Abstract:
A data de-identification method and an apparatus performing the data de-identification method are disclosed. The data de-identification method includes receiving identification data including a plurality of input feature vectors and generating a graph neural network (GNN) model including a plurality of nodes each having a value corresponding to each of the input feature vectors, determining a de-identification vector to which a correlation between the nodes is applied from the input feature vectors through the GNN model, and extracting an output feature vector by grouping values in each of the input feature vectors using the GNN model.
Abstract:
A software router includes a main memory configured to comprise a hash table consisting of one or more buckets (hereinafter, referred to as “buckets A”) wherein each bucket stores destination information to which a unique key is mapped; and a central processing unit (CPU) configured to comprise a temporary table that stores the destination information present in the hash table, to determine a location of a bucket (hereinafter, referred to as “bucket B”) in the temporary table by applying a specific key to a designated hash function, wherein the specific key is extracted from a received packet, and to transmit the received packet by obtaining destination information from bucket B at the determined location in the temporary table.
Abstract:
Provided is a method of localizing an anomaly in a target image. The method includes training a reconstruction model using a normal image, deriving a reconstructed image by applying a target image, which is subject to detection, to the trained reconstruction model, generating an anomaly map on the basis of a result of comparing the reconstructed image and the target image, and localizing an anomaly through the generated anomaly map.
Abstract:
Provided are a method and apparatus capable of improving the feature extraction required for image stitching, the computational efficiency of homography calculation based on the feature extraction, and the performance of image stitching. The image stitching method according to the present invention includes: based on two images and additional information as needed, calculating an overlapping area in which two images overlap each other; masking an area in which the two images do not overlap each other based on information about the calculated overlapping area to provide masked images; extracting significant features to be used for image stitching from the masked images; calculating a homography to be used for image transformation based on the extracted features; and transforming and stitching the images based on the calculated homography.
Abstract:
A method of managing system health is provided. The method includes calculating a reconstruction missing value with respect to the second domain data, determining a degree of degradation of the system on the basis of the reconstruction missing value, predicting a second remaining useful life (RUL) prediction value {tilde over (y)} of the system on the basis of the second domain data, based on a result of the determination of the degree of degradation, optimizing a degradation compensation function on the basis of a distribution of a first RUL prediction value y of the system predicted based on the first domain data in a pre-learning process of the diagnosis model, and predicting a final RUL prediction value {tilde over (y)}′ obtained by compensating for the second RUL prediction value {tilde over (y)}, by using the optimized degradation compensation function.
Abstract:
A mixed reality content providing apparatus is disclosed. The mixed reality content providing apparatus may recognize an OOI included in a 360-degree VR image to generate metadata of the OOI and may provide a user with mixed reality content where the metadata is overlaid on the 360-degree VR image.
Abstract:
Provided is a table lookup method for a set membership query and a table lookup apparatus using the same. The table lookup apparatus includes a storage configured to store a first table and a second table, which include information needed for responding to a set membership query, and a controller configured to, when a set membership query for an element occurs, search the first table and the second table and output set information corresponding to the element, wherein the first table includes information about at least one element stored in each entry thereof according to a partial hash key of the at least one element, and the second table stores the at least one element and set information corresponding to the at least one element.