Abstract: Capture membranes for lanthanide metal ions can be made from fusion proteins having at least one lanthanide metal binding sequence (SEQ ID NO: 1-4) covalently bound to a silk-elastin-like polymer (SELP). Capture membranes can be made from silk nanofibrils that are surface-modified with a lanthanide metal binding molecule. The capture membranes can have a layered structure or can contained cross-linked peptides in a hydrogel.

Abstract: A system for classifying working memory task magnetoencephalography based on machine learning, including: the magnetoencephalography data acquisition module configured to acquire magnetoencephalography data of a subject in different working memory task states; the magnetoencephalography data preprocessing module configured to control the quality of magnetoencephalography data in different working memory tasks and separate noises and artifacts; the magnetoencephalography source reconstruction module configured for sensor signal analysis and source reconstruction analysis for the data processed by the magnetoencephalography data preprocessing module; and the machine learning classification module is configured to classify the working memory tasks to which the subjects belong by taking power time series as features.

Abstract: A system for precisely locating abnormal areas of brain fiber bundles. The system extracts fiber connections of the whole brain from diffusion magnetic resonance data, and fiber bundle pathways extracts through self-defined fiber bundle pathways or based on brain fiber bundle templates. A selected fiber bundle pathway is projected on a fiber connection result of the whole brain and finely segmented. The imaging indexes such as fractional anisotropy, mean diffusivity, intra-neurite volume fraction and orientation dispersion index are calculated from diffusion magnetic resonance data, so as to obtain the imaging index of each node of each fiber bundle pathway. These imaging indexes are configured to classify the disease group and the healthy group by a machine learning method, and which nodes on which fiber bundle pathways have abnormal changes with different diseases can be precisely located.

Abstract: A method and a system for simulating magnetic resonance echo-planar imaging artifacts. Firstly, for K-space artifacts, K-space data are restored through normal magnetic resonance images, and the K-space data are modified pertinently, and then images with artifacts are reconstructed; for susceptibility artifacts, a susceptibility model is constructed through normal magnetic resonance images, and the magnetic field distribution is reconstructed, and then the images with distortion artifacts are reconstructed. According to the present disclosure, a large number of artifact data sets with different artifact types and artifact degrees can be quickly created through a small number of normal images, thus laying a foundation for the research of identifying artifacts, eliminating or weakening artifacts.

Abstract: A system for predicting disease with graph convolutional neural network based on multimodal magnetic resonance imaging, which extracts the radiomics information of multiple brain regions across modals as the features of nodes from multimodal magnetic resonance data, and extracts the connectomics information between brain regions to form an adjacency matrix. T1-weighted structural images extract cortical information through cortical reconstruction, and resting-state magnetic resonance data are used to calculate amplitude of low frequency fluctuations, regional homogeneity and functional connectivity. Through multimodal data preprocessing, image index extraction and structured data integration, multimodal unstructured magnetic resonance image data are integrated into unified graph-structured data, and the disease is predicted by a graph convolutional neural network method.

Abstract: A cognitive training material generation method, a cognitive training method, a device, and a medium are provided. The cognitive training material generation method includes: acquiring a first feature and a second feature, the first feature including a multimedia material and semantic information corresponding to the multimedia material, the second feature including a magnetic resonance representation; fitting the first feature and the second feature, obtaining a semantic map according to a fitting result and a preset brain map, and acquiring target semantic information corresponding to a target point according to the semantic map; taking the first feature as input of a deep learning model and the second feature as a constraint of the deep learning model, training the deep learning model, and determining a weight parameter of the deep learning model; generating a cognitive training material according to the target semantic information and the weight parameter of the deep learning model.

Abstract: Disclosed is a method for removing impurity mercury from crude selenium. The method includes: mixing a vulcanizing agent with a crude selenium slag that is crushed to not more than 200 mesh uniformly, and performing briquetting to obtain a mixed material; adding the mixed material into a sealed furnace, and subjecting the mixed material to vulcanization by heating under an inert atmosphere to obtain a vulcanized selenium; subjecting the vulcanized selenium to primary vacuum distillation, such that selenium is converted into a gas phase and collected in a form of a volatile, and generated mercury sulfide and valuable elements are enriched in a resulting residue; and subjecting the selenium to secondary distillation to further remove mercury.

Abstract: Disclosed is a multi-dimensional analysis method for a tripping risk of a whole transmission line due to a lightning shielding failure. A quantity of thunderstorm days, a tower size, a terrain proportion, an altitude, and insulation configuration data are collected for a transmission line for which a tripping risk due to a lightning shielding failure needs to be analyzed, and a striking distance, an exposure distance, a lightning resisting level of the line after altitude factor correction, and a lightning shielding failure risk of a single-base tower are calculated in turn. Characteristics of a lightning shielding failure under different nominal heights, quantities of thunderstorm days, and terrains are studied. Representative combination conditions are selected to calculate a tripping risk of a typical tower due to the lightning shielding failure. A weight coefficient is extracted, to calculate a tripping risk of the whole line due to the lightning shielding failure.

Abstract: A part identification method includes acquiring an image including a part, detecting the image based on a detection model and identifying a type of the part, and determining part information based on the type of the part identified and outputting the part information. The determining the part information based on the type of the part identified includes determining a part in a predetermined region in the image based on the type of the part identified, and determining the part information based on the part determined. The predetermined region includes a planar region or a spatial region.

