Abstract: Disclosed is an acquisition method for domain rule knowledge of an industrial process. The method comprises the steps of: establishing a domain rule base, establishing a semantic knowledge base, and combining the domain rule base and the semantic knowledge base so as to realize an augmented update of a domain rule knowledge base; describing the domain knowledge of the industrial process by using weighted first-order logic rules so as to form a training sample set of the first-order logic rules; performing a weight learning by applying probability soft logic and the training sample set of the first-order logic rules so as to realize weight to non-weighted rules; performing rule learning through a machine learning algorithm so as to obtain a first-order logic rule on a change in optimization decision-making semantic when multi-source data semantic information changes.

Abstract: Disclosed is an optimization decision-making method of an industrial process fusing domain knowledge and multi-source data. The method comprises the steps of: acquiring the domain knowledge of the industrial process by using probability soft logic, and building an domain rule knowledge base of the industrial process; fusing multi-source data semantics and multi-source data features to form a new semantic knowledge representation of the industrial process, and constructing a semantic knowledge base of the industrial process; under a posteriori regularization framework, utilizing the domain rule knowledge base of the industrial process and the semantic knowledge base of the industrial process to obtain an optimization decision-making model embedded with the domain rule knowledge and obtain a posteriori distribution model; and migrating knowledge in the optimization decision-making model embedded with the domain rule knowledge into the posteriori distribution model through the knowledge distillation technology.

Abstract: Disclosed is an optimization decision-making method of an industrial process fusing domain knowledge and multi-source data. The method comprises the steps of: acquiring the domain knowledge of the industrial process by using probability soft logic, and building an domain rule knowledge base of the industrial process; fusing multi-source data semantics and multi-source data features to form a new semantic knowledge representation of the industrial process, and constructing a semantic knowledge base of the industrial process; under a posteriori regularization framework, utilizing the domain rule knowledge base of the industrial process and the semantic knowledge base of the industrial process to obtain an optimization decision-making model embedded with the domain rule knowledge and obtain a posteriori distribution model; and migrating knowledge in the optimization decision-making model embedded with the domain rule knowledge into the posteriori distribution model through the knowledge distillation technology.

Abstract: Provided are a method and an apparatus for determining a measurement time, determining a camped cell, for configuring a neighboring cell list, and for determining other parameters. Determining measurement time may include receiving configuration information of an automatic neighbor relation (ANR) that includes a measurement configuration parameter, an ANR measurement duration or an ANR measurement timer. ANR measurement is performed based on the configuration information. When a first condition is satisfied, the ANR measurement is finished. The first condition includes an ANR measurement duration, an ANR measurement timer, or an ANR measurement result acquisition.

Abstract: Techniques are disclosed that enable training a plurality of policy networks, each policy network corresponding to a disparate robotic training task, using a mobile robot in a real world workspace. Various implementations include selecting a training task based on comparing a pose of the mobile robot to at least one parameter of a real world training workspace. For example, the training task can be selected based on the position of a landmark, within the workspace, relative to the pose. For instance, the training task can be selected such that the selected training task moves the mobile robot towards the landmark.

Abstract: Depths of one or more objects in a scene may be measured with enhanced accuracy through the use of a light-field camera and a depth sensor. The light-field camera may capture a light-field image of the scene. The depth sensor may capture depth sensor data of the scene. Light-field depth data may be extracted from the light-field image and used, in combination with the sensor depth data, to generate a depth map indicative of distance between the light-field camera and one or more objects in the scene. The depth sensor may be an active depth sensor that transmits electromagnetic energy toward the scene; the electromagnetic energy may be reflected off of the scene and detected by the active depth sensor. The active depth sensor may have a 360° field of view; accordingly, one or more mirrors may be used to direct the electromagnetic energy between the active depth sensor and the scene.

Abstract: A die casting method includes stirring an aluminum alloy liquid in a stirrer under an airtight vacuum condition. The stirrer includes an electromagnetic inductor and a stirring rod. The aluminum alloy liquid is simultaneously subjected to an electromagnetic stirring in a direction of a magnetic field generated by the electromagnetic inductor and a mechanical stirring under a rotation action of the stirring rod. The aluminum alloy liquid is stirred for 20-80 minutes until the aluminum alloy liquid becomes semisolid to obtain a semisolid aluminum alloy slurry. The method further includes injecting the semisolid aluminum alloy slurry into a filter die to perform die casting molding at an injection speed of 1.5-2.5 m/s, an injection specific pressure of 30-80 MPa, a pressurization pressure of 60-80 MPa, and a temperature of the filter die of 250-400° C., and maintaining pressure for 7-30 seconds to obtain the filtering cavity.

Abstract: The techniques described herein relate to methods and apparatus for a resistive switching device. The resistive switching device includes a first electrode formed in a substrate. The resistive switching device also includes a plurality of layers formed above the first electrode, including a plurality of oxide layers, wherein one or more of the plurality of oxide layers comprise doped oxide layers, and one or more conductive spacers, wherein each pair of oxide layers of the plurality of oxide layers are separated by a conductive spacer of the one or more conductive spacers. The resistive switching device also includes a second electrode formed above the plurality of layers, such that the first electrode, the plurality of layers, and the second electrode are in series.

