Abstract: A device and method for glaucoma auxiliary diagnosis, and a non-transitory storage medium are provided. The device includes an obtaining unit and a processing unit. The obtaining unit is configured to obtain a color fundus image of a patient. The processing unit is configured to perform feature extraction on the color fundus image to obtain a first feature map. The processing unit is further configured to perform image segmentation on the color fundus image according to the first feature map to obtain an optic disc image in the color fundus image, where the optic disc image corresponds to an optic disc area in the color fundus image. The processing unit is further configured to perform feature extraction on the optic disc image and the color fundus image according to the first feature map to obtain a probability that the patient has glaucoma.

Abstract: A method for detecting and locating a lesion in a medical image is provided. A target medical image of a lesion is obtained and input into a deep learning model to obtain a target sequence. A first feature map output from the last convolution layer in the deep learning model is extracted. A weight value of each network unit corresponding to each preset lesion type in a fully connected layer is extracted. For each preset lesion type, a fusion feature map is calculated according to the first feature map and the corresponding weight value and resampled to the size of the target medical image to generate a generic activation map. The maximum connected area in each generic activation map is determined, and a mark border surrounding the maximum connected area is created. A mark border corresponding to each preset lesion type is added to the target medical image.

Abstract: A device and method for glaucoma auxiliary diagnosis, and a non-transitory storage medium are provided. The device includes an obtaining unit and a processing unit. The obtaining unit is configured to obtain a color fundus image of a patient. The processing unit is configured to perform feature extraction on the color fundus image to obtain a first feature map. The processing unit is further configured to perform image segmentation on the color fundus image according to the first feature map to obtain an optic disc image in the color fundus image, where the optic disc image corresponds to an optic disc area in the color fundus image. The processing unit is further configured to perform feature extraction on the optic disc image and the color fundus image according to the first feature map to obtain a probability that the patient has glaucoma.

Abstract: A neural network model training method and apparatus, a computer device, and a storage medium are provided. The method includes: obtaining a model prediction value of each of all reference samples based on a trained deep neural network model, calculating a difference measurement index between the model prediction value of each reference sample and a real annotation corresponding to the reference sample, and using a target reference sample whose difference measurement index is less than or equal to a preset threshold as a comparison sample; using a training sample whose similarity with the comparison sample meets a preset augmentation condition as a to-be-augmented sample; and performing data augmentation on the to-be-augmented sample, and using the obtained target training sample as a training sample to train the trained deep neural network model until model prediction values of all verification samples in a verification set meet a preset training ending condition.

Abstract: A method for detecting and locating a lesion in a medical image is provided. A target medical image of a lesion is obtained and input into a deep learning model to obtain a target sequence. A first feature map output from the last convolution layer in the deep learning model is extracted. A weight value of each network unit corresponding to each preset lesion type in a fully connected layer is extracted. For each preset lesion type, a fusion feature map is calculated according to the first feature map and the corresponding weight value and resampled to the size of the target medical image to generate a generic activation map. The maximum connected area in each generic activation map is determined, and a mark border surrounding the maximum connected area is created. A mark border corresponding to each preset lesion type is added to the target medical image.

Abstract: A palm-type mechanical gripper with variable-position and rotatable fingers and a crank-rocker-slider parallel mechanism adopts crank-rocker-slider mechanisms and three identical flexible plate spring fingers, wherein one finger is fixed, and the other two fingers can rotate and move to achieve translational motions and are respectively and symmetrically installed on connecting rods or rockers on left and right sides. The crank-rocker-slider mechanism on the left side is an active driving structure and is driven by two stepping motors to respectively generate angular displacement of cranks and linear movement of sliders. The crank-rocker-slider mechanism on the right side is a driven mechanism and is driven at a constant speed by a pair of gears. The eccentricities of the cranks, the positions and angles of the two fingers respectively on the two connecting rods or rockers and the position of the other fixed finger can be changed through manual adjustment.

Abstract: The invention relates to a poly silsesquioxane-acrylic nanocomposite auxiliary for leather process and its preparation method. By mixing octavinyl silsesquioxane, organic solvent, ammonium persulfate, distilled water and surfactant in one system, and adding acrylic acid dropwise into the mixing system, cooling to adjust pH to obtain poly silsesquioxane-acrylic nanocomposite auxiliary for leather process. The auxiliary obtained in this invention is easily to penetrate into gap of the collagen fibers, and forms nano and micro-scale combination with the leather collagen, which can further improve the multi-point combination of the acrylic polymer with the collagen. Thus, the filling property of the leather that treated by the auxiliary is improved without affect the yield of leather, and the chromium content in the waste water is significantly reduced.

