Abstract: A speech separation method is provided, and relates to the field of speech. The method includes: obtaining, in a speaking process of a user, audio information including a user speech and video information including a user face; coding the audio information to obtain a mixed acoustic feature; extracting a visual semantic feature of the user from the video information; inputting the mixed acoustic feature and the visual semantic feature into a preset visual speech separation network to obtain an acoustic feature of the user; and decoding the acoustic feature of the user to obtain a speech signal of the user. An electronic device, a chip, and a computer-readable storage medium are provided.

Abstract: The present disclosure includes: transforming a time-domain voltage signal collected by an MPI system device to a frequency domain; calculating a square root of a square sum of a real part and an imaginary part at each frequency point of a frequency domain signal; arranging acquired amplitudes in a descending order, and acquiring a screening threshold by an amplitude ratio method; screening an amplitude through the screening threshold and constructing frequency domain signal data; acquiring a row vector of a system matrix corresponding to each frequency point of the data, so as to construct an update system matrix; and solving, based on the frequency domain signal array and the update system matrix, an inverse problem in a form of a least square based on an L2 constraint to obtain a three-dimensional magnetic particle concentration distribution result, so as to achieve a fast reconstruction of the MPI system.

Abstract: The field of high-speed data acquisition and network data processing, and particularly relates to an Ethernet data stream recording method, an Ethernet data stream recording system, and an Ethernet data stream recording device for a high-speed data acquisition system. It is intended to solve problems such as a low utilization rate of CPU, poor system compatibility, difficulty in packaging and deployment and low reliability of system transmission of the traditional high-speed data acquisition system.

Abstract: An image processing method, a related device, and a computer storage medium are provided. The method includes: obtaining a feature intensity image corresponding to a training image, where an intensity value of a pixel in the feature intensity image is used to indicate importance of the pixel for recognizing the training image, and resolution of the training image is the same as resolution of the feature intensity image; and occluding, based on the feature intensity image, a to-be-occluded region in the training image by using a preset window, to obtain a new image, where the to-be-occluded region includes a to-be-occluded pixel, and the new image is used to update an image recognition model. According to the embodiments of the present application, a prior-art problem that a model has low accuracy and relatively poor generalization performance because of limited training data can be resolved.

Abstract: The present disclosure belongs to a field of biomedical imaging technology, and in particularly to a non-uniform excitation field-based method and system for performing a magnetic nanoparticle imaging. The present disclosure includes: separating the non-uniform excitation field into independent space and current time functions by a spatialtemporal separation method; calculating a normalized signal peak through the current time function; constructing a reconstruction mathematical model based on the normalized signal peak and an imaging subunit volume; and quantitatively reconstructing a spatial distribution of a nanoparticle by combining the normalized signal peak, a non-uniform spatial function of the excitation field and the reconstruction mathematical model, so as to achieve the magnetic nanoparticle imaging of a to-be-reconstructed object.

Abstract: A method for pedestrian attribute identification and positioning is provided. The method includes: performing feature extraction on a to-be-detected image at a plurality of different abstraction degrees, to obtain a plurality of first feature maps of a pedestrian attribute; performing convolution on the plurality of first feature maps, to obtain a plurality of second feature maps; mapping each second feature map to a plurality of areas (bins) that overlap each other, and performing max pooling on each bin, to obtain a plurality of high-dimensional feature vectors, where the plurality of bins that overlap each other evenly cover each second feature map; processing the plurality of high-dimensional feature vectors into a low-dimensional vector, to obtain an identification result of the pedestrian attribute; and further obtaining a positioning result of the pedestrian attribute based on the plurality of second feature maps and the plurality of high-dimensional feature vectors.

Abstract: Provided are a device, a system and a method for acquiring a force information based on a bionic structure, including: a force information acquisition layer and a magnetic field signal acquisition chip; wherein a permanent magnet is embedded in the force information acquisition layer; wherein the force information acquisition layer has an elastic structure configured to generate a deformation corresponding to a first force information of a force after being subjected to the force, so that the permanent magnet moves with the deformation to generate a magnetic field signal corresponding to the force information; wherein the magnetic field signal acquisition chip is arranged in parallel with the force information acquisition layer, and is configured to acquire the magnetic field signal and convert the magnetic field signal into an electrical signal.