Abstract: The present disclosure provides a method and a system for quickly determining transient stability of a half-wavelength transmission system. The method includes: obtaining power and a power angle of a feeding-end generator of a half-wavelength transmission system; and determining transient power angle stability and a power angle instability mode of the half-wavelength transmission system by using a constructed index system, where two power angle instability modes, that is, an instability mode 1 and an instability mode 2, are specifically constructed for the half-wavelength transmission system based on an equal area method. Based on the equal area method, the present disclosure constructs two instability modes specific to the half-wavelength transmission system, so as to accurately describe transient power angle characteristics of the half-wavelength transmission system under a severe fault, and characteristics of the two instability modes are significantly different from those of an AC transmission mode.

Abstract: A method includes: generating fault alarm information, and sending the fault alarm information through a serializer/deserializer (SerDes) bus. The fault alarm information indicates a fault that occurs in a first apparatus and/or a target communication link, and the target communication link is a link for communication between the first apparatus and a second apparatus.

Abstract: A circuit-breaker includes a battery module terminal, a battery pack system terminal, and a plurality of switching channels connected in parallel and coupled between the battery module terminal and the battery pack system terminal. Each of the switching channels includes one or more semiconductor switching devices and is configured to turn on/off a circuit between the battery module terminal and the battery pack system terminal. During abnormality diagnosis, at least one of the switching channels is set to be in a turned-on state.

Abstract: A low-voltage lithium battery circuitry includes a busbar, a battery signal transmitter unit, a battery management system, and a lithium battery module connected to the battery management system through the busbar and the battery signal transmitter unit. The lithium battery module is configured to provide energy for an external load and supply power to the battery management system. The battery management system is configured to monitor electrical parameters acquired in the lithium battery module and, when any one of the electrical parameters exceeds a protection threshold range corresponding thereto, perform a protection operation.

Abstract: The present disclosure provides a method for recognizing a small target based on a deep learning network. The method comprises: determining, based on a collected image, spot defect information through a recognition model including a first feature determination layer, a second feature determination layer, and a spot defect determination layer, determining, based on the collected image, a first feature map, determining, based on the first feature map, a second feature map by fusing with positional encoding, determining, based on the second feature map, a third feature map through the second feature determination layer, and obtaining, based on the third feature map, positional information of the spot defect through a first determination layer, and determining, based on the third feature map, classification information of the spot defect through a second determination layer.

Abstract: The present disclosure provides a method for recognizing a small target based on a deep learning network. The method comprises: determining, based on a collected image, spot defect information through a recognition model including a first feature determination layer, a second feature determination layer, and a spot defect determination layer, determining, based on the collected image, a first feature map, determining, based on the first feature map, a second feature map by fusing with positional encoding, determining, based on the second feature map, a third feature map through the second feature determination layer, and obtaining, based on the third feature map, positional information of the spot defect through a first determination layer, and determining, based on the third feature map, classification information of the spot defect through a second determination layer.

Abstract: An intelligent harvester with instantaneous stop functions includes a harvester body, a detecting system for detecting a human body within an area range on a traveling route of the harvester body, and a brake system arranged on the harvester body and operatively connected to the detecting system. When the detecting system detects a human body present within the area range on a traveling path of the harvester body, the brake system controls the harvester body to brake.

Abstract: Disclosed is an intelligent vehicle-mounted radar device for reducing signal interference, wherein, the antenna module includes a dual-polarized antenna, namely, any polarized signal can be measured, and polarization information can be processed and extracted in real time by the polarization digital processor module, the present invention is featured by rapid and real-time. In addition, when the local oscillation module is turned on, the first rectifier diode, the first switch module, the first resistor, the second resistor and the second rectifier diode make the current flowing through the local oscillation module rise gradually to suppress signal interference, and thus improve the performance of the intelligent vehicle-mounted radar device.

Abstract: Disclosed is an intelligent vehicle-mounted radar device for reducing polarization loss, wherein, the antenna module includes a dual-polarized antenna, namely, any polarized signal can be measured, and polarization information can be processed and extracted in real time by the polarization digital processor module, the present invention is featured by rapid and real-time.

Abstract: A method for making wooden straws from a solid wood stick includes a step of providing a solid wood stick; a step of clamping the solid wood stick by a molding set, and two ends of the solid wood stick protruding beyond the molding set, and a step of drilling an axial passage through the solid wood stick by at least one machining unit to form a wooden straw. The wooden straws are bio-degradable and durable. The wooden straws do not affect beverage taste and can be manufactured in mass production. The molding set for making the wooden straws includes two dies and each die includes a groove. The solid wood stick is accommodated in the two respective grooves. At least one machining unit is used to drill an axial passage through the solid wood stick to form the wooden straw.

Abstract: The present invention relates to an optical module and optical module system using the same. The optical module comprises a transceiving unit, an antenna and an MCU. The transceiving unit receives control commands from one or more control computers via the antenna and transfers them to the MCU. Then the MCU processes the control commands and provides feedback information to the one or more control computers through the transceiving unit. In the optical module of the present invention, as a result of an additional IOT wireless unit, the optical module is capable of communicating with remote control computers, thereby achieving remote testing and control for optical modules, instead of using conventional control methods for optical modules.