Abstract: According to an embodiment of the present invention, a method for providing a motion recognition dance game comprises the steps of: (a) displaying a sound source list provided from a server; (b) requesting the server for a motion video corresponding to one sound source selected by a user from the sound source list, and receiving the motion video and first motion data from the server; (c) playing back the motion video, receiving second motion data generated in real time from a motion recognition sensor worn on the body of the user, and comparing the second motion data with the first motion data; and (d) calculating a grade on the basis of a matching rate of the first and second motion data, wherein the sound source list includes sound sources previously stored in the user terminal.

Abstract: According to an embodiment of the present invention, a method for providing a motion recognition dance game comprises the steps of: (a) displaying a sound source list provided from a server; (b) requesting the server for a motion video corresponding to one sound source selected by a user from the sound source list, and receiving the motion video and first motion data from the server; (c) playing back the motion video, receiving second motion data generated in real time from a motion recognition sensor worn on the body of the user, and comparing the second motion data with the first motion data; and (d) calculating a grade on the basis of a matching rate of the first and second motion data, wherein the sound source list includes sound sources previously stored in the user terminal.

Abstract: There is provided a method for recognizing a user context using multimodal sensors, and the method includes classifying accelerometer data by extracting candidates for movement feature from the accelerometer data collected from an accelerometer, selecting one or more movement features from the extracted candidates for movement feature based on relevance and redundancy thereof, and then inferring a user's movement type based on the selected movement features using a first time-series probability model; classifying audio data by extracting surrounding features from the audio data collected from an audio sensor and inferring the user's surrounding type based on the extracted surrounding features; and recognizing a user context by recognizing the user context based on either of the movement type or the surrounding type.

Abstract: A method of recognizing an activity on the basis of a semi-Markov conditional random field (CRF) model is provided. The method includes segmenting an input signal measured by an accelerometer to output frame sequences, extracting training feature vectors from the frame sequences, building a codebook containing kernel vectors from the training feature vectors; quantizing vector sequences into discrete symbol sequences, using linear chain semi-Markov CRF model to compute the likelihood of a label given its corresponding symbol sequence.