Avatar

Sasan Jafarnejad

Researcher | data scientist

SECAN-Lab

University of Luxembourg

Biography

I received my Ph.D. from University of Luxembourg where I worked on driver modeling and machine learning at the SECAN-Lab of the SnT. In particular my research topic was the application of machine learning for driver identification and distraction detection. For my MSc thesis I worked on Security of Automotive Embedded Systems and Connected Vehicles. My undergraduate studies are in Electrical and Communication engineering.

Interests

  • Sequence Modeling
  • Natural Language Processing
  • Driver Behavior modeling
  • Projects close to the metal!

Education

  • Ph.D. in Computer Science, 2020

    University of Luxembourg

  • M.Sc. in Computer Science, 2015

    University of Luxembourg

  • B.Sc. Information and Communication Technology, 2012

    Kashani University

Recent Posts

What is driver identification?

The prevalence of smartphones have changed our lives, perhaps mostly for better but in a few cases they have caused harm. Gig-economies …

A trick for pandas groupby!

I often work with sensor measurements such as those from car CAN-bus. These measurements are often collected over multiple sessions, …

NGINX in docker

How to build a NGINX docker image with GeoIP2 module

Projects

*

Driver Identification

Driver Identification is the main topic of my Ph.D., the main idea is to identify drivers using their driving patterns. Click on the …

Car hacking

For my Masters’ Thesis I hacked! a Renault Twizy and managed to some extent control it remotely, I also did some interesting …

Vajehyab

Vajehyab is an initiative to preserve and promote Persian (Farsi) language through providing several tools to users so they can easily …

Sharjeman

A Fintech startup operating in Tehran, Sharjeman’s mission is to facilitate maintenance of the residential and commercial …

Publications

Triplet Loss and its Applications to Driver Identification and Verification [WIP]

A major issue in driver identification is lack of enough data from the target group of drivers. In this work I use Triplet loss to …

Driver Identification only using GPS trajectories: A Deep Learning Approach

This is one of my latest works in which I apply deep learning to problem of driver identification using GPS data collected from …

Revisiting Gaussian Mixture Models for Driver Identification

The increasing penetration of connected vehicles nowadays has enabled driving data collection at a very large scale. Many telematics …

Non-intrusive Distraction Detection Based on Car Sensor Data

Nowadays Internet-enabled phones have become ubiquitous, and we all witness the flood of information that often arrives with a …

Characterizing Driving Behaviors Through a Car Simulation Platform

Human mobility has opened up to many themes in recent years. Human behavior and how a driver might react to certain situations, whether …

Towards a Real-Time Driver Identification Mechanism Based on Driving Sensing Data

The growing penetration of telematics systems and connectivity in vehicles has enabled a large variety of possible value-added services …

An Open Dataset for Human Activity Analysis usingSmart Devices

The study of human mobility and activities has opened up to an incredible number ofstudies in the past, most of which included the use …

A car hacking experiment: When connectivity meets vulnerability

Interconnected vehicles are a growing commodity providing remote access to onboard systems for monitoring and controlling the state of …

Evaluating the Security of Connected Vehicles

Interconnected vehicles are a growing commodity providing remote access to on-board systems for monitoring and controlling the state of …

Contact