Abstract: The present disclosure relates to an artificial intelligence (AI) system for simulating functions of a human brain such as cognition and decision-making by using machine learning algorithms such as deep learning, and applications thereof. In particular, the present disclosure provides a method of recognizing an object by using an AI system and its application, including: extracting pieces of first feature information respectively regarding a plurality of images, each image including an object; generating at least one piece of second feature information representing a correlation between the plurality of images by combining together the extracted pieces of first feature information respectively regarding the plurality of images; and recognizing, based on the at least one piece of second feature information, the object included in each of the plurality of images by using a pre-generated learning network model.

Abstract: An apparatus and method for processing an image are disclosed. The method includes preprocessing an image, recognizing an object in the preprocessed image, determining whether to use a recognition result of the object based on a quality of the recognition result, selecting, in response to a determination that the recognition result is not to be used, one of a first process for postprocessing the preprocessed image and a second process for predicting the object based on a set operation mode, and operating according to the selected process.

Abstract: A battery pack for providing different power sources may include: a low voltage battery configured to supply a first voltage; a high voltage battery configured to supply a second voltage, the second voltage being higher than the first voltage; a charging circuit configured to charge the low voltage battery using the high voltage battery; and/or a controller configured to control the charging circuit to charge the low voltage battery when a charge state of the low voltage battery is less than a desired charge state.

Abstract: Provided are an artificial intelligence (AI) system that simulates functions of a human brain such as recognition and judgment by utilizing a machine learning algorithm such as deep learning, etc., and an application of the AI system. Provided are an AI system and a method of recognizing an object according to the application of the AI system, the method including: obtaining a plurality of pieces of sensor data about the object from a plurality of different types of sensors; converting at least some of the plurality of pieces of sensor data into two-dimensional (2D) sensor data; and recognizing the object by using a previously generated learning network model based on 2D image data obtained from an image sensor, which is one of the plurality of sensors, and the 2D sensor data.

Abstract: A method and system for controlling motor driven power steering are provided. The system includes a magnetic field generation detection module that detects generation of a magnetic field upon operating an electric part of a vehicle and a torque offset determination unit that determines whether a temporary torque offset has occurred in a torque to be applied to a motor based on a detection signal of the magnetic field generation detection module. A torque offset correction unit then corrects the torque offset to a normal torque range based on a torque offset correction logic in response to determining that the torque offset has occurred.

Abstract: The present invention relates to a slot die coating apparatus. A slot die coating apparatus according to an embodiment of the present invention includes: a slot die configured to perform a coating process by applying ink to a substrate; an image capturing unit disposed adjacent to the slot die and configured to capture a state of the slot die and a state of ink applied to the substrate during the coating process; and a control unit configured to compare an image captured by the image capturing unit with a reference image and control an operation of the slot die and a transfer of the substrate.

Abstract: A walking assistance apparatus including a first fixing device and a second fixing device to be attached to both legs of a user, respectively, a motor device configured to provide an active assistance force to the first fixing device and the second fixing device using at least one motor, and a passive assistance force transmitter connected to the first fixing device and the second fixing device to provide a passive assistance force to the first fixing device and the second fixing device may be provided.

Abstract: An insole may include an insole body in a shape receivable in a shoe; an electronic element provided in the insole body; a connection line configured to electrically connect to the electronic element and including a contact terminal exposed to the outside of the insole body; and a connector including a detachable member configured to at least partially protrude outward from the insole body and configured to support the contact terminal.

Abstract: An insole may include an insole body in a shape receivable in a shoe; an electronic element provided in the insole body; a connection line configured to electrically connect to the electronic element and including a contact terminal exposed to the outside of the insole body; and a connector including a detachable member configured to at least partially protrude outward from the insole body and configured to support the contact terminal.

Abstract: A method of manufacturing an insole may include providing an electronic element on a support layer; connecting a connector to the support layer; providing the support layer to a lower mold frame; covering the lower mold frame with an upper mold frame; and applying a foam material between the lower mold frame and the upper mold frame.

Abstract: Provided is a server for performing a low power communication and an operation method of the server that may generate a packet including collected data based on a maximum number of data items transmitted based on a maximum transmission unit (MTU) established between a client and the server and an allowable delay time of at least one service, and may transmit the generated packet to the client.

Abstract: A method and device for outputting a torque of a walking assistance device is provided. The method and device may determine a degree of progress in a gait cycle based on data received through wireless communication, calculate a torque corresponding to the determined degree of progress, and output the torque to a driver of the walking assistance device. However, when the data received through wireless communication is not updated data, the method and device may determine reference data based on a reference pattern, and update the data using the determined reference data.

Abstract: An torque pattern adjustment apparatus including a display configured to display a first torque pattern corresponding to a gait cycle, and a generator configured to generate a second torque pattern by adjusting at least a portion of the first torque pattern in response to a reception of an input, and a torque pattern adjustment method using the same may be provided. The first torque pattern may be applied to a joint of a user.

Abstract: An torque pattern adjustment apparatus including a display configured to display a first torque pattern corresponding to a gait cycle, and a generator configured to generate a second torque pattern by adjusting at least a portion of the first torque pattern in response to a reception of an input, and a torque pattern adjustment method using the same may be provided. The first torque pattern may be applied to a joint of a user.

Abstract: A multi-pattern matching algorithm may be provided that includes: a moving step of moving a moving window from the start of a string one byte by one byte; a DF1 checking step of converting the string on a current position of the moving window into an integer value, and of checking whether or not a bit of a related position in a first direct filter DF1 for patterns having lengths larger than 2 bytes is set to 1; a DF moving step of checking one or more direct filters DF when the bit is set to 1 according to the DF1 checking step; a re-moving step of moving the moving window by one byte again when the bit of a related position in the direct filter DF, which has been checked lastly, is 0; and a terminating step of checking whether the moving window is located at the end of the string or not, and of terminating the algorithm when the moving window is positioned at the end of the string.

Abstract: The present disclosure in some embodiments provides a method and an apparatus for accelerated loading of mobile application content which are capable of automatically discover opportunities for application acceleration to remarkably reduce a response time of a mobile application.

Abstract: A battery pack including a case, a battery included in the case and relatively movable with respect to the case, a generator attached to the battery and including a generation axis, and a rotation member connected to the generation axis, wherein the rotation member is configured to act a torque enabling the generation axis to be rotatable when the battery is in motion.

Abstract: A battery pack for providing different power sources may include: a low voltage battery configured to supply a first voltage; a high voltage battery configured to supply a second voltage, the second voltage being higher than the first voltage; a charging circuit configured to charge the low voltage battery using the high voltage battery; and/or a controller configured to control the charging circuit to charge the low voltage battery when a charge state of the low voltage battery is less than a desired charge state.

Abstract: Provided are an imaging device and a video generation method by the imaging device, and more specifically, an imaging device, which enlarges an object selected in a video displayed on a screen and displays same, and a video generation method by the imaging device. According to an example embodiment, an object selected in a video displayed on a screen is enlarged, and the enlarged object is tracked and then displayed on the screen.

Abstract: A motion assistance apparatus may include a first fixing member to be fixed to a portion of a user, a second fixing member to be fixed to another portion of the user, a driving source provided in the first fixing member, a power transmitting member connected between the driving source and the second fixing member, a sensing portion configured to sense a fixing state of the first fixing member or the second fixing member, and a controller configured to control the driving source based on information received from the sensing portion.