Abstract: An anomaly detection method includes collecting and preprocessing time series data every preset detection cycle; detecting an anomaly in time series data preprocessed for a current detection cycle using a deep learning model trained with an unsupervised learning scheme using features of time series data of a previous detection cycle; retraining the deep learning model by further using the time series data preprocessed for at least one detection cycle included in the current learning cycle; and detecting an anomaly in time series data collected and preprocessed for a detection cycle after the current learning cycle using the retrained deep learning model.

Abstract: A method and system are provided to integrate IoTs and related components, users and applications into an ecosystem, and then on a per-component basis to provide real-time security solutions. Ecosystem security provides isolation, communications and security for technologies that fulfill a specific function or set of functions and their related and supporting platform elements.

Abstract: An apparatus, a system, and a method for providing a customized clothing recommendation service are provided. The method for providing a customized clothing recommendation service recommending clothing products with a neckline suitable for a user by a neckline recommendation service providing server, comprises: constructing a database for storing clothing product information matching neckline type information to clothing products; receiving an image of a user's upper body; detecting a face from the received upper body image and determining a face type of the detected face; and determining neckline type information matching the determined face type and detecting one or more clothing products matching the determined neckline type information; and providing the detected clothing products to the user.

Abstract: A system and a method for detecting image forgery through a convolutional neural network are capable of detecting image manipulation of compressed and/or color images. The system comprises a manipulated feature pre-processing unit applying an input image to a high-pass filter to enhance features due to image forgery; a manipulated feature extraction unit extracting image manipulated feature information from the image with the enhanced features through a pre-trained convolutional neural network; a feature refining unit refining the extracted image manipulated feature information; and a manipulation classifying unit determining the image forgery based on the image manipulated feature information refined by the feature refining unit.

Abstract: A URL collecting method includes accessing, by a URL collecting apparatus, a web server of a first URL; receiving, by the URL collecting apparatus, a first web page from the web server; and a URL dynamic collecting step of collecting, by the URL collecting apparatus, one or more URLs invoked while performing some or all of source codes of the first web page.

Abstract: A system and a method for training and utilizing deep convolutional neural networks to perform diagnostic and image enhancement operations on images of dentition uses digital images and other auxiliary parameters as inputs for a convolutional neural network. The neural network can output a tooth segmentation map, tooth identifiers, a probability map indicating the presence of caries, cavities or other dental anomalies/conditions, and recommended parameters for use in image enhancement algorithms.

Abstract: A method and apparatus for predicting game difficulty by using a deep-learning based game play server predict a difficulty of stage maps of a match puzzle game using a deep-learning based game play server that performs the match puzzle game and modify the stage maps. The deep-learning based game play server includes: a communicator configured to receive first stage maps of a first size and second stage maps of a second size; memory configured to store an agent model; at least one processor configured to perform learning of the agent model and perform the match puzzle game using the learned agent model.

Abstract: A method and system for creating a virtual image based on deep learning according to an embodiment of the present disclosure creates a virtual image based on deep learning by an image application executed by a processor of a computing device, where the method comprises obtaining a plurality of product images with respect to one product; classifying the obtained product images into a plurality of categories according to different pose types; determining a target category from among the plurality of categories for which the virtual image is to be created; creating a virtual image of a first pose type matched to the determined target category based on at least one product image among the plurality of product images; and displaying the created virtual image.

Abstract: A URL address determining method includes receiving a URL address extracted from a target server; requesting a response corresponding to the URL address from the target server; when receiving response data from the target server, extracting a response URL address corresponding to the URL address from the response data; and determining a resource indicated by the URL address by using the response URL address.

Abstract: A method for providing a product search result of a meta shopping mall comprises constructing a database by receiving store information and product information from servers for stores; receiving the store information and the product information from the stores, generating a store index document and a product index document including search words, and storing the store index document and the product index document on the database; generating keyword comprehensive information about a store which has registered a keyword, generating a keyword index document matching the keyword to the store which has registered the keyword, and storing the keyword index document on the database; receiving a search word input from a user; and searching the keyword index document within the database for the search word and providing the user with a store search result output interface for a product corresponding to the keyword.

Abstract: A method and system are provided to integrate IoTs and related components, users and applications into an ecosystem, and then on a per-component basis to provide real-time security solutions. Ecosystem security provides isolation, communications and security for technologies that fulfill a specific function or set of functions and their related and supporting platform elements.

