Abstract: A method and apparatus for estimating execution time of a neural network are provided, the method of estimating execution time of a neural network in a multi-core accelerator, the method including generating trace information including operation timing information for each core of the multi-core accelerator, and calculating the execution time of the neural network reflecting communication overhead between cores of the multi-core accelerator and memory access time for each core of the cores, based on the trace information.

Abstract: There is provided a multi-scale object detection device. The device includes an image frame acquisition unit for acquiring a plurality of consecutive image frames, a critical region extractor for extracting at least one second critical region from a current image frame based on at least one first critical region extracted from a previous image frame among the consecutive image frames, a multi-scale object detector whose operation involves a first object detection process for the current image frame and a second object detection process for the at least one second critical region, and an object detection integration unit for integrating the results of the first and second object detection processes.

Abstract: Mite proteins according to an aspect may be used in diagnosing allergic diseases. Results of diagnosing allergic diseases by using the proteins have high reliability and validity. Further, the proteins may be used in a composition for preventing or treating allergic diseases.

Abstract: The present invention relates to a bio-electrode for current measurement including silicon carbide (SiC) doped at least partially with nitrogen (N). The bio-electrode for current measurement according to an embodiment of the present invention is a bio-electrode for a current measurement which is contact with an object to be analyzed, which generates a current signal by an electrochemical reaction, and includes silicon carbide (SiC) doped at least partially with nitrogen (N). The electrode may be used in a high-sensitive bio-quantification kit, a high-sensitive bio-quantification device, and an immunoassay device.

Abstract: Disclosed is a multi-core cable fault classification system which includes a reference signal measurement unit configured to measure a core-specific reference signal generated by applying an electromagnetic signal to a multi-core cable having at least two cores, a reflected-signal measurement unit configured to measure a core-specific reflected signal generated by reflecting the generated core-specific reference signal at a point of the multi-core cable, a data processing unit configured to extract, from time-series data for the measured core-specific reflected signal, core-specific partial time-series data based on whether baseline data of the multi-core cable is present, configured to transform the core-specific partial time-series data into a time-frequency distribution, and configured to extract faulty-core determination data, and a faulty core classification unit configured to classify a fault core from the multi-core cable by inputting the extracted faulty-core determination data to a neural network.

Abstract: There is provided a method of preparing a synchronized piezoelectric and luminescence material. The method includes mixing a solution (a) including light-emitting particles or precursors thereof and a solution (b) including ligands having a piezoelectric property in a polar solvent; and optionally, mixing a solution (c) including ligands having a piezoelectric property in an antisolvent together with the solution (a) and the solution (b), if necessary.

Abstract: Provided are an electrochemical aptamer biosensor that detects a target material, which is a phthalate-based material, a method of manufacturing the same, and a method of analyzing the target material using the same, and the electrochemical aptamer biosensor may be simply manufactured and may conveniently and quickly measure the target material, and may have a wide measurable concentration range of the target material and a low detection limit and thus may accurately and precisely measure a concentration of the target material in a sample for analysis.

Abstract: The present invention relates to an electrochemical biosensor for detecting a target RNA, and the present invention can detect a very small amount of target RNA with high sensitivity without a nucleic acid amplification reaction through a CRISPR/Cas13a trans-cleavage reaction, thereby having an advantage of being useful for point-of-care diagnostic testing of fast-spreading RNA-based infectious diseases such as COVID-19.

Abstract: Provided are a method for providing information about the diagnosis of a gallbladder polyp and a device for providing information about the diagnosis of a gallbladder polyp using same. The method for providing information about the diagnosis of a gallbladder polyp being implemented by a processor includes the steps of receiving an ultrasound medical image including a gallbladder part of a subject, determining the pathogenesis of a gallbladder polyp in the subject using a first assessment model configured to determine the pathogenesis of a gallbladder polyp on the basis of the ultrasound medical image, and determining characteristics of the gallbladder polyp on the basis of a second assessment model configured to classify characteristics of the gallbladder polyp when the gallbladder polyp is determined in the ultrasound medical image.

Abstract: A system for predicting prime editing efficiency by using deep learning, including: an information input unit that receives an input of data on prime editing efficiency of a prime editor, a predictive model generator for generating prime editing efficiency predictive models by performing deep learning to learn a relationship between features affecting prime editing efficiency and prime editing efficiency, by using the data received from the information input unit, a candidate sequence input unit that receives an input of a candidate target sequence for prime editing; and an efficiency predictor for predicting prime editing efficiency by applying the candidate target sequence input into the candidate sequence input unit to an efficiency predictive model generated in the predictive model generator.

