Abstract: An electroencephalogram signal classification method includes: obtaining a first electroencephalogram signal; processing the first electroencephalogram signal using at least two electroencephalogram signal classification models to obtain respective motor imagery probability distributions from the at least two electroencephalogram signal classification models; and determining a motor imagery type of the first electroencephalogram signal based on the motor imagery probability distributions. A plurality of electroencephalogram signal classification models is respectively trained using an augmented data set obtained through augmentation. During prediction, by combining the plurality of electroencephalogram signal classification models, the accuracy of classifying an electroencephalogram signal to determine a motor imagery type may be improved, when using a model trained with a relatively small number of training samples.

Abstract: An electroencephalogram (EEG) signal classification method and apparatus, a device, a storage medium, and a program product are provided, and relate to the field of signal processing technologies. The method includes: obtaining a first EEG signal; obtaining time-frequency feature maps of at least two electrode signals in the first EEG signal; performing feature extraction based on the time-frequency feature maps of the at least two electrode signals to obtain a first extracted feature map; performing weighting processing based on an attention mechanism on the first extracted feature map to obtain an attention feature map; and obtaining a motor imagery type of the first EEG signal based on the attention feature map.

Abstract: The present invention discloses a pyrimidine-fused ring compound having an inhibitory effect on KRAS gene mutation, or a pharmaceutically acceptable salt, a stereoisomer, or a solvate thereof. Further, the present invention also discloses a pharmaceutical composition comprising the compound, and use thereof in the preparation of drugs against cancers.

Abstract: Provided are a method for the parallel processing of data, a device, and a storage medium. The method includes: identifying, from multiple first computing nodes, at least three first computing nodes which have a logical relationship are identified and defining the at least three first computing nodes which have the logical relationship as a first parallel node group, where the first parallel node group includes a first preceding node and at least two first subsequent nodes; acquiring a first input data model of the first preceding node and generating a first input tensor of the first preceding node; computing a first output tensor of the first preceding node according to the first input data model and the first input tensor; and acquiring a second input data model of the at least two first subsequent nodes and using the first output tensor as a second input tensor.

Abstract: A bolter miner includes a rack, a cutting device and a bolt support device. The cutting device is configured for a cutting operation and is arranged on the rack to swing up and down. The bolt support device includes a lifting assembly, a work platform, a first drilling frame assembly and a stabilization assembly. The lifting assembly is arranged between the rack and the work platform and is configured to lift the work platform. The first drilling frame assembly and the stabilization assembly are arranged on the work platform. The first drilling frame assembly has a bolt support position and an avoidance position. The work platform can extend and retract to switch the bolt support position and the avoidance position of the first drilling frame assembly. The stabilization assembly can be supported between the cutting device and a tunnel roof, so as to enhance the stability of the first drilling frame assembly during a bolt support operation.

Abstract: Embodiments described herein relate to an apparatus, that includes a substrate, where the substrate includes a semiconductor material. In an embodiment, a first layer is on the substrate, and the first layer includes a first dielectric material. In an embodiment, a device is embedded within the first layer. In an embodiment, the apparatus further includes a second layer that is embedded within the first layer. In an embodiment, the second layer includes a second dielectric material, and a sidewall of the second layer is exposed.

Abstract: An image processing method can reduce costs related to manual labeling, improve training efficiency, and increase a quantity of training samples, thereby improving the accuracy of an image classification model. First images and second images are processed using an image classification model to obtain predicted classification results. The first images include a classification label and the second images include a pseudo classification label. A first loss value indicating accuracy is acquired based on the predicted classification results, the corresponding classification labels, and the corresponding pseudo classification labels. A second loss value indicating accuracy is acquired based on the predicted classification results and the corresponding pseudo classification labels. A model parameter of the image classification model is updated based on the first loss value and the second loss value. Classification processing and acquisition is performed until a target image classification model is obtained.

Abstract: A tunnel tunneling system includes a bolter miner, a bolter-integrated transportation machine, a transfer machine, a self-moving tail and a belt conveyor. The bolter miner includes a rack, a cutting device, a drilling device and a control device. The cutting device is arranged on the rack and is swingable in an up-down direction, and has a lowest swing angle and a highest swing angle. The drilling device is arranged on the rack, and includes a drilling rig and a sensor. The drilling rig is configured to drill a tunnel floor and/or a tunnel roof, and the sensor is configured to monitor a set parameter of the drilling rig and generate a monitoring data signal when the drilling rig is drilling. The control device is configured to receive and analyze the monitoring data signal.

Abstract: A method, computer system, and computer program product are provided for dynamic power saving for wireless access points. It is determined that a wireless client has not requested to connect to a first access point for a first threshold duration of time. Power is disabled to one or more front-end modules of a plurality of front-end modules associated with the first access point except for one designated front-end module that remains powered. Monitoring is performed for an incoming request to connect to the first access point. Power is restored to the one or more front-end modules of the plurality of front-end modules.

Abstract: Methods and apparatuses for image processing are provided. A first image belonging to a first image domain is acquired and input to an image processing model to be trained to obtain a second image belonging to a second image domain. A first correlation degree between an image feature of the first image and an image feature of the second image to obtain a target feature correlation degree is calculated. A second correlation degree between feature value distribution of the image feature of the first image and feature value distribution of the image feature of the second image is calculated to obtain a distribution correlation degree. Model parameters of an image processing model are adjusted to a direction in which the target feature correlation degree is increased and a direction in which the distribution correlation degree is increased to obtain a trained image processing.

