Methods and Systems for Applying Weights to Information From Correlated Measurements for Likelihood Formulations Based on Time or Position Density
Within examples, methods and systems for applying weights to information from correlated measurements for likelihood formulations based on time or position density are described. An example method includes receiving data from sensors of a device for an estimation of movement of the device, determining measurements from the data that are collected within a threshold time of each other or collected from locations within a threshold distance of each other, determining a magnitude of a weight to apply to the determined measurements based on a number of measurements in the determined measurements, and applying, by a processor, the weight to the determined measurements to reduce influence of the determined measurements on the estimation of movement of the device.
1 . A method comprising:
receiving data from sensors of a device, wherein the data are usable to estimate movement of the device;
determining measurements from the data that are collected within a threshold time of each other or collected from locations within a threshold distance of each other;
determining a magnitude of a weight to apply to the determined measurements based on a number of measurements in the determined measurements; and
applying, by one or more processors, the weight to the determined measurements to reduce influence of the determined measurements on an estimation of movement of the device.
2 . The method of claim 1 , wherein applying the weight to the determined measurements comprises down-weighting the determined measurements.
3 . The method of claim 1 , wherein the data from sensors of the device comprises GPS data, and wherein consecutive GPS measurements are about the same, and wherein applying the weight comprises applying the weight to the consecutive GPS measurements to down-weight the consecutive GPS measurements based on a number of the consecutive GPS measurements.
4 . The method of claim 1 , wherein receiving data from sensors of a device comprises receiving data from one or more sensors including an accelerometer, a gyroscope, a WiFi transceiver, and a GPS module.
5 . The method of claim 1 , wherein the threshold time is within about 20 seconds.
6 . The method of claim 1 , wherein the threshold distance is within about five meters.
7 . The method of claim 1 , further comprising applying the weight to measurements from the data that are collected within the threshold time of each other and collected from locations within the threshold distance of each other.
8 . The method of claim 1 , further comprising:
determining given measurements from the data that are substantially the same; and
applying a given weight to the determined given measurements so as to consider the determined given measurements as a single measurement for purposes of the estimation of movement of the device.
9 . The method of claim 1 , further comprising determining the estimation of movement of the device based on the weighted determined measurements.
10 . The method of claim 1 , further comprising:
determining an amount of correlation of the determined measurements, wherein the amount of correlation is related to the time between collection of the determined measurements or the distance between locations of collection of the determined measurements; and
applying the weight to the determined measurements based on the amount of correlation of the determined measurements so as to increase the weight based on a higher correlation.
11 . The method of claim 1 , further comprising:
determining given measurements from the data that are consecutively output from the sensors of the device within the threshold time of each other; and
determining a given magnitude of the weight to apply to the given consecutive measurements based on a number of measurements in the given consecutive measurements; and
applying the weight to the given consecutive measurements to reduce influence of the given measurements on the estimation of movement of the device.
12 . A non-transitory computer readable medium having stored therein instructions, that when executed by a computing device, cause the computing device to perform functions comprising:
receiving data from sensors of a device, wherein the data are usable to estimate movement of the device;
determining measurements from the data that are collected within a threshold time of each other or collected from locations within a threshold distance of each other;
determining a magnitude of a weight to apply to the determined measurements based on a number of measurements in the determined measurements; and
applying the weight to the determined measurements to reduce influence of the determined measurements on an estimation of movement of the device.
13 . The non-transitory computer readable medium of claim 12 , wherein applying the weight to the determined measurements comprises down-weighting the determined measurements.
14 . The non-transitory computer readable medium of claim 12 , wherein the functions further comprise:
determining given measurements from the data that are substantially the same; and
applying a given weight to the determined given measurements so as to consider the determined given measurements as a single measurement for purposes of the estimation of movement of the device.
15 . The non-transitory computer readable medium of claim 12 , wherein the functions further comprise:
determining an amount of correlation of the determined measurements, wherein the amount of correlation is related to the time between collection of the determined measurements or the distance between locations of collection of the determined measurements; and
applying the weight to the determined measurements based on the amount of correlation of the determined measurements so as to increase the weight based on a higher correlation.
16 . The non-transitory computer readable medium of claim 12 , wherein the functions further comprise:
determining given measurements from the data that are consecutively output from the sensors of the device within the threshold time of each other; and
determining a given magnitude of the weight to apply to the given consecutive measurements based on a number of measurements in the given consecutive measurements; and
applying the weight to the given consecutive measurements to reduce influence of the given measurements on the estimation of movement of the device.
17 . A system comprising:
one or more processors;
data storage configured to store instructions that, when executed by the one or more processors, cause the system to perform functions comprising:
receiving data from sensors of a device, wherein the data are usable to estimate movement of the device;
determining measurements from the data that are collected within a threshold time of each other or collected from locations within a threshold distance of each other;
determining a magnitude of a weight to apply to the determined measurements based on a number of measurements in the determined measurements; and
applying the weight to the determined measurements to reduce influence of the determined measurements on an estimation of movement of the device.
18 . The system of claim 17 , wherein the data from sensors of the device comprises GPS data, and wherein consecutive GPS measurements are about the same, and wherein applying the weight comprises applying the weight to the consecutive GPS measurements to down-weight the consecutive GPS measurements based on a number of the consecutive GPS measurement.
19 . The system of claim 17 , wherein receiving data from sensors of a device comprises receiving data from one or more sensors including an accelerometer, a gyroscope, a WiFi transceiver, and a GPS module.
20 . The system of claim 17 , wherein the functions further comprise:
determining given measurements from the data that are substantially the same; and
applying a given weight to the determined given measurements so as to consider the determined given measurements as a single measurement for purposes of the estimation of movement of the device.