Abstract: The present invention relates to a method and device for diagnosing a defect of a collaborative robot, the method comprising the steps in which: an electronic device generates a sensing data structure for managing sensing data collected from at least one collaborative robot; the electronic device generates an operation data structure for managing operation data associated with the operation of the collaborate robot; the electronic device generates a malfunction data structure for managing malfunction data of a point in which the severity of the operation equals to or is higher than a threshold; and the electronic device stores data collected from the at least one collaborative robot in accordance with the structures. Application to other embodiments is also possible.

Abstract: The present invention relates to a method and system for health monitoring of a collaborative robot, includes the steps of calling a test program installed in a collaborative robot for health monitoring of the collaborative robot when the collaborative robot satisfies a call condition of the test program, performing a test by operating the collaborative robot based on the test program, and collecting and analyzing a result of the test by the collaborative robot, and may be applicable as another embodiment.

Abstract: The present invention relates to a method and apparatus for fault diagnosis of a programmable robot, and includes the steps of collecting sensing data corresponding to an operation of a programmable robot, identifying a program and motion related to the sensing data, generating an execution pattern based on the sensing data, extracting a standard pattern corresponding to the identified program and motion, and diagnosing a fault of the programmable robot by comparing the standard pattern with the execution pattern, and the present invention may be applicable as another embodiment.

Abstract: The present disclosure relates to a method for filtering selectively obstacle to be an obstacle to machine learning according to a learning purpose and a system thereof. A system for filtering obstacle data in machine learning of medical images may include an obstacle data definition unit configured to receive definitions of obstacle data according to a machine learning purpose; a filter generation unit configured to generate a filter for filtering the obstacle data; and a filtering unit configured to remove obstacle data in machine learning using the generated filter.

Abstract: The present invention relates to a method and apparatus for tracing a fault of a collaborative robot, including the steps of setting, by an electronic device, a basic index which serves as an analysis criterion of operational data generated by the collaborative robot, setting, by the electronic device, an analysis index for analyzing the operational data, receiving, by the electronic device, a plurality of operational data from the collaborative robot, and tracing, by the electronic device, a fault generated in at least one of the plurality of operational data using the basic index and the analysis index, and the application to other exemplary embodiments is possible.

Abstract: A dataset validating method based on a feature coverage according to an exemplary embodiment of the present disclosure includes extracting a feature of a first dataset including a plurality of data using a classification model trained for a predetermined second dataset; clustering labels of the first dataset according to the extracted feature; and validating a coverage of a partial dataset which is a part selected from the first dataset based on the clustering result.

Abstract: Provided is a method for tracking a position of a capsule endoscope including: receiving, by an apparatus for tracking a position of a capsule endoscope, an image captured by the capsule endoscope; distinguishing, by the apparatus for tracking a position of a capsule endoscope, a gastrointestinal tract junction from the image using a machine-learned classification model based on the gastrointestinal tract junctions; and tracking, by the apparatus for tracking a position of a capsule endoscope, the position of the capsule endoscope based on the distinguished gastrointestinal tract junctions.

Abstract: The present disclosure relates to a method for evaluating quality of a medical image dataset and a system thereof capable of confirming whether medical image data is suitable to be used for machine learning. Evaluation items may include data normality which means a ratio of normal frames in all frames; learning fitness which means a ratio of labeled or labelable frames in the received data; and anatomical completeness which means a ratio of anatomical elements included in the received data against anatomical elements based on medical standards.

Abstract: The present disclosure relates to a method for filtering selectively obstacle to be an obstacle to machine learning according to a learning purpose and a system thereof. A system for filtering obstacle data in machine learning of medical images may include an obstacle data definition unit configured to receive definitions of obstacle data according to a machine learning purpose; a filter generation unit configured to generate a filter for filtering the obstacle data; and a filtering unit configured to remove obstacle data in machine learning using the generated filter.

Abstract: According to an exemplary embodiment of the present disclosure, a capsule endoscopic image analyzing method includes: receiving signs from a user, by a capsule endoscopic image analyzing apparatus; determining a disease which shows the signs using disease information included in a knowledge model, by the capsule endoscopic image analyzing apparatus; determining findings which are found from a gastrointestinal tract due to the disease using findings included in the knowledge model, by the capsule endoscopic image analyzing apparatus; and separately providing only frames in which the findings appear in an image photographed by a capsule endoscope, by the capsule endoscopic image analyzing apparatus.

Abstract: Provided is a method for tracking a position of a capsule endoscope including: receiving, by an apparatus for tracking a position of a capsule endoscope, an image captured by the capsule endoscope; distinguishing, by the apparatus for tracking a position of a capsule endoscope, a gastrointestinal tract junction from the image using a machine-learned classification model based on the gastrointestinal tract junctions; and tracking, by the apparatus for tracking a position of a capsule endoscope, the position of the capsule endoscope based on the distinguished gastrointestinal tract junctions.

Abstract: A method for providing a user interface, the method includes displaying a foreground application window on a touch screen of a mobile communication device, detecting an input pattern for displaying a multi-tasking bar, displaying the multi-tasking bar on the touch screen in response to detecting the input pattern for displaying the multi-tasking bar, the multi-tasking bar configured to divide the touch screen into at least two areas, and resizing the foreground application window within a first area of the at least two areas.