Abstract: Disclosed is a degradation prediction device predicting a lifetime of a target material, including: at least one processor, and the at least one processor is configured to train a degradation index prediction model based on the representative value of a degradation index of a material by environmental conditions and the environmental information of a material subjected to a destructive testing, train a LMP (Larson-Miller Parameter) value prediction model based on the representative value of a degradation index of a material by environmental conditions and a theoretical value of LMP at a destructive testing, predict a degradation index for a target material using the degradation index prediction model for which training is completed based on environmental information of the target material and predict a LMP value of the target material using the LMP value prediction model for which training is completed based on the predicted degradation index.

Abstract: Disclosed is an annotation device including at least one processor. The at least one processor generates a plurality of superpixels in an annotation target image based on a predetermined non-parametric segmentation method, recommends segmentation regions based on outlines of the plurality of superpixels, respectively, and performs labeling for each of the recommended segmentation regions based on a user input for labeling.

Abstract: The present disclosure relates to a system and a method for validating the validity of a sensor, in particular, validating the validity of a sensor using a control limit. The present disclosure provides a method for validating the validity of a sensor using a control limit, including inferring a posterior distribution of a parameter in a Bayesian technique using a prior distribution of the parameter of sensor data and historical data of the sensor, setting a target credible interval for the posterior distribution of the parameter and setting a control line of the sensor data using the set credible interval, and validating the validity of the sensor by monitoring whether the actual measurement data of the sensor deviates from the control line. According to the present disclosure, it is possible to set the control limit based on the Bayesian inference and validate the validity of the sensor from the actual sensor data reliably using the control limit.