Abstract: The present application relates to a method and system for generating multi-task learning-type generative adversarial network for low-dose PET reconstruction, and relates to the field of deep learning. The method includes connecting layers of the encoder with layers of the decoder by skip connection to provide a U-Net type picture generator; generating a group of generative adversarial networks by matching a plurality of picture generators with a plurality of discriminators in one-to-one manner; obtaining a first multi-task learning-type generative adversarial network; designing a joint loss function 1 for improving image quality; and training the first multi-task learning-type generative adversarial network according to the joint loss function 1 in combination with an optimizer to provide a second multi-task learning-type generative adversarial network.

Abstract: A centrifuge for cleaning a reaction vessel unit comprises a rotor and a rotor chamber in which the rotor is positioned and supported in rotary fashion. The rotor chamber is delimited by a housing having a drainage channel beneath the rotor. Adjacent to the channel, the inner surface of the housing is embodied in the form of a funnel that feeds into the channel. This centrifuge does not require a suction pump for suctioning liquids from the rotor chamber. In addition, the centrifuge can be provided with an exchangeable module that delimits the rotor chamber and includes the rotor. The exchangeable module can be exchanged after a predetermined amount of use and replaced with another. It is also possible, however, for the module to be removed from the centrifuge, cleaned, and reinserted.

Abstract: A single-shot Fresnel non-coherent correlation digital holographic device based on a polarization-oriented planar lens, comprising: A polarization-oriented planar lens (1) for wavefront modulation and beam splitting, a focusing element (2), a half-wave plate (3) with a small hole and a polarization imaging camera (4). Incident light passes through the polarization-oriented planar lens (1) and the focusing element (2) and is divided into two beams with different polarizations, that is, focused and parallel or focused and divergent beams, wherein the focused beam passes through the small hole of the half-wave plate (3), the parallel or divergent beam passes through the half-wave plate (3), so as to make the polarization of the two beams consistent behind pass through the half-wave plate (3).

Abstract: Disclosed are information transmission method, apparatus, device and medium for medical imaging application. The method includes: an imaging device corresponding to an application authorization request is determined according to the received application authorization request, and an application permission profile of the imaging device is acquired; and a medical imaging application corresponding to the imaging device is determined according to the application permission profile of the imaging device, and medical imaging application information corresponding to the medical imaging application is transmitted to the imaging device.

Abstract: A method, device, terminal, and storage medium for reusing parameters of a deep learning model are disclosed, the method including: training a target model with a preset training set; obtaining a pre-trained original model; obtaining correspondences between layers of the target model and the original model having identical network structures, and parameter correspondences between corresponding layers; extracting multiple original model parameters from layers of the original model each having an identical network structure with respective layer of the target model; based on the parameter correspondences, replacing the corresponding parameters of the target model one by one with the original model parameters, validating the replaced target model with the preset validation set, and when the validation is passed, recording that the corresponding original model parameter is reusable; and using all reusable original model parameters to replace the corresponding parameters in the target model to obtain and train a n

Abstract: Provided are a parallel magnetic resonance imaging method and apparatus based on adaptive joint sparse codes and a computer-readable medium. The method includes solving an l2?lF?l2,1 minimization objective, where the l2 norm is a data fitting term, the lF norm is a sparse representation error, and the l2,1 mixed norm is the joint sparsity constraining across multiple channels; separately updating each of a sparse matrix, a dictionary and K-space data with a corresponding algorithm, and obtaining a reconstructed image by a sum of root mean squares of all the channels. The joint sparsity of the channels is developed using the norm l2,1. In this manner, calibration is not required while information sparsity is developed. Moreover, the method is robust.

