Eva Michelaraki has successfully defended her PhD dissertation titled: Improving driver safety tolerance zone through holistic analysis of road, vehicle and behavioural risk factors, under the supervision of NTUA Prof. George Yannis. Data from 190 drivers who participated in a large on-road and simulator driving experiment were exploited. An innovative methodology, consisting of both statistical analyses (Generalized Linear Models, Structural Equation Models) and machine learning techniques (Decision Trees, k-Nearest Neighbors, Neural Networks and Random Forests) was implemented. Results indicated that RF models outperformed the DT and kNN models across all metrics, making them the most effective for predicting speeding and headway, with overall accuracy up to 90%. It was also revealed that task complexity was positively correlated with risk, while coping capacity was negatively correlated with risk, indicating that drivers with higher coping capacity are better equipped to handle challenging driving situations.
Archives
Tag cloud
accident severity
alcohol
buses
campaigns
cell phone
cerebral diseases
children
culture
cyclists
data analysis
distraction
driving simulator
education & training
enforcement
equipment
esafety
fatigue
helmet
impact assessment
international comparisons
junctions
lighting
lorries
measures assessment
mobility and transport
mopeds
motorcyclists
motorways
naturalistic driving
older drivers
pedestrians
road fatalities
road interventions
road safety data
rural roads
safety assessment
safety equipment
seat belt
speed
strategy
traffic
urban safety
weather
work related safety
young drivers