2results about How to "Relieve memory pressure" patented technology

This invention proposes a lightweight image super-resolution method based on superpixel guidance. The method includes: processing a low-resolution image using SLIC to obtain a superpixel label map; performing a convolutional mapping on the low-resolution image using lightweight convolution to obtain a shallow feature map; using the shallow feature map as input to a feature enhancement block to obtain the output feature map of an intermediate feature enhancement block; using the output feature map of the intermediate feature enhancement block as input to the next feature enhancement block, and stacking a predetermined number of feature enhancement blocks to obtain a deep feature map; using the deep feature map and the shallow feature map to obtain a final feature map; and obtaining a high-resolution image using the final feature map and the low-resolution image. This invention unifies "region-level context," "structure-sensitive sparse aggregation," and "fine-grained texture modeling" into a single lightweight module, achieving both structure preservation and detail recovery at a lower cost.

The application discloses a high-altitude pulmonary edema early disease data collection system based on multi-gene mutation characteristics and relates to the field of bioinformatics, and is used for solving the problem of data collection of various users when the database information has reached the peak, that is, all parameters cannot be collected as reference, some data must be screened out, but the prediction result of the user cannot be affected, and the problem of screening the data collection of various users, comprising a data acquisition module, a user distinguishing module, a data screening module and an optimization matching module; the modules are signal-connected, receive user gene data and user average altitude sent by the data acquisition, establish PRS standardization processing, divide user risks, determine the importance of the historical data of multiple categories in predicting various user data through a LASSO regression model according to the occurrence frequency and the historical data uploading speed of the historical data, screen out data with a characteristic coefficient reduced to zero, so that the prediction result deviation is small, and the system runs smoothly.