Mobility and transportation has been an essential part of humankind existence. It is the key factor of the evolution of technology and economy. The traffic and mobility problems are the results of concentration of population and markets. Hence, the challenges in mobility are related to many factors and actors such vehicle, safety, sustainability, traffic jams, incident, human behaviour, etc. From this perspective our ITS Team focuses on contributing on the following fields:
This is about using spatio-temporal mobility analysis in order to detect communities in the mobile cellular networks using CDR data.
Conducting patterns extraction based mobility characteristics from the trajectory records.
Simulating pedestrian movement for mobility analysis and emergency evacuation situtation.
Simulating road traffic in urban areas for mobility analysis and addressing issues related to urbanization.
Simulating mobile networks to generate data logs that can help in investigating the usages and integration of mobile data in transportation and smart mobility.
In this topic, we are trying to use CDR data as a mean to localize and position the mobile users in the mobile networks.
We are investigating the use of map-matching techniques to solve issues related to GPS errors, positioning accuracy, or noise in the geolocation data.
This topic is related to extract mobility episode from the cell based trajectories extracted from the CDR data.
Developing techniques and algorithms to increase the accuracy of travel time estimation and prediction for navigation and fleet management purposes.
Investigating algorithms and methods for estimating the road traffic status, congestion detection, incident detection, etc.
The idea is to build an understanding of the indoor environment by creating a 3D representation model of the surrounding using sensors.
The use of sensors such as cameras, lasers, radars, ridars to create a model of the outdoor environment for the purpose of navigation and SLAM.
This topic is about the use of cameras and sensors to identify and detect pedestrians, which is one of the important features in ADAS systems for safety purposes.
Detecting vehicles and recognizing them is a key component for future autonomous vehicle navigation systems.
Recognizing the handwritten characters is the ability of making the machine recognize the characters which has impact on artificial intelligence applications such as autonomous vehicles, signature verification, location based services, etc.
Investigating the usage of internet of vehicles for improving the V2V and V2I solutions and also computing strategies for real time systems.
Conducting research on the enhancement and usage of V2V and V2I communications for the purpose of information exchange and cooperative probes.