Abstract: Disclosed are a method for preparing a AgNPs@SASP substrate material and application thereof. The present disclosure uses cyclohexane as an organic phase and ethanol as an inducer, and uses the interfacial tension of an organic/water interface for self-assembly to arrange the nanoparticles in a single layer. The addition of a low-dielectric solvent as an inducer reduces the charge density on the nanoparticles. As a result, the van der Waals force combined with the reduction of the Coulomb repulsion force cause the nanoparticles to reassemble at the organic/water interface to form a new equilibrium, and a SERS platform of AgNPs in a two-dimensional array is prepared. SERS detection and peak attribution analysis of different food-borne pathogen spores are carried out, and qualitative analysis is carried out by a multivariate statistical method to realize the rapid identification of spore-forming bacteria.

Abstract: A handle trigger control apparatus and a handle having the handle trigger control apparatus are disclosed. The handle trigger control apparatus comprises a trigger bracket, and further comprises: a trigger that is movably disposed on the trigger bracket and is provided thereon with a trigger magnet; a bracket magnet that is movable and can be fixedly provided on the trigger bracket; and a control device configured to control the bracket magnet to approach or go away from the trigger magnet to adjust an action distance between the trigger magnet and the bracket magnet.

Abstract: The invention discloses a torque strengthening device for land surfboard adapters, comprising an upper connecting plate and a lower connecting plate, wherein a number of tension springs are connected between the upper connecting plate and the lower connecting plate; the upper connecting plate and the lower connecting plate are provided with the same number of evenly arranged spring connecting blocks on the side facing the tension springs; the number of the tension springs is twice the number of the spring connecting blocks on the upper connecting plate, and each of the spring connecting blocks is provided with two spring connecting holes; the spring connecting blocks of the upper connecting plate and the spring connecting blocks on the lower connecting plate are alternately arranged. The invention can replace tension springs with different torques to obtain different surfing feelings.

Abstract: A trigger device and an interactive terminal having the same are disclosed. The trigger device includes, but is not limited to, a trigger bracket and a trigger movably arranged on the trigger bracket, and further includes: a trigger electromagnet, which is fixed on the trigger; a bracket electromagnet, which is fixed on the trigger bracket, and has an effect of attracting or repulsing with the trigger electromagnet in a pressed state; an electromagnetic control device, which is connected to an electromagnetic coil of the trigger electromagnet and the electromagnetic coil of the bracket electromagnet respectively, and is configured to adjust the voltage or current of the electromagnetic coil of the trigger electromagnet and the electromagnetic coil of the bracket electromagnet.

Abstract: A trigger driving apparatus and hand-held terminal having said apparatus are provided. Wherein the trigger driving apparatus comprises a bracket (8) and a movable trigger housing arranged on the bracket, and further comprises: a drive device, wherein a drive shaft of the drive device is connected to one end of a link rod mechanism, the other end of the link rod mechanism is connected to the trigger housing, and the drive shaft is configured to drive the trigger housing to move; a detection device is configured to detect the state of the trigger housing; a control device is configured to receive the state signal detected by the detection device, and control the output torque of the drive device according to the state signal.

Abstract: A gamepad and a joystick feedback force apparatus thereof are disclosed. The joystick feedback force apparatus comprises a joystick that is configured to accept a user's operation and is rotatably installed in a casing of the gamepad. It further comprises a torque output device and a deceleration device. An output shaft of the torque output device is connected with an input end of the deceleration device, an output end of the deceleration device is connected with a rotating shaft of the joystick to apply a torque output by the torque output device to the rotating shaft. When the user operates the joystick to rotate, a certain torque is applied to the rotating shaft after being decelerated by the deceleration device, namely, the corresponding torque is applied to the joystick to form a feedback force to the user.

Abstract: A gamepad and a joystick feedback force device therefor are disclosed. The joystick feedback force device comprises a joystick that is configured to accept a user's operation and is rotatably installed in a casing of the gamepad. The joystick feedback force device further comprises a torque output device, and an output shaft of the torque output device is connected with a rotating shaft of the joystick, so that a torque is applied to the rotating shaft to form a feedback force to the joystick.

