Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

A VISSIM based ADAS simulation platform to complement the UKCITE real world connected vehicle test environment

Published in Conference: 25th ITS World Congress. At: Copenhagen, Denmark, 2018

This explores the integration of advanced driver assistance systems (ADAS) in real-world testing environments. A key component discussed is the Cooperative Adaptive Cruise Control (CACC) which enables vehicles in a platoon to maintain appropriate spacing and speed, using vehicle-to-vehicle communication to adjust to perturbations quickly. The paper also examines the impact of Emergency Electronic Brake Light (EEBL) systems which alert drivers to hard braking incidents ahead, even when the braking vehicle is not directly in sight. These systems are tested on a VISSIM-based simulation platform, which provides a detailed microscopic traffic simulation, integrating MATLAB, Python, and C++ for robust testing of ADAS functionalities under varied driving conditions.

Recommended citation: Esugo, Martin & Haas, Olivier & Agbaje, Oluwaleke & Antoine, Stephan & Matheo, Girbal. (2018). "A VISSIM based ADAS simulation platform to complement the UKCITE real world connected vehicle test environment." Conference: 25th ITS World Congress http://komehz.github.io/files/2018-09-17-paper-001.pdf

Short-Term Traffic Flow Forecasting A wide and deep approach with periodic feature selection

Published in TechRxiv, 2022

This paper presents a novel approach to traffic flow forecasting that utilizes a hybrid wide and deep learning architecture. This model integrates both spatial-temporal and periodic features, aiming to enhance the predictive accuracy of traffic forecasting systems. The wide component of the model focuses on capturing periodic features, particularly the weekly patterns, shown to be most impactful, while the deep component, built on a conv-LSTM architecture, extracts spatial-temporal features. The effectiveness of this model is demonstrated through extensive experiments that compare its performance against traditional models, showing notable improvements in forecasting accuracy.

Recommended citation: Martin Esugo, Qian Lu, Olivier Haas. "Short-Term Traffic Flow Forecasting A wide and deep approach with periodic feature selection." TechRxiv. May 17, 2022 http://komehz.github.io/files/2022-05-17-paper-002.pdf