Abstract: An embodiment of the present invention provides an active dichroic optical device including a substrate; a first phase tunable material layer applied on the substrate; a metal nanostructure deposited on the first phase tunable material layer; and a second phase tunable material layer applied on the metal nanostructure, in which the first and second phase tunable material layers modulate the refractive index of light applied to the active dichroic optical device as external energy is applied and the metal nanostructure reflects, transmits, and scatters the resonance wavelength of the applied light.

Abstract: A method for training a student network including at least one or more of a transformer neural network by using knowledge distillation in a teacher network including at least one or more of the transformer neural network is disclosed. The method includes: pre-training the teacher network using a training data and fine tuning the trained teacher network; copying a weight parameter of a bottom layer of the teacher network to the student network; and performing the knowledge distillation to the student network through the fine-tuned teacher network. The performing the knowledge distillation includes: extracting a feature structure from the result value of a layer of the fine-tuned teacher network; extracting a feature structure from the result value of a layer of the student network; and adjusting the feature structure of the extracted student network based on the feature structure of the extracted teacher network.

Abstract: The present invention relates to disorder spectrum diagnosis technology, and more particularly, to a device and method for predicting autism spectrum disorder in infants and young children on the basis of deep learning by using auto-encoder feature representation, wherein autism spectrum disorder can be identified from the speech of infants and young children by using auto-encoder feature representation.

Abstract: The present invention relates to representation learning in an artificial neural network, and more specifically, to a device and method for learning representations using a spherization layer, which places all hidden vectors on a hyperspherical surface, and learns representations using only angles on the basis of hyperplanes fixed to the origin. According to an embodiment of the present invention, as all hidden vectors are represented on a hypersphere in a space of one dimension higher, and representation learning is performed thereon using only angles through the hyperplanes fixed to the origin, the problem of performance degradation of artificial neural networks can be solved by ensuring that all information learned by the artificial neural network from input data is contained in the angle without loss.

Abstract: The present invention relates to a PUF-based IoT device authentication technique, and more specifically, to a PUF-based IoT device using channel state information, and an authentication method thereof. According to an embodiment of the present invention, security of an authentication key may be strengthened by simultaneously utilizing a PUF-based authentication method and an RF characteristic-based authentication method.

Abstract: The present invention relates to a method for creating a neural network model which can imitate retouching styles of a plurality of experts, and creating a black-and-white photo which gives aesthetics by inputting a color photo into the neural network model.

Abstract: The present disclosure relates to a speech enhancement apparatus, and specifically, to a method and apparatus for a target exaggeration for deep learning-based speech enhancement. According to an embodiment of the present disclosure, the apparatus for a target exaggeration for deep learning-based speech enhancement can preserve a speech signal from a noisy speech signal and can perform speech enhancement for removing a noise signal.

Abstract: The present invention provides: a composite hydrogel including gelatin and reduced graphene oxide: a preparation method therefor; and a conduit or film manufactured using the same, wherein the composite hydrogel of the present invention overcomes the low conductivity and brittleness of a conventional functional hydrogel to maintain, through excellent elasticity and excellent ductility, high electrical conductivity and mechanical properties even if repeatedly compressed and bent, thereby being variously usable as a platform material for a conductive hydrogel, and thus can be effectively used, in a field requiring a conductive hydrogel, as an in vivo tissue engineering scaffold, a drug delivery system, a flexible body-implantable electrode, and an electronic device, which move a lot.

Abstract: The present invention which is a method for generating a scene structure using a neural network model applied to a baseline network performing an image processing task by a plug-and-play scheme by using the scene structure includes: generating a plurality of eigenvectors for an image according to an affinity matrix of the image; and generating the scene structure by convolutioning the plurality of eigenvectors, and outputting the scene structure to the baseline network.

Abstract: The present disclosure relates to an apparatus and method for measuring the velocity of a surface wave using a laser ultrasound imaging technique. A method of measuring the velocity of a surface wave according to an embodiment of the present disclosure includes: emitting a laser pulse to a target material; obtaining wavefront image of a surface wave, which propagates on a surface of the target material due to the laser pulse, by emitting a probe beam to the target material; and determining a velocity of the surface wave based on variation of the wavefront image according to a time delay between the laser pulse and the probe beam.

Abstract: Provided is an encoding apparatus including a memory configured to store instructions and a processor electrically connected to the memory and configured to execute the instructions, wherein the processor may be configured to perform a plurality of operations, when the instructions are executed by the processor, wherein the plurality of operations may include obtaining an input audio signal, generating an embedded audio signal by embedding signal components of a second frequency band of the input audio signal in a first frequency band of the input audio signal, generating additional information associated with the first frequency band and the second frequency band, generating an encoded audio signal by encoding the embedded audio signal, and formatting the encoded audio signal and the additional information into a bitstream.

