Abstract: According to one embodiment of the present disclosure, the speaker verification device comprises a memory configured to store a neural network model including a student network and a teacher network; and at least one processor configured to train the neural network model, wherein the at least one processor is configured to determine a first loss function based on a difference between outputs of the student network and the teacher network for unlabeled utterances; determine a second loss function based on a difference between an output of the student network for labeled utterances and a one-hot encoding result for the labeled utterances; update parameters of the student network based on the first and second loss functions; and update parameters of the teacher network based on an exponential moving average of the updated parameters of the student network.

Abstract: An apparatus for estimating bio-information is disclosed. The apparatus may include: a pulse wave sensor configured to measure a pulse wave signal from an object; a force sensor configured to obtain a force signal by measuring an external force exerted onto the force sensor; and a processor configured to obtain a first input value, a second input value, and a third input value based on the pulse wave signal and the force signal, to extract a feature vector by inputting the first input value, the second input value, and the third input value into a first neural network model, and to obtain the bio-information by inputting the feature vector into a second neural network model.

Abstract: An apparatus for estimating blood pressure includes: a photoplethysmogram (PPG) sensor configured to measure a PPG signal from an object; a force sensor configured to measure a force signal acting between the object and the PPG sensor; and a processor configured to (i) divide a predetermined blood pressure range into a plurality of classes, (ii) input the measured PPG signal and the measured force signal into a blood pressure estimation model to obtain the probability values for each of the classes, and (iii) estimate blood pressure based on the obtained probability values for the respective classes.

Abstract: An apparatus for estimating bio-information is disclosed. The apparatus may include: a pulse wave sensor configured to measure a pulse wave signal from an object; a force sensor configured to obtain a force signal by measuring an external force exerted onto the force sensor; and a processor configured to obtain a first input value, a second input value, and a third input value based on the pulse wave signal and the force signal, to extract a feature vector by inputting the first input value, the second input value, and the third input value into a first neural network model, and to obtain the bio-information by inputting the feature vector into a second neural network model.

Abstract: Provided are an automatic precipitation sampler system and an operation method thereof. The automatic precipitation sampler system, includes a main body having an water receiving port provided in the upper portion thereof, a driving unit disposed in the main body, a circular table disposed in the main body and rotating by the driving unit, a plurality of sample containers arranged at uniform intervals from each other at positions spaced away from the center of the circular table by a predetermined distance in the radial direction of the circular table, and a plurality of funnels arranged on top of each of the plurality of sample containers such that any one of the plurality of funnels is aligned with the water receiving port.

Abstract: Disclosed herein are a method and apparatus for delivering user-assisted multimedia data using periodic multicast, which provide stable high-capacity Video-On-Demand (VOD) streaming service by proposing a user-assisted video transfer scheme capable of replacing a client-server configuration in providing high-capacity VOD streaming service.

Abstract: Disclosed is an apparatus for calibrating and validating an MRR, the apparatus including a correlation calculation unit configured to determine a correlation between a precipitation strength value and a precipitation measurement value, a regression equation calculation unit configured to calculate a regression equation for the precipitation strength value and to calculate a result value of the regression equation, an optimum accumulation time determination unit configured to determine an optimum accumulation time based on the correlation and the result value, a rain cloud vertical sampling unit configured to sample a rain cloud example, a vertical reflectance comparison unit configured to compare a calibrated MRR at a shortest range distance with a vertical reflectance according to a wind system, and a radar constant correction unit configured to correct a constant of an MRR based on the optimum value or the sampling and a result value of the comparison.

Abstract: Disclosed herein are a method and apparatus for delivering user-assisted multimedia data using periodic multicast, which provide stable high-capacity Video-On-Demand (VOD) streaming service by proposing a user-assisted video transfer scheme capable of replacing a client-server configuration in providing high-capacity VOD streaming service.

Abstract: An email security system for company security is disclosed. The email security system has a transmission server and a reception server. The transmission server has a mail code assigning and mail separating unit, a database, a security violation checking unit, a virus checking and curing unit, and a mail sending unit; and the reception server has a CGI operating unit. The security violation checking unit checks whether or not the email written and sent by a mail sender violates security, and sets a flag to prevent a mail receiver from reading the email if the email violates the security. The virus checking and curing unit checks whether the main body and the attached file are infected with computer viruses, and sets the flag to prevent the mail receiver from reading the email if the main body and the attached file are infected with the computer viruses.