Abstract:
The present invention relates to a method which comprises the steps of: collecting a multi-application time-series data; calculating a hidden variable of the collected time-series data; harmonic processing for detecting a harmonic mixing weight and harmonics characteristics of the calculated result; removing a phase shift in the harmonic operation; and performing data clustering based on the result of importance of a harmonic element with the phase shift is removed, and a terminal supporting the same.
Abstract:
PURPOSE: A recording medium in which a navigation application, a client with the same, and a server system capable of transmitting the client additionally provide the names and coordinates information of buildings in which a user is interested. CONSTITUTION: A recording medium in which a navigation application makes a computing device function as a building database member (111), an item data base member (112), an interest information database member (113), and an additional information inference member (114). The building database member stores building instances fetching the names and the coordinate information of buildings existed in a navigation map. The item database member stores the product or services provided by each building as item instances matched with the building instances respectively. The interest information database member sets at least one of the item instances as user interest information, thereby storing the instance. The additional information inference member inferences the building instances matched with the user interest information in a destination or on a moving passage and display the names and the coordinates information corresponding to the inferred building instance on the navigation map. [Reference numerals] (111) Building database member; (112) Item database member; (113) Interest information database member; (114) Additional information inference member; (115) Destination input member; (116) Visiting purpose input unit; (117) History database member; (118) Attribute database member
Abstract:
PURPOSE: An epileptic seizure predicting method using an adaptive autoregressive model of mandatory access is provided to increase an epileptic seizure prediction rate of epileptic brainwave data having complex features such as non-linear, informal, and aperiodic features. CONSTITUTION: An autoregressive model is established to estimate a future value by using data values. The autoregressive model is established by setting an autoregressive parameter of the model as '1'. A fractal dimension is used for determining a degree of the autoregressive parameter and a box-counting method is applied for calculating the fractal dimension.
Abstract:
PURPOSE: A heterogeneous data fusing/supplying system of a web page and a method thereof are provided to supply a convenient searching result to a user by integrating data into one document in a systematic sequence. CONSTITUTION: A training module(102) classifies property of a webpage having specific information and property of a webpage not having specific information through a Bayes theorem. The training module learns probability which refers whether the feature is on a web page. A data dictionary constructing module(104) constructs an ontology data dictionary for supporting search of high accuracy.
Abstract:
An LED(Light Emitting Diode) base object control system for a table top display for supplying the improved accuracy of input signal recognition through an ultraviolet ray emitting intensity measurement is provided to sense the input signal from the outside without additional work by including an infrared ray emitting diode and a switch. A radiated intensity measuring unit(220) generates radiated intensity information by measuring the transition change of the radiated ratio by unit stereo angle. If the value of the radiant intensity information is changed, a switch(240) authorizes the radiant intensity information to a controller(250). According to the radiant intensity information applied from the switch, the controller produces the external input information.
Abstract:
A disease grouping system through a face image for classifying the disease of a user through SVM is provided to prevent the deterioration of disease by previously classifying the disease of the user through SVM which is a kind of statistical classification method of data mining based on extracted facer image. A face image loading module(110) loads a face image. The face image extracting module extracts the face image by comparing pixel color difference signal values by each pixel of the loaded face image. A face range segmentation module(130) divides the extracted face image into the tile of the fixed number. A feature extraction module(140) extracts the average of the divided face image luminance value, a color difference signal value, a color tone value, a saturation value and a brilliance value and standard deviations as the specific value of corresponding face images. A normalization module(150) normalizes extracted face image feature.