Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment

Abstract Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in 136Xe. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a 228Th calibration source. We train a network on Monte Carlo-simulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses.

Download Full-text

Three-dimensional convolutional neural networks for neutrinoless double-beta decay signal/background discrimination in high-pressure gaseous Time Projection Chamber

Journal of Instrumentation ◽

10.1088/1748-0221/13/08/p08015 ◽

2018 ◽

Vol 13 (08) ◽

pp. P08015-P08015 ◽

Cited By ~ 2

Author(s):

P. Ai ◽

D. Wang ◽

G. Huang ◽

X. Sun

Keyword(s):

Neural Networks ◽

High Pressure ◽

Beta Decay ◽

Convolutional Neural Networks ◽

Time Projection Chamber ◽

Three Dimensional ◽

Neutrinoless Double Beta Decay ◽

Double Beta Decay ◽

Decay Signal ◽

Time Projection

Download Full-text

Data Augmentation with Gabor Filter in Deep Convolutional Neural Networks for Sar Target Recognition

IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium ◽

10.1109/igarss.2018.8518792 ◽

2018 ◽

Cited By ~ 6

Author(s):

Ting Jiang ◽

Zongyong Cui ◽

Zhi Zhou ◽

Zongjie Cao

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Data Augmentation ◽

Gabor Filter ◽

Target Recognition ◽

Deep Convolutional Neural Networks ◽

Sar Target Recognition

Download Full-text

Environmental Sound Classification Using Deep Convolutional Neural Networks and Data Augmentation

2018 IEEE Recent Advances in Intelligent Computational Systems (RAICS) ◽

10.1109/raics.2018.8635051 ◽

2018 ◽

Cited By ~ 7

Author(s):

Nithya Davis ◽

K Suresh

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Data Augmentation ◽

Deep Convolutional Neural Networks ◽

Environmental Sound ◽

Sound Classification

Download Full-text

Understanding unconventional preprocessors in deep convolutional neural networks for face identification

SN Applied Sciences ◽

10.1007/s42452-019-1538-5 ◽

2019 ◽

Vol 1 (11) ◽

Author(s):

Chollette C. Olisah ◽

Lyndon Smith

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Network Architecture ◽

Data Augmentation ◽

Color Space ◽

Back Propagation ◽

Face Identification ◽

Deep Convolutional Neural Networks ◽

Softmax Classifier ◽

Deep Network

Abstract Deep convolutional neural networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessor’s module of the network. Therefore, in this paper, the network’s preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the deep network architecture, to investigate the contribution preprocessing makes to the network. Commonly used preprocessors are the data augmentation and normalization and are termed conventional preprocessors. Others are termed the unconventional preprocessors, they are: color space converters; grey-level resolution preprocessors; full-based and plane-based image quantization, Gaussian blur, illumination normalization and insensitive feature preprocessors. To achieve fixed network parameters, CNNs with transfer learning is employed. The aim is to transfer knowledge from the high-level feature vectors of the Inception-V3 network to offline preprocessed LFW target data; and features is trained using the SoftMax classifier for face identification. The experiments show that the discriminative capability of the deep networks can be improved by preprocessing RGB data with some of the unconventional preprocessors before feeding it to the CNNs. However, for best performance, the right setup of preprocessed data with augmentation and/or normalization is required. Summarily, preprocessing data before it is fed to the deep network is found to increase the homogeneity of neighborhood pixels even at reduced bit depth which serves for better storage efficiency.

Download Full-text

Combining data from high-energy pp-reactions and neutrinoless double-beta decay: Limits on the mass of the right-handed boson

International Journal of Modern Physics E ◽

10.1142/s0218301316500816 ◽

2016 ◽

Vol 25 (10) ◽

pp. 1650081

Author(s):

Osvaldo Civitarese ◽

Jouni Suhonen ◽

Kai Zuber

Keyword(s):

Beta Decay ◽

Hadron Collider ◽

Neutrinoless Double Beta Decay ◽

High Energy ◽

Double Beta Decay ◽

Minimal Extension ◽

Mixing Angle ◽

Combining Data ◽

The Right ◽

Lower Limits

From the recently established lower-limits on the nonobservability of the neutrinoless double-beta decay of [Formula: see text]Ge (GERDA collaboration) and [Formula: see text]Xe (EXO-200 and KamLAND-Zen collaborations), combined with the ATLAS and CMS data, we extract limits for the left–right (LR) mixing angle, [Formula: see text], of the [Formula: see text] electroweak Hamiltonian. For the theoretical analysis, which is a model dependent, we have adopted a minimal extension of the Standard Model (SM) of Electroweak Interactions belonging to the [Formula: see text] representation. The nuclear-structure input of the analysis consists of a set of matrix elements and phase-space factors, and the experimental lower-limits for the half-lives. The other input are the ATLAS and CMS cross-section measurements of the [Formula: see text]-collisions into two-jets and two-leptons, performed at the large hadron collider (LHC). Our analysis yields the limit [Formula: see text] for [Formula: see text], by combining the model-dependent limits extracted from the double-beta-decay measurements and those extracted from the results of the CMS and ATLAS measurements.

Download Full-text