Abstract: A method for determining duplication of a vulnerability may include a vulnerability extraction step of extracting vulnerability uniform resource locator (URL) addresses including the vulnerability from an analysis target server; a hash generation step of generating the URL hash value corresponding to the extracted vulnerability from the vulnerability URL address; and a duplication determination step of determining, when the URL hash value is present in the first comparison table, that the vulnerability is duplicated and excluding the corresponding vulnerability from vulnerability information.

Abstract: A method for providing similar or related products based on deep-learning, which is performed by a data processing unit of a shopping mall server, includes: acquiring an item image and item information for an item registered in a shopping mall; detecting bounding boxes for one or more objects by object-detecting the item image; setting a bounding box for an object associated with the item based on the item information; creating a main bounding box image by cropping a portion of the item image in the set bounding box; creating a padding image by padding-processing the main bounding box image; extracting a feature vector for the padding image; matching the feature vector with the item and storing the feature vector in a database; and creating the database for a similar or related product search service.

Abstract: A method and apparatus provide a virtual clothing wearing service based on deep-learning. A virtual clothing wearing server based on deep-learning includes a communicator configured to receive a user image and a v clothing image; a memory configured to store a program including first and second deep-learning models; a processor configured to generate an image of virtually dressing a virtual wearing clothing on a user. The program is configured to: generate, by the first deep-learning model, a transformed virtual wearing clothing image by transforming the virtual wearing clothing image in accordance with a body of the user in the user image based on the user image and the virtual wearing clothing image, and generate, by the second deep-learning model, the virtual wearing person image by dressing the transformed virtual wearing clothing on the body of the user based on the user image and the transformed virtual wearing clothing image.

Abstract: A method and system are provided to integrate IoTs and related components, users and applications into an ecosystem, and then on a per-component basis to provide real-time security solutions. Ecosystem security provides isolation, communications and security for technologies that fulfill a specific function or set of functions and their related and supporting platform elements.

Abstract: An input recognition method carried out by an electronic device implemented by a computer comprises the steps of generating a virtual grid of which the distance between lines is variable, in correspondence with at least a partial region of a display included in or connected to the electronic device; and recognizing, by using an index of the virtual grid, a position selected by a user of the electronic device in the region of the display corresponding to the virtual grid.

Abstract: A method for analyzing vulnerabilities may include: an analysis target URL receiving step of receiving a plurality of analysis target uniform resource locator (URL) addresses extracted from the analysis target server; an identification key setting step of setting respective identification keys corresponding to the plurality of analysis target URL addresses; a vulnerability analyzing step of performing a simulated attack so as to access the external server by the analysis target server by inserting an analysis hypertext transfer protocol (HTTP) request sentence including a URL address of an external server and the identification key into the analysis target URL address; an access record checking step of requesting an access record of the analysis target server to the external server; and a vulnerability extracting step of extracting a vulnerability of the analysis target server by using the identification key included in the access record.

Abstract: A global cloud network quality measurement method may include generating an Internet protocol (IP) list of open web servers having at least one externally open port for each country; collecting packet data through communication with each of the open web servers based on the IP list; and analyzing a network quality with respect to at least one of a region, an Internet service provider (ISP), and an autonomous system number (ASN) based on the collected packet data.

Abstract: A URL processing method includes a response data determining step in which a URL processing apparatus determines whether to exclude one or more URLs included in a first web page from a valid URL list using header information for the first web page of a first web site and a similarity based valid URL calculating step of estimating a similarity between web pages corresponding to respective URLs according to a predetermined criterion with respect to one or more URLs included in the first web page and selecting some of URLs of a similar web page calculated according to the similarity and adding the selected URLs in the valid URL list.

Abstract: An air-conditioning apparatus using a heat pipe is provided, where the state of the outside air is compared with the state of set supply air. The heat exchange and mixed supply of outside air and ventilation air are effectively performed by changing the passage of the ventilation air and the outside air through the selective opening/shutting of dampers, cooling the outside air through latent heat by spraying mist, and by controlling supply air in a set state through the cooling and humidification of the supply air. Accordingly, energy efficiency can be improved and the energy necessary for the air-conditioning apparatus can be reduced using the evaporation latent heat of water. Furthermore, operation costs can be reduced and financial gains can be obtained because an efficient operation can be performed in response to the state of a measured outside air.