Abstract: A method for providing proactive driving alerts includes determining a road segment of interest, receiving GPS data and contextual data, and identifying a triggering condition in a vicinity of the segment of interest. The method also includes determining an applicability of the triggering condition to the segment of interest, retrieving an alert threshold corresponding to the triggering condition, and obtaining an action factor correlating to a user's driving behavior. The method further includes determining whether the action factor exceeds the alert threshold and providing a proactive alert related to the triggering condition to the user.

Abstract: A method includes receiving, from a mobile device disposed within a vehicle, a set of sensor measurements collected from an accelerometer of the mobile device during a first time period and converting the set of sensor measurements into a frequency domain. The method also includes filtering the set of sensor measurements to eliminate high frequency sensor measurements and defining a set of contiguous windows based on a remaining sensor measurements in the set of sensor measurements. Each contiguous window of the set of contiguous windows represents a contiguous portion of the remaining sensor measurements. The method further includes generating, for each contiguous window of the set of contiguous windows, a set of features by resampling the remaining sensor measurements of the contiguous window at one or more predefined frequencies and generating an estimated speed of the vehicle during the first time period using the set of features.

Abstract: Embodiments of the present invention provide systems and methods for combining sensor data to measure vehicle movement. Embodiments may collect vehicle and driving data using sensors of a mobile device of a user, such as a location determination sensor and a movement determination sensor. In some embodiments, the data from the sensors may be combined to more accurately estimate vehicle movement, such as vehicle acceleration.

Abstract: Apparatuses and methods for predicting a crash using estimated vehicle speed. A set of sensor measurements are received from a mobile device disposed within a vehicle. A set of contiguous windows based on the sensor measurements may be defined. Each contiguous window represents a contiguous portion of the sensor measurements. A set of sensor measurements may be defined for each contiguous window. A trained neural network may execute, using the set of features, to generate one or more speed predictions. A vehicle crash prediction may be generated using the speed prediction. The vehicle crash prediction may then be transmitted to a remote device.

Abstract: According to some embodiments of the invention, movement measurements may be obtained from a movement sensor (e.g., an accelerometer) of a mobile device in a vehicle. In addition, location measurements may be obtained from a location sensor (e.g., a GPS) of the mobile device in the vehicle. The movement measurements and the location measurements may be cross-referenced to each other to remove erroneous measurements, such as physically impossible measurements. The remaining measurements may be used to draw conclusions about the movements or locations, such as to identify a movement event (e.g., a braking event, an acceleration event, or the like).

Abstract: A method of providing a quaternion for reference frame transformation includes (a) initiating a driving event in a vehicle having a vehicle reference frame and (b) receiving, from a mobile device, mobile device data associated with a time stamp. The method also includes (c) computing a quaternion operable to transform the mobile device data to the vehicle reference frame and (d) determining if the driving event is complete. The method further includes incrementing the time stamp and iterating steps (a), (b), (c), and (d) if the driving event is not complete and providing the quaternion for reference frame transformation if the driving event is complete.

Abstract: A system for pattern-based identification of a driver of a vehicle includes a mobile device; and a server configured to communicate with the mobile device. The mobile device collects movement information during a driving trip via one or more sensors in the mobile device, and communicates the collected movement information to a server. The server analyzes the movement information via a classifier, identifies driving features for the driver based at least in part on the analysis of the movement information, creates an identification model for the driver based on identified driving features, and stores the identification model.

Abstract: Techniques are disclosed for virtual tagging of vehicles that include generating an association between a user of a mobile device and the mobile device. The techniques include receiving a first set of measurements from one or more sensors of the mobile device while the mobile device is positioned in a first vehicle during a trip and training a machine-learning model using the first set of measurements. The techniques further include receiving a second set of measurements from the one or more sensors of the mobile device and determining, by executing the machine-learning model using the third set of measurements, that the mobile device is positioned in the first vehicle or a second vehicle.

Abstract: A method of determining a mode of transportation includes: collecting trip data utilizing sensors included in a mobile device during a trip; receiving contextual data related to a transportation system; forming one or more segments using the collected trip data; determining that at least one of the one or more segments is not associated with an airplane; determining that the at least one of the one or more segments is not associated with a train; determining that the at least one of the one or more segments is not associated with a bus; marking the at least one of the one or more segments as associated with a car.

