Road transport is known to be the most dangerous of all transport modes and poses a major societal challenge for EU. It has been claimed that 90% of road-traffic crashes are caused by driver error, being unsafe behaviour a significant factor in traffic accidents. Improving road safety means understanding the individual and collective behaviour of actors involved (drivers, two wheelers, pedestrians) and their interaction between themselves and safety-related systems and services. The goal of SIMUSAFE (SIMUlator of Behavioural Aspects for SAFEr Transport) following the FESTA-V model methodology is to develop realistic multi-agent behavioural models in a transit environment where researchers will be able to monitor and introduce changes in every aspect , gathering data not available in real world conditions.
Driving simulators of several vehicles (cars, motorcycles, bicycles) and Virtual Reality (for pedestrians) will be used to simulate test environments. This will also enable the evaluation of scenarios which are not possible even with naturalistic driving (dangerous conditions, multiple monitored actors in the same scene, under influence of substances). Data collected from simulations will be correlated with naturalistic driving tests, such that the simulation and model aspects are the closest
possible to real world data. From the developed model and collected data, impacting factors causing an event (crash, nearcollision,infractions) from the environment and road users will be identified and quantified. Such knowledge will be the base for the development of more effective and pro-active measures for the prevention and mitigation of such factors, with subsequent impact in the safety devices market, regulations and driver education.
90 test participants required: click
|First Name||Last Name||Title|
|Mobyen Uddin||Ahmed||Associate Professor|
|Mir Riyanul||Islam||Doctoral student|
|Gunnar||Widforss||Senior Project Manager|
|Md Aquif||Rahman||Research Assistant|
Convolutional Neural Network for Driving Manoeuvre Identification based on Inertial Measurement Unit (IMU) and Global Positioning System (GPS) (Sep 2020) Mobyen Uddin Ahmed, Shahina Begum Frontiers in Sustainable Cities-Governance and Cities (Advances in Road Safety Planning) (Frontiers)
Towards Intelligent Data Analytics: A Case Study in Driver Cognitive Load Classification (Aug 2020) Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum Brain Sciences (Special Issue: Brain Plasticity, Cognitive Training and Mental States Assessment) (Brain Sci)
A Novel Mutual Information based Feature Set for Drivers’ Mental Workload Evaluation using Machine Learning (Aug 2020) Mir Riyanul Islam, Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum, Pietro Aricò , Gianluca Borghini , Gianluca Di Flumeri Brain Sciences (Special Issue: Brain Plasticity, Cognitive Training and Mental States Assessment) (Brain Sci)
Reaction Time Variability Association with Safe Driving Indexes (Jun 2020) Mohammed Ghaith Altarabichi, Mobyen Uddin Ahmed, Maria Rita Ciceri , Stefania Balzarotti , Federica Biassoni , Debora Lombardi , Paolo Perego Transport Research Arena (TRA2020)
A Machine Learning Approach to Classify Pedestrians’ Event based on IMU and GPS (May 2020) Mobyen Uddin Ahmed, Staffan Brickman , Alexander Dengg , Niklas Fasth , Marko Mihajlovic , Jacob Norman International Journal of Artificial Intelligence (IJAI)
Supervised Learning for Road Junctions Identification using IMU (Mar 2019) Mohammed Ghaith Altarabichi, Mobyen Uddin Ahmed, Shahina Begum First International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2019)
|Hök instrument AB||Industrial|