PROJECT TITLE :
Detection of Dangerous Cornering in GNSS-Data-Driven Insurance Telematics
We have a tendency to propose a framework for the detection of dangerous vehicle cornering events, primarily based on statistics related to the no-sliding and no-rollover conditions. The input variables are estimated using an unscented Kalman filter applied to global navigation satellite system (GNSS) measurements of position, speed, and bearing. The resulting take a look at statistic is evaluated in a very field study where 3 smartphones are used as measurement probes. A general framework for performance evaluation and estimator calibration is presented as relying on a generic loss operate. Furthermore, we have a tendency to introduce loss functions designed for applications getting to either minimize the amount of missed detections and false alarms, or to estimate the chance level in every cornering event. Finally, the performance characteristics of the estimator are presented as relying on the detection threshold, as well as on design parameters describing the driving behavior. Since the estimation solely uses GNSS measurements, the framework is particularly well suited to smartphone-based insurance telematics applications, reaching to avoid the logistic and monetary costs associated with, e.g., on-board-diagnostics or black-box dependent solutions. The design of the estimation algorithm permits for immediate feedback to be given to the motive force and, hence, supports the inclusion of real-time worth-added services in usage-based insurance programs.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here