Abstract: A method for training an image segmentation model includes calling an encoder to perform feature extraction on a sample image and a scale image to obtain a sample image feature and a scale image feature. The method also includes performing a class activation graph calculation to obtain a sample class activation graph and a scale class activation graph. The method also includes calling a decoder to obtain a sample segmentation result of the sample image, and calling the decoder to obtain a scale segmentation result of the scale image. The method also includes calculating a class activation graph loss and calculating a scale loss. The method also includes training the decoder based on the class activation graph loss and the scale loss.

Abstract: Disclosed by the present application are an antibody library construction method and an application thereof. The method comprises the following steps: inserting a first element and a second element into a same vector or different vectors, and transfecting the vectors into the cells to obtain an antibody expression cell library, i.e., the antibody library. The first element comprises CIS activators and selection marker genes; the second element comprises extracellular antibody library coding domain, Notch nuclear structure domain and intracellular transcription structure domain.

Abstract: The present invention provides a single-end-to-differential microphone circuit, including a power supply end for inputting a first bias voltage, a microphone capacitor, a coupling capacitor, a first primary amplifier, a second primary amplifier, a signal processing module, current sharing amplifier, a feedback resistor at positive end, a feedback capacitor at positive end, a feedback resistor at negative end, a feedback capacitor at negative end. Compared with the prior art, the single-end-to-differential microphone circuit of the present invention can utilize the current sharing amplifier with a small input common mode voltage range and low noise to realize the single-end-to-differential of the signal, which is beneficial to improve the signal to noise ratio of the circuit.

Abstract: Disclosed is a text sentence processing method performed by a computer device, including: acquiring sample text sentences including entity pairs and relationship labels of the entity pairs; extracting positive and negative example sentence pairs from the sample text sentences according to the relationship labels, and performing positive-negative example sampling, to obtain a training set; inputting the training set into a relationship extraction model to generate loss values; and adjusting parameters of the relationship extraction model according to the loss values, and repeating the step of extracting positive and negative example sentence pairs from the sample text sentences according to the relationship labels to perform iterative training of the relationship extraction model until a training end condition is met, to obtain an updated relationship extraction model, the relationship extraction model being configured to identify an entity relationship of an entity pair in an input text sentence.

Abstract: The present application is applicable to the field of medical imaging technologies, and provides an image-driven brain atlas construction method and apparatus, a device and a storage medium. The method includes: acquiring multi-modal data of a brain to be predicted, where the multi-modal data is acquired according to image data collected when the brain is under at least three different modalities; inputting the multi-modal data into a preset fusion network for processing to output and acquire feature parameters of the brain; where the processing of the multi-modal data by the fusion network includes: extracting a non-Euclidean spacial feature and an Euclidean spacial feature of the multi-modal data, and performing hypergraph fusion on the non-Euclidean spacial feature and the Euclidean spacial feature to acquire the feature parameters, where the feature parameters are used to characterize a brain connection matrix and/or a disease category of the brain.

Abstract: Disclosed is a connector, which comprises a first main body with a rotation end and a closed end and a second main body rotatably connected to the first main body, wherein a first through groove is provided at an inner side of the first main body, a second through groove is provided at the second main body, the first through groove and the second through groove enclose to form a fixed cavity, the first main body is further provided with a connection pipe communicated with the first through groove, and the connector further comprises a locking device used to open or close the fixed cavity. When the fitness equipment is disassembled, only the first main body and the second main body need to be unlocked by the locking device without disassembling the sporting equipment connected to the connection pipe, which makes mounting and disassembly of the fitness equipment more convenient.

Abstract: A cryogenic full containment storage tank for realizing a low-liquid-level material extraction function by using a pump column, comprising an inner tank, an outer tank, a pump column, a submersible pump and a material pre-extraction device; wherein the material pre-extraction device comprises a cofferdam, a Venturi mixer, a backflow pipe, a return control valve, a lead-out pipeline and a liquid level detection system. The cryogenic full containment storage tank can make use of a low-temperature medium flowing back from the pump column to extract the low liquid level material outside the cofferdam into the cofferdam to form a local high liquid level and maintain the normal operation of the submersible pump.

Abstract: Provided are a new vertical cavity surface emitting laser structure and a manufacturing method thereof. The structure includes a substrate layer, a lower N-type DBR, an active region, an upper N-type DBR and a mixed dielectric DBR sequentially arranged from bottom to top, where a second-class tunnel junction is arranged on one side of the active region close to the upper N-type DBR, where the second-class tunnel junction is embedded in a bottom of the upper N-type DBR and surrounded by the upper N-type DBR, and the substrate layer, the lower N-type DBR, the active region, the upper N-type DBR, the mixed dielectric DBR and the second-class tunnel junction are all coaxial elliptical cylinders; negative electrodes are arranged on the lower N-type DBR, and positive electrodes are arranged on the upper N-type DBRs substrate layer.

Abstract: A bone conduction microphone is provided. The bone conduction microphone may include a laminated structure formed by a vibration unit and an acoustic transducer unit. The bone conduction microphone may include a base structure configured to carry the laminated structure. At least one side of the laminated structure may be physically connected to the base structure. The base structure may vibrate based on an external vibration signal. The vibration unit may be deformed in response to the vibration of the base structure. The acoustic transducer unit may generate an electrical signal based on the deformation of the vibration unit. The bone conduction microphone may include at least one damping structural layer. The at least one damping structural layer may be arranged on an upper surface, a lower surface, and/or an interior of the laminated structure, and the at least one damping layer may be connected to the base structure.

Abstract: A crystalline form A of 2,2-bis(4-fluorophenyl)-2-phenylacetamide is provided. The crystalline form has good light stability, high temperature stability, and high humidity stability.

Abstract: Disclosed is an atomizing device, including: a housing, in which a first installation space and a host compartment are formed, the first installation space being spaced apart from the host compartment; an oil storage structure disposed in the first installation space and containing an oil storage chamber for storing oil; an atomizing tube disposed in the oil storage structure, in which an oil inlet is disposed at an air inlet end of the atomizing tube; an atomizing core disposed in the atomizing tube and spaced from the air inlet end of the atomizing tube in a longitudinal direction of the oil storage structure; and an oil guide member disposed between the atomizing tube and the atomizing core, in which the oil guide member is connected with the atomizing core, and is in communication with the oil storage chamber through the oil inlet.

Abstract: A power line data transceiver is for transmitting or receiving data over a power line. The power line is adapted to distribute electric power. The power line transmitter has a data transceiver coupled to the at least two wires of the shielded cable via a capacitive coupling network. The data transceiver is configured to transmit or receive a data signal over the at least two wires of the shielded cable. A power supply is coupled to the shielded cable over an inductive coupling network. The power supply is configured to inject a feeding current on the at least two wires of the shielded cable for feeding the electric load with electric power, and to receive a return current from the electric load over the conductive shield of the shielded cable.