Abstract: A tree crown extraction method based on UAV multi-source remote sensing includes: obtaining a visible light image and LIDAR point clouds, taking a digital orthophoto map (DOM) and the LIDAR point clouds as data sources, using a method of watershed segmentation and object-oriented multi-scale segmentation to extract single tree crown information under different canopy densities. The object-oriented multi-scale segmentation method is used to extract crown and non-crown areas, and a tree crown distribution range is extracted with the crown area as a mask; a preliminary segmentation result of single tree crown is obtained by the watershed segmentation method based on a canopy height model; a brightness value of DOM is taken as a feature, the crown area of the DOM is performed secondary segmentation based on a crown boundary to obtain an optimized single tree crown boundary information, which greatly increases the accuracy of remote sensing tree crown extraction.

Abstract: Techniques for building a machine learning framework with tracking, model building and maintenance, and feedback loop are provided. In one technique, a prediction model is generated based on features of multiple entities. For each entity indicated in a first database, multiple feature values are identified, which include feature values stored in the first database and feature values based on sub-entity data regarding individuals associated with the entity. The feature values are input into the prediction model to generate a score for the entity. Based on the score, a determination is made whether to add, to a second database, a record for that entity. The second database is analyzed to identify other entities. For each such entity, a determination is made whether to generate a training instance; if so, a training instance is generated and added to training data, which is used to generate another prediction model.

Abstract: A tree crown extraction method based on UAV multi-source remote sensing includes: obtaining a visible light image and LIDAR point clouds, taking a digital orthophoto map (DOM) and the LIDAR point clouds as data sources, using a method of watershed segmentation and object-oriented multi-scale segmentation to extract single tree crown information under different canopy densities. The object-oriented multi-scale segmentation method is used to extract crown and non-crown areas, and a tree crown distribution range is extracted with the crown area as a mask; a preliminary segmentation result of single tree crown is obtained by the watershed segmentation method based on a canopy height model; a brightness value of DOM is taken as a feature, the crown area of the DOM is performed secondary segmentation based on a crown boundary to obtain an optimized single tree crown boundary information, which greatly increases the accuracy of remote sensing tree crown extraction.

Abstract: Provided is a photovoltaic module, including a first intermediate busbar having a first lead-out terminal provided at an end thereof; a second intermediate busbar having a second lead-out terminal provided at an end thereof; and a first jumper wire arranged on a first isolation bar; the first lead-out terminal and the second lead-out terminal are located on two opposite sides of the first jumper wire, and the first lead-out terminal and the second lead-out terminal abut against two opposite side surfaces of the first isolation bar or overlap a top surface of the first isolation bar. Compared with the related art, the first isolation bar where the first jumper wire is located is clamped or pressed by the first lead-out terminal and the second lead-out terminal, to prevent short circuit or shielding of the cell caused by free movement of the first jumper wire, the first and second intermediate busbars.

Abstract: The present disclosure provides a battery housing including a recess and a communication wiring socket. The recess is recessed inward from a side wall of the battery housing. The communication wiring socket is provided on an inner wall of the recess and configured to connect with a battery management system disposed within the battery housing. The recess is configured to provide a handheld space and to receive a communication wiring terminal plugged into the communication wiring socket. The present disclosure further provides an energy storage battery including the battery housing, and an energy storage system including the energy storage battery.

Abstract: Provided is a method for treating diseases related to cardiac tissue damage or cardiac insufficiency in a subject. The method includes the step of locally applying a mesenchymal stem cell sheet such as an umbilical cord mesenchymal stem cell sheet to the heart of the subject. Also provided are related use and compositions of the mesenchymal stem cell sheet.

Abstract: Provided is a method for fabricating a photovoltaic module. The method includes: providing a cell sheet having a predetermined thickness, and cutting the cell sheet along a direction parallel to busbars of the cell sheet, to form cutting lines on a surface of the cell sheet; splitting the cell sheet along the cutting lines, to obtain multiple cell pieces; coating, for each of the cell pieces, a conductive adhesive material on a busbar located at an edge of the cell piece; arranging the multiple cell pieces in a preset overlapping manner; curing the conductive adhesive material among the cell pieces, to form a cell string in which the cell pieces are conductively connected; and encapsulating the cell string to obtain the photovoltaic module.

Abstract: A lower limb traction device for intramedullary nail implantation operation includes a chassis with a first end portion and a second end portion opposite to each other; a first slide block slidably provided at a second end portion of the chassis in a longitudinal direction of the chassis; a lower leg support plate having two opposite end portions and two opposite side portions, wherein one end portion is connected to the first slide block; an upper leg back plate having opposite end portions and opposite side portions, wherein one end portion of the upper leg back plate is connected to the second end portion of the chassis, and the other end portion of the upper leg back plate is connected to the other end of the lower leg support plate; and a pulling mechanism provided at the first end portion of the chassis.

