Estimation of plasma equilibrium parameters via a neural network approach

Plasma equilibrium parameters such as position, X-point, internal inductance, and poloidal beta are essential information for efficient and safe operation of tokamak. In this work, the artificial neural network is used to establish a non-linear relationship between the measured diagnostic signals and selected equilibrium parameters. The estimation process is split into a preliminary classification of the kind of equilibrium(limiter or divertor) and subsequent inference of the equilibrium parameters. The training and testing datasets are generated by the tokamak simulation code(TSC), which has been benchmarked with the EAST experimental data. The noise immunity of the inference model is tested. Adding noise to model inputs during training process is proved to have a certain ability for maintaining performance.

Fiber-based optical parametric amplifier for 40-Gb/s NRZ-DPSK signal transmission system employing QC-LDPC codes

In this letter, we investigate quasi-cyclic low-density parity-check （QC-LDPC） codes in a 40-Gb/s nonreturn-to-zero differential phase-shift keying （NRZ-DPSK） signal transmission system based on a fiber- based optical parametric amplifier （FOPA）. A constructed algorithm of QC-LDPC codes according to the optimizing set of shift vMues on the circulant permutation matrix （CPM） of the basis matrix is proposed. Simulation results prove that the coding gain in the encoded system can be realized at 10.2 dB under QC- LDPC codes with a code rate of 5/6 when the bit error rate （BER） is 10-9. In addition, the error-floor level originating from the uncoded system is suppressed.

Deep Natural Image Reconstruction from Human Brain Activity Based on Conditional Progressively Growing Generative Adversarial Networks

Brain decoding based on functional magnetic resonance imaging has recently enabled the identification of visual perception and mental states.However,due to the limitations of sample size and the lack of an effective reconstruction model,accurate reconstruction of natural images is still a major challenge.The current,rapid development of deep learning models provides the possibility of overcoming these obstacles.Here,we propose a deep learning-based framework that includes a latent feature extractor,a latent feature decoder,and a natural image generator,to achieve the accurate reconstruction of natural images from brain activity.The latent feature extractor is used to extract the latent features of natural images.The latent feature decoder predicts the latent features of natural images based on the response signals from the higher visual cortex.The natural image generatoris applied to generate reconstructed images from the predicted latent features of natural images and the response signals from the visual cortex.Quantitative and qualitative evaluations were conducted with test images.The results showed that the reconstructed image achieved comparable,accurate reproduction of the presented image in both highlevel semantic category information and low-level pixel information.The framework we propose shows promise for decoding the brain activity.