arXiv subjects

Pengcheng Ai

Publications and source records attributed to Pengcheng Ai.

10 recordsLinked to original sources

arXiv2026

Structured generalized sliced Wasserstein distance for keV X-ray polarization analysis with Gas Pixel Detector

Because of the special angular distribution of excited electrons by the photoelectric effect, the Gas Pixel Detector (GPD) is effective in measuring keV X-ray polarization of astrophysical events (e.g. gamma-ray bursts), by capturing ionization tracks of excited electrons as polarized images. Traditionally, the emission angles of photoelectrons are extracted from polarized images first, and statistics are then performed on these angles to infer the polarization direction and intensity. However, observation with the wide field of view requires the incident angle of X-rays not directly attainable through the traditional analysis process. In this paper, we propose using the generalized sliced Wasserstein (GSW) distance, projected by neural networks with random weights, as a completely data-driven approach to analyze X-ray polarization based on two-dimensional polarized images. We find the structures of the randomized neural networks matter when focusing on different aspects of the polarized images, and take advantage of the discrimination abilities by different neural network structures. The proposed method, named the structured GSW distance, successfully distinguishes polarized images with different configurations of incident angles and polarization directions. Furthermore, we build a simplified statistical model based on the von Mises distribution and the circular Wasserstein distance and compare the model against the proposed method, showing their high consistency. The computational method reported in this paper may benefit GPD-based polarimetry in astroparticle experiments and also pattern analysis on raw data from pixel detectors.

physics.data-an↗

arXiv2025

Towards energy-insensitive and robust neutron/gamma classification: A learning-based frequency-domain parametric approach

Neutron/gamma discrimination has been intensively researched in recent years, due to its unique scientific value and widespread applications. With the advancement of detection materials and algorithms, nowadays we can achieve fairly good discrimination. However, further improvements rely on better utilization of detector raw signals, especially energy-independent pulse characteristics. We begin by discussing why figure-of-merit (FoM) is not a comprehensive criterion for high-precision neutron/gamma discriminators, and proposing a new evaluation method based on adversarial sampling. Inspired by frequency-domain analysis in existing literature, parametric linear/nonlinear models with minimum complexity are created, upon the discrete spectrum, with tunable parameters just as neural networks. We train the models on an open-source neutron/gamma dataset (CLYC crystals with silicon photomultipliers) preprocessed by charge normalization to discover and exploit energy-independent features. The performance is evaluated on different sampling rates and noise levels, in comparison with the frequency classification index and conventional methods. The frequency-domain parametric models show higher accuracy and better adaptability to variations of data integrity than other discriminators. The proposed method is also promising for online inference on economical hardware and portable devices.

physics.ins-det↗

arXiv2025

Scintillation pulse characterization with spectrum-inspired temporal neural networks: case studies on particle detector signals

Particle detectors based on scintillators are widely used in high-energy physics and astroparticle physics experiments, nuclear medicine imaging, industrial and environmental detection, etc. Precisely extracting scintillation signal characteristics at the event level is important for these applications, not only in respect of understanding the scintillator itself, but also kinds and physical property of incident particles. Recent researches demonstrate data-driven neural networks surpass traditional statistical methods, especially when the analytical form of signals is hard to obtain, or noise is significant. However, most densely connected or convolution-based networks fail to fully exploit the spectral and temporal structure of scintillation signals, leaving large space for performance improvement. In this paper, we propose a network architecture specially tailored for scintillation pulse characterization based on previous works on time series analysis. The core insight is that, by directly applying Fast Fourier Transform on original signals and utilizing different frequency components, the proposed network architecture can serve as a lightweight and enhanced representation learning backbone. We prove our idea in two case studies: (a) simulation data generated with the setting of the LUX dark matter detector, and (b) experimental electrical signals with fast electronics to emulate scintillation variations for the NICA/MPD calorimeter. The proposed model achieves significantly better results than the reference model in literature and densely connected models and demonstrates higher cost-efficiency than conventional machine learning methods.

physics.ins-det↗

arXiv2023

Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning

Pulse timing is an important topic in nuclear instrumentation, with far-reaching applications from high energy physics to radiation imaging. While high-speed analog-to-digital converters become more and more developed and accessible, their potential uses and merits in nuclear detector signal processing are still uncertain, partially due to associated timing algorithms which are not fully understood and utilized. In this paper, we propose a novel method based on deep learning for timing analysis of modularized detectors without explicit needs of labelling event data. By taking advantage of the intrinsic time correlations, a label-free loss function with a specially designed regularizer is formed to supervise the training of neural networks towards a meaningful and accurate mapping function. We mathematically demonstrate the existence of the optimal function desired by the method, and give a systematic algorithm for training and calibration of the model. The proposed method is validated on two experimental datasets based on silicon photomultipliers (SiPM) as main transducers. In the toy experiment, the neural network model achieves the single-channel time resolution of 8.8 ps and exhibits robustness against concept drift in the dataset. In the electromagnetic calorimeter experiment, several neural network models (FC, CNN and LSTM) are tested to show their conformance to the underlying physical constraint and to judge their performance against traditional methods. In total, the proposed method works well in either ideal or noisy experimental condition and recovers the time information from waveform samples successfully and precisely.

physics.ins-det↗

arXiv2023

PulseDL-II: A System-on-Chip Neural Network Accelerator for Timing and Energy Extraction of Nuclear Detector Signals

