Abstract: Provided is a packaging structure for packaging a display device, the packaging structure comprising: at least one composite film layer, wherein the composite film layer comprises an inorganic pattern and an organic pattern, the inorganic pattern comprises a plurality of curved structures arranged at intervals, the organic pattern comprises a first organic sub-pattern, and the first organic sub-pattern and the inorganic pattern are located in a same layer and are complementary in position; and wherein an orthographic projection of the composite film layer onto the display device at least covers a display area of the display device. A display substrate, a display apparatus, and a method for packaging a display device are also provided.

Abstract: The present disclosure belongs to the technical field of image processing, and provides a multi-modal image classification system and method using an attention-based multi-interaction network. The present disclosure utilizes a U-net network structure to fuse low-level visual features and high-level semantic features. An attention network is introduced to solve the problem of weak feature discrimination, and high attention is given to discriminative features, so that the attention network plays an important role in the final classification process. A sufficient multi-modal interaction mechanism is introduced, so that more effective correlation information and discriminative information are obtained among a plurality of modalities, and sufficient interaction among the plurality of modalities is completed, thereby solving the problems of weak feature discrimination and insufficient interaction among modalities in a multi-modal image classification task.

Abstract: An image recognition method and system of convolutional neural network based on global detail supplement, as follows: acquire the image to be recognized and then input it to trained feature extraction network for feature extraction, and obtain features of each stage; learn detail feature according to the image to be tested, and extract the detail feature map; use the self-attention mechanism to fuse the feature map and detail feature map output at the last stage to obtain global detail features; fuse the global detail feature and the features in each stage to obtain the features after global detail supplement; and classify according to the features after global detail supplement, and the category of the maximum value after calculation is the image classification result. The invention constructs a convolution neural network based on global detail supplement, and uses progressive training for image fine granularity classification, further improving fine granularity classification accuracy.

Abstract: A method and system for rapid retrieval of target images based on artificial intelligence, obtaining a template image and a plurality of known labels corresponding to the template image; extracting an image to be detected from a target image database; inputting both the image to be detected and the template image into a trained convolutional neural network, and outputting a hash code of the image to be detected and a hash code of the template image; obtaining a similarity between the images based on a Hamming distance between the hash codes, then selecting one or more images to be detected with the similarity higher than a set threshold as a retrieval result to output. Accordingly, the method and system is able to better cope with the retrieval of items in complex scenarios.

Abstract: A disc-type three-degree-of-freedom magnetic suspension switched reluctance motor includes a stator and a double-disc rotor. The stator includes an axial stator core, a permanent magnet ring, and a radial stator core coaxially connected to each other in sequence from outside to inside. Axial suspension teeth are distributed on two axial ends of the axial stator core, several axial torque teeth are evenly distributed between adjacent axial suspension teeth by axial magnetic isolation blocks, and axial suspension windings and axial torque windings are respectively wound on the axial suspension teeth and the axial torque teeth. Radial suspension teeth are distributed on the inner circumference of the radial stator core, radial torque teeth are evenly distributed between adjacent radial suspension teeth by a radial magnetic isolation block, and a radial suspension winding and a radial torque winding are respectively wound on the radial suspension teeth and the radial torque teeth.

Abstract: A disc-type three-degree-of-freedom magnetic suspension switched reluctance motor includes a stator and a double-disc rotor. The stator includes an axial stator core, a permanent magnet ring, and a radial stator core coaxially connected to each other in sequence from outside to inside. Axial suspension teeth are distributed on two axial ends of the axial stator core, several axial torque teeth are evenly distributed between adjacent axial suspension teeth by axial magnetic isolation blocks, and axial suspension windings and axial torque windings are respectively wound on the axial suspension teeth and the axial torque teeth. Radial suspension teeth are distributed on the inner circumference of the radial stator core, radial torque teeth are evenly distributed between adjacent radial suspension teeth by a radial magnetic isolation block, and a radial suspension winding and a radial torque winding are respectively wound on the radial suspension teeth and the radial torque teeth.

Abstract: A malware detection system for evaluating sample programs for malware incorporates an evasion code detector. The evasion code detector includes semantic patterns for identifying conditional statements and other features employed by evasion code. The system inserts breakpoints at conditional statements, compares expected and actual evaluated values of conditional variables of the conditional statements, and changes the execution path of the sample program based on the comparison. Changing the execution path of the sample program to an expected execution path counteracts the evasion code, allowing for the true nature of the sample program to be revealed during runtime.

