MULTIMODE SENSOR DEVICES
The disclosure provides BMDs that have multiple device modes depending on operational conditions of the devices, e.g., motion intensity, device placement, and/or activity type. The device modes are associated with various data processing algorithms. In some embodiments, the BMD is implemented as a wrist-worn or arm-worn device. In some embodiments, methods for tracking physiological metrics using the BMDs are provided. In some embodiments, the process or the BMD determines that the user is engaged in a particular activity type by detecting a signature signal selectively associated with the particular activity type, and quantifies a physiological metric for the particular activity type.
1 . A method of tracking a user's physiological activity using a worn biometric monitoring device having one or more sensors providing sensor output data indicative of the user's physiological activity, the method comprising:
(a) determining that the user is engaged in a first type of activity by detecting a first signature signal in a sensor output data, the first signature signal being selectively associated with the first type of activity;
(b) quantifying a first physiological metric for the first type of activity from a first set of sensor output data;
(c) determining that the user is engaged in a second type of activity by detecting a second signature signal in a subsequent sensor output data, the second signature signal being selectively associated with the second type of activity and different from the first signature signal; and
(d) quantifying a second physiological metric for the second type of activity from a second set of sensor output data,
wherein the first type of activity differs from the second type of activity.
2 . The method of claim 1 , wherein the sensor output data comprises one or more of the following: motion data, location data, pressure data, light intensity data, and/or altitude data.
3 . The method of claim 1 , wherein the first type of activity and the second type of activity comprise two different activities selected from the group consisting of: running, walking, elliptical machine exercise, stair master exercise, cardio exercise machines, weight training, driving, swimming, biking, stair climbing, and rock climbing.
4 . The method of claim 1 , wherein the one or more sensors comprise one or more motion sensors providing motion intensity data.
5 . The method of claim 4 , wherein the one or more motion sensors comprise one or more accelerometers, gyroscopes, inertial sensors, and/or GPSs.
6 . The method of claim 1 , wherein the worn biometric monitoring device comprises a wrist-worn biometric monitoring device or an arm-worn biometric monitoring device.
7 . The method of claim 1 , wherein detecting the first signature signal in the sensor output data comprises characterizing the sensor output data based on a signal norm, signal energy/power in certain frequency bands, a wavelet scale parameter, and/or a number of samples exceeding one or more thresholds.
8 . The method of claim 1 , wherein detecting the second signature signal in the sensor output data comprises characterizing the sensor output data based on a signal norm, signal energy/power in certain frequency bands, a wavelet scale parameter, and/or a number of samples exceeding one or more thresholds.
9 . The method of claim 1 , wherein the sensor output data comprise raw data directly obtained from the sensor.
10 . The method of claim 1 , further comprising:
analyzing the first or the second set of sensor output data to determine that the first or second set of sensor output data has a relatively low signal-to-noise ratio (SNR) while the user is active;
applying a frequency domain analysis to the first or second set of sensor output data to process and/or identify a periodic component; and
determining a physiological metric of the user from the periodic component.
11 . The method of claim 10 , wherein the frequency domain analysis comprises: a Fourier transform, a cepstral transform, a wavelet transform, a filterbank analysis, a power spectral density analysis and/or a periodogram analysis.
12 . The method of claim 10 , wherein the frequency domain analysis comprises filtering a time domain signal with a frequency band pass filter, and then applying a peak detection analysis in the time domain.
13 . The method of claim 10 , wherein the frequency domain analysis comprises finding a spectral peak that is a function of an average step rate.
14 . The method of claim 10 , wherein the frequency domain analysis comprises finding spectral peaks that are a function of an average step rate.
15 . The method of claim 10 , wherein the frequency domain analysis comprises performing a Fisher's periodicity test.
16 . The method of claim 10 , wherein the frequency domain analysis comprises using a harmonic to estimate a period and/or a test periodicity.
17 . The method of claim 10 , wherein the frequency domain analysis comprises performing a generalized likelihood ratio test whose parametric models incorporate a harmonicity of a motion signal.
18 . The method of claim 1 , wherein the physiological metric comprises a heart rate.
19 . The method of claim 1 , wherein the first or second physiological metric comprises stairs climbed, calories burned, and/or sleep quality.
20 . The method of claim 1 , further comprising applying a classifier to the sensor output data or the subsequent sensor output data to determine the placement of the biometric monitoring device on the user.
21 . The method of claim 20 , wherein quantifying a first physiological metric or quantifying a second physiological metric comprises using information regarding the placement of the biometric monitoring device to determine a value of the physiological metric.
22 . A biometric monitoring device comprising:
one or more sensors providing sensor output data comprising information about a user's activity level when the biometric monitoring device is worn by the user;
control logic configured to:
(a) determine that the user is engaged in a first type of activity by detecting a first signature signal in a sensor output data, the first signature signal being selectively associated with the first type of activity;
(b) quantify a first physiological metric for the first type of activity from a first set of sensor output data;
(c) determine that the user is engaged in a second type of activity by detecting a second signature signal in a subsequent sensor output data, the second signature signal being selectively associated with the second type of activity and different from the first signature signal; and
(d) quantify a second physiological metric for the second type of activity from a second set of sensor output data,
wherein the first type of activity differs from the second type of activity.
23 . The biometric monitoring device of claim 22 , wherein the sensor output data and the subsequent sensor output data comprise motion data.
24 . The biometric monitoring device of claim 22 , wherein the sensor output data and the subsequent sensor output data further comprise: location data, pressure data, light intensity data, and/or altitude data.
25 . The biometric monitoring device of claim 22 , wherein the biometric monitoring device comprises a wrist-worn biometric monitoring device or an arm-worn biometric monitoring device.