Abstract: A depth network detection method for diabetic retinopathy based on a genetic fuzzy tree. The method includes: first, enhancing a retina image to widen a lesion area, and compress a normal area; next, building a network model U-net to accurately segment images of retinal blood vessels and blood vessel tips; subsequently, performing training according to the vascular images segmented by the model and real diagnosis results, so as to construct an interpretable fuzzy decision tree; then, encoding weights of the decision tree and constructing a fitness function, and a plurality of decision trees being combined and optimized based on a genetic algorithm; and finally, introducing an accuracy index to dynamically adjust a penalty term in a loss function.

Abstract: A preparation method and a use of 2D MoS2 materials are provided. Molybdenum source and sulfur powder are used as raw materials, and inert gas is used as carrier gas. Through an intermediate evaporation process, the raw materials are transported to the molten glass surface and deposited into solid molybdenum sulfide. In the subsequent etching-spreading-sulfurization-precipitation process, ultra-high quality and ultra-large area MoS2 single-crystal domains are obtained under normal pressure and without hydrogenation. The single-crystal domain size of the prepared 2D MoS2 material can reach 1.5 cm, and then grow into a wafer-level 2D MoS2 material with a size of 2 inches and a thickness of 1-2 layers.

Abstract: The present disclosure is a three-way U-Net method for accurately segmenting an uncertain boundary of a retinal blood vessel, includes: describing an uncertainty of a blood vessel boundary label, constructing an upper bound and a lower bound of the uncertain boundary based on the dilation operator and the erosion operator respectively to obtain a maximum value and a minimum value for the blood vessel boundary, and mapping the boundary with uncertain information into one range; combining an uncertainty representation of the boundary with a loss function, and designing a three-way loss function; training network parameters by adopting a stochastic gradient descent algorithm and utilizing a total loss of the three-way loss function; and designing and implements an auxiliary diagnosis application system for intelligently segmenting the retinal blood vessel with functions of the fundus data acquisition, the intelligent accurate segmentation and the auxiliary diagnosis for the retinal blood vessel.

Abstract: The present disclosure is a three-way U-Net method for accurately segmenting an uncertain boundary of a retinal blood vessel, includes: describing an uncertainty of a blood vessel boundary label, constructing an upper bound and a lower bound of the uncertain boundary based on the dilation operator and the erosion operator respectively to obtain a maximum value and a minimum value for the blood vessel boundary, and mapping the boundary with uncertain information into one range; combining an uncertainty representation of the boundary with a loss function, and designing a three-way loss function; training network parameters by adopting a stochastic gradient descent algorithm and utilizing a total loss of the three-way loss function; and designing and implements an auxiliary diagnosis application system for intelligently segmenting the retinal blood vessel with functions of the fundus data acquisition, the intelligent accurate segmentation and the auxiliary diagnosis for the retinal blood vessel.

Abstract: A method for classifying multi-granularity breast cancer genes based on a double self-adaptive neighborhood radius includes large-scale gene locus data are read and normalized, and a data analysis is performed on the large-scale gene loci. An optimum value K is selected by adopting a combination of contour coefficients and a PCA dimensionality reduction visualization, and a model of information granulation is adjusted. A heuristic reduction algorithm is used to implement a multi-granularity attribute reduction of a self-adaptive neighborhood radius based on a cluster center distance and a multi-granularity attribute reduction of a neighborhood radius based on an attribute inclusion degree, and big data for breast cancer genes are classified and predicted by adopting a machine learning classification algorithm based on a SVM support vector machine.

Abstract: A method for classifying multi-granularity breast cancer genes based on a double self-adaptive neighborhood radius includes large-scale gene locus data are read and normalized, and a data analysis is performed on the large-scale gene loci. An optimum value K is selected by adopting a combination of contour coefficients and a PCA dimensionality reduction visualization, and a model of information granulation is adjusted. A heuristic reduction algorithm is used to implement a multi-granularity attribute reduction of a self-adaptive neighborhood radius based on a cluster center distance and a multi-granularity attribute reduction of a neighborhood radius based on an attribute inclusion degree, and big data for breast cancer genes are classified and predicted by adopting a machine learning classification algorithm based on a SVM support vector machine.

Abstract: A display substrate includes a rigid substrate, a flexible substrate, a pixel structure, and bonding terminals. The rigid substrate includes a portion corresponding to a display region of the display substrate. The flexible substrate is disposed on the rigid substrate, and includes a portion corresponding to the display region and a portion corresponding to a bonding region of the display substrate. The pixel structure is disposed in a region on the flexible substrate corresponding to the display region. The bonding terminals are disposed in a region one the flexible substrate corresponding to the bonding region. The portion of the flexible substrate corresponding to the bonding region is bendable.

Abstract: The invention provides various high mannose glycosylated polypeptides that are useful in a vaccine formulations. The invention also provides methods for making such glycosylated polypeptides and its uses in eliciting HIV-neutralizing antibodies.

Abstract: The invention provides various high mannose glycosylated polypeptides that are useful in a vaccine formulations. The invention also provides methods for making such glycosylated polypeptides and its uses in eliciting HIV-neutralizing antibodies.