Abstract: A method and an apparatus for generating a face rotation image are provided. The method includes: performing pose encoding on an obtained face image based on two or more landmarks in the face image, to obtain pose encoded images; obtaining a plurality of training images each including a face from a training data set, wherein presented rotation angles of the faces included in the plurality of training images are the same; performing pose encoding on a target face image based on two or more landmarks in the target face image in the foregoing similar manner, to obtain pose encoded images, wherein the target face image is obtained based on the plurality of training images; generating a to-be-input signal based on the face image and the foregoing two types of pose encoded images; and inputting the to-be-input signal into an face rotation image generative model to obtain a face rotation image.

Abstract: A physiological signal prediction method includes: collecting a video file, the video file containing long-term videos, and contents of the video file containing data for a face of a single person and true physiological signal data; segmenting a single long-term video into multiple short-term video clips; extracting, by using each frame of image in each of the short-term video clips, features of interested regions for identifying physiological signals so as to form features of interested regions of a single frame; splicing, for each of the short-term video clips, features of interested regions of all fixed frames corresponding to the short-term video clip into features of interested regions of a multi-frame video, and converting the features of the interested regions of the multi-frame video into a spatio-temporal graph; inputting the spatio-temporal graph into a deep learning model for training, and using the trained deep learning model to predict physiological signal parameters.

Abstract: A multi-label object detection method based on an object detection network includes: selecting an image of an object to be detected as an input image; based on a trained object detection network, obtaining a class of the object to be detected, coordinates of a center of the object to be detected, and a length and a width of a detection rectangular box according to the input image; and outputting the class of the object to be detected, the coordinates of the center of the object to be detected, and the length and the width of the detection rectangular box. The method of the present invention can perform real-time and accurate object detection on different classes of objects with improved detection speed and accuracy, and can solve the problem of object overlapping and occlusion during the object detection.

Abstract: The present invention relates to a rotating self-drilling device for extraterrestrial objects.

Abstract: A reconfigurable joint track compound mobile robot has a main vehicle body, yaw joints and an auxiliary track module. The main vehicle body has a main track, and a clutch brake and a first wheel joint arranged in a main track driving wheel. A second wheel joint is arranged in a main track driven wheel. The main vehicle body is provided with main track driving mechanisms and a wheel joint driving mechanism. The main track driving wheel is driven to rotate by the main track driving mechanisms, which are connected with the clutch brake. The second wheel joint is driven to rotate by the wheel joint driving mechanism. Each wheel joint is correspondingly connected with the yaw joints, which are rotatably connected with the auxiliary track module. A yaw driving mechanism that drives the auxiliary track module to swing is arranged in each yaw joint.

Abstract: The application presents a multi-posture lower limb rehabilitation robot, which includes a robot base and a training bed. The training bed comprises two sets of leg mechanisms, a seat, a seat width adjustment mechanism, a mechanism for adjusting the gravity center of human body, a back cushion, a weight support system and a mechanism for adjusting the back cushion angle. The robot base comprises a mechanism for adjusting the bed angle. The mechanisms for adjusting the angles of bed and back cushion can be used together to provide paralysis patients with multiple training modes of lying, sitting, and standing postures. Each leg mechanism comprises hip, knee, and ankle joints, which are driven by electric motors; angle and force sensors are installed on each joint, and can be used to identify patients' motion intention to provide patients with active and assistant training.

Abstract: A method for parsing a question in a knowledge base includes: receiving a question entered by a user; performing phrase detection on the question to determine candidate phrases; mapping the candidate phrases to resource items in the knowledge base; further determining values of observed predicates and possible question parse spaces; performing uncertain inference on each proposition set in the possible question parse spaces according to the values of the observed predicates and values of hidden predicates, and calculating confidence; acquiring a combination of true propositions in a proposition set whose confidence satisfies a preset condition; generating a formal query statement according to the combination of true propositions.

