Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: Proposed are a wafer heating apparatus and a wafer processing apparatus using the same. More particularly, proposed are a wafer heating apparatus having an improved structure to enable efficient cooling of a terminal block, and a wafer processing apparatus using the same. A wafer heating apparatus for heating a wafer according to one embodiment includes a heater disposed below the wafer and configured to serve as a heat source, a cooling plate disposed below the heater and configured to provide cool air, and a terminal block configured to supply power to the heater and having a lower end portion in contact with the cooling plate.

Abstract: An electronic device may have a display with touch sensors. One or more shielding layers may be interposed between the display and the touch sensors. The shielding layers may include shielding structures such as a conductive mesh structure and/or a transparent conductive film. The shielding structures may be actively driven or passively biased. In the active driving scheme, one or more inverting circuits may receive a noise signal from a cathode layer in the display and/or from the shielding structures, invert the received noise signal, and drive the inverted noise signal back onto the shielding structures to prevent any noise from the display from negatively impacting the performance of the touch sensors. In the passive biasing scheme, the shielding structures may be biased to a power supply voltage.

Abstract: There is provided a self-directed visual intelligence system, The self-directed visual intelligence system according to an embodiment prepares data necessary for training a visual intelligence model when a change in a visual context of a real world is recognized, configures a visual intelligence model and configures training data of the visual intelligence model, based on the changed visual context of the real world, trains the configured visual intelligence model with the training data, and evaluates performance of the trained visual intelligence model. Accordingly, the visual intelligence model is corrected/improved in a self-directed way according to a change in a visual context of a real world, and is grown/advanced by itself, so that performance of the visual intelligence model is maintained in a best state even in response to any change in the context of the real world.

Abstract: The disclosed technology relates to a method and device for generating a fat suppression magnetic resonance image. The method includes: inputting, by an imaging device, a magnetic resonance image to an encoder of a neural network to extract features of the magnetic resonance image; and generating, by a generator of the neural network, a T2-weighted fat suppression image based on the features, in which the neural network is trained according to a result of discriminating, by a discriminator of the neural network, a loss due to a generation of a T2-weighted fat suppression image and as a result of reconstructing, by a decoder, the magnetic resonance image input to the encoder using a Bloch equation before the magnetic resonance image is input.

Abstract: Provided is a connection system for connecting a metaverse of a virtual world and a contact center of a real world, the connection system including a contact center provider configured to provide a virtual contact center in at least one metaverse platform and to collect a consultation request through the provided virtual contact center; a validity determiner configured to, in response to the collected consultation request, collect customer information on a user that requests a consultation and determine a validity of the user based on the collected customer information; and a consultation processing unit configured to provide the customer information on the user of which the validity is determined to a server of a real contact center and to connect a consultation channel between a user in the at least one metaverse platform and the real contact center.

Abstract: An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.

Abstract: Provided is a system for providing an insurance service based on artificial intelligence (AI), the system including a first terminal configured to provide an insurance consulting service and to filter potential customer information; a server configured to interact with the first terminal, to deliver the filtered potential customer information to the first terminal, and to deliver feedback on a quality of consultation for the insurance consulting service to the first terminal; and a plurality of second terminals configured to interact with the first terminal and the server, to deliver a request for the insurance consulting service to the server, and to receive customized insurance information about each of users from the server.

Abstract: There are provided AI model learning method and system based on self-learning for focusing on specific areas. According to an embodiment, a network learning system includes: a detection module configured to detect a specific area from unlabeled images, and to generate unlabeled area images; a configuration module configured to configure self-learning data by using the generated area images; and a learning module to cause a backbone network to perform self-learning by using the configured self-learning data. Accordingly, an AI model may be trained based on self-learning for focusing on a desired specific area according to a desired purpose, and high-performance analysis specified for various purposes and characteristics of various types of specific areas is possible.

