Abstract: Disclosed are a device and a method for allocating physical cell identifier (PCI) of a mobile base station. The device comprises: an acquiring unit configured to acquire location and movement speed of the mobile base station; a determining unit configured to determine a valid time interval for PCI of the mobile base station based on at least one of the location and the movement speed; an information collection unit configured to collect information relating to network configuration within a predetermined range where the mobile base station is located when the valid time interval is expired; and a PCI determining unit configured to determine the PCI of the mobile base station based on the information relating to network configuration within the predetermined range where the mobile base station is located.

Abstract: An example method for controlling an external electronic device of an electronic device, according to various embodiments, includes: receiving data information corresponding to at least one function of the external electronic device from an external electronic device connected to the electronic device; displaying a setting window for setting a user interface for controlling the external electronic device using the data information; selecting a control item corresponding to the at least one function included in the setting window according to user input reception; and setting and displaying the user interface corresponding to the selected control item.

Abstract: Systems and methods for image-based perception. The methods comprise: obtaining, by a computing device, images captured by a plurality of cameras with overlapping fields of view; generating, by the computing device, spatial feature maps indicating locations of features in the images; defining, by the computing device, predicted cuboids at each location of an object in the images based on the spatial feature maps; and assigning, by the computing device, at least two cuboids of said predicted cuboids to a given object when predictions from images captured by separate cameras of the plurality of cameras should be associated with a same detected object.

Abstract: An information processing apparatus includes: a memory; and a processor coupled to the memory and the processor configured to: acquire a plurality of sample videos; identify a position and time at which an attribute appears in each of the plurality of sample videos, the attribute being output by each of one or more pre-trained models to which each of the plurality of sample videos is input; cluster attribute labels based on the position and time of the attribute for each of the plurality of sample videos; and generate a rule by combining attribute labels included in a cluster having a highest frequency of appearance among cluster groups obtained for all of the plurality of sample videos.

Abstract: A vehicle is provided and includes an image acquisition device and an image processing apparatus that receives an original frame for an image obtained by the image acquisition device at a set time interval in the parking state and obtains a key frame having the same pixel with each other by comparing a plurality of original frames received at the set time interval. The image processing apparatus obtains a plurality of delta frames having pixels different from the reference original frame from remaining original frames by comparing each of the reference original frame and the remaining original frames among the plurality of frames and compresses the key frame and the plurality of delta frames, respectively. A storage device stores the key frame and a plurality of delta frames compressed by the image processing apparatus.

Abstract: A luminance determining unit 14 determines a luminance distribution of an exterior circumstantial image in a line-of-sight direction of a driver 300, and a luminance changing unit 15 determines a bright region 301 of this luminance distribution. Further, the luminance changing unit 15 determines a luminance after the change in a peripheral region 302 of this bright region 301. A virtual-image creating unit 16A creates a virtual image based on the determined luminance, and a display processing unit 17 displays this virtual image on a display unit 200. In this manner, since a display system 1A displays the virtual image for use in increasing the luminance in periphery of the bright region 301, the feeling of the brightness for the driver 300 can be moderated, and therefore, the visual recognition can be improved. That is, the display system 1A can output the virtual image depending on the circumstances.

Abstract: In some embodiments, techniques for using machine learning to enable visible light pupilometry are provided. In some embodiments, a smartphone may be used to create a visible light video recording of a pupillary light reflex (PLR). A machine learning model may be used to detect a size of a pupil in the video recording over time, and the size over time may be presented to a clinician. In some embodiments, a system that includes a smartphone and a box that holds the smartphone in a predetermined relationship to a subject's face is provided. In some embodiments, a sequential convolutional neural network architecture is used. In some embodiments, a fully convolutional neural network architecture is used.

Abstract: A system and method for recognizing a person, including: capturing an identifying feature of the person; identifying the person based on the identifying feature to return a person identity; using the person's identity, retrieving information about the person from a person information database; and displaying the retrieved information in an overlay with a facial image of the person to a user. menu items can also be displayed. The identifying feature may be a biometric or a non-biometric feature.

Abstract: According to a first aspect of the present invention, there is provided a computer implemented method, a computer system and a computer program product, including training a set of exploitation models, training a set of exploration models, generating a combined exploitation and exploration heat map, and inputting the combined exploitation and exploration heat map into a convoluted neural network.

