Abstract: A battery module includes: a battery cell assembly having a plurality of battery cells; a top plate configured to cover an upper side of the battery cell assembly; a bottom plate configured to cover a lower side of the battery cell assembly; a sensing assembly disposed to cover a front side and a rear side of the battery cell assembly; a pair of side plates disposed at side surfaces, respectively, of the battery cell assembly; and a pair of compression pads disposed between the pair of side plates and the battery cell assembly, respectively.

Abstract: Provided are a face de-identification method and system and a graphical user interface (GUI) provision method for face de-identification employing facial image generation. According to the face de-identification method and system and the GUI provision method, a facial area including eyes, a nose, and a mouth in a face of a person detected in an input image is replaced with a de-identified facial area generated through deep learning to maintain the face in a natural shape while protecting the person's portrait right. Accordingly, qualitative degradation of content is prevented, and viewers' concentration on the image is increased.

Abstract: The present invention relates to an apparatus and method for identifying music in a content, The present invention includes extracting and storing a fingerprint of an original audio in an audio fingerprint DB; extracting a first fingerprint of a first audio in the content; and searching for a fingerprint corresponding to the fingerprint of the first audio in the audio fingerprint DB, wherein the first audio is audio data in a music section detected from the content.

Abstract: Disclosed are a people counting device and a method for counting the number of people capable of executing built-in artificial intelligence (AI) algorithms and/or machine learning algorithms to count the number of people and communicating with user terminals and servers in a 5G communication environment. The method according to an embodiment of the present disclosure can include collecting, by a first collector, probe request packets for a predetermined time from a user terminal transmitting the probe request packets to confirm the existence of an access point, measuring, by a measurer, the density of the probe request packets and generating density data, and estimating, by a estimator, the number of people using a people counting learning model pre-trained to count people according to the density of the probe request packets based on the density data generated by collecting the probe request packets from the user terminal.

Abstract: Disclosed are a learning data generation method and apparatus needed to learn animation characters on the basis of deep learning. The learning data generation method needed to learn animation characters on the basis of deep learning may include collecting various images from an external source using wired/wireless communication, acquiring character images from the collected images using a character detection module, clustering the acquired character images, selecting learning data from among the clustered images, and inputting the selected learning data to an artificial neural network for character recognition.

Abstract: The present invention relates to a double-sided adhesive tape used for applications including the attachment of front glass for mobile devices. A core layer of the double-sided adhesive tape is prepared by adding an acrylic elastomer free of carbon-carbon double bonds while being highly miscible with an acrylic resin to an acrylic monomer(s) and performing curing, and thus can improve the impact resistance of the final double-sided adhesive tape. Also, the core layer may take a form of foam due to the introduced filler such as glass bubbles or organic microspheres, and thus can further contribute to improving the impact resistance of the final double-sided adhesive tape.

Abstract: A method for receiving a mono sound source audio signal including phase information as an input, and separating into a plurality of signals may comprise performing initial convolution and down-sampling on the inputted mono sound source audio signal; generating an encoded signal by encoding the inputted signal using at least one first dense block and at least one down-transition layer; generating a decoded signal by decoding the encoded signal using at least one second dense block and at least one up-transition layer; and performing final convolution and resize on the decoded signal.

Abstract: Disclosed are a learning data generation method and apparatus needed to learn animation characters on the basis of deep learning. The learning data generation method needed to learn animation characters on the basis of deep learning may include collecting various images from an external source using wired/wireless communication, acquiring character images from the collected images using a character detection module, clustering the acquired character images, selecting learning data from among the clustered images, and inputting the selected learning data to an artificial neural network for character recognition.

Abstract: An apparatus for recognizing a person includes a content separator configured to receive contents and separate the contents into video content and audio content; a video processor configured to recognize a face from an image in the video content received from the content separator and obtain information on a face recognition section by analyzing the video content; an audio processor configured to recognize a speaker from voice data in the audio content received from the content separator and obtain information on a speaker recognition section by analyzing the audio content; and a person recognized section information provider configured to provide information on a section of the contents in which a person appears based on the information on the face recognition section and the information on the speaker recognition section.

Abstract: A method of arranging components in an integrated circuit includes providing two or more circuit cells of a first type and providing two or more circuit cells of a second type. The circuit cells of the first type are configured to operate in conjunction with the circuit cells of the second type. The method further includes arranging the circuit cells of the first and second types in an alternating pattern such that each circuit cell of the first type is adjacent to at least one circuit cell of the second type. The alternating pattern may be an array of rows and columns and may include a repeating pattern of one first type cell and one second type cell in each of the columns. The alternating pattern may include a repeating pattern of one cell of the first type and two cells of the second type in each of the columns.

