Abstract: A method and a system for automatically detecting nitrogen content, an electronic device and a medium are provided and relate to the field of nitrogen content detection. The method includes: selecting an optimal nitrogen content prediction model from a prediction model base according to a variety and a growth stage of a target crop to obtain a target model; detecting, based on a spectral image of the target crop, a nitrogen content of the target crop by using the target model to obtain a predicted value of the nitrogen content. The optimal nitrogen content prediction model is the model with best performance among a first nitrogen content prediction model constructed based on a hyperspectral vegetation index, a second nitrogen content prediction model constructed based on a sensitive band, and a third nitrogen content prediction model constructed based on a machine learning method.

Abstract: The present disclosure provides a method and system for determining an optimal flight height of an unmanned aerial vehicle (UAV), an electronic device, and a medium. The method includes: obtaining a multi-band crop spectral image of an experimental area in a preset scenario; performing data processing on the multi-band crop spectral image, to obtain multi-spectral orthographies of a plurality of sample plots; calculating a ground resolution of the multi-spectral orthography of each sample plot, simulating and determining a multi-band crop spectral image of each sample plot at a different flight height by a nearest neighbor interpolation method based on the ground resolution of the multi-spectral orthography of each sample plot; and for the multi-band crop spectral image of each sample plot at the different flight height, determining an optimal flight height corresponding to each sample plot by a hypothetical test method.

Abstract: Disclosed in the present invention is a lightweight anomaly detection neural network model retraining method with anti-overfitting, which retrains an anomaly detection model based on depth variational autoencoders. When a data distribution changes, a conditional distribution of a hidden state and reconstructed data samples obtained by an encoder and a decoder of the depth variational autoencoders will also change. The present invention uses a mapping function to adjust the conditional distribution of the hidden state and the reconstructed data obtained by the calculation of an old model to adapt to a new data distribution. The mapping function has simple and convex characteristics, and can ensure a fast convergence rate and light overhead in a retraining process on a premise of using a loss function form defined by the present invention.

Abstract: Disclosed in the present invention is a federated learning method against backdoor attacks. Firstly, a few benign model updates with high confidences are selected through cluster-based voting, and then the selected model updates are regarded as benign modes of model updates. An anomaly detection method based on a variational autoencoder progressively selects more benign model updates from the remaining candidate model updates, so that the size of a population of the selected benign model updates is continuously expanded. The present invention does not rely on adjustment of differential privacy, weight clipping and a learning rate, and only a minor change is made to an original federated learning protocol, which on the one hand has little impact on the accuracy of the global model, and on the other hand is easy to integrate with an existing federated learning system. Compared with an existing federated learning method against backdoor attacks, the present invention has stronger adaptability.

Abstract: Provided is a method for evaluating citrus fruit cracking. In the method, five indicators for evaluating citrus fruit cracking are determined and subjected to correlation analysis with field experiment data of fruit cracking rates of citrus fruits, and analysis results show that these five indicators are positively correlated with a cracking rate of fruits. By detecting these five indicators, the correlation of fruit cracking characteristics with a variety and cultivation conditions can be accurately described to fundamentally understand a cause for fruit cracking. In addition, it is convenient to determine the five indicators, and the five indicators can be detected in both fruits on a fruit tree and picked fruits. The method provides a technical support for improving the fruit cracking characteristics of a variety through breeding or guiding measures for controlling the fruit cracking including application of a specified fertilizer or reduction of a watering quantity.

Abstract: A fruit sterilizing and cooling device using a plasma-activated ice-water mixture includes a top-opened tank body, where the tank body includes a front side provided with an ice-water tank, and a rear side provided with a cooling tank; a clapboard is provided between the ice-water tank and the cooling tank; a water passing port is formed in an upper portion of the clapboard; a grid plate is inserted at the water passing port; ice cubes are added to an upper portion of the ice-water tank; one side of a lower portion of the ice-water tank is connected to a plasma-activated water (PAW) generator; a valve is provided at a water outlet of the PAW generator; a fixed fence frame and a movable fence frame are provided in the cooling tank; and fruits to be treated are placed in the movable fence frame.

Abstract: A fruit post-harvest disinfection and conveying production line is provided. The production line solves the problem of waxberry type fruits, that is, due to the exposed flesh, it is necessary to minimize the time that water remains on the surface of the fruit during the spraying disinfection process. The fruit post-harvest disinfection and conveying production line includes a workbench, where the workbench is provided with multiple sets of conveyor belts; each set of conveyor belts includes a first conveyor belt and a second conveyor belt; an upper part of a front end of the conveyor belts is provided with an inclined feeding hopper; and the feeding hopper is provided with feeding ports corresponding to each set of conveyor belts.

Abstract: A fruit post-harvest disinfection and conveying production line is provided. The production line solves the problem of waxberry type fruits, that is, due to the exposed flesh, it is necessary to minimize the time that water remains on the surface of the fruit during the spraying disinfection process. The fruit post-harvest disinfection and conveying production line includes a workbench, where the workbench is provided with multiple sets of conveyor belts; each set of conveyor belts includes a first conveyor belt and a second conveyor belt; an upper part of a front end of the conveyor belts is provided with an inclined feeding hopper; and the feeding hopper is provided with feeding ports corresponding to each set of conveyor belts.