Abstract: A method of orienting a mobile device to a vehicle includes determining an orientation of a gravity vector and aligning a first axis of the mobile device with respect to the gravity vector. The method also includes determining an orientation of a magnetic direction and aligning a second axis of the mobile device with respect to the magnetic direction. The method further includes determining a direction of travel for the vehicle and orienting the mobile device to the vehicle.

Abstract: Embodiments of the present invention provide systems and methods for combining sensor data to measure vehicle movement. Embodiments may collect vehicle and driving data using sensors of a mobile device of a user, such as a location determination sensor and a movement determination sensor. In some embodiments, the data from the sensors may be combined to more accurately estimate vehicle movement, such as vehicle acceleration.

Abstract: A system for pattern-based identification of a driver of a vehicle includes a mobile device; and a server configured to communicate with the mobile device. The mobile device collects movement information during a driving trip via one or more sensors in the mobile device, and communicates the collected movement information to a server. The server analyzes the movement information via a classifier, identifies driving features for the driver based at least in part on the analysis of the movement information, creates an identification model for the driver based on identified driving features, and stores the identification model.

Abstract: Apparatuses and methods for predicting a crash using estimated vehicle speed. A set of sensor measurements are received from a mobile device disposed within a vehicle. A set of contiguous windows based on the sensor measurements may be defined. Each contiguous window represents a contiguous portion of the sensor measurements. A set of sensor measurements may be defined for each contiguous window. A trained neural network may execute, using the set of features, to generate one or more speed predictions. A vehicle crash prediction may be generated using the speed prediction. The vehicle crash prediction may then be transmitted to a remote device.

Abstract: Embodiments of the present invention provide systems and methods for combining sensor data to measure vehicle movement. Embodiments may collect vehicle and driving data using sensors of a mobile device of a user, such as a location determination sensor and a movement determination sensor. In some embodiments, the data from the sensors may be combined to more accurately estimate vehicle movement, such as vehicle acceleration.

Abstract: A system for pattern-based identification of a driver of a vehicle includes a mobile device; and a server configured to communicate with the mobile device. The mobile device collects movement information during a driving trip via one or more sensors in the mobile device, and communicates the collected movement information to a server. The server analyzes the movement information via a classifier, identifies driving features for the driver based at least in part on the analysis of the movement information, creates an identification model for the driver based on identified driving features, and stores the identification model.

Abstract: According to some embodiments of the invention, movement measurements may be obtained from a movement sensor (e.g., an accelerometer) of a mobile device in a vehicle. In addition, location measurements may be obtained from a location sensor (e.g., a GPS) of the mobile device in the vehicle. The movement measurements and the location measurements may be cross-referenced to each other to remove erroneous measurements, such as physically impossible measurements. The remaining measurements may be used to draw conclusions about the movements or locations, such as to identify a movement event (e.g., a braking event, an acceleration event, or the like).

Abstract: According to some embodiments of the invention, movement measurements may be obtained from a movement sensor (e.g., an accelerometer) of a mobile device in a vehicle. In addition, location measurements may be obtained from a location sensor (e.g., a GPS) of the mobile device in the vehicle. The movement measurements and the location measurements may be cross-referenced to each other to remove erroneous measurements, such as physically impossible measurements. The remaining measurements may be used to draw conclusions about the movements or locations, such as to identify a movement event (e.g., a braking event, an acceleration event, or the like).

Abstract: Embodiments of the present invention provide systems and methods for combining sensor data to measure vehicle movement. Embodiments may collect vehicle and driving data using sensors of a mobile device of a user, such as a location determination sensor and a movement determination sensor. In some embodiments, the data from the sensors may be combined to more accurately estimate vehicle movement, such as vehicle acceleration.

Abstract: A system for pattern-based identification of a driver of a vehicle includes a mobile device; and a server configured to communicate with the mobile device. The mobile device collects movement information during a driving trip via one or more sensors in the mobile device, and communicates the collected movement information to a server. The server analyzes the movement information via a classifier, identifies driving features for the driver based at least in part on the analysis of the movement information, creates an identification model for the driver based on identified driving features, and stores the identification model.

Abstract: A method of determining a mode of transportation includes: collecting trip data utilizing sensors included in a mobile device during a trip; receiving contextual data related to a transportation system; forming one or more segments using the collected trip data; determining that at least one of the one or more segments is not associated with an airplane; determining that the at least one of the one or more segments is not associated with a train; determining that the at least one of the one or more segments is not associated with a bus; marking the at least one of the one or more segments as associated with a car.