System and method for vehicle sensing and analysis
A method for monitoring vehicle motion using a mobile device associated with a user including collecting activity data at a mobile device associated with the user; determining a user activity state based on the activity data; determining motion data collection parameters associated with an operating state of the mobile device, based on the user activity state; and collecting motion data at the mobile device based on the motion data collection parameters.
1 . A method for selectively collecting information at a mobile device, the method comprising:
with a set of sensors onboard the mobile device, collecting a 1 st set of Global Positioning System (GPS) data;
based on the 1 st set of GPS data, detecting a wake event associated with the mobile device by evaluating a 1 st portion of a tree-based model;
increasing a rate of power consumption of the mobile device in response to detecting the wake event;
collecting a 2 nd set of GPS data in association with the increased rate of power consumption;
evaluating a 2 nd portion of the tree-based model based on the 2 nd set of GPS data;
calculating a set of trip parameters in response to evaluation of the 2 nd portion of the tree-based model, the set of trip parameters comprising a distance parameter;
updating a score of a user associated with the mobile device based on the set of trip parameters;
detecting an end event of a trip associated with the set of trip parameters; and
decreasing a rate of power consumption of the mobile device in response to detecting the end event.
2 . The method of claim 1 , wherein the tree-based model is trained with machine learning.
3 . The method of claim 2 , wherein the tree-based model comprises a set of nodes, wherein at least a portion of the set of nodes is each associated with a condition evaluated based on the first set of GPS data.
4 . The method of claim 3 , wherein the 1 st portion comprises a 1 st subset of the set of nodes and wherein the 2 nd portion comprises a 2 nd subset of the set of nodes.
5 . The method of claim 3 , wherein the set of nodes is associated with a variety of processing resource costs.
6 . The method of claim 1 , wherein evaluating the 2 nd portion of the tree-based model comprises calculating a difference between two sequential locations from the 2 nd set of GPS data and comparing the difference with a predetermined threshold.
7 . The method of claim 6 , wherein in an event that the difference does not exceed the predetermined threshold, the method further comprises checking for a 2 nd wake event.
8 . The method of claim 1 , wherein the first set of GPS data is collected at a first frequency and the second set of GPS data is collected at a second frequency, the second frequency separate and distinct from the first frequency.
9 . The method of claim 8 , wherein the second frequency has a larger value than the first frequency.
10 . The method of claim 1 , wherein increasing the rate of power consumption of the mobile device in response to detecting the wake event is configured to minimize a false positive trip determination.
11 . A system for selectively collecting information at a mobile device, the system comprising:
a software development kit (SDK) in communication with a set of sensors onboard the mobile device and a set of client applications executing on the mobile device, wherein the SDK:
collects a 1 st set of Global Positioning System (GPS) data from the set of sensors;
based on the 1 st set of GPS data, detects a wake event associated with the mobile device by evaluating a 1 st portion of a tree-based model;
triggers an increased rate of power consumption of the mobile device in response to detecting the wake event;
collects a 2 nd set of GPS data in association with the increased rate of power consumption;
evaluates a 2 nd portion of the tree-based model based on the 2 nd set of GPS data;
calculates a set of trip parameters in response to evaluation of the 2 nd portion of the tree-based model, the set of trip parameters comprising a distance parameter;
updates a score of a user associated with the mobile device based on the set of trip parameters;
detects an end event of a trip associated with the set of trip parameters; and
decreases a rate of power consumption of the mobile device in response to detecting the end event.
12 . The system of claim 11 , wherein the increased rate of power consumption is configured to minimize a false positive trip determination.
13 . The system of claim 11 , wherein the tree-based model is trained with machine learning.
14 . The system of claim 13 , wherein the tree-based model comprises a set of nodes, wherein at least a portion of the set of nodes is each associated with a condition evaluated based on the first set of GPS data.
15 . The system of claim 14 , wherein the 1 st portion comprises a 1 st subset of the set of nodes and wherein the 2 nd portion comprises a 2 nd subset of the set of nodes.
16 . The system of claim 14 , wherein the set of nodes is associated with a variety of processing resource costs.
17 . The system of claim 11 , wherein evaluating the 2 nd portion of the tree-based model comprises calculating a difference between two sequential locations from the 2 nd set of GPS data and comparing the difference with a predetermined threshold.
18 . The system of claim 17 , wherein in an event that the difference does not exceed the predetermined threshold, the SDK further checks for a 2 nd wake event.
19 . The system of claim 11 , wherein the first set of GPS data is collected at a first frequency and the second set of GPS data is collected at a second frequency, the second frequency separate and distinct from the first frequency.
20 . The system of claim 19 , wherein the second frequency has a larger value than the first frequency.