| CPC G07C 5/0841 (2013.01) [G06N 20/10 (2019.01); G07C 5/0808 (2013.01)] | 19 Claims |

|
1. A method comprising:
collecting vehicle data associated with a vehicle from one or more sensors based on a determination that a vehicular trip has been initiated;
determining one or more trip segments for at least a portion of the vehicular trip;
determining, using the vehicle data, one or more time domain features and one or more frequency domain features for each trip segment of the one or more trip segments;
generating a first feature vector using the one or more time domain features and the one or more frequency domain features;
after determining that a quantity of features in the first feature vector exceeds a reduced quantity of features that is sufficient for predicting a vehicle mode, generating a second feature vector that comprises the reduced quantity of features, wherein the features in the second feature vector are determined by applying principal component analysis to the features of the first feature vector;
determining an accuracy measure based on the second feature vector;
predicting a mode for the vehicle based on the accuracy measure, the mode for the vehicle includes a type of vehicle; and
ceasing the collection of vehicle data associated with the vehicle from the one or more sensors, and while the vehicle is still traveling, upon a determination that the mode can be predicted.
|