Abstract: A method of driving a pixel array includes providing a ramp signal to one or more columns of the pixel array. For each cycle of the ramp signal, the method further includes providing a first row driving signal to at least a first row of the pixel array and a second row driving signal to a second row of the pixel array. A pixel array driver may include a ramp signal generator configured to produce a ramp signal, a first amplifier configured to receive the ramp signal and produce a first amplified ramp signal, and a second amplifier configured to receive the ramp signal and produce a second amplified ramp signal. The first amplified ramp signal may be electrically connected to a first set of pixels of a pixel array, and the second amplified ramp signal may be electrically connected to a second set of pixels of the pixel array.

Abstract: A signature actor determination method for video identification includes setting a list of actors who appear in each of a plurality of videos, generating a plurality of subsets including the actors, and determining that an actor included in a single final set indicating a first video among the plurality of subsets is a signature actor of the first video. Accordingly, video identification is possible by using just a little information.

Abstract: Disclosed are a people counting device and a method for counting the number of people capable of executing built-in artificial intelligence (AI) algorithms and/or machine learning algorithms to count the number of people and communicating with user terminals and servers in a 5G communication environment. The method according to an embodiment of the present disclosure can include collecting, by a first collector, probe request packets for a predetermined time from a user terminal transmitting the probe request packets to confirm the existence of an access point, measuring, by a measurer, the density of the probe request packets and generating density data, and estimating, by a estimator, the number of people using a people counting learning model pre-trained to count people according to the density of the probe request packets based on the density data generated by collecting the probe request packets from the user terminal.

Abstract: A method for determining a video-related emotion and a method of generating data for learning video-related emotions include separating an input video into a video stream and an audio stream; analyzing the audio stream to detect a music section; extracting at least one video clip matching the music section; extracting emotion information from the music section; tagging the video clip with the extracted emotion information and outputting the video clip; learning video-related emotions by using the at least one video clip tagged with the emotion information to generate a video-related emotion classification model; and determining an emotion related to an input query video by using the video-related emotion classification model to provide the emotion.

Abstract: Provided are a synthetic wood and a preparation method thereof. More particularly, provided are a synthetic wood having excellent flexural property and impact strength by including a polyester resin having excellent compatibility with wood flour, and a preparation method thereof.

Abstract: The present invention relates to a double-sided adhesive tape used for applications including the attachment of front glass for mobile devices. A core layer of the double-sided adhesive tape is prepared by adding an acrylic elastomer free of carbon-carbon double bonds while being highly miscible with an acrylic resin to an acrylic monomer(s) and performing curing, and thus can improve the impact resistance of the final double-sided adhesive tape. Also, the core layer may take a form of foam due to the introduced filler such as glass bubbles or organic microspheres, and thus can further contribute to improving the impact resistance of the final double-sided adhesive tape.

Abstract: A method for determining a video-related emotion and a method of generating data for learning video-related emotions include separating an input video into a video stream and an audio stream; analyzing the audio stream to detect a music section; extracting at least one video clip matching the music section; extracting emotion information from the music section; tagging the video clip with the extracted emotion information and outputting the video clip; learning video-related emotions by using the at least one video clip tagged with the emotion information to generate a video-related emotion classification model; and determining an emotion related to an input query video by using the video-related emotion classification model to provide the emotion.

Abstract: Disclosed is a direct synthesis method of nanostructured catalyst particles on surfaces of various supports.

Abstract: A method of driving a pixel array includes providing a ramp signal to one or more columns of the pixel array. For each cycle of the ramp signal, the method further includes providing a first row driving signal to at least a first row of the pixel array and a second row driving signal to a second row of the pixel array. A pixel array driver may include a ramp signal generator configured to produce a ramp signal, a first amplifier configured to receive the ramp signal and produce a first amplified ramp signal, and a second amplifier configured to receive the ramp signal and produce a second amplified ramp signal. The first amplified ramp signal may be electrically connected to a first set of pixels of a pixel array, and the second amplified ramp signal may be electrically connected to a second set of pixels of the pixel array.

Abstract: An apparatus and method of analyzing and identifying a song with high performance identify a subject song in which global and local characteristics of a feature vector are reflected, and quickly identify a cover song in which changes in tempo and key are reflected by using a feature vector extracting part, a feature vector condensing part, and a feature vector comparing part, and by condensing a feature vector sequence into global and local characteristics in which a melody characteristic is reflected.