Abstract: The present disclosure provides a medical hyperspectral image (MHSI) classification method based on a fast fully convolutional network (FCN), and relates to the technical field of MHSIs. The MHSI classification method includes: preprocessing and sampling an MHSI to obtain a training sample set; inputting the training sample set into an encoder-decoder-based FCN to train the MHSI; and inputting a to-be-classified pixel of the MHSI into a trained encoder-decoder-based FCN to obtain a classification result. The present disclosure provides the MHSI classification method based on a fast FCN. In order to resolve problems of low efficiency and insufficient performance of an existing MHSI classification method, the present disclosure designs a classification method based on the fast FCN, which avoids redundant computation in an overlapping region between image patches, greatly improving an inference speed.

Abstract: Provided is a magnetic particle imaging (MPI) reconstruction method based on a time-domain system matrix and x-space, including: obtaining a voltage signal through MPI scanning based on a Cartesian trajectory; obtaining an original image according to an x-space-based reconstruction method; constructing, based on the voltage signal as well as a velocity compensation step and a grading step in the x-space-based reconstruction method, a forward model for time-domain-based MPI and x-space-based reconstruction; taking the original image as an input of an inverse problem solver of the forward model, and obtaining an optimized particle distribution diagram through solving. Based on the original image obtained through the x-space-based reconstruction, the forward model describing MPI and x-space-based reconstruction processes is established.

Abstract: The present disclosure provides a fast medical hyperspectral image (MHSI) classification method based on similarity tangent mapping, and relates to the technical field of hyperspectral image (HSI) processing. The fast MHSI classification method includes: preprocessing a to-be-classified MHSI; extracting a sample set from the to-be-classified MHSI; dividing the sample set into a training sample set and a test sample set; constructing a cosine similarity tangent mapping (CSTM) model based on the training sample set; and inputting the test sample set into the CSTM model to obtain a classification result. Tangent mapping is performed for a cosine similarity to evaluate a similarity between pixels, and a similarity between a to-be-classified pixel and each different type of training sample is calculated based on a joint local region. Afterwards, a category label of the to-be-classified pixel is allocated based on the similarity to quickly obtain a stable classification result.

Abstract: The present invention relates to an automatic history matching system for an oil reservoir based on transfer learning, comprising a data reading module, a population reinitializing module, an optimization module, a simulated calculation module, a comparative judgment module and an output module, wherein the data reading module reads an optimized result of an existing oil reservoir, outputs the optimized result to the population reinitializing module, obtains an initial population of a new oil reservoir by calculation and outputs the initial population to the optimization module; the optimized result is outputted to the simulated calculation module to obtain oil reservoir production simulated data, and the oil reservoir production simulated data is outputted to the comparative judgment module; when an error between the simulated data and observed data meets the requirement, the optimized result is outputted to the output module, and the system operation is completed; and if the error does not meet the requirem

Abstract: A stacked-type lithium ion battery, comprising a core, a battery shell, and a cover plate; said core is placed in the battery shell, said cover plate is coupled to the battery shell in a sealed manner; said core comprises a plurality of layers of positive plates, negative plates, and membranes that are stacked together with each other, and the membrane is between the positive plate and the negative plate; wherein at least two membranes are in a 5-175° included angle between their tensile directions. Since the tensile directions of the membranes are different, the overall tensile strengths of the battery in all tensile directions are essentially same; therefore, the phenomenon of short circuit in the battery resulted from membrane rupture in lower tensile strength directions can be prevented, and the battery safety performance is greatly enhanced.

Abstract: The present invention relates to an Exendin 4 polypeptide fragment, which has hypoglycemic activity, and can be used for the treatment of type II diabetes mellitus. The polypeptide sequence described herein is HGEGTX1TSDLSKQX2EEEAVX3LFIEWLKNGX4PX5, where X1 represents Phe or Tyr, X2 represents Met, Ile or Leu, X3 represents Lys, X4 represents Gly or deletion, X5 represents Arg or deletion. Additionally, the present invention relates to a method for the Exendin 4 polypeptide fragment preparation.

Abstract: The present invention relates to an Exendin 4 polypeptide fragment, which has hypoglycemic activity, and can be used for the treatment of type II diabetes mellitus. The polypeptide sequence described herein is HGEGTX1TSDLSKQX2EEEAVX3LFIEWLKNGX4PX5, where X1 represents Phe or Tyr, X2 represents Met, Ile or Leu, X3 represents Lys, X4 represents Gly or deletion, X5 represents Arg or deletion. Additionally, the present invention relates to a method for the Exendin 4 polypeptide fragment preparation.