Abstract: The present disclosure relates to a virus detection method that detects whether viruses are arranged in multiple layers and the density of viruses using a color change of a virus detector. A virus detection method according to an embodiment of the present disclosure includes: taking an image of a virus detector reacting with a target analysis object; and determining whether viruses are arranged in multiple layers and density of the viruses in the target analysis object in accordance with a saturation value of the image.

Abstract: The present invention relates to apparatus for a nanoparticle thermal therapy based on an open magnetic particle image. The apparatus for a nanoparticle thermal therapy based on an open magnetic particle image according to an exemplary embodiment of the present invention may include: a selection coil generating a field free point (FFP) for a nanoparticle in a first direction; a focus coil generating a magnetic field and moving the FFP in a second direction; and a heating coil heating the nanoparticle in a target area based on the FFP in the second direction.

Abstract: The present disclosure relates to a method of aligning images included in a focal stack and estimates depth information of an object in the images by extracting features of the aligned images, using a neural network model. A focal stack alignment method according to an embodiment of the present disclosure includes: calculating a relative Field of View (FoV) of a focal stack photographed by a photographing device using metadata of the photographing device; primarily aligning the focal stack on the basis of the relative FoV; determining a flow field of the focal stack using radial motion, horizontal motion, and vertical motion features of each of primarily aligned images; and secondarily aligning the focal stack using the flow field.

Abstract: The present disclosure relates to a method for sampling a random vector corresponding to an intention of a pedestrian non-stochastically or applying a social statistical element that the majority of pedestrians move in groups to training, in training a neural network model for pedestrian trajectory prediction.

Abstract: The present disclosure relates to a method of inferring an epipolar plane image and extrapolating a view of a target image using the epipolar plane image. A view extrapolation method using an epipolar plane image according to an embodiment of the present disclosure includes: creating an Epipolar Plane Image (EPI) using a target image and a depth map corresponding to the target image; creating a super-resolution EPI and a disparity of the EPI on the basis of the EPI; creating an EPI mask by warping the super-resolution EPI in accordance with the disparity; and creating a restored EPI by applying the EPI mask to the warped super-resolution EPI, and creating an extrapolated image for the target image using the restored EPI.

Abstract: Provided is a mixed reality-based experience simulator including an imaging part including first and second cameras installed on an experience object to capture images of different viewpoints from the experience object, a display part worn by a participant and configured to display a mixed reality image of the experience object to the participant, and an image processing unit configured to provide the mixed reality image to the display part and configured to generate the mixed reality image such that images captured by the first and second cameras are included in the mixed reality image. The mixed reality-based experience simulator according to the present invention generates a mixed reality image on the basis of images captured by a plurality of cameras installed on an experience object and provides the generated mixed reality image to a participant so that a more realistic experience is provided.

Abstract: The present disclosure relates to a surface inspection method using a mold surface inspection device, and more specifically, to a surface inspection method using a mold surface inspection device including a setting part in which an inspection object is set, a light source part configured to irradiate the inspection object with irradiated light so that a reflective highlight is generated on a surface of the inspection object, an imaging part configured to image the surface of the inspection object so that a highlight region where a reflective highlight is generated is included, and an image processing part configured to process an image imaged in the imaging part to provide the image to a worker so that the worker determines whether defects are generated on the surface of the inspection object on the basis of the image.

Abstract: Disclosed is a genome reconstruction method using whole genome data. According to the present invention, the genome reconstruction method reduces detection errors by converting a nucleotide sequence having a structural variation into a graph form, and then reconstructing the graph so that the structural variation and the copy number variation have consistent values. Thereafter, the genome arrangement form was restored by constructing a haplotype graph using heterozygous single nucleotide polymorphism information and then finding an Eulerian path with a minimum entropy value.

Abstract: Disclosed are a one-pot biosensor and an immunoassay method using the same. The one-pot biosensor includes a photocatalyst substrate deposited with metal nanoparticles; and a reaction pad which is disposed on an upper surface of the photocatalyst substrate and includes a first binding material-fluorescent material complex specifically binding to a molecule to be detected, and the immunoassay method using the same. The one-pot biosensor may detect a target by once solution injection and has a size enough to be portable. Accordingly, since the one-pot biosensor can detect the target by only once solution injection without a washing step, because of a sensor platform capable of being easily used by an individual other than a diagnostic expert, it is predicted to be positioned as a means capable of confirming the health condition of the individual without seeing the doctor, such as a pregnancy diagnostic kit which has been currently commercialized.