Front-end electronics equipped with high-speed digitizers are being used and proposed for future nuclear detectors. Recent literature reveals that deep learning models, especially one-dimensional convolutional neural networks, are promising when dealing with digital signals from nuclear detectors. Simulations and experiments demonstrate the satisfactory accuracy and additional benefits of neural networks in this area. However, specific hardware accelerating such models for online operations still needs to be studied. In this work, we introduce PulseDL-II, a system-on-chip (SoC) specially designed for applications of event feature (time, energy, etc.) extraction from pulses with deep learning. Based on the previous version, PulseDL-II incorporates a RISC CPU into the system structure for better functional flexibility and integrity. The neural network accelerator in the SoC adopts a three-level (arithmetic unit, processing element, neural network) hierarchical architecture and facilitates parameter optimization of the digital design. Furthermore, we devise a quantization scheme compatible with deep learning frameworks (e.g., TensorFlow) within a selected subset of layer types. We validate the correct operations of PulseDL-II on field programmable gate arrays (FPGA) alone and with an experimental setup comprising a direct digital synthesis (DDS) and analog-to-digital converters (ADC). The proposed system achieved 60 ps time resolution and 0.40% energy resolution at signal to noise ratio (SNR) of 47.4 dB.

physics.ins-det↗

arXiv2022

Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning

Characterizing uncertainty is a common issue in nuclear measurement and has important implications for reliable physical discovery. Traditional methods are either insufficient to cope with the heterogeneous nature of uncertainty or inadequate to perform well with unknown mathematical models. In this paper, we propose using multi-layer convolutional neural networks for empirical uncertainty estimation and feature extraction of nuclear pulse signals. This method is based on deep learning, a recent development of machine learning techniques, which learns the desired mapping function from training data and generalizes to unseen test data. Furthermore, ensemble learning is utilized to estimate the uncertainty originating from trainable parameters of the network and to improve the robustness of the whole model. To evaluate the performance of the proposed method, simulation studies, in comparison with curve fitting, investigate extensive conditions and show its universal applicability. Finally, a case study is made using data from a NICA-MPD electromagnetic calorimeter module exposed to a test beam at DESY, Germany. The uncertainty estimation method successfully detected out-of-distribution samples and also achieved good accuracy in time and energy measurements.

physics.data-an↗

arXiv2021

Neural network--featured timing systems for radiation detectors: performance evaluation based on bound analysis

Waveform sampling systems are used pervasively in the design of front end electronics for radiation detection. The introduction of new feature extraction algorithms (eg. neural networks) to waveform sampling has the great potential to substantially improve the performance and enrich the capability. To analyze the limits of such algorithms and thus illuminate the direction of resolution optimization, in this paper we systematically simulate the detection procedure of contemporary radiation detectors with an emphasis on pulse timing. Neural networks and variants of constant fraction discrimination are studied in a wide range of analog channel frequency and noise level. Furthermore, we propose an estimation of multivariate Cramér Rao lower bound within the model using intrinsic-extrinsic parametrization and prior information. Two case studies (single photon detection and shashlik-type calorimeter) verify the reliability of the proposed method and show it works as a useful guideline when assessing the abilities of various feature extraction algorithms.

physics.data-an↗

arXiv2020

A deep learning approach to multi-track location and orientation in gaseous drift chambers

Accurate measuring the location and orientation of individual particles in a beam monitoring system is of particular interest to researchers in multiple disciplines. Among feasible methods, gaseous drift chambers with hybrid pixel sensors have the great potential to realize long-term stable measurement with considerable precision. In this paper, we introduce deep learning to analyze patterns in the beam projection image to facilitate three-dimensional reconstruction of particle tracks. We propose an end-to-end neural network based on segmentation and fitting for feature extraction and regression. Two segmentation branches, named binary segmentation and semantic segmentation, perform initial track determination and pixel-track association. Then pixels are assigned to multiple tracks, and a weighted least squares fitting is implemented with full back-propagation. Besides, we introduce a center-angle measure to judge the precision of location and orientation by combining two separate factors. The initial position resolution achieves 8.8 $μm$ for the single track and 11.4 $μm$ (15.2 $μm$) for the 1-3 tracks (1-5 tracks), and the angle resolution achieves 0.15$^{\circ}$ and 0.21$^{\circ}$ (0.29$^{\circ}$) respectively. These results show a significant improvement in accuracy and multi-track compatibility compared to traditional methods.

physics.data-an↗

arXiv2019

Timing and characterization of shaped pulses with MHz ADCs in a detector system: a comparative study and deep learning approach

Timing systems based on Analog-to-Digital Converters are widely used in the design of previous high energy physics detectors. In this paper, we propose a new method based on deep learning to extract the time information from a finite set of ADC samples. Firstly, a quantitative analysis of the traditional curve fitting method regarding three kinds of variations (long-term drift, short-term change and random noise) is presented with simulation illustrations. Next, a comparative study between curve fitting and the neural networks is made to demonstrate the potential of deep learning in this problem. Simulations show that the dedicated network architecture can greatly suppress the noise RMS and improve timing resolution in non-ideal conditions. Finally, experiments are performed with the ALICE PHOS FEE card. The performance of our method is more than 20% better than curve fitting in the experimental condition.

physics.data-an↗

arXiv2018

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

In the search for neutrinoless double-beta decay, the high-pressure gaseous Time Projection Chamber has a distinct advantage, because the ionization charge tracks produced by particle interactions are extended and the detector captures the full three-dimensional charge distribution with appropriate charge readout systems. Such information of tracks provides a crucial extra-handle for discriminating signal events against backgrounds. In this paper, we constructed a toy model to demonstrate where the discrimination power comes from and how much of it the neural network models have already harnessed. Then we adapted 3-dimensional convolutional and residual neural networks on the simulated double-beta and background charge tracks and tested their capabilities in classifying these two types of events. We show that both the 3D structure and the overall depth of the neural networks significantly improve the accuracy of the classifier and lead to results better than previous works. We also studied their performance under various spatial granularities as well as different diffusion and noise conditions. The results indicate that the methods are stable and generalize well despite varying experimental conditions.

physics.data-an↗