Abstract: A wireless device configured to acquire network support information associated with a neighbor cell, wherein the network support information indicates that the neighbor cell supports a Stand-Alone (SA) mode of operation and/or a Non-Stand-Alone (NSA) mode of operation; and transmit to a serving network node a report comprising identification information associated with the neighbour cell and the network support information indicating that the neighbor cell supports a SA mode of operation and/or a NSA mode of operation. A serving network node configured to receive a report transmitted by a wireless device, wherein the report comprises identification information associated with the neighbor cell and network support information indicating that the neighbor cell supports a Stand-Alone (SA) mode of operation and/or a Non-Stand-Alone (NSA) mode of operation; and determine, based on the report, a type of interface to establish between the serving network node and the neighbor network node.

Abstract: A method for handling call originations is provided. The method includes sending origination information from a mobile device to an application server in an enterprise network using Short Message Service (SMS) and determining whether a hotline feature is present in a subscriber profile associated with the mobile device. Data is then routed from the mobile device to a predetermined destination based on the hotline feature.

Abstract: The present invention discloses a system for precise representation of object segmentation with multi-modal input for real-time video applications. The multi-modal segmentation system takes advantage of optical, temporal as well as spatial information to enhance the segmentation for AR and VR or other entrainment purpose with accurate details. The system can segment foreground objects such as human and salient objects within a video frame and allows locating object-of-interest for multiple-purposes.

Abstract: Methods and systems are disclosed for image process biological samples to infer biomarker values. An image of a biological sample can be accessed. The image can be segmented into a set of patches. Edge detection performed on each patch can be used to identify one or more biological features represented by the patch. An indication of the one or more features of each patch may be used to generate one or more image level metrics. A value of a biomarker may be inferred using the one or more image level metrics. The value of the biomarker can then be output.

Abstract: In some embodiments, techniques for using machine learning to enable visible light pupilometry are provided. In some embodiments, a smartphone may be used to create a visible light video recording of a pupillary light reflex (PLR). A machine learning model may be used to detect a size of a pupil in the video recording over time, and the size over time may be presented to a clinician. In some embodiments, a system that includes a smartphone and a box that holds the smartphone in a predetermined relationship to a subject's face is provided. In some embodiments, a sequential convolutional neural network architecture is used. In some embodiments, a fully convolutional neural network architecture is used.

Abstract: Disclosed herein are an intelligent massage chair and a control method thereof. The intelligent chair includes a sensing unit mounted on the intelligent chair, and including at least one sensor, and a controller. The controller performs a control to determine a user's body condition based on the information about the user's body acquired through the sensing unit, and to determine an operation mode based on the determined user's body condition, and to add the information about the user's body, when it is determined that the determined operation mode is not an optimum operation mode for the user. One or more of an intelligent massage chair, an autonomous vehicle, a user terminal and a server of the present disclosure can be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.

Abstract: Systems and methods are described for determining quality attributes of raw material of textile.

Abstract: Computer implemented method for training a software infrastructure based on machine learning techniques and intended for analysis of data obtained from a three-dimensional tomographic inspection of objects of a predetermined type, such as logs, with the aim of determining information about internal characteristics of interest of the self-same objects, wherein, once a training set comprising a plurality of objects of the same predetermined type has been selected, for each object the software infrastructure is supplied with training input data and corresponding training output data, which are processed by the software infrastructure for setting internal processing parameters of the software infrastructure which correlate the training input data with the training output data; where the training input data comprise data obtained from a three-dimensional tomographic inspection of the object, and the training output data comprise information about internal characteristics of interest assessed at internal points of

Abstract: An image processing method, an image processing device, an electronic device, and a non-transitory computer readable storage medium are provided.

Abstract: A system or method can analyze symbols on a set of objects having different sizes. The system can identify a characteristic object dimension corresponding to the set of objects. An image of a first object can be received, and, a first virtual object boundary feature (e.g., edge) in the image can be identified for the first object based on the characteristic object dimension. A first symbol can be identified in the image, and whether the first symbol is positioned on the first object can be determined, based on the first virtual object boundary feature.

Abstract: Method for examining a multiplicity of distributed objects (1) by using an overview image (200) of the area (2) in which the objects (1) are distributed, wherein the overview image (200) is converted (110) into a binary image (210) by virtue of the intensity values (202) of the pixels (201) of the overview image (200) being classified (202a, 202b) as to whether they are on the near or far side of a prescribed threshold (208); the binary image (210) is cleared (120) of structures (219) that are smaller than the objects (1), so that a cleared image (220) is produced; and the cleared image (220) is morphologically closed (130), so that a binary object mask (230) is produced that indicates which locations in the area (2) belong to objects (1) and which locations in the area (2) do not belong to an object.