Abstract: A fruit sterilizing and cooling device using a plasma-activated ice-water mixture includes a top-opened tank body, where the tank body includes a front side provided with an ice-water tank, and a rear side provided with a cooling tank; a clapboard is provided between the ice-water tank and the cooling tank; a water passing port is formed in an upper portion of the clapboard; a grid plate is inserted at the water passing port; ice cubes are added to an upper portion of the ice-water tank; one side of a lower portion of the ice-water tank is connected to a plasma-activated water (PAW) generator; a valve is provided at a water outlet of the PAW generator; a fixed fence frame and a movable fence frame are provided in the cooling tank; and fruits to be treated are placed in the movable fence frame.

Abstract: A method for simultaneously separating and purifying myricetin-3-O-(2?-O-galloyl)-a-L-rhamnoside and myricetin-3-O-(4?-O-galloyl)-a-L-rhamnoside from Bayberry leaves, and the use of the compounds prepared by the method. The method includes: (1) alcohol extraction and concentration: mixing Bayberry leaves with an alcohol solution; (2) solid-phase extraction column adsorption: injecting the crude Bayberry leaf flavonol alcohol extract into a solid-phase extraction column; washing with a mobile phase for the first gradient elution; (3) preparative liquid chromatography purification: using a solid-phase chromatography column; wherein the solid-phase extraction powder obtained from step (2) is subjected to a second gradient elution with a mobile phase and then processed to obtain the target products: myricetin-3-O-(2?-galloyl)-?-L-rhamnoside monomer and myricetin-3-O-(4?-galloyl)-?-L-rhamnoside monomer.

Abstract: Embodiments of the present disclosure provide a method for reduced-medicine treatment for post-harvest preservation of bayberries. The method includes: (1) packing after picking: placing ripe bayberries into a skeletonized injection-molded package after picking, the bayberries being spaced apart and evenly arranged in the skeletonized injection-molded package; (2) low-concentration peroxyacetic acid solution treatment: spraying a peroxyacetic acid solution with a concentration of 0.1% onto a surface of the bayberries; and (3) atmospheric plasma treatment: performing an atmospheric plasma treatment on the bayberries treated with the peroxyacetic acid solution for 5 minutes, and temporarily storing the bayberries in a refrigerated warehouse at 4° C. after the treatment. By combining peroxyacetic acid with atmospheric plasma, an amount of peroxyacetic acid solution used can be effectively reduced and efficacy of the treatment can be increased.

Abstract: A method and a system for automatically detecting nitrogen content, an electronic device and a medium are provided and relate to the field of nitrogen content detection. The method includes: selecting an optimal nitrogen content prediction model from a prediction model base according to a variety and a growth stage of a target crop to obtain a target model; detecting, based on a spectral image of the target crop, a nitrogen content of the target crop by using the target model to obtain a predicted value of the nitrogen content. The optimal nitrogen content prediction model is the model with best performance among a first nitrogen content prediction model constructed based on a hyperspectral vegetation index, a second nitrogen content prediction model constructed based on a sensitive band, and a third nitrogen content prediction model constructed based on a machine learning method.

Abstract: The present disclosure relates to use of an oxymethyl-modified derivative of quercetin in preparation of a drug for inhibiting tumor cell proliferation, and belongs to the technical field of drug preparation. The present disclosure provides use of an oxymethyl-modified derivative of quercetin in preparation of a drug for inhibiting tumor cell proliferation. The oxymethyl-modified derivative of quercetin may inhibit tumor cell proliferation, inhibit proliferation of a transplanted tumor in vivo, inhibit tumor cell metastasis, and induce tumor cell apoptosis.

Abstract: A continuous quantitative spraying structure for sterilization of harvested fruits is provided. The continuous quantitative spraying structure includes a track provided thereon with equally spaced trays for conveying fruits, where the trays each include a circular tray body; a central part of the tray body is provided with a central hole allowing the fruit to fall off; a bottom part of the central hole is provided with two parallel rollers; an inner bottom surface of the tray body is provided with a flap; an inner end of a central shaft of the roller passes through the flap, and is fixed to a rolling wheel; a bearing is provided between the roller and the flap; the track is provided with a spraying sterilization section; the spraying sterilization section is sequentially provided with 3 to 4 sets of sterilization nozzles above a tray conveying route.

Abstract: A continuous quantitative spraying structure for sterilization of harvested fruits is provided. The continuous quantitative spraying structure includes a track provided thereon with equally spaced trays for conveying fruits, where the trays each include a circular tray body; a central part of the tray body is provided with a central hole allowing the fruit to fall off, a bottom part of the central hole is provided with two parallel rollers; an inner bottom surface of the tray body is provided with a flap; an inner end of a central shaft of the roller passes through the flap, and is fixed to a rolling wheel; a bearing is provided between the roller and the flap; the track is provided with a spraying sterilization section; the spraying sterilization section is sequentially provided with 3 to 4 sets of sterilization nozzles above a tray conveying route.

Abstract: The present disclosure provides a method and system for determining an optimal flight height of an unmanned aerial vehicle (UAV), an electronic device, and a medium. The method includes: obtaining a multi-band crop spectral image of an experimental area in a preset scenario; performing data processing on the multi-band crop spectral image, to obtain multi-spectral orthographies of a plurality of sample plots; calculating a ground resolution of the multi-spectral orthography of each sample plot, simulating and determining a multi-band crop spectral image of each sample plot at a different flight height by a nearest neighbor interpolation method based on the ground resolution of the multi-spectral orthography of each sample plot; and for the multi-band crop spectral image of each sample plot at the different flight height, determining an optimal flight height corresponding to each sample plot by a hypothetical test method.