Abstract: A vehicle recognition method includes: acquiring a training set including multiple vehicle images which includes vehicles at a designated crossroad and corresponding vehicle information; performing learning and sampling by a neural network to obtain a subnetwork model and determining same as a current model, and training the current model by using the training set to obtain reward parameters; calculating a constraint condition value of the current model, calculating a reward value on the basis of the constraint condition value and the reward parameters, updating trainable parameters of the neural network by using the reward value, and returning to execute the operation of obtaining the subnetwork model until a preset condition is reached; after the preset condition is reached, selecting an optimal network model; and inputting a vehicle picture to be recognized into the optimal network model, to obtain vehicle information of the vehicle picture to be recognized.

Abstract: The present application relates to the technical field of computers. Provided is a small sample fine-turning method, the method comprising: inputting a data set, and forming an input sample according to a fixed template; constructing a candidate tag word set and a candidate prompt template set; by means of reinforcement learning, searching an optimal tag word corresponding to the input sample from the candidate tag word set, and a prompt template corresponding to the input sample from the candidate prompt template set; and outputting a mapping relationship of the optimal tag word and an optimal prompt template format corresponding to the prompt template.

Abstract: Disclosed in embodiments of the present application are a display panel and a display device. The display panel includes: an array substrate, a cover plate, and a touch driver board; the cover plate is arranged on the array substrate, a side of the cover plate away from the array substrate includes a touch driver board binding area, the touch driver board binding area includes a first binding area and a second binding area, and the first binding area and the second binding area are arranged in a stepped mode; the touch driver board includes a first conductive part and a second conductive part, the first conductive part is exposed, the second conductive part is not exposed, the first conductive part is arranged in the first binding area and part of the second binding area, and the second conductive part is arranged in the second binding area.

Abstract: An automatic modeling method for object detection model, the method includes: S1, searching for an NAS network model according to a predetermined first neural network; S2, training a first object detection model by using a training set, evaluating the current first object detection model by using a validation set after a number of training times reaches a first preset number of times, and outputting an evaluation result, wherein the first object detection model is a model obtained by detection part fusion of the NAS network model and a second object detection model; S3, calculating a reward corresponding to the current first object detection model; S4, adjusting parameters used for searching for the NAS network model according to the reward: repeating the steps S1-S4 for a second preset number of times, and determining an optimal first object detection model according to the evaluation result. Further disclosed in the present invention is an automatic modeling device.

Abstract: An image data enhancement method and apparatus, a computer device, and a storage medium are provided. The method includes: segmenting an original image to obtain segmented images and target categories of the segmented images, and obtaining, by means of the target categories, categories to be enhanced (S1); binarizing the original image according to the categories to be enhanced, and obtaining instance images, according to a connected domain of the binary images, from the original image (S2); performing perspective processes on the instance images to obtain first instance images, and zooming the first instance images to obtain second instance images (S3); obtaining a vanishing point position from the original image, determining pasting positions of the second instance images according to the vanishing point position and the second instance images, and pasting the second instance images to the original image according to the pasting positions to obtain an enhanced image (S4).

Abstract: This disclosure discloses a network model training method and apparatus, an electronic apparatus and a computer-readable storage medium.

Abstract: An image data enhancement method and apparatus, a computer device, and a storage medium are provided. The method includes: segmenting an original image to obtain segmented images and target categories of the segmented images, and obtaining, by means of the target categories, categories to be enhanced (S1); binarizing the original image according to the categories to be enhanced, and obtaining instance images, according to a connected domain of the binary images, from the original image (S2); performing perspective processes on the instance images to obtain first instance images, and zooming the first instance images to obtain second instance images (S3); obtaining a vanishing point position from the original image, determining pasting positions of the second instance images according to the vanishing point position and the second instance images, and pasting the second instance images to the original image according to the pasting positions to obtain an enhanced image (S4).

Abstract: The disclosure provides compositions and methods of treating a metabolic disease, such as, e.g., diabetes and hyperlipidemia, in a subject, by administering to the subject a therapeutically effective amount of a polypeptide derived from hepatitis B virus or a pharmaceutical composition comprising the polypeptide.

Abstract: A vehicle recognition method includes: acquiring a training set including multiple vehicle images which includes vehicles at a designated crossroad and corresponding vehicle information; performing learning and sampling by a neural network to obtain a subnetwork model and determining same as a current model, and training the current model by using the training set to obtain reward parameters; calculating a constraint condition value of the current model, calculating a reward value on the basis of the constraint condition value and the reward parameters, updating trainable parameters of the neural network by using the reward value, and returning to execute the operation of obtaining the subnetwork model until a preset condition is reached; after the preset condition is reached, selecting an optimal network model; and inputting a vehicle picture to be recognized into the optimal network model, to obtain vehicle information of the vehicle picture to be recognized.

Abstract: The disclosure provides compositions and methods of treating a metabolic disease, such as, e.g., diabetes and hyperlipidemia, in a subject, by administering to the subject a therapeutically effective amount of a polypeptide derived from hepatitis B virus or a pharmaceutical composition comprising the polypeptide.

Abstract: The invention discloses a nitrogen-doped mesoporous carbon-coated Titanium dioxide composite photocatalyst, a preparation method and use thereof. The preparation method comprises the steps of: dissolving an organic ligand and Ti(OC3H7)4 in a mixture of methanol and DMF at a certain ratio, performing a hydrothermal reaction, centrifuging and drying to obtain a Titanium-based metal organic framework (Ti-MOF); pyrolyzing the obtained Ti-MOF under an inert atmosphere, and oxidizing the same for etching to obtain a nitrogen-doped mesoporous carbon-coated Titanium dioxide composite photocatalyst. The obtained composite photocatalyst not only facilitates the adsorption, enrichment and mass transfer of low concentration VOCs, but also efficiently degrades VOCs under sunlight. It has high degradation activity and stability when performing photocatalytic removal of VOCs in the presence of visible light, is simple in synthesis, low in preparation cost, and has strong potential for the use in environmental protection.