Abstract: There are provided a method and a system for image segmentation utilizing a GAN architecture. A method for training an image segmentation network according to an embodiment includes: inputting an image to a first network which is trained to output a region segmentation result regarding an input image, and generating a region segmentation result; and inputting the region segmentation result generated at the generation step and a ground truth (GT) to a second network, and acquiring a discrimination result, the second network being trained to discriminate inputted region segmentation results as a result generated by the first network and a GT, respectively; and training the first network and the second network by using the discrimination result. Accordingly, region segmentation performance of a semantic segmentation network regarding various images can be enhanced, and a very small image region can be exactly segmented.

Abstract: The disclosed technology relates to a method and device for generating a fat suppression magnetic resonance image. The method includes: inputting, by an imaging device, a magnetic resonance image to an encoder of a neural network to extract features of the magnetic resonance image; and generating, by a generator of the neural network, a T2-weighted fat suppression image based on the features, in which the neural network is trained according to a result of discriminating, by a discriminator of the neural network, a loss due to a generation of a T2-weighted fat suppression image and as a result of reconstructing, by a decoder, the magnetic resonance image input to the encoder using a Bloch equation before the magnetic resonance image is input.

Abstract: An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.

Abstract: A medical radiofrequency coil may comprise: a base substrate; and a radio coil unit having a first coil element which has a rectangular shape and is formed along an edge of the inner peripheral surface of the base substrate, and a second coil element which is formed at the inner side of the first coil element and has a shape of paired paddles connected to each other. Therefore, the present inventive concept provides a radiofrequency coil, which can minimize an image distortion due to a beam-hardening artifact effect, and a medical imaging device including the same.

Abstract: A method and a system for processing an FMCW radar signal by using a lightweight deep learning network are provided. The data processing method using an AI model includes: converting n-dimensional data into a plurality of pieces of 2D data; inputting the plurality of pieces of 2D data into the AI model through different channels; and processing the plurality of pieces of 2D data inputted to the AI model by analyzing. Accordingly, an amount of computation and a memory usage can be reduced and characteristics of an object can be learned and inferred by the lightweight deep learning network.

Abstract: An audio segmentation method based on an attention mechanism is provided. The audio segmentation method according to an embodiment obtains a mapping relationship between an “inputted text” and an “audio spectrum feature vector for generating an audio signal”, the audio spectrum feature vector being automatically synthesized by using the inputted text, and segments an inputted audio signal by using the mapping relationship. Accordingly, high quality can be guaranteed and the effort, time, and cost can be noticeably reduced through audio segmentation utilizing the attention mechanism.

Abstract: An audio synthesis method adapted to video characteristics is provided. The audio synthesis method according to an embodiment includes: extracting characteristics x from a video in a time-series way; extracting characteristics p of phonemes from a text; and generating an audio spectrum characteristic St used to generate an audio to be synthesized with a video at a time t, based on correlations between an audio spectrum characteristic St-1, which is used to generate an audio to be synthesized with a video at a time t?1, and the characteristics x. Accordingly, an audio can be synthesized according to video characteristics, and speech according to a video can be easily added.

Abstract: Deep learning-based automatic gesture recognition method and system are provided. The training method according to an embodiment includes: extracting a plurality of contours from an input image; generating training data by normalizing pieces of contour information forming each of the contours; and training an AI model for gesture recognition by using the generated training data. Accordingly, robust and high-performance automatic gesture recognition can be performed, without being influenced by an environment and a condition even while using less training data.

Abstract: The present disclosure relates to a method and system for controlling loudness of an audio based on signal analysis and deep learning. The method includes analyzing an audio characteristic in a frame level based on signal analysis, analyzing the audio characteristic in the frame level based on learning, and controlling loudness of the audio in the frame level, by combining the analysis results. Accordingly, reliability of audio characteristic analysis can be enhanced and audio loudness can be optimally controlled.

Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

Abstract: The present invention relates to a pharmaceutical composition containing a poorly soluble drug, hyaluronic acid, and a fatty acid, and to a method for preparing the same. The pharmaceutical composition of the present application has excellent stability even for long-term storage and allows a sustained release of the drug, thereby preventing an overdose of the drug and improving the therapeutic efficiency at an effected area.