Bin Yang

In this letter, we propose a Global navigation satellite system (GNSS) spoofing suppression method based on spoofing correlation peak cancellation (SCPC). The approach estimates the spoofing signal from the baseband sampling sequence, and generates a reverse cancellation sequence to suppress GNSS spoofing attack. Based on this, a receiver scheme with SCPC function is proposed by adding a suppression module to the general GNSS receiver model. The experimental verification is conducted based on the TEXBAT dataset. By comparing the correlation peaks, carrier-to-noise ratio and peak trajectories of spoofed, mitigated and non-spoofed clean data, the results demonstrate that SCPC can correct the spoofing mixed navigation signals and effectively suppress spoofing attack.

Summary: The general Global Navigation Satellite System (GNSS) receiver faces several challenges because of jamming signals, spoofing signals, and multipath signals, which severely influence its safety. In this paper, a receiver scheme with an interference recognition function is designed. In the latter, the correlation peak with different shapes is produced according to different interferences. The machine learning method is then applied to recognize and classify these feature maps. This transforms the interference recognition problem into a machine learning‐based classification problem. In order to reduce the complexity of the machine learning network, only the finite‐length correlation peak region of interest (ROI) is extracted as network input, endowing the shallow neural network with the interference recognition function. Afterward, five data acquisition environments are designed: authentic, spoofing, jamming, non‐line‐of‐sight (NLOS) multipath, and line‐of‐sight (LOS) multipath. Moreover, several experimental data are acquired, followed by the production of the correlation peak maps dataset, that are then learned and tested using two machine learning networks: one‐dimensional convolutional neural network (1D‐CNN) and bidirectional long short‐term memory neural network (BiLSTM‐NN). The results demonstrate that a recognition accuracy rate of over 98% can be reached using the shallow machine learning network.

Since there are a lot of complex and changing characteristics of mass in mammography with great difficulty in mass segmentation, region growing become a reliable method to accomplish it. An adaptive region growing method for mass segmentation is presented so as to improve its precision and reliability and reduce the over-growing and lack-growing when dealing with different images in one principle. Background removing and region suppression are used to preprocessing the area of interest (ROI) of mass, and then it use the number of image pixels to determine the seed point for region growing, and determine whether the adaptive region growing is out of edge though the gradient distribution and tends of mass ROI in order to obtain the best growth criteria. The experimental results show that the adaptive region growing algorithm for segmentation compared to the three-terrain segmentation algorithm and model segmentation algorithm is more accurate and reliable.

The author presents a new algorithm for tracking the signal subspace recursively. It is based on a novel interpretation of the signal subspace as the solution of a projection like unconstrained minimization task. It is shown that the recursive least squares technique can be applied to solve this problem by approximation projections appropriately. The resulting algorithm has a computational complexity of O(nr) where n is the dimension of the problem and r is the number of desired eigencomponents, respectively. Simulation results show that the frequency tracking capability of this algorithm is virtually identical to and in some cases more robust than the more computationally expensive batch eigendecomposition.