Hierarchical context detection method to determine location of a mobile device on a person's body
View Patent ↗The present invention is related to detecting location of a navigation device using sensor data analysis, where the sensor is coupled to the navigation device. A hierarchical algorithm is used for making a series of decisions regarding the location of the navigation device, with each decision corresponding to a class among a plurality of classes related to the possible motion modes and/or precise location of the device, including the location of the device with respect to a person's body. By accurately identifying the device location, the hierarchical algorithm facilitates in providing relevant contextual information, thereby enhancing situational awareness.
1. A method for using position information about a mobile device to enhance user experience, the method comprising:
detecting, by a processor, a motion mode of the mobile device based on data collected from one or more sensors coupled to the mobile device;
detecting, by the processor, a location of the mobile device on a user's body based on the detected motion mode and on the collected sensor data; and
providing situational awareness information to the user based on the detected motion mode and the detected location of the mobile device,
wherein detecting the motion mode of the mobile device includes:
obtaining frequency-domain spectral information from the collected sensor data;
comparing the spectral information from the collected sensor data to spectral information in two or more sets of training data, each set of training data in the two or more sets of training data corresponding to one of a plurality of particular motion modes; and
determining, based on the comparison, the motion mode of the mobile device.
2. The method of claim 1 , wherein detecting the location of the mobile device on the user's body comprises performing one or both of time-domain analysis and frequency-domain analysis of the data collected from the one or more sensors.
3. The method of claim 1 , wherein detecting the location of the mobile device on the user's body comprises performing a time-domain classification using classifiers of data collected from the one or more sensors.
4. The method of claim 3 , wherein the classifiers include one or more of standard deviation of acceleration, mean of norm of acceleration, zero crossings in the norm of acceleration, number of peaks in the norm of acceleration, amplitude of pitch variation, amplitude of yaw variation, and amplitude of roll variation.
5. The method of claim 1 , wherein obtaining the frequency-domain spectral information comprises computing a set of linear predictor coefficients (LPC) for the collected sensor data.
6. The method of claim 5 , wherein comparing the spectral information in the collected sensor data to spectral information in two or more sets of training data further comprises:
converting the LPC to linear spectral frequencies (LSF) for the collected sensor data; and
calculating a spectral distortion between the LSF for the collected sensor data and a LSF for each set of training data in the two or more sets of training data.
7. The method of claim 6 , wherein determining, based on the comparison, the motion mode of the mobile device the plurality of motion modes comprises:
identifying a particular motion mode whose corresponding set of training data has LSF that have a least amount of spectral distortion with the LSF of the collected sensor data.
8. The method of claim 1 , wherein the plurality of particular motion modes includes two or more of: stationary, walking, fast walking, jogging, climbing up/down stairs, going up/down on an escalator, going up/down on an elevator, biking, driving, and riding in a vehicle.
9. The method of claim 1 , wherein the detected location is used to select a dead-reckoning (DR) positioning algorithm.
10. The method of claim 1 , wherein the plurality of particular motion modes includes at least one non-stationary motion mode.
11. The method of claim 1 , wherein detecting the location of the mobile device on the user's body includes:
determining whether an orientation of the mobile device is one of a first orientation and a different second orientation.
12. The method of claim 11 , wherein the detected motion mode is walking or fast walking.
13. The method of claim 11 , wherein detecting the location of the mobile device on the user's body further includes:
determining whether the mobile device is located near the user's head, in the user's hand, or in a bag carried by the user in response to determining that the orientation of the mobile device is the first orientation.
14. The method of claim 13 , wherein the detected motion mode is jogging or running.
15. The method of claim 11 , wherein detecting the location of the mobile device on the user's body further includes:
determining whether the mobile device is located in the user's trousers, near the user's waist, in the user's hand, in the user's shirt, or in a bag carried by the user in response to determining that the orientation of the mobile device is the second orientation.
16. The method of claim 1 , wherein detecting the location of the mobile device on the user's body includes:
determining a head or trouser location of the mobile device.
17. The method of claim 1 , wherein the sensors comprise an inertial measurement unit (IMU).