Abstract: The present application pertains to a sialyloligosaccharide for augmenting the stemness of stem cells and a use thereof and provides a composition for augmenting stemness of stem cells, a method of culturing stem cells in a medium containing a sialyloligosaccharide, a method of augmenting stemness of stem cells, a stem cell with augmented stemness, obtained by the method, and a cell therapy composition including the stem cells as an active ingredient. The composition or the method according to one or more embodiments may suppress the aging of stem cells and may maintain and augment stemness.

Abstract: A method of fabricating a semiconductor device includes forming a semiconductor layer, the semiconductor layer including a two-dimensional semiconductor material, forming a sacrificial layer on the semiconductor layer, forming a metal contact layer on the sacrificial layer, and removing the sacrificial layer. After the sacrificial layer is removed, the semiconductor layer and the metal contact layer are bonded to each other through a van der Waals bond.

Abstract: The method for estimating mental health and providing solution for mental health by learning psychological data and biological data based on machine learning includes: (a) acquiring, by mental health estimating device, psychological data for testing and biological data for testing of test subject from terminal of the test subject in state in which first estimated model is learned by referring to estimated mental health data for learning output from the first estimated model and ground truth mental health data corresponding to the estimated mental health data after psychological data for learning and biological data for learning of learning subjects are input to the first estimated model; and (b) inputting, by the mental health estimating device, the psychological data for testing and the biological data for testing to the first estimated model to allow the first estimated model to output estimated mental health data for testing.

Abstract: A generative adversarial network-based audio signal generation model for generating a high quality audio signal may comprise: a generator generating an audio signal with an external input; a harmonic-percussive separation model separating the generated audio signal into a harmonic component signal and a percussive component signal; and at least one discriminator evaluating whether each of the harmonic component signal and the percussive component signal is real or fake.

Abstract: The present disclosure relates to a method for producing cultured meat, the method including: forming a cell sheet by culturing cells usable for producing cultured meat; and culturing the cells in a form in which a nanofilm is formed on a surface of the cell sheet by coating the cell sheet. The present disclosure provides a method for producing cultured meat that implements excellent mechanical strength by protecting a cell layer from external stress and performing stable cell proliferation, and provides cultured meat implementing quality and taste that are improved compared to those of conventional cultured meat by reproducing tissue similar to muscle tissue of an actual animal.

Abstract: A method, executed by a processor for compressing an audio signal in multiple layers, may comprise: (a) restoring, in a highest layer, an input audio signal as a first signal; (b) restoring, in at least one intermediate layer, a signal obtained by subtracting an upsampled signal, which is obtained by upsampling the audio signal restored in the highest layer or an immediately previous intermediate layer, from the input audio signal as a second signal; and (c) restoring, in a lowest layer, a signal obtained by subtracting an upsampled signal, which is obtained by upsampling the audio signal restored in an intermediate layer immediately before the lowest layer, from the input audio signal as a third signal, wherein the first signal, the second signal, and the third signal are combined to output a final restoration audio signal.

Abstract: A device for providing a location-based automatic participation chat room, the device, when a request to open a chat room is received along with service location information from at least one host terminal, creates at least one chat room, and sets a chat room identifier and a recognition code corresponding to each of the at least one chat room, and when at least one guest terminal accesses a location corresponding to the service location information using a pre-set participation means or the recognition code included in the participation means is received, makes the guest terminal participate in the chat room corresponding to the recognition code.

Abstract: A memory system includes a memory module and a memory controller. The memory module stores a code word group including first and second data words and a flag. The memory controller includes an error correction code (ECC) engine including a data-width aware (DWA) encoder that generates the code word group by using the first and second data words, and performs an error detection and error correction operation in one of first to third modes based on a size of each of the first and second data words, and a DWA decoder that receives the code word group, performs an error detection and error correction operation in one of the first to third modes according to a type of the code word group determined based on the flag, and extracts the first data word and the second data word from the code word group.

Abstract: The present invention relates to a method and system for augmenting aneurysm learning data for augmenting artificial images formed of various result values calculated from simulation results.

Abstract: Disclosed is a memory system using a heterogeneous data format, which provides a personalized recommendation algorithm function to an internet service user based on a plurality of items, which includes a user preference analyzer for each item that calculates a user preference value corresponding to each item of a analysis target service; and a memory that stores data related to the each item in a first data format or stores data related to the each item in a second data format with required bits less than the first data format, based on the user preference value of the each item.