Abstract: The present disclosure relates to a method of extracting spatiotemporal features of electrocardiogram (ECG) and photoplethysmography (PPG) signals corresponding to each other using a neural network and of estimating blood pressure on the basis of the spatiotemporal features. The method includes: generating a target signal of a plurality of channels by respectively combining ECG signals and PPG signals corresponding to each other; extracting a first feature composed of a plurality of channels by inputting the target signal of a plurality of channels into a 1D convolution layer; generating a channel-wise weight vector by compressing the first feature; computing a second feature composed of a plurality of channels by applying the channel-wise weight vector to the first feature; extracting a third feature by inputting the second feature into a CNN model; and determining systolic and diastolic blood pressures by inputting the third feature into an LSTM model.

Abstract: The filter for carbon dioxide adsorption according to the present invention is composed of multiple unit filters that are mutually connected and stacked, and the unit filters include a repeating three-dimensional patterned part formed using one selected from vat photopolymerization, powder bed fusion, or additive manufacturing processes; flow paths formed in the three-dimensional patterned part; a three-dimensional exposed surface that is exposed to the mixed gas flowing through the flow paths; and a carbon dioxide adsorption layer coated on the exposed surface.

Abstract: Disclosed according to various embodiments is a thermoelectric material for colossal Seebeck coefficients comprising an Mg-poor Mg2Sn crystal and Secondary Sn phase.

Abstract: A processor-implemented method with homomorphic encryption includes: receiving a first ciphertext corresponding to a first modulus; generating a second ciphertext corresponding to a second modulus by performing modulus raising on the first ciphertext; and performing bootstrapping by encoding the second ciphertext using a commutative property and an associative property of operations included in a rotation operation.

Abstract: An operation method of performing a neural network operation of fully homomorphic encrypted data is provided. The operation method includes: receiving data for performing the neural network operation and receiving a parameter for generating an approximation polynomial corresponding to the neural network operation; obtaining layer information corresponding to layers of a neural network model, the layer information based on the data; determining importances of the layers, respectively, wherein the determining of the importances is based on the parameter and the layer information; generating an approximation polynomial approximating the neural network operation for each of the layers, wherein the generating is based on the layer importance; and generating an operation result by performing the neural network operation based on the approximation polynomial, wherein the parameter includes a computation time condition that the neural network operation must satisfy.

Abstract: A processor-implemented method includes receiving data for performing a neural network operation of homomorphic encrypted data and a parameter for generating an approximate polynomial corresponding to the neural network operation, obtaining layer information corresponding to each of a plurality of layers configuring a neural network based on the data, determining layer importance corresponding to each of the plurality of layers, based on the parameter and the layer information, generating an approximate polynomial approximating the neural network operation for each of the plurality of layers, based on the layer importance, and generating an operation result by performing the neural network operation based on the approximate polynomial.

Abstract: The present invention relates to a method of providing diagnostic information for brain diseases classification, which can classify brain diseases in an improved and automated manner through magnetic resonance image pre-processing, steps of contourlet transform, steps of feature extraction and selection, and steps of cross-validation. The present invention relates to a diagnostic information providing method capable of providing an optimal diagnostic means. The present invention relates to a method for providing diagnostic information for brain diseases classification, and relates to a method for providing an optimal diagnostic means for classifying brain diseases in an improved and automated manner through the steps of the magnetic resonance imaging pre-processing, contourlet transform, feature extraction and selection, and cross-validation.

Abstract: The present invention relates to a method for estimating blood pressure from photoplethysmography (PPG) signals. The blood pressure estimation method using the CFR model according to an embodiment of the present invention is characterized in that it comprises the steps of extracting a plurality of blood flow characteristics from PPG signals for training, calculating systolic and diastolic blood pressures from ambulatory blood pressures for training, labeling the systolic and diastolic blood pressures with the plurality of blood flow characteristics to train a cascade forest regression model, and inputting the PPG signals of a target user into the trained cascade forest regression model to determine the systolic and diastolic blood pressures of the target user.

Abstract: Disclosed is an encryption method and apparatus. The encryption method using homomorphic encryption may include generating a ciphertext by encrypting data, and bootstrapping the ciphertext by performing a modular reduction based on a selection of one or more target points for a modulus corresponding to the ciphertext.

Abstract: In a method of killing or reducing a growth of methicillin-resistant Staphylococcus aureus (S. aureus), a composition including a peptide consisting of the amino acid sequence of SEQ ID NO:2 or 3 is administered to a subject in need thereof. The peptide can be usefully applied as an active ingredient for antibiotics, cosmetic compositions, food additives, feed additives, biological pesticides and quasi-drugs.

