Abstract: An image processing method and apparatus based on machine learning are disclosed. The image processing method based on machine learning, according to the present invention, may comprise the steps of: generating a first corrected image by inputting an input image to a first convolution neural network; generating an intermediate image on the basis of the input image; performing machine learning on a first loss function of the first convolution neural network on the basis of the first corrected image and the intermediate image; and performing machine learning on a second loss function of the first convolution neural network on the basis of the first corrected image and a natural image.

Abstract: In a system and method for controlling the electric vehicle, the method for controlling the electric vehicle may be performed by a controller. The method may include obtaining virtual shift information based on drive information of the electric vehicle, detecting a power-on upshift based on the virtual shift information, in response to the detecting of the power-on upshift, determining whether a set condition for push-feel control is satisfied, and based on whether the set condition is satisfied, performing a torque control for a motor of the electric vehicle in either a normal control mode or a push-feel control mode.

Abstract: A method of guiding vehicle shift timing which may provide information related to the shift timing to a driver includes determining, by a controller, a virtual engine speed of an electric vehicle, determining, by the controller, a predicted speed limit arrival time taken for the determined virtual engine speed to reach a predetermined speed limit, controlling, by the controller, operation of a shift indicator configured to guide manual shift timing based on the determined virtual engine speed and predicted speed limit arrival time, and operating, by the controller, the shift indicator to provide shift timing information to the driver.

Abstract: A method for controlling a virtual engine sound of an electric vehicle, may include steps of, which are performed by a controller, collecting a driving state including the vehicle speed of the electric vehicle and the opening amount of an accelerator pedal, determining a virtual gear position based on the vehicle speed of the electric vehicle and the opening amount of the accelerator pedal, obtaining the virtual engine speed of the electric vehicle based on the vehicle speed and the virtual gear position, and outputting a virtual engine sound corresponding to the virtual engine speed.

Abstract: A launch control system and method for an electric vehicle, which are capable of satisfying a driver's demand for a high-performance vehicle by realizing the high performance of the electric vehicle. The system and method maximize acceleration at an initial stage of launching the electric vehicle from a standstill, thereby shortening the time to reach the maximum acceleration when launching the electric vehicle from the standstill.

Abstract: A method of guiding a shiftable gear stage of a vehicle provides information about a shiftable gear stage by a driver in a manual shift mode of a virtual gear shift system of the vehicle. The method includes: determining, by a control unit, whether a virtual gear shift system of an electric vehicle enters a manual shift mode; when the virtual gear shift system enters the manual shift mode; determining a shiftable gear stage by a driver on the basis of a current vehicle speed; and outputting and displaying the determined shiftable gear stage on a display device inside the electric vehicle.

Abstract: A virtual gear shift control apparatus for an electric vehicle is disclosed. The apparatus includes a driving information detector that detect information indicating a vehicle driving state. The apparatus also includes a controller that generates a motor torque command for satisfying a driver's demand torque based on the vehicle driving information including the information detected by the driving information detector. The controller determines whether the vehicle driving state of the electric vehicle corresponds to a predetermined power-off condition, determines, in response to a determination that the vehicle driving state corresponds to the predetermined power-off condition, a coasting torque corresponding to a current virtual gear stage and a current virtual engine speed. The controller also generates a motor torque command using the determined coasting torque as a command value.

Abstract: An apparatus and a method for predicting re-rupture of a tendon based an artificial intelligence (AI) are provided. The apparatus includes a communication module to make communication with an external device, an acquiring module to acquire at least one arthroscopic image including a surgical portion of a patient experiencing a surgery, a storage module to store at least one process based on the AI, and a control module to perform an operation for predicting the re-rupture of the tendon based on the AI, through the at least one process. The control module performs a pre-processing operation for the at least one arthroscopic image, predicts a probability of the re-rupture of the tendon by inputting the at least one arthroscopic image, which is pre-processed, into a pre-trained model based on the AI, and generates prediction information for the patient based on a prediction result.

Abstract: A video quality improvement method may comprise: inputting a structure feature map converted from current target frame by first convolution layer to first multi-task unit and second multi-task unit, which is connected to an output side of first multi-task unit, among the plurality of multi-task units; inputting a main input obtained by adding the structure feature map to a feature space, which is converted by second convolution layer from those obtained by concatenating, in channel dimension, a previous target frame and a correction frame of the previous frame to first multi-task unit; and inputting current target frame to Nth multi-task unit connected to an end of output side of second multi-task unit, wherein Nth multi-task unit outputs a correction frame of current target frame, and machine learning of the video quality improvement model is performed using an objective function calculated through the correction frame of current target frame.

Abstract: Provided is a full-duplex NOMA-based transmit power control device, the device including a state information collector configured to set a role of each of vehicle user equipments (VUEs) constituting a sub-system in a hyper-fractionated zone of a Manhattan mobility model and collect network state information from the sub-system, an actor network configured to determine transmit power of each of the VUEs on the basis of the network state information, a reward calculator configured to calculate a reward value for the network state information and the transmit power, a replay memory configured to store the network state information collected by the network state information collector, the transmit power determined by the actor network, and the reward value calculated by the reward calculator, and a critic network configured to evaluate the transmit power determined by the actor network and give feedback to the actor network.

