A5021918820- Nuclear Physics and Applications
- Radiation Detection and Scintillator Technologies
- Neural Networks and Applications
- Medical Imaging Techniques and Applications
- Image and Signal Denoising Methods
- CCD and CMOS Imaging Sensors
- Infrared Target Detection Methodologies
- Advanced X-ray and CT Imaging
- Minerals Flotation and Separation Techniques
- Chaos-based Image/Signal Encryption
- Advanced Steganography and Watermarking Techniques
- Earthquake Detection and Analysis
- Neural dynamics and brain function
- Atomic and Subatomic Physics Research
- Particle Detector Development and Performance
- Cellular Automata and Applications
- Radioactivity and Radon Measurements
- Metal Extraction and Bioleaching
- Extraction and Separation Processes
- Advanced Image Fusion Techniques
Chengdu University of Technology
2016-2025
The Engineering & Technical College of Chengdu University of Technology
2021-2025
Southwestern Institute of Physics
2023-2025
Chengdu University of Information Technology
2023
Sichuan University
2023
Since the mid-1990s, X-ray phase contrast imaging (XPCI) has attracted increasing interest in industrial and bioimaging fields due to its high sensitivity weakly absorbing materials gained widespread acceptance. XPCI can simultaneously provide three modalities with complementary information, offering enriched details data. This study proposes an image fusion method that retrieves channels of XPCI. It integrates block features, non-subsampled contourlet transform (NSCT), a spiking cortical...
Abstract In this study, the anti-noise performance of a pulse-coupled neural network (PCNN) was investigated in neutron and gamma-ray ( n − $$\gamma$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>γ</mml:mi> </mml:math> ) discrimination field. The experiments were conducted two groups. first group, radiation pulse signals pre-processed using Fourier filter to reduce original noise signals, whereas second left untouched simulate an extremely high-noise scenario. For each...
Improving the efficiency of current neural networks and modeling them on biological systems have become prominent research directions in recent years. The pulse-coupled network (PCNN) is widely used to mimic computational characteristics human brain computer vision fields. However, PCNN faces limitations such as limited connections, high costs, a lack stochastic properties. This study proposes random-coupled (RCNN) address these limitations. RCNN employs inactivation process, selectively...
Accurately selecting neutron signals and discriminating gamma from a mixed radiation field is key research issue in detection.This paper proposes fractal spectrum discrimination approach by means of different spectral characteristics neutrons rays.Figure merit average discriminant error ratio are used together to evaluate the effects.Different with various noise pulse pile-up simulated according real data literature.The proposed compared digital charge integration gradient methods.It found...
Improving the efficiency of current neural networks and modeling them in biological systems have become popular research directions recent years. Pulse-coupled network (PCNN) is a well applicated model for imitating computation characteristics human brain computer vision fields. However, differences between PCNN remain: limited connection, high computational cost, lack stochastic property. In this study, random-coupled (RCNN) proposed. It overcomes these difficulties PCNN's neuromorphic...
In China, both vanadium(V) and chromium(VI) are present in wastewater resulting from vanadate precipitation (AVP wastewater) leaching vanadium-chromium reduction slag. Addressing environmental preservation the comprehensive utilization of metal resources necessitates extraction separation V(V) Cr(VI) these mixed solutions. However, their is complicated by very similar physicochemical properties. This study establishes a method for dynamic selective adsorption such mixtures. It evaluates...
This study utilized the Tempotron, a robust classifier based on third-generation neural network model, for pulse shape discrimination. By eliminating need manual feature extraction, Tempotron model can process signals directly, generating discrimination results prior knowledge. The performed experiments using GPU acceleration, resulting in over 500 times faster compared to CPU-based and investigated impact of noise augmentation performance. Experimental substantiated that serves as...
In this study, a spiking cortical model (SCM) based n-γ discrimination method is proposed. The SCM-based algorithm compared with three other methods, namely: (i) the pulse-coupled neural network (PCNN), (ii) charge comparison, and (iii) zero-crossing. objective evaluation criteria used for comparison are FoM-value time consumption of discrimination. Experimental results demonstrated that our proposed outperforms methods significantly highest FoM-value. Specifically, exhibits 34.81%...