From Connected to Sustainable Mobility (FREEDOM)

hh.sePublications

Simple search

Advanced search -
Research publications Advanced search -
Student theses Statistics

Change search

ExportLink to record

Permanent link

Direct link

https://hh.diva-portal.org/smash/project.jsf?pid=project:2697

BETA

Project

Project type/Form of grant

Project grant

Title [sv]

From Connected to Sustainable Mobility (FREEDOM)

Title [en]

From Connected to Sustainable Mobility (FREEDOM)

Abstract [sv]

Syfte och mål:The combination of the massive amount of relevant but under-utilised data and the AI expertise led to FREEDOM project. Collaboration of WirelessCar and CAISR aims to reduce the carbon footprint of personal transportation by empowering end-users to make smart choices that contribute to UN Agenda 30 and Global Goals, responsible consumption & climate action. We analyse connectivity data from cars and their impact on CO2 emissions to understand the efficiency of current mobility and transport systems, how various factors affect it, and which of them are actionable for different actors.Förväntade effekter och resultat:With the amount of data WirelessCar has available, and the machine learning expertise at Halmstad University, the project will provide cutting edge results to be disseminated through high-impact publications and new innovative services that allow travellers to reduce their CO2 footprint. These results will further contribute to the alignment of interests between the end-users and vehicle producers, as well as policymakers, leading to sustainable outcomes for the overall transportation system. New services will lead to sustainable and efficient resource utilisation.Upplägg och genomförande:We will develop novel methods for analysing travel data expanding on recent results from the emerging field of Graph Neural Networks. It is a field that combines the success of deep learning, most prominent in analysing images, with the flexibility of graph theory. It extends the classical deep neural network paradigm to allow encoding the inherent structure in the input space in the FREEDOM context, there is a clear application to map data, with key infrastructure nodes and their spatial relations, characterised by two essential dimensions; spatial and temporal aspects.

Abstract [en]

Purpose and goal:The combination of the massive amount of relevant but under-utilised data and the AI expertise led to FREEDOM project. Collaboration of WirelessCar and CAISR aims to reduce the carbon footprint of personal transportation by empowering end-users to make smart choices that contribute to UN Agenda 30 and Global Goals, responsible consumption & climate action. We analyse connectivity data from cars and their impact on CO2 emissions to understand the efficiency of current mobility and transport systems, how various factors affect it, and which of them are actionable for different actors.Expected results and effects:With the amount of data WirelessCar has available, and the machine learning expertise at Halmstad University, the project will provide cutting edge results to be disseminated through high-impact publications and new innovative services that allow travellers to reduce their CO2 footprint. These results will further contribute to the alignment of interests between the end-users and vehicle producers, as well as policymakers, leading to sustainable outcomes for the overall transportation system. New services will lead to sustainable and efficient resource utilisation.Approach and implementation:We will develop novel methods for analysing travel data expanding on recent results from the emerging field of Graph Neural Networks. It is a field that combines the success of deep learning, most prominent in analysing images, with the flexibility of graph theory. It extends the classical deep neural network paradigm to allow encoding the inherent structure in the input space in the FREEDOM context, there is a clear application to map data, with key infrastructure nodes and their spatial relations, characterised by two essential dimensions; spatial and temporal aspects.