Advanced pulse shape discrimination via machine learning for applications in thermonuclear fusion

Gelfusa, M.; Rossi, Riccardo; Lungaroni, M.; Belli, F.; Spolladore, Luca; Wyss, Ivan; Gaudio, P.; Murari, A.; Contributors, Jet

doi:10.1016/j.nima.2020.164198

Cited by 24 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, machine learning methods are also widely used in the tasks of thermonuclear fusion. In the study [12] the authors compare two machine learning tools: Gaussian Mixture Models and Support Vector Machine to carry out the classification taskdistinguishing neutrons and gamma-rays in thermonuclear fusion. As a result, the authors declare that the approaches are in very good agreement and these methods greatly outperform previously used classification algorithms, by providing the probability of each example being a neutron or a gamma-ray.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

The study of statistical features of the evolution of complex physical systems using adaptive machine learning methods

Yunusov

Demin

Elenev

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In this work, we discuss various machine learning methods and their implementation in the field of complex physical systems for the analysis of experimental data. These methods: classical machine learning, neural nets and deep learning allow greatly outperforming classical analysis methods by giving the algorithm the ability to “learn” and perform tasks adapting to the data provided and search. Neural nets and deep learning approaches are used to search for hidden patterns of the suggested input data that can’t be analyzed using common methods. This variety of methods can be applied to study collective phenomena in plasma and thermonuclear fusion on the basis of experimental data of physical experiments with a higher level of performance than classical approaches.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

The study of statistical features of the evolution of complex physical systems using adaptive machine learning methods

Yunusov

Demin

Elenev

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The first time interval represents the whole pulse, while the second one represents the decaying portion of the pulse. The CC method is usually used in state-of-the art methods for performance comparison [16][17][18][19][20]. Furthermore, many recent techniques have used the CC method to label the collected pulses for training and testing classification models [21,22].…”

Section: Related Workmentioning

confidence: 99%

“…Recently, machine learning has been employed for pulse classification to improve the discrimination performance [1,18,21,22,28,29]. In [21], Both Linear Vector Quantization (LVQ) and Self-Organized Maps (SOM) were employed.…”

Section: Related Workmentioning

confidence: 99%

Robust pulse shape discrimination algorithm using canonical correlation analysis of gamma and neutron pulses

El-Shazly

Abdelhakim

2023

J. Inst.

View full text Add to dashboard Cite

In this paper, a robust pulse shape discrimination algorithm is proposed to classify neutron and gamma pulses in radiation detectors. Scalogram of the induced pulses, which represent the absolute value of the Continuous Wavelet Transform (CWT) coefficients in the time-frequency domain, is used as feature descriptors. A two-dimensional principal component analysis (2D PCA) is employed to achieve dimensionality reduction of the obtained features and remove the redundancy in the given data. Accordingly, dominant features are selected and stacked together to construct two feature sets representing the two classes (neutron and gamma). Canonical Correlation Analysis is performed between the testing and training feature sets to find the basis vectors on which the new projected set pairs are highly correlated. Experimental results showed that the proposed method outperforms the other state-of-the art PSD methods in terms the discrimination accuracy.

show abstract

“…Gần đây, mạng nơron nhân tạo (MNRNT) đã được ứng dụng rất thành công trong các bài toán phân nhóm đối tượng, và đặc biệt hiệu quả đối với những đối tượng có các đặc điểm nhận dạng phức tạp 12 . Mặc dù MNRNT đã được nghiên cứu ứng dụng vào nhận dạng xung nơtron/gamma [13][14][15][16] , nhưng các nghiên Trích dẫn bài báo này: Chuân P V, Hải N X, Anh N N, Hải P X, Phong M X, Khang P D, Minh T V, Tài D T, Duyên L T H.…”

Section: Tóm Tắtunclassified

Application of artificial neural network in neutron/gamma pulse shape discrimination for EJ301 scintillation detector

Phan

Nguyen²,

Nguyễn³

et al. 2021

Sci. Tech. Dev. J.- Eng. Tech.

View full text Add to dashboard Cite

The scintilator detectors are sensitive to both neutron and gamma radiation. Therefore, right identification of the pulses which generated by neutrons or gamma ray from these detectors plays an important role in neutron measurement by using scintilator detector. In order to improve the ability to pulse shape discrimination (PSD), many PSD techniques have been studied, developed and applied. In this work, we use a basic configuration of a Fully connected Neural network (Fc- Net) where the number of elements of the network is minimum, and each element corresponds to identified specification of neutron or gamma pulses measured by using EJ-301 scintilator detector. The minimum of error principle has been applied for neuron network design; therefore, the accuracy of recognitions did not affect by this reduced network. The obtained results show that the identify accuracy of FcNet is higher than those of digital charge integration (DCI) method. Being tested using 60Co radioactive source, it is shown that, with the application of the FcNet, the accuracy of the gamma pulses discrimination acquires 98.60% in the energy region from 50 to 2000 keV electron equivalent energy (keVee), and 95.59% in the energy region from 50 to 150 keVee. In general, the obtained results indicate that the artificial neural network method can be applied to build neutron/gamma spectrometers with limited hardware.

show abstract

Advanced pulse shape discrimination via machine learning for applications in thermonuclear fusion

Cited by 24 publications

References 11 publications

The study of statistical features of the evolution of complex physical systems using adaptive machine learning methods

The study of statistical features of the evolution of complex physical systems using adaptive machine learning methods

Robust pulse shape discrimination algorithm using canonical correlation analysis of gamma and neutron pulses

Application of artificial neural network in neutron/gamma pulse shape discrimination for EJ301 scintillation detector

Contact Info

Product

Resources

About