Abstract: An electronic device is disclosed. The electronic device of the present invention comprises a communication unit and a processor for receiving information on a refrigerator from the refrigerator through the communication unit, dividing an operation section of the refrigerator into an event section and a normal section on the basis of the received information, and determining whether the refrigerator is abnormal on the basis of a state of the refrigerator in the normal section or the event section among the received information. The event section includes a section from a time point when a door of the refrigerator is opened to a time point when the temperature of the refrigerator reaches a predetermined temperature after the door is closed, and the normal section includes a section from a time point when the temperature of the refrigerator reaches the predetermined temperature to a time point before the door is opened.

Abstract: Disclosed is an image segmentation method including receiving an image to be segmented and segmenting the received image by using a neural network learned through a Mumford-Shah function-based loss function.

Abstract: Disclosed are an unsupervised learning-based image registration method using a neural network with cycle consistency and an apparatus therefor. An image registration method includes receiving a first image and a second image for image registration, outputting a deformation field for the first image and the second image using an unsupervised learning-based neural network with cycle consistency for the deformation field, and generating a registration image for the first image and the second image based on a spatial deformation function using the output deformation field. The outputting of the deformation field includes outputting the deformation field for the first image for registering the first image to the second image may be output, when the first image is a moving image and the second image is a fixed image, and the generating of the registration image includes generating the registration image by applying the deformation field for the first image to the first image using the spatial deformation function.