Abstract: Porous compositions and methods of making and using same. The compositions may be one or more layer(s) of mesoporous inorganic materials. The mesoporous inorganic material(s) may be a plurality of inorganic nanocages, which may be microporous. A composition may include homostacks of layers of the same inorganic mesoporous materials. A composition may include heterostacks of layers of inorganic mesoporous materials, where at least two of the layers are different. The compositions may be surface functionalized. The compositions may be formed in a reaction mixture including one or more precursor(s), one or more surfactant(s), water, and one or more organic solvent(s). The compositions may be formed at the liquid-liquid interface between the water and the one or more organic solvent(s). A composition may be used as a catalyst, in a catalytic method, as a separation medium, in a separation method, in nanomedicine applications, or the like.

Abstract: This application provides a scraper conveyor straightening method based on a rolling time-domain control concept. The scraper conveyor straightening method includes an execution space, a deduction space, and a prediction space.

Abstract: Described is a versatile surface modification approach to, for example, modularly and orthogonally functionalize nanoparticles (NPs) such as, for example, PEGylated nanoparticles, ith various types of different functional ligands (functional groups) on the NP surface. It enables the synthesis of, for example, penta-functional PEGylated nanoparticles integrating a variety of properties into a single NP, e.g., fluorescence detection, specific cell targeting, radioisotope chelating/labeling, ratiometric pH sensing, and drug delivery, while the overall NP size remains, for example, below 10 nm.

Abstract: The present invention discloses a packaging structure for a kiloampere-level single-switch SiC power semiconductor module, primarily including components such as SiC chips, substrates, baseplate, power and signal terminals, integrated gate/Kelvin source resistors, and housing. The packaging structure proposed in this invention improves the electrothermal performance of multi-chip SiC power modules, reduces the size of the power module, and breaks through the limitations on the number of parallel-connected SiC chips. It significantly enhances the current capacity and power density of existing SiC power semiconductor modules, making it particularly suitable for 1.7 kV˜6.5 kV single-switch power semiconductor modules in high-power applications such as rail transit traction and flexible DC power transmission. Furthermore, the packaging structure proposed in this invention is compatible with conventional fabrication processes such as soldering, wire bonding, and potting encapsulation.

Abstract: Disclosed is preparation of dual cross-linked zein-carboxymethyl chitosan nanoparticles for improving the thermal stability of polyphenol. After covalently cross-linked zein, tannic acid is used to prepare tannic acid cross-linked zein-carboxymethyl chitosan nanoparticles loaded with quercetin, Ca2+ is then added to increase a degree of crosslinking between the tannic acid and the carboxymethyl chitosan, as well as between molecules of the carboxymethyl chitosan in the zein nanoparticles to make the structure tighter, such that structural stability of the nanoparticles can be maintained during the thermal processing after the nanoparticles are formed, the quercetin encapsulated inside is protected well, and a retention rate of quercetin during the thermal processing is improved.

Abstract: A data classification and recognition method includes: obtaining a first data set and a second data set, the second data set including second data, samples in the second data being labeled; performing training using first data in an unsupervised training mode and using the second data in a supervised training mode to obtain a first classification model; obtaining a second classification model; performing distillation training on a model parameter of the second classification model to obtain a data classification model; and performing class prediction on target data by using the data classification model.

Abstract: A tunneling and anchoring machine (100) and a tunneling system, the tunneling and anchoring machine (100) comprising a rack (1), a cutting device (2), a drilling device (3) and a control device; the cutting device (2) has a lowest swing angle (B) and a highest swing angle (?); the drilling device (3) comprises a drilling machine (31) and a sensor, the sensor is electrically connected to the drilling machine (31), the drilling machine (31) is suitable for drilling a roadway floor and/or a roadway roof, and the sensor is suitable for, when the drilling machine (31) is drilling, monitoring a set parameter of the drilling machine (31) and generating a monitoring data signal; the sensor is electrically connected to the control device, and the control device is suitable for receiving and analyzing the monitoring data signal; when the drilling machine (31) drills a first thickness of the roadway floor, if the monitoring data signal is greater than a first threshold, the control device is suitable for adjusting the l

Abstract: An object recognition method includes extracting, by a first transformer network, spatial features of a plurality of medical images respectively, the plurality of medical images being images of a same object at different times, and fusing the extracted plurality of spatial features, to obtain a first fusion spatial feature of the object. The method further includes extracting, by a second transformer network, a spatial-temporal feature of the object based on the first fusion spatial feature. The spatial-temporal feature indicates a change in the spatial features of the plurality of medical images at the different times. The method further includes recognizing a state of the object based on the spatial-temporal feature, to obtain a recognition result of the object.

Abstract: An image segmentation method includes: encoding an original image containing a target object based on a prior knowledge vector, to obtain a target feature map, the prior knowledge vector comprising a plurality of prior knowledge weights each representing accuracy of a corresponding rater labeling a region of an object in an image; decoding the target feature map, to obtain a first segmented image of the original image, the first segmented image indicating a target region in which the target object is located in the original image; performing image reconstruction on the first segmented image based on the prior knowledge vector, to obtain labeled segmented images, wherein one labeled segmented image corresponds to one prior knowledge weight and indicates a target region labeled by a corresponding rater; and processing the target feature map based on the labeled segmented images, to obtain a second segmented image of the original image.

Abstract: This application provides a gesture information processing method and apparatus, an electronic device, and a storage medium. The method includes: acquiring an electromyography signal sample generated by an electromyography signal collection target object in connection with performing multiple gestures; dividing the electromyography signal sample through a sliding window having a fixed window value and a fixed stride into different electromyography signals of the target object; and applying the different electromyography signals to a first neural network model to determine gesture information matching the multiple gestures performed by the target object.