Abstract: Provided is a composite sheet that is particularly useful as an AQDL component in absorbent articles. The composite sheet includes a fluid acquisition component and an airlaid component. The airlaid component may include one or more airlaid layers that are successively formed overlying each other. Each of the airlaid layers are adjacent to, and in direct contact with, immediately adjacent layers of the airlaid component so that adjacent layers are in fluid communication with respect to each other. The fluid acquisition component includes a nonwoven fabric comprising a carded nonwoven fabric comprised of a plurality of staple fibers that are air through bonded to each other to form a coherent nonwoven fabric. The airlaid layer(s) include a blend of cellulose and non-cellulose staple fibers. The staple fibers may be bicomponent fibers having a polyethyelene sheath and a polypropylene or polyethylene terephthalate core, and mixtures of such fibers.

Abstract: A full-effective reverse osmosis membrane element and a water purification machine are provided. The reverse osmosis membrane element includes a reverse osmosis membrane (20) and a central tube (10) provided with several water-inlet holes (11). The reverse osmosis membrane (20) is wound around the central tube (10) and covers each water-inlet hole (11) and forms a raw water flow channel. Two sides of the reverse osmosis membrane (20) are sealed by first and second water division bands (21) (22). The first water division band (21) and the central tube (10) form a first concentrated water-outlet (211). The first water division band (21) and the reverse osmosis membrane (20) form a second concentrated water-outlet (212). The second water division band (22) and the reverse osmosis membrane (20) form a first raw water-inlet (221). The second water division band (22) and the central tube (10) form a second raw water-inlet (222).

Abstract: A cotton topping unmanned aerial vehicle having cutter discs and front grain lifting baffle plates is provided, the unmanned aerial vehicle includes an unmanned aerial vehicle body, a carrying component, a grain lifting component, and a cutting component. The carrying component includes a suspension, an electric push rod mounting base, an electric push rod, a motor mounting base, and motors. An upper end of the electric push rod is bolted to the electric push rod mounting base. The motor mounting base is welded to a lower end of the electric push rod. The grain lifting component is grain lifting baffle plates which include a left baffle plate and a right baffle plate, and both the left baffle plate and the right baffle plate are welded to guard plates.

Abstract: The rotating electric machine (1) having a housing comprising first (14) and second (15) clamp members and an inner face, a stator comprising a stator body (41) clamped between the first and second clamp members and having an outer face extending opposite the inner face together defining an annular cooling chamber (21) surrounding the stator body, the stator body comprising a longitudinal stack of stator sheets (410), each stator pack of which comprises an annular core having an outer circumference and at least two radially centrifugal protuberances projecting from the outer circumference of the annular core, in the annular cooling chamber, and diametrically opposite one another, the stator sheets of the longitudinal stack being identical and two adjacent stator sheet of the longitudinal stack being angularly offset from each other such that the respective protuberances thereof do not extend opposite one another.

Abstract: The invention relates to a rotating electrical machine (1) comprising a housing (10) including two bearings (52, 53), a rotor shaft (5) mounted to rotate freely in the housing via the bearings, a rotor (6) clamped to the rotor shaft so as to rotate the rotor shaft and comprising first (62) and second (63) axial end faces, and a cooling circuit comprising a coolant supply duct (51) arranged coaxially in the rotor shaft, and a radially oriented feed duct (54) arranged in the rotor shaft and in fluid communication with the supply duct and the rotor, characterized in that the cooling circuit further comprises a cooling chamber (61) in fluid communication with the feed duct, extending axially between the rotor and the rotor shaft, opening onto the first and second axial end faces and delimited radially by an angular portion of an external surface (55) of the rotor shaft and an angular portion (65) of an internal surface of the rotor, the two portions extending opposite and at a distance from one another.

Abstract: The present disclosure provides a culture device and a preparation method for a cell membrane, and relates to the field of cell culture technology. The culture device for a cell membrane includes a semiconductor refrigerator, and one or more culture vessels configured to culture a cell membrane. The semiconductor refrigerator includes a first insulating substrate, a second insulating substrate, and at least one semiconductor thermocouple disposed between the first insulating substrate and the second insulating substrate. The one or more culture vessels are disposed on a side of the first insulating substrate away from the second insulating substrate.

Abstract: The present disclosure provides pilocarpine ionic liquid analogs useful in the treatment of ophthalmological disorders such as glaucoma.

Abstract: Some embodiments of the disclosure provide an artificial neural network system for recognizing a lesion in a fundus image. The system includes a pre-processing module configured to pre-process a target fundus image and a reference fundus image taken from one person separately, a first neural network (12) configured to generate a first advanced feature set from the target fundus image, a second neural network (22) configured to generate a second advanced feature set from the reference fundus image, a feature combination module (13) configured to combine the first advanced feature set and the second advanced feature set to form a feature combination set, and a third neural network (14) configured to generate, according to the feature combination set, a judgmental result of lesions.

Abstract: Some embodiments of the disclosure provide a diabetic retinopathy recognition system (S) based on fundus image. According to an embodiment, the system includes an image acquisition apparatus (1) configured to collect fundus images. The fundus images include target fundus images and reference fundus images taken from a person. The system further includes an automatic recognition apparatus (2) configured to process the fundus images from the image acquisition apparatus by using a deep learning method. The automatic recognition apparatus automatically determines whether a fundus image has a lesion and outputs the diagnostic result. According to another embodiment, the diabetic retinopathy recognition system (S) utilizes a deep learning method to automatically determine the fundus images and output the diagnostic result.