Abstract: An image sensor and a manufacturing method thereof are provided. The image sensor includes a substrate including first and second surfaces opposed to each other, a first pixel group in the substrate including a first to forth unit pixels adjacent to one another in a plan view, a photoelectric conversion area in the first to fourth unit pixels, a first isolation trench in the substrate surrounding the first pixel group, a second isolation trench in the substrate between the first unit pixel and the fourth unit pixel and between the second unit pixel and the third unit pixel, the second isolation trench in contact with the second surface of the substrate, and a first color filter on the second surface of the substrate covering the first pixel group.

Abstract: There is provided a method for neural network-based video encoding. The method includes estimating a motion vector between an input image and a reference image based on a temporal layer of the input image, transforming the motion vector into a latent representation, scaling the latent representation of the motion vector based on the temporal layer of the input image and obtaining a temporal context of the input image based on the scaled latent representation of the motion vector and the reference image.

Abstract: A device and method of estimating state-of-health of a battery is provided. A device of estimating a state-of-health (SOH) of a battery includes: a memory configured to load a program for calculating a state-of-balance (SOB) value by voltage of a plurality of cells constituting the battery and estimating a state-of-health balance value which is a state-of-health value of the battery to which the state-of-balance value by voltage is applied; and a processor configured to execute instructions included in the program loaded by the memory. A device and method of estimating state-of-charge of a battery is provided. A device of estimating state-of-charge (SOC) of a battery includes: a memory configured to load a program for correcting a voltage-to-remaining capacity correlation, in which a battery voltage is matched for each remaining capacity, based on a state-of-balance value by voltage of the battery; and a processor configured to execute instructions included in the program loaded in the memory.

Abstract: Provided is a method for computing a SYNTAX score using a cardio angiogram, which is performed by at least one processor of a computing device, and includes acquiring an angiogram of a cardiovascular system, providing a cardiovascular segment map associated with the angiogram, in response to a user input that selects one of one or more frames included in the acquired angiogram and associates the selected one frame with a cardiovascular segment included in the cardiovascular segment map, associating the selected one frame with the cardiovascular segment, generating, using the selected one frame, an analysis result for a lesion in the associated cardiovascular segment, determining, based on the analysis result, a SYNTAX score for at least a part of the cardiovascular system, and generating an indication of the SYNTAX score.

Abstract: The present invention relates to a method and apparatus for recognizing a sound source. According to the sound source recognition method of the present invention, acoustic signals are detected from four acoustic sensors arranged in a rectangular shape when viewed in a horizontal direction, sound arrival times are measured, six Interactive Time Differences (ITDs) are generated based on differences in sound arrival time between the respective acoustic sensors, and the location of a sound source is estimated based on the six ITDs. In addition, the type of sound source is determined by extracting and classifying features of the sound source by using a sum signal from the four acoustic sensors.

Abstract: Disclosed are a system and a method for notifying an abnormality signal around a vehicle. The system includes: an external sound recognition module mounted on the outside of a vehicle or between the inside and outside of a vehicle, and configured to recognize a sound generated within a radius of a predetermined value or less from a point where the vehicle is located; a noise filtering module configured to filter out noise classified as a noise item; an abnormality signal detection module configured to identify the detailed sound information including the source, magnitude, and type of the detected sound, and to detect an auditory abnormality signal; and a notification module configured to notify each of the type, magnitude, and generation location of the auditory abnormality signal by means of any one or more of a visual signal and an auditory signal.

Abstract: There are provided a sound source visualization device and method. A sound source visualization device according to an embodiment includes: a sound source detection module configured to detect a sound source signal by using a plurality of sound source detection sensors; a preprocessing module configured to filter out the noise and amplify the sound source signal; a calculation module configured to calculate an approximate sound source location by analyzing the preprocessed sound source signal; a search module configured to generate a plurality of pseudo-planes by using the altitude information, to select planes, and to generate three-dimensional sound source location and altitude information by including information, obtained using the selected planes, in the approximate sound source location; and a visualization module configured to output sound source information to a preset system host or to convert this sound source information into a visualization signal and display the visualized signal.

Abstract: Provided is a method for selecting an optimal frame using a distribution of intensities for each frame image of a medical image, which is performed by one or more processors of an information processing system. The method includes receiving a medical image associated with a blood vessel injected with a contrast agent, the medical image including a plurality of frame images, calculating an intensity for each of the plurality of frame images of the medical image, determining, based on a distribution of a plurality of intensities corresponding to the plurality of frame images, a frame section corresponding to a plurality of consecutive frame images of the plurality of frame images, and selecting, based on the determined frame section, a frame image from among the plurality of consecutive frame images.

Abstract: An electronic device includes a processor configured to generate a position movement prediction field indicating prediction of a potential positional change of a branch path by a patient's biological activity for one or more branch paths based on a blood vessel image of a reference frame, correct guidewire information extracted from a blood vessel image of a target frame with respect to a catheter position of the reference frame, and select a branch path to dispose the guidewire information, among one or more branch paths of a blood vessel region based on the position movement prediction field and the corrected guidewire information; and a display configured to visualize the guidewire information on the selected branch path.

