Abstract: An unsupervised learning-based detection method according to one technical aspect of the present disclosure relates to an unsupervised learning-based detection method using a supervised-learned model, and includes: generating a first plurality of matrix data on the basis of driving data; generating encoding information by encoding the first plurality of matrix data using a convolutional neural network; modeling a time series feature of the encoding information by using a long short-term memory (LSTM) network, so as to derive a correlation between variables according to a time series; re-implementing a second plurality of matrix data through a deconvolution calculation of the correlation between the variables according to the time series; and determining whether the driving data corresponds to a pre-supervised learned driver profile, on the basis of a difference between the first plurality of matrix data and the second plurality of matrix data.
Abstract: An unsupervised learning-based detection method according to one technical aspect of the present disclosure relates to an unsupervised learning-based detection method using a supervised-learned model, and includes: generating a first plurality of matrix data on the basis of driving data; generating encoding information by encoding the first plurality of matrix data using a convolutional neural network; modeling a time series feature of the encoding information by using a long short-term memory (LSTM) network, so as to derive a correlation between variables according to a time series; re-implementing a second plurality of matrix data through a deconvolution calculation of the correlation between the variables according to the time series; and determining whether the driving data corresponds to a pre-supervised learned driver profile, on the basis of a difference between the first plurality of matrix data and the second plurality of matrix data.
Abstract: Provided are a real-time acceleration sensor calibration apparatus for measuring a movement of a vehicle and an acceleration sensor calibration method, the acceleration sensor calibration apparatus including an acceleration sensor configured to measure a triaxial acceleration value, a gyroscope configured to measure a triaxial angular velocity value, an acceleration data calibrator configured to primarily transform a vector of the measured acceleration value using a gravity vector calculated based on the triaxial acceleration value and the triaxial angular velocity value measured by the acceleration sensor and the gyroscope, and a communicator configured to transmit information related to the movement of the vehicle to a server based on calibrated acceleration data.
Type:
Grant
Filed:
April 9, 2018
Date of Patent:
October 20, 2020
Assignee:
SUNTECH INTERNATIONAL LTD.
Inventors:
Jung Hun Kim, Sun A Kim, Dae Sung Lee, Jai Chang Yang
Abstract: Provided are a real-time acceleration sensor calibration apparatus for measuring a movement of a vehicle and an acceleration sensor calibration method, the acceleration sensor calibration apparatus including an acceleration sensor configured to measure a triaxial acceleration value, a gyroscope configured to measure a triaxial angular velocity value, an acceleration data calibrator configured to primarily transform a vector of the measured acceleration value using a gravity vector calculated based on the triaxial acceleration value and the triaxial angular velocity value measured by the acceleration sensor and the gyroscope, and a communicator configured to transmit information related to the movement of the vehicle to a server based on calibrated acceleration data.
Type:
Application
Filed:
April 9, 2018
Publication date:
September 12, 2019
Applicant:
SUNTECH INTERNATIONAL LTD.
Inventors:
Jung Hun Kim, Sun A Kim, Dae Sung Lee, Jai Chang Yang