Abstract: An apparatus for transmitting power wirelessly using capacitive coupling, provided in a wearable device, includes: a transmission electrode including a plurality of unit electrode pairs, each unit electrode pair being formed by a transmission signal electrode and a transmission ground electrode; and a control module configured to select a unit electrode pair, forming capacitive coupling with the reception electrode, among the plurality of unit electrode pairs provided in the reception electrode, to wirelessly transmit power to a reception electrode included in an implantable device.

Abstract: An apparatus with a neural network operation of homomorphic encrypted data includes: one or more processors configured to: generate homomorphic conjugation data of encrypted data based on the encrypted data, wherein the encrypted data corresponds to an output of each of a plurality of layers included in a neural network; and remove noise of the encrypted data based on the encrypted data and the homomorphic conjugation data.

Abstract: In accordance with various embodiments, an electronic device for colorizing a black and white image using a Generative Adversarial Network (GAN)-based model comprising a transformer block includes a processor, wherein the processor is set to: obtain a black and white image including only first information about a luminance channel; and generate a pseudo color image including only second information about a chrominance channel by applying the black and white image to the GAN-based model, the GAN-based model includes a generator network including a plurality of transformer blocks for color conversion, a plurality of convolution layers, and a plurality of transpose convolution layers, the plurality of transformer blocks each include a Depth Wise Convolution (DWC) layer, a first Layer Normalization (LN) layer, a Window-based Multi-head Self Attention (W-MSA) layer, a second LN layer, and a Colorization Feed Forward (CFF) block. Other various embodiments are possible.

Abstract: The present invention provides a robot configured to assist movements of limbs of a user.

Abstract: Disclosed is an apparatus for dynamic resource allocation in cloud radio access networks, and the dynamic resource allocation apparatus includes: a deep reinforcement learning unit learning load fluctuation of a remote radio head by using deep reinforcement learning and predicting the load fluctuation of the remote radio head; a calculation unit calculating a computational resource of a virtual machine corresponding to the remote radio head by using the predicted load fluctuation; and an allocation unit allocating the calculated computational resource to the virtual machine.

Abstract: The present disclosure relates to a power generation apparatus that generates torque and a method of operating the power generation apparatus. According to an embodiment, the power generation apparatus includes: at least a pair of control moment gyroscopes generating torque in different directions; and a unidirectional driving module outputting torque generated in different directions by the at least a pair of control moment gyroscopes in a predetermined direction.

Abstract: An apparatus for classifying heart disease using a MobileNet according to an embodiment of the present invention may comprise: an input unit for receiving a time-domain electrocardiogram signal; a wavelet transform unit for transforming the timedomain electrocardiogram signal into a frequency-domain electrocardiogram signal by using a wavelet transform; and a neural network for classifying the frequency-domain electrocardiogram signal as one of atrial fibrillation (AFIB), left bundle branch block beat (LBBB), normal sinus rhythm (NSR), or premature ventricular contraction (PVC), wherein the neural network may be a MobileNet trained using a training data set.

Abstract: A communication control apparatus and method of an artificial satellite are disclosed. The communication control apparatus includes a processor, a memory operatively connected to the processor, the memory being configured to store at least one piece of code to be executed by the processor, and a transmission and reception interface configured to communicate with a ground control center, wherein the memory stores code enabling the processor to receive location information of a signal generator on the ground from the ground control center, to calculate an angle of arrival for a target signal from the signal generator, received by the artificial satellite, based on the location information of the signal generator and location information of the ground control center, and to perform beamforming in a direction in which the artificial satellite detects the target signal based on the angle of arrival, when the code is executed by the processor.

Abstract: An apparatus includes one or more processors configured to execute instructions; and one or more memories storing the instructions; wherein the execution of the instructions by the one or more processors configures the one or more processors to generate an approximate polynomial, approximating a neural network operation, of a portion of a deep neural network model that is configured to receive input data, by using weighted least squares based on parameters corresponding to the generation of the approximate polynomial, a mean of the input data, and a standard deviation of the input data; and generate a homomorphic encrypted data operation result based on the input data and the approximate polynomial that approximates the neural network operation.

Abstract: An apparatus and method with encrypted data neural network operation is provided. The apparatus includes one or more processors configured to execute instructions and one or more memories storing the instructions, wherein the execution of the instructions by the one or more processors configures the one or more processors to generate a target approximate polynomial, approximating a neural network operation, of a portion of a neural network model, using a determined target approximation region, for the target approximate polynomial, based on a first approximate polynomial generated based on parameters corresponding to a generation of the first approximate polynomial, a maximum value of input data to the portion of the neural network layer, and a minimum value of the input data, and generate a neural network operation result using the target approximate polynomial and the input data.