Abstract: Provided is an apparatus for battery diagnosis and module state change device capable of receiving power from a battery module through a connector connection with a battery module and operating, changing a diagnosis reference value for diagnosing, by a battery management system (BMS), a battery, and changing a setting value of the BMS to change a use of the battery module.

Abstract: A battery management apparatus and a communication method thereof in a battery rack system according to an embodiments of the present invention may wake up in response to power supplied from a battery management apparatus of the battery rack through the first electromagnetic induction coil, receive information about an identifier of the first battery pack from the battery management apparatus of the battery rack through the wireless communication module, allocate an identifier to the first battery pack based on the information about the identifier of the first battery pack, and supply power to a second battery pack located near the first battery pack through the second electromagnetic induction coil, thereby providing a battery management apparatus and a communication method without a communication cable.

Abstract: A computing device is described that receives a notification generated by a notification source. The computing device selects, based at least in part on one or more notification routing rules, one or more computing devices that are to output one or more indications of the notification out of a plurality of computing devices communicably coupled to the computing device. The computing device routes the notification to the one or more computing devices for outputting the one or more indications of the notification by each of the one or more computing devices.

Abstract: A method for generating a super-resolution video by using a multi-camera video may comprise: generating a resolution-improved ultra-wide-angle video frame at an arbitrary time step by inputting an ultra-wide-angle video frame of a first resolution at the arbitrary time step, ultra-wide-angle video frames right before and right after the arbitrary time step, and a wide-angle video frame for reference at the arbitrary time step, to a bidirectional neural network, wherein the generating of the resolution-improved ultra-wide-angle video frame is performed using accumulated information at a past time step based on the arbitrary time step, and accumulated information at a future time step based on the arbitrary time step, and wherein a second resolution, which is a resolution of the generated ultra-wide-angle video frame, is greater than the first resolution.

Abstract: A system and method of accurately evaluating the performance of a vehicle device having a friction component, including a brake disc, a clutch disc, or the like, may be achieved by predicting the accurate friction coefficient of the friction component in consideration of changes in the temperature, rotation speed, and hydraulic pressure of the friction component, and determining the operating torque of the vehicle device or system having the friction component through reflecting the predicted friction coefficient, during the performance evaluation simulation process of the vehicle device including the friction component.

Abstract: A system and method includes upgrading a metamodel for friction coefficient prediction of a brake, in which the metamodel for friction coefficient prediction may be constructed using various derivative parameters relating to the speed, temperature and pressure of a brake disc in addition to basic parameters, such as the speed, temperature and pressure of the brake disc, to greatly improve performance and accuracy in friction coefficient prediction using the metamodel for friction coefficient prediction and to improve accuracy in evaluation of the driving performance of a vehicle through an increase in accuracy of determination of brake torque.

Abstract: A capacitor component includes a body having a first surface and a second surface opposing each other and including a multilayer structure in which a plurality of dielectric layers are stacked and first and second internal electrodes are alternately disposed with respective dielectric layers interposed therebetween and exposed to the first surface and the second surface, respectively, first and second metal layers covering the first surface and the second surface and connected to the first and second internal electrodes, respectively, first and second ceramic layers covering the first and second metal layers, and first and second external electrodes covering the first and second ceramic layers and connected to the first and second metal layers to be electrically connected to the first and second internal electrodes, respectively.

Abstract: An apparatus and a method can accurately estimate and determine a friction coefficient of a brake friction material in real time taking into consideration current driving conditions of a vehicle. The apparatus includes a model generation device configured to generate a friction coefficient meta model to determine the friction coefficient based on information of an operation state of a brake using raw data acquired through a preceding test evaluation process.

Abstract: A capacitor component includes a body having a first surface and a second surface opposing each other and including a multilayer structure in which a plurality of dielectric layers are stacked and first and second internal electrodes are alternately disposed with respective dielectric layers interposed therebetween and exposed to the first surface and the second surface, respectively, first and second metal layers covering the first surface and the second surface and connected to the first and second internal electrodes, respectively, first and second ceramic layers covering the first and second metal layers, and first and second external electrodes covering the first and second ceramic layers and connected to the first and second metal layers to be electrically connected to the first and second internal electrodes, respectively.

Abstract: A braking control method using a predicted friction coefficient of a brake pad in a braking apparatus, which may predict a friction coefficient of a brake pad according to the traveling situation in real time using a wheel velocity, a brake disc temperature, and a braking hydraulic pressure, may include determining a target braking torque determined using the predicted friction coefficient, and then allowing the determined target braking torque to be reflected to a real braking torque through a feedforward control, upon a hydraulic braking control for securing the traveling stability of a vehicle or upon a cooperative control between the regenerative braking and the hydraulic braking, improving the accuracy and response speed of the braking control.