System and method for determining a vehicle classification from gps tracks

Abstract

A method and system for classifying a vehicle based on low frequency GPS tracks. The method and system comprise retrieving a low frequency GPS track having a sampling interval of at least 20 seconds; deriving additional data from the low frequency GPS track, the additional data including interval speed and instantaneous acceleration of the vehicle; extracting a plurality of data sets from the low frequency GPS track and the additional data; generating a plurality of features from the extracted data sets; and providing the plurality of generated features to a classifier that classifies the vehicle into a predetermined class.

What is claimed is: 
     
         1 . A method for classifying a vehicle, the method comprising:
 generating a plurality of features associated with a low frequency Global Positioning System (GPS) track;   selecting an optimal feature set for classifying the vehicle to train a machine learning model for use by a classifier,
 selecting the optimal feature set comprising:
 iteratively removing a feature of a vehicle classification performance from the plurality of features associated with the low frequency GPS track and a plurality of empirical features to create a feature set, and 
 iteratively decreasing the feature set by a predetermined amount at each iteration by discarding one or more features whose removal yields to an area under a curve (AUC) below a threshold level associated with classifying results from the low frequency GPS track; and 
 
   providing the optimal feature set, using the machine learning model, to classify the vehicle into a predetermined class of vehicles based on the low frequency GPS track.   
     
     
         2 . The method of  claim 1 , wherein the low frequency GPS track has sample intervals of at least 20 seconds. 
     
     
         3 . The method of  claim 1 , wherein generating the plurality of features associated with the low frequency GPS track comprises:
 deriving an interval speed from the low frequency GPS track,
 wherein the interval speed is based on a distance between two consecutive data points and their corresponding time stamps; and 
   generating the plurality of features using the derived interval speed.   
     
     
         4 . The method of  claim 1 , wherein generating the plurality of features associated with the low frequency GPS track comprises:
 deriving an interval acceleration from the low frequency GPS track,
 wherein the interval acceleration is based on a difference between two consecutive interval speeds and their corresponding time stamps; and 
   generating the plurality of features using the derived interval acceleration.   
     
     
         5 . The method of  claim 1 , wherein generating the plurality of features associated with the low frequency GPS track comprises:
 deriving an instantaneous acceleration from the low frequency GPS track,
 wherein the instantaneous acceleration is based on a difference between two consecutive instantaneous speed and their corresponding time stamps; and 
   generating the plurality of features using the derived instantaneous acceleration.   
     
     
         6 . The method of  claim 1 , wherein the plurality of empirical features include:
 a total distance of the low frequency GPS track, and   road types of routes covered by the low frequency GPS track.   
     
     
         7 . The method of  claim 1 , further comprising:
 establishing a kernel using the AUC; and   providing the kernel to the classifier to classify the vehicle into the predetermined class of vehicles based on the low frequency GPS track.   
     
     
         8 . A non-transitory storage medium storing instructions, the instructions comprising:
 one or more instructions which, when executed by a processor of a device, cause the processor to:
 generate a plurality of features associated with a low frequency Global Positioning System (GPS) track; 
 select an optimal feature set for classifying a vehicle to train a machine learning model for use by a classifier,
 select the optimal feature set by:
 iteratively removing a feature of a vehicle classification performance from the plurality of features associated with the low frequency GPS track and a plurality of empirical features to create a feature set, and 
 iteratively decreasing the feature set by a predetermined amount at each iteration by discarding one or more features whose removal yields to an area under a curve (AUC) below a threshold level associated with classifying results from the low frequency GPS track; and 
 
 
 provide the optimal feature set, using the machine learning model, to classify the vehicle into a predetermined class of vehicles based on the low frequency GPS track. 
   
     
     
         9 . The non-transitory storage medium of  claim 8 , wherein the low frequency GPS track has sample intervals of at least 20 seconds. 
     
     
         10 . The non-transitory storage medium of  claim 8 , wherein the one or more instructions, that cause the processor to generate the plurality of features associated with the low frequency GPS track, cause the processor to:
 derive an interval speed from the low frequency GPS track,
 wherein the interval speed is based on a distance between two consecutive data points and their corresponding time stamps; and 
   generate the plurality of features using the derived interval speed.   
     
     
         11 . The non-transitory storage medium of  claim 8 , wherein the one or more instructions, that cause the processor to generate the plurality of features associated with the low frequency GPS track, cause the processor to:
 derive an interval acceleration from the low frequency GPS track,
 wherein the interval acceleration is based on a difference between two consecutive interval speeds and their corresponding time stamps; and 
   generate the plurality of features using the derived interval acceleration.   
     
     
         12 . The non-transitory storage medium of  claim 8 , wherein the one or more instructions, that cause the processor to generate the plurality of features associated with the low frequency GPS track, cause the processor to:
 derive an instantaneous acceleration from the low frequency GPS track,
 wherein the instantaneous acceleration is based on a difference between two consecutive instantaneous speed and their corresponding time stamps; and 
   generate the plurality of features using the derived instantaneous acceleration.   
     
     
         13 . The non-transitory storage medium of  claim 8 , wherein the plurality of empirical features include:
 a total distance of the low frequency GPS track, and   road types of routes covered by the low frequency GPS track.   
     
     
         14 . The non-transitory storage medium of  claim 8 , wherein the instructions when executed by the processor, further cause the processor to:
 establish a kernel using the AUC; and   provide the kernel to the classifier to classify the vehicle into the predetermined class of vehicles based on the low frequency GPS track.   
     
     
         15 . A device comprising:
 one or more processors configured to:
 generate a plurality of features associated with a low frequency Global Positioning System (GPS) track; 
 select an optimal feature set for classifying a vehicle to train a machine learning model for use by a classifier,
 select the optimal feature set by:
 iteratively removing a feature of a vehicle classification performance from the plurality of features associated with the low frequency GPS track and a plurality of empirical features to create a feature set, and 
 iteratively decreasing the feature set by a predetermined amount at each iteration by discarding one or more features whose removal yields to an area under a curve (AUC) below a threshold level associated with classifying results from the low frequency GPS track; and 
 
 
 provide the optimal feature set, using the machine learning model, to classify the vehicle into a predetermined class of vehicles based on the low frequency GPS track. 
   
     
     
         16 . The device of  claim 15 , wherein the low frequency GPS track has sample intervals of at least 20 seconds. 
     
     
         17 . The device of  claim 15 , wherein the one or more processors, when generating the plurality of features associated with the low frequency GPS track, cause the processor to:
 derive an interval speed from the low frequency GPS track,
 wherein the interval speed is based on a distance between two consecutive data points and their corresponding time stamps; and 
   generate the plurality of features using the derived interval speed.   
     
     
         18 . The device of  claim 15 , wherein the one or more processors, when generating the plurality of features associated with the low frequency GPS track, cause the processor to:
 derive an interval acceleration from the low frequency GPS track,
 wherein the interval acceleration is based on a difference between two consecutive interval speeds and their corresponding time stamps; and 
   generate the plurality of features using the derived interval acceleration.   
     
     
         19 . The device of  claim 15 , wherein the one or more processors, when generating the plurality of features associated with the low frequency GPS track, cause the processor to:
 derive an instantaneous acceleration from the low frequency GPS track,
 wherein the instantaneous acceleration is based on a difference between two consecutive instantaneous speed and their corresponding time stamps; and 
   generate the plurality of features using the derived instantaneous acceleration.   
     
     
         20 . The device of  claim 15 , wherein the one or more processors are further configured to:
 establish a kernel using the AUC; and   provide the kernel to the classifier to classify the vehicle into the predetermined class of vehicles based on the low frequency GPS track.