Abstract: Disclosed are a method and apparatus for training an image restoration model, an electronic device, and a computer-readable storage medium. The method for training an image restoration model includes: pre-processing training images to obtain a low-illumination image sample set (110); determining, based on low-illumination image samples in the low-illumination image sample set and the image restoration model, a weight coefficient of the image restoration model (120), wherein the image restoration model is a neural network model determined on a U-Net network and a deep residual network; and adjusting the image restoration model according to the weight coefficient, and further training the adjusted image restoration model using the low-illumination image samples until the image restoration model restores parameters of all the low-illumination image samples in the low-illumination image sample set into a preset range (130).

Abstract: A method for detecting hidden malicious traffic based on a traffic interaction map and a device are provided. The method includes monitoring traffic passing through a gateway by a detection system operating in the gateway; obtaining a data packet granularity feature by performing feature extraction of granularity of a data packet on the traffic monitored; constructing a traffic interaction map according to the data packet granularity feature to represent a long-term interaction mode of the traffic by a graph structure of the traffic interaction map; and detecting an abnormal local structure on the traffic interaction map by a detection algorithm of graph learning based on the traffic interaction map, and marking the abnormal local structure as the corresponding hidden malicious traffic.

Abstract: The present invention relates to methods of preparing a therapeutic exosome using a protein newly-identified to be enriched on the surface of exosomes. Specifically, the present invention provides methods of using the proteins for affinity purification of exosomes. It also provides methods of localizing a therapeutic peptide on exosomes, and targeting exosomes to a specific organ, tissue or cell by using the proteins. The methods involve generation of surface-engineered exosomes that include one or more of the exosome proteins at higher density, or a variant or a fragment of the exosome protein.

Abstract: Provided is an electromagnetic field simulation method based on a face-centered cubic and a subgrid, including setting periodic boundary conditions and a metal plate to construct an electromagnetic field simulation model based on the face-centered cubic, FDTD and the subgrid; through the electromagnetic field simulation model, setting the source point in the subgrid region, selecting the detecting point, simulating the electromagnetic field simulated, and obtaining the moment domain waveform diagram of the electric field in the simulation region.

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate object tracking paths for the vehicle to facilitate navigational controls in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs-such as feature descriptor maps including feature descriptor vectors corresponding to objects included in a sensor(s) field of view. The outputs may be decoded and/or otherwise post-processed to reconstruct object tracking and to determine proposed or potential paths for navigating the vehicle.

Abstract: The present disclosure discloses a hotpatch method for vulnerabilities in embedded Internet of Things (IoT) devices. The method includes acquiring vulnerability information of the embedded IoT devices to be patched; selecting a corresponding vulnerability patching mode based on different vulnerability types of the vulnerability information, and acquiring an eBPF patch bytecode file (first patch) and an eBPF patch code configuration file from a server according to the vulnerability patching mode; compiling the eBPF patch bytecode based on the eBPF patch bytecode and the eBPF patch code configuration file to generate a patch binary code file (second patch) and configuration information of the patch binary code; and adopting three approaches to trigger the patch binary code to patch the vulnerability information based on the configuration information and the vulnerability patching mode.

Abstract: Disclosed are a method and apparatus for labeling an object contour in a target image, a non-transitory computer-readable storage medium and an electronic device. The method for labeling an object contour in a target image includes acquiring a target image feature of a target image, inputting the target image feature into a target generator, and acquiring a target mask of the target image generated by the target generator, wherein the target mask is used for labeling a contour of the target object.

Abstract: Disclosed herein are extracellular vesicles comprising an immunomodulating component. Also provided are methods for producing the extracellular vesicles and methods for using the extracellular vesicles for treating cancer, GvHD, and autoimmune diseases.

Abstract: A compact rotary algae biofilm reactor includes an algae biofilm module and a light guide module. The algae biofilm module includes a plurality of rotary members and a reaction tank. In the rotary member, an algae biofilm growth carrier and a power transmission belt are wound on a driving shaft and a driven shaft. A top end of the rotary member is fixed on a fixing frame while a bottom end thereof is submerged in the reaction tank. The light guide module includes a rotatable lens holder. The rotatable lens holder is fixedly provided with a linear Fresnel lens on an upper end thereof and is provided with a light guide plate on a lower end thereof. One side of the linear Fresnel lens is provided with a step motor configured to control the linear Fresnel lens to rotate with an angle of sunlight.

