 081102 ;

摘要：

In this work, we assess the use of machine learning to classify fission events in the Active Target Time Projection Chamber (AT-TPC) using data from an experiment performed at the National Superconducting Cyclotron Laboratory at Michigan State University. The experiment produces an extremely large quantity of data, less than 3% of which are fission events. Therefore, separating fission events from the background beam events is critical to an efficient analysis. A heuristic method was developed to classify events as Fission or Non-Fission based on hand-tuned parameters. However, this heuristic method places 5% of all events into an Unlabeled category, including 15% of all fission events. We present a PointNet model trained on the data labeled by the heuristic method. This model is then used to generate labels for the events in the Unlabeled category. Using the heuristic and machine learning methods together, we can successfully identify 99% of fission events.

引用

页数：9

共 13 条

[1] Commissioning of the Active-Target Time Projection Chamber
Bradt, J.
Bazin, D.
Abu-Nimeh, F.
Ahn, T.
Ayyad, Y.
Novo, S. Beceiro
Carpenter, L.
Cortesi, M.
Kuchera, M. P.
Lynch, W. G.
Mittig, W.
Rost, S.
Watwood, N.
Yurkon, J.
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2017, 875 : 65 - 79
[2] Search for α-Cluster Structure in Exotic Nuclei with the Prototype Active-Target Time-Projection Chamber
Fritsch, A.
Ayyad, Y.
Bazin, D.
Beceiro-Novo, S.
Bradt, J.
Carpenter, L.
Cortesi, M.
Mittig, W.
Suzuki, D.
Ahn, T.
Kolata, J. J.
Howard, A. M.
Becchetti, F. D.
Wolff, M.
PROCEEDINGS OF THE 14TH INTERNATIONAL SYMPOSIUM ON NUCLEI IN THE COSMOS (NIC2016), 2016,
[3] The Prototype Active-Target Time-Projection Chamber used with TwinSol radioactive-ion beams
Ahn, T.
Bardayan, D. W.
Bazin, D.
Novo, S. Beceiro
Becchetti, F. D.
Bradt, J.
Brodeur, M.
Carpenter, L.
Chajecki, Z.
Cortesi, M.
Fritsch, A.
Hall, M. R.
Hall, O.
Jensen, L.
Kolata, J. J.
Lynch, W.
Mittig, W.
O'Malley, P.
Suzuki, D.
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION B-BEAM INTERACTIONS WITH MATERIALS AND ATOMS, 2016, 376 : 321 - 325
[4] Breakup, transfer, and fusion studies of exotic "halo" nuclei using an active-target time projection chamber.
Kolata, J. J.
Bazin, Daniel
Suzuki, Daisuke
Mittig, Wolfgang
5TH INTERNATIONAL CONFERENCE FUSION11, 2011, 17
[5] Fusion studies with low-intensity radioactive ion beams using an active-target time projection chamber
Kolata, J. J.
Howard, A. M.
Mittig, W.
Ahn, T.
Bazin, D.
Becchetti, F. D.
Beceiro-Novo, S.
Chajecki, Z.
Febbrarro, M.
Fritsch, A.
Lynch, W. G.
Roberts, A.
Shore, A.
Torres-Isea, R. O.
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2016, 830 : 82 - 87
[6] Fusion studies of low-intensity exotic beams using an active-target time-projection chamber
Howard, Alan M.
Kolata, James J.
Mittig, Wolfgang
Ahn, Tan
Bazin, Daniel
Becchetti, Frederick D.
Beceiro-Novo, Saul
Febbraro, Michael
Fritsch, Adam
Kohley, Zachary
Meisel, Zachary
Roberts, Amy
Torres-Isea, Ramone O.
ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2013, 246
[7] The Notre-Dame Cube: An active-target time-projection chamber for radioactive beam experiments and detector development
Ahn, T.
Randhawa, J. S.
Aguilar, S.
Blankstein, D.
Delgado, L.
Dixneuf, N.
Henderson, S. L.
Jackson, W.
Jensen, L.
Jin, S.
Koci, J.
Kolata, J. J.
Lai, J.
Levano, J.
Li, X.
Mubarak, A.
O'Malley, P. D.
Martin, S. Ramirez
Renaud, M.
Serikow, M. Z.
Tollefson, A.
Wilson, J.
Yan, L.
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2022, 1025
[8] Machine learning method for 12C event classification and reconstruction in the active target time-projection chamber
Wu, Huangkai
Wang, Youjing
Wang, Yumiao
Deng, Xiangai
Cao, Xiguang
Fang, Deqing
Ma, Weihu
He, Wanbing
Fu, Changbo
Ma, Yugang
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2023, 1055
[9] 3D lidar point-cloud projection operator and transfer machine learning for effective road surface features detection and segmentation
Li, Heyang Thomas
Todd, Zachary
Bielski, Nikolas
Carroll, Felix
VISUAL COMPUTER, 2022, 38 (05): : 1759 - 1774
[10] 3D lidar point-cloud projection operator and transfer machine learning for effective road surface features detection and segmentation
Heyang Thomas Li
Zachary Todd
Nikolas Bielski
Felix Carroll
The Visual Computer, 2022, 38 : 1759 - 1774

← 1 2 →