Abstract: A nickel-based MOF film photocatalyst grown in-situ on a foamed nickel surface, a preparation method therefor, and an application thereof. The nickel-based MOF film photocatalyst grown in-situ on a foamed nickel surface is prepared by first immersing foamed nickel in a diluted acid and performing ultrasonic processing, then cleaning the foamed nickel with deionized water, and drying the foamed nickel to obtain surface-activated foamed nickel; immersing the surface-activated nickel foam in a mixture of an imidazole compound, sodium formate, and a solvent and reacting at 100° C. to 180° C. to obtain an unactivated nickel-based MOFs film on the surface of the foamed nickel, and after cooling to room temperature, removing same and soaking in an organic solvent to activate, and then drying the obtained product.

Abstract: An automatic modeling method for object detection model, the method includes: S1, searching for an NAS network model according to a predetermined first neural network; S2, training a first object detection model by using a training set, evaluating the current first object detection model by using a validation set after a number of training times reaches a first preset number of times, and outputting an evaluation result, wherein the first object detection model is a model obtained by detection part fusion of the NAS network model and a second object detection model; S3, calculating a reward corresponding to the current first object detection model; S4, adjusting parameters used for searching for the NAS network model according to the reward: repeating the steps S1-S4 for a second preset number of times, and determining an optimal first object detection model according to the evaluation result. Further disclosed in the present invention is an automatic modeling device.

Abstract: The present invention discloses a strain of Achromobacter xylosoxidans with monomethylamine degradability and the application thereof. This strain, named Achromobacter xylosoxidans GDUTAN5, was deposited on May 24, 2017 in the China Center for Type Culture Collection in Wuhan University (No. 299 Bayi Road, Wuchang District, Wuhan City, Hubei Province) with a deposit number of CCTCC NO: M 2017285. This Achromobacter xylosoxidans GDUTAN5 was Gram-negative and rod-shaped, and the colony appeared to be round, light yellow, opaque and smooth, having a diameter of 1-2 mm. The Achromobacter xylosoxidans GDUTAN5 of the present invention can be applied to environmental restoration, degrading monomethylamine in the environment at a high degradation efficiency. When it degraded monomethylamine for 96 h at a substrate concentration of 5 mg/L, the degradation efficiency could reach 92.3%.

Abstract: The invention discloses a nitrogen-doped mesoporous carbon-coated Titanium dioxide composite photocatalyst, a preparation method and use thereof. The preparation method comprises the steps of: dissolving an organic ligand and Ti(OC3H7)4 in a mixture of methanol and DMF at a certain ratio, performing a hydrothermal reaction, centrifuging and drying to obtain a Titanium-based metal organic framework (Ti-MOF); pyrolyzing the obtained Ti-MOF under an inert atmosphere, and oxidizing the same for etching to obtain a nitrogen-doped mesoporous carbon-coated Titanium dioxide composite photocatalyst. The obtained composite photocatalyst not only facilitates the adsorption, enrichment and mass transfer of low concentration VOCs, but also efficiently degrades VOCs under sunlight. It has high degradation activity and stability when performing photocatalytic removal of VOCs in the presence of visible light, is simple in synthesis, low in preparation cost, and has strong potential for the use in environmental protection.

Abstract: The disclosure relates to therapeutic medicaments for nonalcoholic fatty liver disease. Specifically, the disclosure relates to use of a polypeptide comprising an amino acid sequence derived from hepatitis B virus (HBV) or a pharmaceutical composition comprising the polypeptide in the manufacture of a medicament for treating or preventing nonalcoholic fatty liver disease.

Abstract: The disclosure provides compositions and methods of treating a metabolic disease, such as, e.g., diabetes and hyperlipidemia, in a subject, by administering to the subject a therapeutically effective amount of a polypeptide derived from hepatitis B virus or a pharmaceutical composition comprising the polypeptide.

Abstract: This disclosure relates to medicaments and methods for treating and preventing hepatitis B virus-related liver diseases using sufficient dosage. Specifically, the disclosure provides a method for treating and preventing hepatitis B virus-related liver diseases comprising administering to a subject in need of treatment and prevention a sufficient dosage of a polypeptide or a pharmaceutical composition comprising the polypeptide per day, wherein the polypeptide comprises an amino acid sequence derived from hepatitis B virus (HBV) Pre-S1; the sufficient dosage is a daily dosage at which the polypeptide reaches the saturating level in a liver target organ after the polypeptide is administered in the sufficient dose for several days.

Abstract: A short channel ordered mesoporous carbon loaded indium cobalt sulfide and indium nickel sulfide ternary composite photocatalyst, and a preparation method and application thereof. The short channel ordered mesoporous carbon loaded indium cobalt sulfide and indium nickel sulfide ternary composite photocatalyst is prepared by mixing pretreated short channel mesoporous carbon with cobalt salt, nickel salt, indium salt and reducing agent with a hydrothermal reaction. The short channel ordered mesoporous carbon is obtained by calcining a short channel ordered mesoporous silica and a carbon source under the protection of nitrogen, wherein the short channel ordered mesoporous silica is prepared by carrying out reactions of sol-gel-hydrothermal-calcination sequentially using a mixture of a surfactant, a hydrochloric acid solution, ammonium fluoride and tetraethyl orthosilicate.

Abstract: The present disclosure provides a drug formulation for hepalatide, comprising hepalatide and a buffer salt, and containing or not containing an osmotic regulator and/or an excipient.