Abstract: Disclosed is a method for performing image convolution by considering a hierarchical relationship of hyperbolic feature vectors in a hyperbolic space. According to an embodiment of the present disclosure, an image convolution method in a hyperbolic space includes steps of embedding an image feature vector on a Euclidean space into a hyperbolic feature vector on a hyperbolic space, allocating a hierarchical weight on the hyperbolic feature vector based on a hierarchical property of the hyperbolic feature vector, and convolutioning the hyperbolic feature vector by applying the hierarchical weight.

Abstract: Disclosed are a temperature measurement method using the fluorescence characteristic of an optical material having temperature dependence and a temperature sensor technology using the same. According to the present disclosure, the temperature measurement technology using the fluorescence signal intensity ratio has a self-compensation function to reduce optical signal noise caused by fluctuations in light source output and optical waveguide loss, and uses two fluorescence signals with a strong fluorescence signal intensity to solve the existing disadvantage of generating a lot of noise due to a low fluorescence signal.

Abstract: The present disclosure relates to a herringbone-type fluid guiding unit and an apparatus for concentrating fluid using same. The herring-bone type fluid guiding unit includes: a front member formed on a flow path and formed so that the width between the left side and the right side widens from a front end part toward the back, with respect to the flow direction of a fluid; and a rear member extending from the front member toward the back, wherein the rear member is provided with a recessed part that is recessed to a specific depth from the rear edge toward the front or with a protruding part that protrudes toward the back.

Abstract: The present disclosure relates to a method and apparatus for split liability assessment of a car accident video using deep learning. The method for split liability assessment of a car accident video using deep learning according to an embodiment of the present disclosure may include: (a) obtaining car accident video data; and (b) outputting accidental split liability information by applying the obtained car accident video data to an accidental split liability determination model.

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.

Abstract: Disclosed is an array antenna which is capable of shifting a phase of light. According to one aspect of the present exemplary embodiment, an optical phase shifting array antenna includes: a receiving unit configured to distribute input light to a plurality of antenna element waveguides; a phase shifting unit configured to shift a phase of light propagated to each antenna element waveguide by applying heat to each antenna element waveguide; an output unit including a plurality of antenna elements, and configured to output the light, which is propagated to each antenna element waveguide after a phase is varied in the phase shifting unit, to each antenna element; and a base part configured to seat the receiving unit, the phase shifting unit, and the output unit.

Abstract: The present invention relates to a multi-microorganism detection system, and more particularly, to a multi-microorganism detection system using a dielectrophoresis force. Provided is a rapid and accurate multi-microorganism detection system. Microorganisms are concentrated at a high throughput using DEP after synthesizing the microorganisms and fluorescent magnetic particles, and when a complex in which the fluorescent magnetic particles are bound to the microorganisms passes through a detection unit by moving only the microorganisms to the detection unit after separating the magnetic particles from the complex (i.e., the microorganisms to which the magnetic particles are bound) using a DEP force, a fluorescence signal of a specific wavelength band is generated according to the type of the fluorescent magnetic particle and the concentration of the microorganisms according to the type of microorganism is measured by measuring and analyzing the fluorescence signal.

Abstract: Provided are a method and device for detecting malicious activity over an encrypted secure channel. The method includes (a) extracting at least one record from a plurality of packets each including a header and a payload and (b) determining whether the plurality of packets correspond to a malicious flow using feature information based on the at least one record.

Abstract: Provided is an optical phase array antenna including a coupling part configured to receive light from a laser generator, an optical distributor configured to distribute the light transmitted from the coupling part to a plurality of antenna element waveguides, a phase modulator configured to modulate a phase of the light transmitted through the plurality of antenna element waveguides, and a light outputter configured to output the light modulated by the phase modulator, the light outputter including the plurality of antenna element waveguides extending in one direction, wherein each of the plurality of antenna element waveguides includes a double grating antenna part in which a downward-curved portion curved downward from an upper surface and an upward-curved portion curved upward from a lower surface are repeatedly formed in the one direction.

Abstract: Provided are a method and electronic device for identifying a size of a measurement target object. The method includes imaging a reference object, which is a reference for identifying the size of the measurement target object, to acquire a reference object image, imaging the measurement target object to acquire a target object image, fusing the acquired reference object image and the acquired target object image, and inputting the fused reference object image and target object image to a first neural network model to acquire size information of the measurement target object from the first neural network model.

Abstract: The present disclosure relates to a microorganism detection apparatus using a dielectrophoresis (DEP) force.