Abstract: A method for microscopic image acquisition based on a sequential slice. The method includes; acquiring a sample of the sequential slice and a navigation image thereof; identifying and labeling the sample of the sequential slice in the navigation image by utilizing methods of image processing and machine learning; placing the sample of the sequential slice in a microscope, establishing a coordinate transformation matrix for a navigation image-microscope actual sampling space coordinate, and navigating and locating a random pixel point in the navigation image to a center of the microscope's visual field; locating the sample of the sequential slice under a low resolution visual field, binding a sample acquisition parameter; based on the binding of the sample acquisition parameter, recording a relationship of relative of locations between a center point of a high resolution acquisition region and a center point after being matched with a sample template.

Abstract: A method for concurrent reading of mixed radix DFT/IDFT data, a method for concurrent calculation of mixed radix DFT/IDFT method, an apparatus for concurrent reading of mixed radix DFT/IDFT data, and an apparatus for concurrent calculation of mixed radix DFT/IDFT. The method for concurrent reading includes: configuring dual circulation parameters according to the number of points corresponding to the number of series to be computed and the number of points corresponding to the number of series accomplished; then, determining the value size between the maximum number of concurrently read data and the product of the number of points corresponding to the number of series accomplished; and based on the result of determination, calculating the dual circulation parameters corresponding thereto according to the result of determination, and concurrently reading data based on the calculated dual circulation parameters.

Abstract: The present invention relates to a Torus-Quorum based channel rendezvous method for directional antennas. A pair of directional antennas facing any side initially points to the other party mutually in one Torus-Quorum system cycle through a rotation closure attribute of a Torus-Quorum system; and a receiver and a sender switch to a same available channel according to frequency hopping sequences to realize channel rendezvous. In the Torus-Quorum based channel rendezvous method for directional antennas proposed in the present invention, the directional antennas are rotated based on the Torus-Quorum, and elements are ensured to coincide with each other within limited time through the rotation closure attribute of the Torus-Quorum system, i.e., directions are opposite, thereby effectively shortening channel rendezvous time of the directional antennas.

Abstract: The present application discloses a method for assessing aesthetic quality of a natural image based on multi-task deep learning. Said method includes: step 1: automatically learning aesthetic and semantic characteristics of the natural image based on multi-task deep learning; step 2: performing aesthetic categorization and semantic recognition to the results of automatic learning based on multi-task deep learning, thereby realizing assessment of aesthetic quality of the natural image. The present application uses semantic information to assist learning of expressions of aesthetic characteristics so as to assess aesthetic quality more effectively, besides, the present application designs various multi-task deep learning network structures so as to effectively use the aesthetic and semantic information for obtaining highly accurate image aesthetic categorization.

Abstract: A method for automatic segmentation of brain tumors merging full convolution neural networks with conditional random fields. The present application intends to address the issue that presently the technology of deep learning is unable to ensure the continuity of the segmentation result in shape and in space when segmenting brain tumors. For this purpose, the present application includes the following steps: step 1, processing a magnetic resonance image comprising brain tumors by utilizing a method for non-uniformity bias correction and brightness regularization, to generate a second magnetic resonance image; step 2, performing brain tumor segmentation for said second magnetic resonance image by utilizing a neural network merging a full convolutional neural network with a conditional random field, and outputting a result of brain tumor segmentation. The present method may execute brain tumor segmentation end-to-end and slice by slice during testing, which has relatively high computation efficiency.

Abstract: The present invention discloses an upper limb rehabilitation robot system comprising a computer (8) and a rehabilitation robot (7), wherein the computer (8) is used for performing information interaction (11) with the rehabilitation robot (7), recording training information, sending control command to the rehabilitation robot (7), showing the virtual training environment, providing rehabilitation training visual feedback (14), and showing the control interface and rehabilitation training information; wherein the rehabilitation robot (7), acting as a system actuator, is connected to the computer (8) for receiving the control command from the computer (8) to complete the motion control and terminal force output, and sending sensor data to the computer (8) at the same time.