Master of Science
Prof. Steven Beauchemin
Future automobiles are going to experience a fundamental evolution by installing semiotic predictor driver assistance equipment. To meet these equipment, Continuous driving-behavioral data have to be observed and processed to construct powerful predictive driving assistants. In this thesis, we focus on raw driving-behavioral data and present a prediction method which is able to prognosticate the next driving-behavioral state. This method has been constructed based on the unsupervised double articulation analyzer method (DAA) which is able to segment meaningless continuous driving-behavioral data into a meaningful sequence of driving situations. Thereafter, our novel model by mining the sequences of driving situations can define and process the most influential data parameters. After that, our model by utilizing these parameters can interpret the dynamic driving data and predict the next state of the determined vehicle. Proficiency of this model has been evaluated using over three terabytes driving behavioral data which include 16 drivers’ data, totally for more than 17 hours and over 456 Km.
Hesabgar, Maedeh, "Advanced Driving Assistance Prediction Systems" (2016). Electronic Thesis and Dissertation Repository. 3695.