Abstract: The present disclosure relates to a magnetic particle imaging device having a field of view (FOV) wide enough to be applicable to the human body. A magnetic particle imaging device according to some embodiments includes at least: an FFP generation unit generating a field free point (FFP) in a FOV; first to third operation coil units moving the FFP in first to third directions which are vertical to each other, respectively; an excitation coil unit generating a magnetic field in the FOV, and exciting a magnetic particle in the FOV; a reception coil unit receiving a magnetic signal generated from the magnetic particle; and a processor dividing the FOV into a plurality of partial FOVs, controlling the first to third operation coil units so that the FFP moves in each partial FOV, and generating an image for the FOV based on the magnetic signal for each partial FOV.

Abstract: The present invention relates to a data augmentation apparatus for action recognition through self-supervised learning based on objects, including: an image input unit for inputting image information; an information extraction unit for extracting a feature vector with object information from motion data of the inputted image information; and a motion information synthesis unit for synthesizing motion data taking a different action and the feature vector with the object information to generate new motion data.

Abstract: The present invention relates to a blood diagnostic device, which includes one or more blood input parts into which blood is injected, a deterministic lateral displacement separation part which communicates with the blood input part to form a blood flow path along which the blood flows and separates white blood cells from remaining blood components, a first microchannel which communicates with the deterministic lateral displacement separation part so that the white blood cells separated through the deterministic lateral displacement separation part flow therein, one or more second microchannels which communicate with the deterministic lateral displacement separation part so that the remaining blood components separated through the deterministic lateral displacement separation part flow therein, a first discharge part which communicates with the first microchannel so that the white blood cells flowing in the first microchannel are discharged therethrough, and a second discharge part which communicates with the

Abstract: The present invention relates to a resistance-based on-chip temperature sensor which may autonomously operate in a chip. A resistance-based on-chip temperature sensor according to an exemplary embodiment of the present invention includes: a first RC oscillator having an in-chip first resistor as a component; a second RC oscillator having an in-chip second resistor as the component; and a control unit determining the temperature of the chip according to what difference between the numbers of clocks output from the first and second RC oscillators, respectively is for the same time.

Abstract: The present disclosure relates to a secure transmitting and receiving method that crates a dynamic key on the basis of the features of real-time data, thereby performing authentication operation. A secure transmitting method for real time data according to an embodiment of the present disclosure includes: collecting an n-th datum; compressing the n-th datum; creating and storing an n-th dynamic key in a memory on the basis of a feature extracted in the compressing; creating an n-th security key using an n-m-th dynamic key stored in the memory and transmitting the n-th security key to a server; and transmitting the compressed n-th datum to the server when receiving an authentication success signal from the server.

Abstract: The present disclosure relates to an apparatus for evaluating thermal conductance of an interface on the basis of how much the phases of acoustic phonons, which are produced in a semiconductor, change on a semiconductor interface. The apparatus for evaluating thermal conductance of a semiconductor interface according to an embodiment of the present disclosure includes: a spectrometer exciting acoustic phonons in a semiconductor by irradiating a laser beam to the semiconductor; and a processor evaluating thermal conductance of an interface of the semiconductor in accordance with a phase difference of a ascending acoustic phonon propagating toward the interface and reflecting from the interface and a descending acoustic phonon propagating in an opposite direction to the interface.

Abstract: Provided is an encoding apparatus including a memory configured to store instructions and a processor electrically connected to the memory and configured to execute the instructions, wherein the processor may be configured to perform a plurality of operations, when the instructions are executed by the processor, wherein the plurality of operations may include obtaining an input audio signal, generating an embedded audio signal by embedding signal components of a second frequency band of the input audio signal in a first frequency band of the input audio signal, generating additional information associated with the first frequency band and the second frequency band, generating an encoded audio signal by encoding the embedded audio signal, and formatting the encoded audio signal and the additional information into a bitstream.

Abstract: The present disclosure relates to a force and complex vibration rendering system using a force feedback device and a wideband resonance actuator, and a method for providing force and complex vibration using the system.

Abstract: The present disclosure relates to an automatic metal sorting system using laser induced breakdown spectroscopy. The system may include: a conveyer configured to move waste metals at a constant speed; a shape measurer configured to measure a position and a shape of at least one waste metal on the conveyer; a laser induced breakdown spectroscopic device configured to determine the kind of the waste metal by emitting a laser to the waste metal and receiving and analyzing a plasma spectrum signal generated by the emitted laser; and a discharger configured to separate and discharge the waste metal in accordance with the determined kind of the waste metal.