Abstract: A palm-type mechanical gripper with variable-position and rotatable fingers and a crank-rocker-slider parallel mechanism adopts crank-rocker-slider mechanisms and three identical flexible plate spring fingers, wherein one finger is fixed, and the other two fingers can rotate and move to achieve translational motions and are respectively and symmetrically installed on connecting rods or rockers on left and right sides. The crank-rocker-slider mechanism on the left side is an active driving structure and is driven by two stepping motors to respectively generate angular displacement of cranks and linear movement of sliders. The crank-rocker-slider mechanism on the right side is a driven mechanism and is driven at a constant speed by a pair of gears. The eccentricities of the cranks, the positions and angles of the two fingers respectively on the two connecting rods or rockers and the position of the other fixed finger can be changed through manual adjustment.

Abstract: Disclosed in present invention is a link state control method. The method includes: within a setting time window, determining the reset fixed code word of a received data stream; according to the situation that each cell corresponding to the data stream is received correctly or incorrectly, determining the leaky bucket value of a link in real time; according to the determined reset fixed code word and the determined leaky bucket value, determining the state of the link. Moreover, the present invention also discloses a link state control apparatus and computer storage medium.

Abstract: The invention relates to a poly silsesquioxane-acrylic nanocomposite auxiliary for leather process and its preparation method. By mixing octavinyl silsesquioxane, organic solvent, ammonium persulfate, distilled water and surfactant in one system, and adding acrylic acid dropwise into the mixing system, cooling to adjust pH to obtain poly silsesquioxane-acrylic nanocomposite auxiliary for leather process. The auxiliary obtained in this invention is easily to penetrate into gap of the collagen fibers, and forms nano and micro-scale combination with the leather collagen, which can further improve the multi-point combination of the acrylic polymer with the collagen. Thus, the filling property of the leather that treated by the auxiliary is improved without affect the yield of leather, and the chromium content in the waste water is significantly reduced.

Abstract: A sulfonatocalixarene tanning agent for leather tanning and a preparation method comprises: using resorcinol and aldehyde monomers as raw materials for the tanning agent; adding an ethanol solution into the resorcinol, dropwise adding an inorganic strong acid catalyst and aldehyde derivatives, heating to react, cooling, carrying out suction filtration, repeatedly washing with ethanol and distilled water, and drying to obtain resorcinol calixarene; and weighing the resorcinol calixarene, and adding a sulfonating agent to react, thereby obtaining a sulfonatocalixarene tanning agent aqueous solution.

Abstract: An ESD protection circuit is disclosed, in which an RC trigger circuit and a transmission gate are used for determination of ESD protection triggering, and a silicon-controlled rectifier for ESD current conductance. The RC trigger circuit and the transmission gate allow improved trigger efficiency. In addition, the silicon-controlled rectifier incorporates first and second resistors, which can be implemented to have very low resistance values and are therefore able to effectively prevent the occurrence of latch-up during normal operation, as well as pull-up and pull-down transistors which can make an additional contribution to latch-up inhibition when turned on.

Abstract: Disclosed in present invention is a link state control method. The method includes: within a setting time window, determining the reset fixed code word of a received data stream; according to the situation that each cell corresponding to the data stream is received correctly or incorrectly, determining the leaky bucket value of a link in real time; according to the determined reset fixed code word and the determined leaky bucket value, determining the state of the link. Moreover, the present invention also discloses a link state control apparatus and computer storage medium.

Abstract: A sulfonatocalixarene tanning agent for leather tanning and a preparation method comprises: using resorcinol and aldehyde monomers as raw materials for the tanning agent; adding an ethanol solution into the resorcinol, dropwise adding an inorganic strong acid catalyst and aldehyde derivatives, heating to react, cooling, carrying out suction filtration, repeatedly washing with ethanol and distilled water, and drying to obtain resorcinol calixarene; and weighing the resorcinol calixarene, and adding a sulfonating agent to react, thereby obtaining a sulfonatocalixarene tanning agent aqueous solution.

Abstract: An ESD protection circuit is disclosed, in which an RC trigger circuit and a transmission gate are used for determination of ESD protection triggering, and a silicon-controlled rectifier for ESD current conductance. The RC trigger circuit and the transmission gate allow improved trigger efficiency. In addition, the silicon-controlled rectifier incorporates first and second resistors, which can be implemented to have very low resistance values and are therefore able to effectively prevent the occurrence of latch-up during normal operation, as well as pull-up and pull-down transistors which can make an additional contribution to latch-up inhibition when turned on.