Abstract: A computer-implemented method is disclosed for training one or more machine-learned models. The method can include inputting a first image frame and a second image frame into a feature disentanglement model and receiving, as an output of the machine-learned feature disentanglement model, a state feature and a perspective feature. The method can include inputting the state feature and the perspective feature into a machine-learned decoder model and receiving, as an output of the machine-learned decoder model, the reconstructed image frame. The method can include comparing the reconstructed image frame with a third image frame corresponding with the location and the perspective orientation. The method can include adjusting one or more parameters of the machine-learned feature disentanglement model based on the comparison of the reconstructed image frame and the third image frame.

Abstract: Training and/or using a machine learning model for locomotion control of a robot, where the model is decoupled. In many implementations, the model is decoupled into an open loop component and a feedback component, where a user can provide a desired reference trajectory (e.g., a symmetric sine curve) as input for the open loop component. In additional and/or alternative implementations, the model is decoupled into a pattern generator component and a feedback component, where a user can provide controlled parameter(s) as input for the pattern generator component to generate pattern generator phase data (e.g., an asymmetric sine curve). The neural network model can be used to generate robot control parameters.

Abstract: The present invention provides a high thermal conductivity aluminum alloy, which comprises the following components in percentage by weight: Al: 80%-90%; Si: 6.5%-8.5%; Fe: 0.2%-0.5%; Zn: 0.8%-3%; V: 0.03%-0.05%; Sr: 0.01%-1%; graphene: 0.02%-0.08%. In the high thermal conductivity aluminum alloy of the present invention, alloying elements including Si, Fe, and Zn are optimized; Sr, V, graphene, among others are added. The amount of each component is controlled so that they coordinate to ALLOW high thermal conductivity, good casting performance and excellent semi-solid die-casting property. Graphene is introduced to the high thermal conductivity aluminum alloy of the present invention to exploit the good thermal conductivity of graphene, allowing the formation of a high thermal conductivity aluminium alloy.

Abstract: The present disclosure is related to systems and methods for orthosis design. The method includes obtaining a three-dimensional (3D) model associated with a subject. The method includes obtaining one or more reference images associated with the subject. The method includes determining, based on the 3D model and the one or more reference images, orthosis design data for the subject. The orthosis design data may be used to determine an orthosis for the subject.

Abstract: The techniques described herein relate to methods and apparatus for a resistive switching device. The resistive switching device includes a first electrode formed in a substrate. The resistive switching device also includes a plurality of layers formed above the first electrode, including a plurality of oxide layers, wherein one or more of the plurality of oxide layers comprise doped oxide layers, and one or more conductive spacers, wherein each pair of oxide layers of the plurality of oxide layers are separated by a conductive spacer of the one or more conductive spacers. The resistive switching device also includes a second electrode formed above the plurality of layers, such that the first electrode, the plurality of layers, and the second electrode are in series.

Abstract: A method of providing LAN service based on a 5G communication network and a terminal device and a server using the same are provided. The method adapted to the terminal device includes: receiving a service ID list broadcasted by the 5G communication network; registering to an isolated 5G core network according to the service ID list so as to obtain an allowed service ID list; transmitting a request message according to the allowed service ID list so as to obtain packet data unit (PDU) session establishment parameter(s) corresponding to a service group in the isolated 5G core network; and communicating with an electronic device in the service group according to the PDU session establishment parameter(s).

Abstract: A light-field video stream may be processed to modify the camera pathway from which the light-field video stream is projected. A plurality of target pixels may be selected, in a plurality of key frames of the light-field video stream. The target pixels may be used to generate a camera pathway indicative of motion of the camera during generation of the light-field video stream. The camera pathway may be adjusted to generate an adjusted camera pathway. This may be done, for example, to carry out image stabilization. The light-field video stream may be projected to a viewpoint defined by the adjusted camera pathway to generate a projected video stream with the image stabilization.

Abstract: A method for accessing a network slice and a user equipment using the same are provided. The method for accessing a network slice includes: transmitting a request message to a 5G communication network; receiving, from the 5G communication network, allowed network slice selection assistance information in response to the request message; obtaining mutually exclusive network slices information according to the allowed network slice selection assistance information; and establishing multiple sessions respectively corresponding to multiple network slices according to the mutually exclusive network slices information.

Abstract: A method for establishing ultra-reliable transmission in a 5G communication network, which is adapted to a UE supporting a first radio access technology and a second radio access technology. The method includes: transmitting a request message to the 5G communication network, wherein the request message includes a multi-data-path indication; receiving setup information from the 5G communication network in response to transmitting the request message to the 5G communication network; and establishing a first data path according to the setup information.

Abstract: The disclosure proposes a hierarchical registration method and related apparatus. In an aspect, the method would include registering to the 5G communication network; establishing a connection with the UE after registering to the 5G communication network; receiving a service request message of the UE for registering to the 5G communication network after establishing the connection with the UE; transmitting a first user plane message which includes the service request message of the UE to the 5G communication network; receiving from the 5G communication network an authentication response message which corresponds to the service request message of the UE and forwarding the authentication response message to the UE; and transmitting to the 5G communication network a second user plane message which includes user data of the UE after the authentication response message indicates that the UE is authorized by the 5G communication network.

Abstract: An implementation method of a virtual print-out system is provided. The method includes setting the number of printing module step; each of the printing modules being in information linking with each of the print-out devices step; inputting rule information step; triggering to print out document logic step; and changing the pointing of the print-out device step, and wherein the virtual print-out system can be simultaneously connected with a plurality of physical print-out devices at different work stations, and the virtual print-out system has plural pieces of rule information preset therein. In this way, the output content of the work station in trouble can be moved quickly to the other work station for printing. Therefore, new store operation or division of labor mode can be achieved by this rapid change of print-out location.