Abstract: The invention discloses a torque strengthening device for land surfboard adapters, comprising an upper connecting plate and a lower connecting plate, wherein a number of tension springs are connected between the upper connecting plate and the lower connecting plate; the upper connecting plate and the lower connecting plate are provided with the same number of evenly arranged spring connecting blocks on the side facing the tension springs; the number of the tension springs is twice the number of the spring connecting blocks on the upper connecting plate, and each of the spring connecting blocks is provided with two spring connecting holes; the spring connecting blocks of the upper connecting plate and the spring connecting blocks on the lower connecting plate are alternately arranged. The invention can replace tension springs with different torques to obtain different surfing feelings.

Abstract: A computer system provides online state estimation (SE) and topology identification (TI) using advanced metering infrastructure (AMI) measurements in a distribution network. The computer system obtains input data including the AMI measurements, a network configuration, and line parameters; solves an SE and TI problem formulated from the input data and power equations of the distribution network; and periodically updates states and topology of the distribution network during power system operation. To solve the SE and TI problem, the computer system constructs a mixed-integer convex approximation programming (MICP) model to obtain an initial topology; generates neighboring spanning trees according to the MICP model and the initial topology; evaluates performance of each neighboring spanning tree with a matching index that is an indication of power flow performance; and chooses a tree topology of a neighboring spanning tree having a minimum matching index as a final network topology of the distribution network.

Abstract: Methods and apparatuses for training a magnetic resonance imaging model, electronic devices and computer readable storage media are provided.

Abstract: There are provided a parallel rapid imaging method and device based on a complex number conjugate symmetry of multi-channel coil data and nonlinear GRAPPA image reconstruction, and a medium. The imaging method includes: obtaining virtual conjugate coil data by expanding the actual multi-channel coil data; combining actual multi-channel coil data and virtual multi-channel coil data to obtain a linear data term and a nonlinear data term; calibrating weighting factors of the linear data term and the nonlinear data term by using combined low-frequency full-sampling data (margins of the low-frequency full-sampling data includes parts of high-frequency data); reconstructing data which is under-sampled in a high-frequency region according to the calibrated weighting factors; fusing the low-frequency full-sampling data and the reconstructed data for the high-frequency region.

Abstract: An apriori guidance network for multitask medical image synthesis is provided. The apriori guidance network includes a generator and a discriminator, wherein the generator includes an apriori guidance module configured to convert an input feature map into a target modal image pointing to a target domain according to an apriori feature, and the apriori feature is a deep feature of the target modal image. The generator is configured to generate a corresponding target domain image by taking the apriori feature of the target modal image and source modal image data as an input. The discriminator is configured to discriminate an authenticity of the target domain image outputted by the generator.

Abstract: A medical image noise reduction method, system, terminal and storage medium are disclosed. The method includes: obtaining a standard-dose PET image and a. constant-value image; inputting the standard-dose PET image and the constant-value image into a decay function to obtain a corresponding low-dose noisy PET image and a noisy constant-value image, respectively; assembling the low-dose noisy PET image and the noisy constant-value image in a width dimension or a height dimension, and then inputting into a trained conjugate generative adversarial network, and outputting a denoised PET image and constant-value image output by the conjugate generative adversarial network.

Abstract: Described herein is a method for joining a first metal pipe with a second metal pipe, the pipes being joined together in an overlapping area by use of a two-component polyurethane adhesive that encapsulates the overlapping area, where the method includes the steps of: (1) applying the two-component polyurethane adhesive onto an inner surface of a fixture; (2) inserting one end of the first metal pipe into one end of the second metal pipe so as to form a pipe assembly having the overlapping area between the two ends, and putting the overlapping area of the pipe assembly into the fixture; (3) closing the fixture such that the overlapping area of the pipe assembly is fixed in the fixture, and such that the adhesive therein encapsulates the overlapping area of the pipe assembly; (4) curing the two-component polyurethane adhesive; and (5) optionally, removing the fixture from the pipe assembly.