Abstract: Provided herein are methods of treating a KRAS mutant cancer (e.g., a KRAS G12C mutant cancer or a KRAS G12D mutant cancer) in a subject, comprising administering to the subject an effective amount of an agent that blocks the interaction between CD47 and SIRP? and an effective amount of a KRAS inhibitor (e.g., a KRAS G12C inhibitor wherein the cancer is a KRAS G12C mutant cancer, or a KRAS G12D inhibitor wherein the cancer is a KRAS G12D mutant cancer). Also provided are methods of stimulating phagocytosis of a population of cancer cells that express a KRAS mutant protein (e.g., a KRAS G12C mutant protein or a KRAS G12D mutant protein) by macrophages, comprising contacting the population with an effective amount of a therapeutic agent that blocks the interaction between CD47 and SIRP? and an effective amount of a KRAS inhibitor (e.g., a KRAS G12C inhibitor wherein the KRAS mutant protein is a KRAS G12C mutant protein, or a KRAS G12D inhibitor wherein the KRAS mutant protein is a KRAS G12D mutant protein).

Abstract: A computer-implemented method of map data processing, comprising generating, for a grid-based representation of map data, raw grid features; building a grid map by reading from a memory that stores the raw grid features; and processing the grid map using one or more post-processing operations including a smoothing operation applied across zero or more grid lines of the grid map according to a rule.

Abstract: An optically addressable pixelated spatial light modulator, comprising: a laser light source, a structured light field encoding projection module, and a superpixel metasurface device. The structured light field encoding projection module comprises a structured light field encoding module, which encodes a laser beam emitted by a laser light source into a structured light beam according to the modulation amount distribution of a target light field. The superpixel metasurface device comprises a plurality of unit cell structures, with each unit cell structure serving as a light field modulation pixel point. Each unit cell structure comprises a plurality of sub-wavelength micro-nano structures, and the unit cell structure generates a light field modulation amount under the action of the structured light beam for the light field modulation.

Abstract: The present disclosure relates to extracellular vesicles comprising one or more antigens from a coronavirus (e.g., SARS-CoV-1 or SARS-CoV-2) and optionally an adjuvant. Also provided herein are methods for producing the EVs and methods for using the EVs to treat and/or prevent diseases or disorders, e.g., infectious diseases.

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate object tracking paths for the vehicle to facilitate navigational controls in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as feature descriptor maps including feature descriptor vectors corresponding to objects included in a sensor(s) field of view. The outputs may be decoded and/or otherwise post-processed to reconstruct object tracking and to determine proposed or potential paths for navigating the vehicle.

Abstract: Provided is an array substrate, including a substrate, a plurality of gate lines, and a plurality of sub-pixels. The gate line includes a plurality of connection portions and a plurality of jumper portions, which are alternately arranged and disposed in different layers. The connection portion includes a connection line segment, a first adapter line segment, and a second adapter line segment. One end of the connection line segment is connected to the first adapter line segment, and the other end is connected to the second adapter line segment. One end of the jumper portion, between adjacent two connection portions, is connected to an end, going away from the connection line segment, of the first adapter line segment in one of the connection portions, and the other end is connected to an end, going away from the connection line segment, of the second adapter line segment in the other connection portion.

Abstract: Systems and methods are provided for a battery management system (BMS) having a protection circuit. In one example, a vehicle battery system may include the BMS, the BMS including a cutoff circuit coupled to a short-circuit protection circuit, and a battery pack, wherein the short-circuit protection circuit may include a diode array, cathodes of the diode array being coupled to a positive terminal post of the battery pack and anodes of the diode array being coupled to a negative terminal post of the battery pack. In some examples, the cutoff circuit may further be coupled to a reverse bias protection circuit including a switchable current path arranged between a control input of the cutoff circuit and an output of the cutoff circuit. In this way, the vehicle battery system may be protected from unexpected voltage conditions via the BMS redirecting and dissipating excess current away from the cutoff circuit.

Abstract: Systems and methods are provided for a battery management system (BMS) having a protection circuit. In one example, a vehicle battery system may include the BMS, the BMS including a cutoff circuit coupled to a short-circuit protection circuit, and a battery pack, wherein the short-circuit protection circuit may include a diode array, cathodes of the diode array being coupled to a positive terminal post of the battery pack and anodes of the diode array being coupled to a negative terminal post of the battery pack. In some examples, the cutoff circuit may further be coupled to a reverse bias protection circuit including a switchable current path arranged between a control input of the cutoff circuit and an output of the cutoff circuit. In this way, the vehicle battery system may be protected from unexpected voltage conditions via the BMS redirecting and dissipating excess current away from the cutoff circuit.

Abstract: The present invention relates to methods of preparing a therapeutic exosome using a protein newly-identified to be enriched on the surface of exosomes. Specifically, the present invention provides methods of using the proteins for affinity purification of exosomes. It also provides methods of localizing a therapeutic peptide on exosomes, and targeting exosomes to a specific organ, tissue or cell by using the proteins. The methods involve generation of surface-engineered exosomes that include one or more of the exosome proteins at higher density, or a variant or a fragment of the exosome protein.