Abstract: Disclosed are a system and a method for notifying an abnormality signal around a vehicle. The system includes: an external sound recognition module mounted on the outside of a vehicle or between the inside and outside of a vehicle, and configured to recognize a sound generated within a radius of a predetermined value or less from a point where the vehicle is located; a noise filtering module configured to filter out noise classified as a noise item; an abnormality signal detection module configured to identify the detailed sound information including the source, magnitude, and type of the detected sound, and to detect an auditory abnormality signal; and a notification module configured to notify each of the type, magnitude, and generation location of the auditory abnormality signal by means of any one or more of a visual signal and an auditory signal.

Abstract: An electronic device includes a processor configured to generate a position movement prediction field indicating prediction of a potential positional change of a branch path by a patient's biological activity for one or more branch paths based on a blood vessel image of a reference frame, correct guidewire information extracted from a blood vessel image of a target frame with respect to a catheter position of the reference frame, and select a branch path to dispose the guidewire information, among one or more branch paths of a blood vessel region based on the position movement prediction field and the corrected guidewire information; and a display configured to visualize the guidewire information on the selected branch path.

Abstract: There are provided a sound source visualization device and method. A sound source visualization device according to an embodiment includes: a sound source detection module configured to detect a sound source signal by using a plurality of sound source detection sensors; a preprocessing module configured to filter out the noise and amplify the sound source signal; a calculation module configured to calculate an approximate sound source location by analyzing the preprocessed sound source signal; a search module configured to generate a plurality of pseudo-planes by using the altitude information, to select planes, and to generate three-dimensional sound source location and altitude information by including information, obtained using the selected planes, in the approximate sound source location; and a visualization module configured to output sound source information to a preset system host or to convert this sound source information into a visualization signal and display the visualized signal.

Abstract: The present invention relates to a method and apparatus for recognizing a sound source. According to the sound source recognition method of the present invention, acoustic signals are detected from four acoustic sensors arranged in a rectangular shape when viewed in a horizontal direction, sound arrival times are measured, six Interactive Time Differences (ITDs) are generated based on differences in sound arrival time between the respective acoustic sensors, and the location of a sound source is estimated based on the six ITDs. In addition, the type of sound source is determined by extracting and classifying features of the sound source by using a sum signal from the four acoustic sensors.

Abstract: The present invention relates to a bi-directional broadcasting system for a small space. More particularly, multiple users enjoy the optimum surround sound and pursue the best convenience simultaneously by wirelessly connected an external receiver, multiple headphones, and external speakers which can be installed and composed variously, while watching a video media which was received through a television transmitting and receiving antenna or external signal input devices by a host television, that was related to a bi-directional broadcasting system for a small space.

Abstract: The present invention relates to a composition for promoting memory or learning ability and to a composition for preventing and treating cognitive impairment, which comprise one, two or more plant extracts selected from the group consisting of Artemisia apiaceae extract, Illicium verum extract and Lepidium apefalum extract. The present invention has the effect of inhibiting neural cell damage, especially, neural cells of the basal part of the cerebrum by inhibiting acetylcholinesterase activity and through antioxidative activity (for example, inhibiting the generation of oxidative reactive species) and affinity for an NMDA receptor. The compositions of the present invention may have the effect of not only promoting memory or learning ability by protecting neural cells and preventing damage to neural cells but also of preventing and treating diseases caused by cognitive impairment.

Abstract: A wind power generator. The wind power generator includes a generator main body formed of fiberglass reinforced plastics (FRP). Built-in fans having blades are connected to four built-in fan motors to generate high pressure air to be ejected to the exterior so that an inductor including magnets is primarily and relatively rotated with respect to a rotor including a rotating shaft to induce electromotive force. In addition, high air (reproduced energy) discharged to the exterior from the built-in fans is acted on the propeller installed behind the rotor including the shaft to rotate the rotor in a reverse direction of the rotational direction of the generator main body, thereby maximizing electromotive force of energy.

Abstract: The present invention relates to a bi-directional broadcasting system for a small space. More particularly, multiple users enjoy the optimum surround sound and pursue the best convenience simultaneously by wirelessly connected an external receiver, multiple headphones, and external speakers which can be installed and composed variously, while watching a video media which was received through a television transmitting and receiving antenna or external signal input devices by a host television, that was related to a bi-directional broadcasting system for a small space.

Abstract: Dehydrated flavorings are produced by using the blood of livestock including hydrolysis of the blood to convert protein to amino acid form, passing the hydrolyzed suspension through a granular type active charcoal column to remove poor color and odor properties from the hydrolyzed suspension, removing salt from the suspension by filtering, causing the suspension to taste meat-like by allowing it to react with sugars, and then powdering the suspension to produce a powdered blood product.