Abstract: A method for determining an enteric disorder by using a machine learning model, including: analyzing a mixture of a sample collected from a subject and a gut environment-like composition; extracting multiple microbial data based on an analysis result of the mixture; selecting a microbe-related feature to be used for the machine learning model from the multiple microbial data based on a predetermined feature selection algorithm; training the machine learning model by using the microbe-related feature; and determining an enteric disorder by inputting, into the trained machine learning model, the microbial data collected from a subject to be tested.

Abstract: An augmented reality (AR)-based route guidance method includes acquiring a driving image captured by an image capturing device of a vehicle which is running, acquiring route data to a destination of the vehicle, recognizing both side lane markings of a lane in which the vehicle is running from the acquired driving image, generating first route guidance linear data based on the recognized both side lane markings for a region in which both side lane markings are recognized in the driving image, generating second route guidance linear data using link linear data of the route data for a region in which both side lane markings are not recognized in the driving image, combining the first route guidance linear data and the second route guidance linear data to generate combined route guidance linear data, and displaying a route guidance object in AR using the generated combined route guidance linear data.

Abstract: A method for determining abdominal pain by using a machine learning model, including: analyzing a mixture of a sample collected from a subject and a gut environment-like composition; extracting multiple microbial data based on an analysis result of the mixture; selecting a microbe-related feature to be used for the machine learning model from the multiple microbial data based on a predetermined feature selection algorithm; training the machine learning model by using the microbe-related feature; and determining abdominal pain by inputting, into the trained machine learning model, the microbial data collected from a subject to be tested. The microbe-related feature includes the content of at least one kind of microbes selected from families belonging to the order Bacillales, the order Lactobacillales, the order Oscillospirales, the order Lachnospirales, the order Coriobacteriales, the order Peptostreptococcales-Tissierellales, the order Bacteroidales, and the order Bifidobacteriales.

Abstract: A 3D space data generation method for flight of an aerial vehicle may include receiving map data for a 3D space in which the aerial vehicle flies, and dividing a space into a flight area in which the aerial vehicle flies and a restricted area in which the aerial vehicle does not fly based on the map data and dividing the flight area and the restricted area into each unit area to generate 3D space data.

Abstract: An augmented reality (AR)-based route guidance method includes acquiring a driving image captured by an image capturing device of a vehicle which is running, acquiring route data to a destination of the vehicle, recognizing both side lane markings of a lane in which the vehicle is running from the acquired driving image, generating first route guidance linear data based on the recognized both side lane markings for a region in which both side lane markings are recognized in the driving image, generating second route guidance linear data using link linear data of the route data for a region in which both side lane markings are not recognized in the driving image, combining the first route guidance linear data and the second route guidance linear data to generate combined route guidance linear data, and displaying a route guidance object in AR using the generated combined route guidance linear data.

Abstract: Disclosed is a method of detecting a dangerous object for an aerial vehicle. The method includes setting an object detection area in air in which the aerial vehicle is in flight using a first sensor, a second sensor, and a third sensor; detecting an object in the set object detection area; generating detailed object information on the detected object; and determining whether the detected object is the dangerous object based on the generated detailed object information.

Abstract: Disclosed is a method of providing augmented reality guidance for an aerial vehicle. A method of providing augmented reality guidance for an aerial vehicle includes acquiring an aerial vehicle flight image captured through a camera installed in the aerial vehicle, acquiring a flight route for a flight to a destination of the aerial vehicle, generating an augmented reality (AR) route guidance object corresponding to the flight route, generating an AR route guidance image by mapping the generated AR route guidance object to the aerial vehicle flight image, and displaying the generated AR route guidance image.

Abstract: Disclosed are an aerial vehicle using a hybrid distributed propulsion system and a control method thereof. According to an embodiment of the present specification, an aerial vehicle includes a power generation unit generating electricity by consuming fuel; a battery unit that is charged with power supplied from the power generation unit or supplied with power from the outside; a plurality of fan modules receiving power from the battery unit or the power generation unit to provide lift to the aerial vehicle; a power supply path control unit selecting at least one of the power generation unit and the battery unit to supply power to at least one of the plurality of fan modules; and a route generation unit generating a flight route from a departure point to a destination of the aerial vehicle.

Abstract: Disclosed is a method of displaying an omnidirectional hazard of aerial vehicle. The method includes generating an omnidirectional image based on the aerial vehicle by using a plurality of flight images acquired from each of a plurality of cameras equipped in the aerial vehicle, determining whether a hazard exists within a predetermined range based on a location of the aerial vehicle, classifying whether the hazard is a mobile object or an immobile object when the hazard exists within the predetermined range based on the location of the aerial vehicle, and displaying a risk guidance object in the omnidirectional image based on the classified hazard.

Abstract: Disclosed is a method of assisting landing of an aerial vehicle based on an image. The method includes acquiring an aerial vehicle landing image captured by a camera installed on the aerial vehicle; generating a landing guide object for guiding the landing of the aerial vehicle; generating a landing assistance image obtained by combining the acquired aerial vehicle landing image and the landing guide object; and displaying the generated landing assistance image.

Abstract: An augmented reality (AR)-based route guidance method includes acquiring a driving image captured by an image capturing device of a vehicle which is running, acquiring route data to a destination of the vehicle, recognizing both side lane markings of a lane in which the vehicle is running from the acquired driving image, generating first route guidance linear data based on the recognized both side lane markings for a region in which both side lane markings are recognized in the driving image, generating second route guidance linear data using link linear data of the route data for a region in which both side lane markings are not recognized in the driving image, combining the first route guidance linear data and the second route guidance linear data to generate combined route guidance linear data, and displaying a route guidance object in AR using the generated combined route guidance linear data.