JCJihui Chen

Jihui Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jihui Chen has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Neutron penumbral image reconstruction with a convolution neural network using fast Fourier transform

    by Jianjun Song, Jianhua Zheng, Zhongjing Chen, Jihui Chen, Feng Wang

    In Inertial Confinement Fusion (ICF), the asymmetry of a hot spot is an important influence factor in implosion performance. Neutron penumbral imaging, which serves as an encoded-aperture imaging technique, is one of the most important diagnostic methods for detecting the shape of a hot spot. The detector image is a uniformly bright range surrounded by a penumbral area, which presents the strength distribution of hot spots. The present diagnostic modality employs an indirect imaging technique, necessitating the reconstruction process to be a pivotal aspect of the imaging protocol. The accuracy of imaging and the applicable range are significantly influenced by the reconstruction algorithm employed. We develop a neural network named Fast Fourier transform Neural Network (FFTNN) to reconstruct two-dimensional neutron emission images from the penumbral area of the detector images. The FFTNN architecture consists of 16 layers that include a FFT layer, convolution layer, fully connected layer, dropout layer, and reshape layer. Due to the limitations in experimental data, we propose a phenomenological method for describing hot spots to generate datasets for training neural networks. The reconstruction performance of the trained FFTNN is better than that of the traditional Wiener filtering and Lucy–Richardson algorithm on the simulated dataset, especially when the noise level is high as indicated by the evaluation metrics, such as mean squared error and structure similar index measure. This proposed neural network provides a new perspective, paving the way for integrating neutron imaging diagnosis into ICF.


  • Lensless computationally defined confocal incoherent imaging with a Fresnel zone plane as coded aperture

    by Jihui Chen, Feng Wang, Yulong Li, Xing Zhang, Ke Yao, Zanyang Guan, Xiangming Liu

    We present a Fresnel zone plate (FZP) mask-based system for single-shot lensless confocal imaging. The system uses an FZP as coded aperture, which allows each point source to cast a unique pattern onto the sensor, representing their horizontal and axial positions. This results in a 2D sensor measurement comprising a series of FZP patterns, which records the spatial intensity distribution of the incoherent illuminant. The reconstruction process is facilitated by an algorithm based on compress sensing (CS) theory and the use of the nuclear norm of gradient scanning and hologram segmentation technology for autofocusing. The simulative and experimental results of this study align well with the expectation that every layered scene can be accurately recovered at the corresponding depth, without undesirable signals from other layers. Additionally, we analyze the deviation of the reconstruction results in the experiment, which emphasizes the need to consider the thickness of the FZP for a precise forward propagation model.


  • Semg based human lower limb contimuous motion of estimation method

    by Y. Tao, Y. Huang, J. Zheng, J. Chen, Z. Zhang, Y. Guo

    For realizing the good perception function of the human lower limbs and improve the quality of human-machine coordination, a method of estimating the continuous movement of the human lower limbs based on sEMG is proposed. Five kinds of time, frequency and time domain characteristic parameters of 8 signals are extracted, and the BP is used to estimate the continuous movement of the lower limbs of the human body. For the traditional neural network, the initial weights and thresholds are set for empirical values, resulting in a relatively high prediction accuracy. Poor, this paper proposes a neural network continuous motion estimation method based on particle swarm optimization. After the experiment, the overall average rmse of the angle estimates of each movement after optimization is optimized from 0.49rad to 0.30rad, and the overall average correlation coefficient is optimized from 0.87 to 0.89.

  • Binary sinusoidal single-order multilayer gratings for tender x-ray region

    by Jihui Chen, Lai Wei, Zuhua Yang, Quanping Fan, Qiangqiang Zhang, Yong Chen, Dongxiao Liu, Weimin Zhou, Changqing Xie, Leifeng Cao, et al.

    We propose and theoretically analyze a single-order diffractive optical element, termed binary sinusoidal multilayer grating (BSMG), to effectively suppress high-order diffractions while retaining high diffraction efficiency in the first order. The key idea is to integrate sinusoidal-shaped microstructures with high-reflectivity multilayer coatings. The dependence of the high-order diffraction property on the microstructure shape and multilayer coatings is investigated. Theoretical calculation reveals that the second-, third-, fourth-, and fifth-order diffraction efficiencies are as low as 0.01%. Strikingly, we show that first-order relative diffraction efficiency (the ratio between the intensity of the first diffraction order versus that of the reflected light) as high as 97.7% can be achieved. Thus, the proposed BSMG should be highly advantageous in future development and application of tender x-ray spectroscopy.