Msc Thesis : Insight into driver behavior and usage of ADAS functions

In today's automotive landscape, ensuring road safety is of utmost importance. Advanced Driver Assistance Systems (ADAS) serve as a crucial safeguard against accidents, yet some drivers opt to disable these functions. This thesis aims to investigate the underlying reasons behind this behavior, delving into the relationship between factors such as location, driver behavior, and the status of ADAS functions. By analyzing a comprehensive dataset, this research aims to uncover patterns and correlations that illuminate the decision-making process of drivers concerning ADAS deactivation.

Objectives:

• Utilize Statistical Methods and Machine Learning Techniques:
  Employ advanced statistical methods and machine learning techniques to discover correlations between driver behavior related signals, location, etc., and ADAS function deactivation.
  Explore the interplay between location-based data, signal patterns, and occurrences of function deactivation, utilizing machine learning models.

• Develop Predictive Models: If within the timeframe, develop predictive models using machine learning algorithms. These models will aim to forecast instances where drivers might deactivate ADAS functions, enhancing our ability to anticipate and prevent such occurrences.

Aim:

This research aims to explore the factors influencing drivers' decision to deactivate Advanced Driver Assistance Systems (ADAS) functions, employing data analytics and machine learning techniques. The focus is on understanding driver behavior and analyzing signals from vehicles. By unraveling these complexities, this study aims to offer valuable insights that can enhance the effectiveness and user acceptance of ADAS technologies.

This thesis proposal is ideally suited for one or two students possessing a strong background in machine learning and proficiency in Python. Prior experience with Pyspark is meritorious.