Abstract: A sandbox system includes a mixed analysis engine that allows for dynamic and static analysis of a sample process for malware. The sample process is executed in a virtual machine and interrupted to allow the mixed analysis engine to identify functions that are called by malware to perform a malicious behavior. The functions are correlated to identify a behavior node that is indicative of the malicious behavior, and behavior nodes are correlated to identify a behavior net. The behavior net is scored to determine if the sample process is malware.

Abstract: Tablet computers send relevant geographic and identification data to an application server (one of the tablets, or a local or remote server) which groups them to form a video wall. Once placed next to one another in substantially the same plane, the tablets snap photographs at more or less the same time and these images are transmitted to the application server. The server determines the relative positions of the tablets and then streams a portion of a video or digital image to each of the tablets in order that all tablets display the video or image in an integrated fashion. The tablets may operate independently or may rely upon the remote application server. Relative positions are determined by analyzing features and determining an up-down or left-right relationship between pairs of images, sorting images into vertical and horizontal rows, and placing the images into a grid.

Abstract: An application document known to include malware (such as a document exploit) is opened and executed by its corresponding software application. Behaviors of this document (such as registry, file system, network and process) are monitored and recorded using internal software drivers and hook modules. A behavior report is generated and a baseline pattern is created including a number of regular expressions. A suspicious document of the same type as the monitored document is opened and executed by the same corresponding software application. Behaviors are monitored in the same way and a behavior report is generated. This behavior report is compared to the baseline pattern and a determination is made as to whether a document exploit is present. Known benign documents may also be opened, monitored and their behavior recorded, resulting in creation of a known benign pattern for the corresponding software application.

Abstract: A single virtual machine is implemented upon a computer and an operating system executes within this virtual machine. A sample file suspected of being malware is received and any number of versions of the software application corresponding to the sample file are installed. Each version of the software application is executed within the operating system, each version opening the sample file. Behavior of each version and of the sample file is collected while each version is executing. A score indicating malicious behavior for each version with respect to the sample file is determined and reported. The versions may execute serially in the happening system, each version terminating before the next version begins executing. Or, all versions may execute concurrently within the operating system. Files and registries are hidden to facilitate installation. System information is changed to facilitate execution.

Abstract: Computers are protected against virtual machine exploits. A computer includes an exploit monitor for a virtual machine running in the computer. Loading of a virtual machine program in the virtual machine triggers the exploit monitor to modify the virtual machine program after the virtual machine program is loaded in the virtual machine but before the virtual machine program is executed in the virtual machine. The modification includes adding monitoring code, such as one or more checkpoints, in the virtual machine program. When the monitoring code is reached during execution of the virtual machine program in the virtual machine, the virtual machine program is evaluated to determine whether or not the virtual machine program is a virtual machine exploit.

Abstract: A control circuit for a switched mode power supply includes a transconductance amplifier circuit for receiving a voltage signal related to a current from an input of the power supply and producing a first signal, an analog signal processor coupled to the amplifier circuit for receiving the first signal and a second signal from the input of the power supply and a third signal from an output of the power supply. The analog signal processor is configured to produce a fourth signal as a function of the first, the second, and the third signals. An adder circuit is coupled to the fourth signal and a dimmer control signal, and the adder circuit is configured to output a fifth signal. A comparator circuit is coupled to the adder circuit for providing a control signal to a power transistor that controls current flow in the power supply based on comparison of the fifth signal and a reference signal.

Abstract: A power supply control system for driving light-emitting diode (LED) loads includes a first power switch for coupling to a voltage source, and a plurality of second power switches, each of which is configured for coupling to one of a corresponding plurality of LED loads. Each of the LED loads can include multiple light-emitting diodes (LEDs) connected in series. The power supply control system also includes an integrated circuit controller that includes a voltage controller configured to control the first power switch to provide an output voltage to each of the LED loads, and a current controller configured for coupling to each of the plurality of second power switches to provide a current through each of the LED loads. The integrated circuit controller is provided in a low-voltage integrated circuit chip, and the first power switch and the plurality of second power switches are high-voltage devices external to the low-voltage integrated circuit chip.

Abstract: A control circuit for a switched mode power supply includes a transconductance amplifier circuit for receiving a voltage signal related to a current from an input of the power supply and producing a first signal, an analog signal processor coupled to the amplifier circuit for receiving the first signal and a second signal from the input of the power supply and a third signal from an output of the power supply. The analog signal processor is configured to produce a fourth signal as a function of the first, the second, and the third signals. An adder circuit is coupled to the fourth signal and a dimmer control signal, and the adder circuit is configured to output a fifth signal. A comparator circuit is coupled to the adder circuit for providing a control signal to a power transistor that controls current flow in the power supply based on comparison of the fifth signal and a reference signal.