In the process of wireless image transmission, there are a large number of interference signals, but the traditional interference signal recognition system is limited by various modulation modes, it is difficult to accurately identify the target signal, and the reliability of the system needs to be further improved. In order to solve this problem, a wireless image transmission interference signal recognition system based on deep learning is designed in this paper. In the hardware part, STM32F107VT and SI4463 are used to form a wireless controller to control the execution of each instruction. In the software part, aiming at the time‐domain characteristics of the interference signal, the feature vector of the interference signal is extracted. With the support of GAP‐CNN model, the interference signal is recognized through the training and learning of feature vector. The experimental results show that the packet loss rate of the designed system is less than 0.5%, the recognition performance is good, and the reliability of the system is improved.
Coherent optical orthogonal frequency-division multiplexing (CO-OFDM) is a promising technique due to its high spectral efficiency and dispersion tolerance. However, CO-OFDM is sensitive to the carrier frequency offset (CFO) which is caused by the frequency difference between the transmitter laser and local oscillator, and linear phase noise (LPN) which is closely related to the laser linewidth. The existing of CFO and LPN can introduce the inter-carrier interference (ICI) and cause the rotation of constellations, thus degrade the system performance. In this paper, we propose to dynamically and jointly track and compensate the CFO and LPN by utilizing the Gaussian particle filter (GPF) and extended kalman filter (EKF). Firstly, the GPF and EKF can dynamically track the CFO and LPN in a real-time manner, thus can achieve accurate estimation result at even high phase noise variance. Secondly, GPF can successfully prevent the particle impoverishment (PI) problem of the conventional sequential importance resampling (SIR) PF, by recursively updating the mean and variance of the particles based on the weights computed from the posterior density and the designed importance sampling function. Thirdly, the joint estimation of CFO and LPN utilizes merely one OFDM symbol, which ensures the effective data transmission efficiency. Also, EKF can convert the nonlinear problem into linearity which helps to reduce the computation complexity. Simulations are carried out to verify the accuracy, robustness and efficiency of the proposed approach by considering the estimation error variance with the Cram´er-Rao lower bound (CRLB), the convergence speed of the GPF and EKF, and the real-time dynamic tracking errors.
During the study age in computer science, postgraduates with various specialties need good mathematical foundation to process their research. Current problem is classical course "Applied Mathematics" did not organically combine to research directions in computer science, which leads to widespread occurrence that students' mathematical knowledge can not be applied in their real work. This paper first analyzes research major specialties in college of computer science, Inner Mongolia University. Then, this paper analyzes and researches on mathematical knowledge and methods of postgraduate students in these specialties. Therefore, a teaching reform of postgraduate course "Applied Mathematics" is presented directionally, which can improves fit degree of this course in study of computer science.
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new version of the previous NTIRE 2019 challenge on real image denoising that was based on the SIDD benchmark. This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+. This challenge has two tracks for quantitatively evaluating image denoising performance in (1) the Bayer-pattern rawRGB and (2) the standard RGB (sRGB) color spaces. Each track ~250 registered participants. A total of 22 teams, proposing 24 methods, competed in the final phase of the challenge. The proposed methods by the participating teams represent the current state-of-the-art performance in image denoising targeting real noisy images. The newly collected SIDD+ datasets are publicly available at: this https URL.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
