5results about How to "Improve estimation performance" patented technology

The invention discloses a pilot optimization method for large-scale MIMO channel estimation based on structural compressed sensing. The method comprises the steps of establishing a channel estimation model for a large-scale MIMO-OFDM (Multiple-Input-Multiple-Output-Orthogonal Frequency Division Multiplexing) system when pilots are placed in an overlapping mode; simplifying the channel estimation model for the large-scale MIMO-OFDM system, thereby enabling the channel estimation model to correspond to a structural compressed sensing model; and obtaining an optimum pilot matrix through utilization of a pilot optimization algorithm. Through adoption of the optimum pilot matrix, according to the channel estimation of the large-scale MIMO system based on structural compressed sensing, the mean square errors MSEs of the channel estimation are clearly reduced, and the channel estimation performance is improved.

The application discloses a kind of robust direction of arrival estimation method based on ADMM-Net, by expanding ADMM algorithm into model-driven deep network ADMM-Net to improve DOA estimation accuracy, speed up DOA estimation speed and have robustness to array disturbance.Firstly, the sparse transformation of source and array received multi-shot data is carried out by space over-complete dictionary, and the DOA estimation is converted into compressed sensing sparse recovery problem;Then, ADMM algorithm is expanded, and model-driven deep network ADMM-Net with explainability is formed;ADMM-Net is used to reconstruct source power spectrum and carry out DOA estimation.The present application can learn the hyperparameters in iterative algorithm and array disturbance, solve the problem that existing compressed sensing DOA estimation method based on calculation speed is slow, and fails under the condition of array disturbance, realize fast, accurate, explainable and robust DOA estimation.

The application discloses a deep learning DOA estimation method based on original IQ data. The application uses I and Q components of the original signal as the input of the model to improve the performance. The application aims to solve the DOA estimation problem of a single signal source, and models the single signal source DOA estimation problem as a single-label multi-classification problem. By discretizing the DOA range, the possible directions of arrival are taken as corresponding labels. A convolutional neural network is designed to adapt to different numbers of snapshots, and accurate DOA estimation can be adaptively obtained for input signals of different lengths. Experimental results show that, compared with existing deep learning DOA estimation methods based on covariance matrix as input, the scheme has more excellent performance, and can provide a more reliable solution for array signal processing.

This invention discloses a sparse Bayesian target azimuth estimation method based on far-field dictionary reconstruction under strong near-field interference. The method includes subspace decomposition of the observation data to construct a signal subspace projection operator; projecting and normalizing the far-field dictionary to obtain a projected reconstruction dictionary, which replaces the far-field dictionary in sparse Bayesian learning, and jointly performing sparse Bayesian iterative estimation with the near-field dictionary; finally, outputting the far-field target azimuth estimation result. This method effectively partitions the subspace and constructs a projection matrix accordingly to suppress the impact of strong near-field interference on far-field azimuth estimation, significantly improving the far-field target azimuth estimation capability of the sparse Bayesian method under strong near-field interference conditions.

This application discloses a three-dimensional spatial PM2.5 concentration estimation method, device, medium, and product, relating to the field of atmospheric environmental monitoring. The method includes: stitching together haze images from multiple perspectives within a sample area to obtain a three-dimensional spatial sample image; the three-dimensional spatial sample image and the corresponding actual PM2.5 concentration value constitute a training sample; inputting multiple training samples into an improved VIT model for training to obtain a PM2.5 concentration prediction model; the improved VIT model includes a multi-scale image feature embedding module and a Transformer encoder module arranged sequentially; inputting the three-dimensional spatial sample image corresponding to the area to be detected into the PM2.5 concentration prediction model to obtain the corresponding estimated PM2.5 concentration value. This application can obtain accurate estimated PM2.5 concentration values.