• School of Engineering and Applied Science, Aston University

      B4 7ET Birmingham

      United Kingdom

    Accepting PhD Students

    PhD projects

    Transfer Learning Solutions for Intelligent Transportation (Artificial Intelligence, Intelligent Transportation, Smart Cities)

    Traditional urban infrastructure is at a breaking point. Given the rampant pollution, traffic congestion, and rising cost of powering energy-inefficient structures that are commonplace in our cities, switching to a more sustainable technological platform to support urban life is an imperative. Smart cities offer a potential solution, with intelligent transportation spearheading the transition from traditional urban traffic monitoring and control to a greener, more cost-effective approach, seamlessly integrated in the urban ecosystem.

    Within this context, our project aims at measurably improving transportation related decision making at every level, from finding the fastest route to work in real time and improving traffic light control, to investing in road infrastructure. The project’s stakeholders, i.e., ASTUTE, Birmingham City Council, and the Department for Transport, will be regularly consulted to inform project work and evaluate its results.

    The initial modelling of urban traffic will draw from the supervisor’s recent work, leveraging several sources of open data.

    The in-depth investigation and comparison of current modelling and prediction techniques, alongside their applications, will lay the groundwork for the original contribution to science, namely new, accurate, robust, scalable, and economical urban traffic prediction algorithms. The PhD researcher will investigate several distinct approaches to modelling and prediction, including time series, deep learning, and evolutionary computation. The algorithms will feature modern transfer learning capabilities, in order to reuse existing knowledge effectively and efficiently.

    Apply here: https://www.aston.ac.uk/study/courses/phd-engineering-and-applied-science

    Personal profile

    Research Interests

    I specialise in evolutionary computation, specifically, genetic programming and its applications in smart cities, with a focus on traffic modelling and prediction. My interests also include autonomic, knowledge-based systems, as well as self-adaptation and self-organisation in computing.

    Teaching Activity

    System Analysis (DC2SAN)

    Professional and Social Aspects of Computing (DC2PSA)

    Data Structures and Algorithms (DC2DSA)

    Individual Project (DC3010)


    Digital & Technology Solutions Degree Apprenticeship Programme Director


    August 2022 - present: Senior Lecturer in Computer Science

    August 2018 - August 2022: Lecturer in Computer Science (Institute of Coding)

    May 2018 - August 2018: Postdoctoral Research Fellow (ERDF Think Beyond Data)

    March 2017 - December 2018: Research Associate (EXCELL - Excellence in Smart Cyber-Physical Systems)

    August 2015 - May 2018: Teaching Fellow (Foundations of Technology Solutions Boot-camp - Digital & Technology Solutions Degree Apprenticeship)

    August 2014 - August 2015: Programming Support Officer (EAS - Computer Science, Aston University)

    Contact Details

    Email: a.patelli2@aston.ac.uk

    Room number: MB265E

    Education/Academic qualification

    SFHEA, Advance HE

    Award Date: 24 Nov 2021

    PhD, Knowledge-Centric Autonomic Systems

    Award Date: 10 Jan 2017

    PhD, Genetic Programming Techniques for Nonlinear Systems Identification, Gheorghe Asachi Technical University of Iasi

    Award Date: 1 May 2011


    • Q Science (General)
    • evolutionary computation
    • intelligent knowledge based systems
    • smart cities


    Dive into the research topics where Alina Patelli is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
    • 1 Similar Profiles

    Collaborations and top research areas from the last five years

    Recent external collaboration on country/territory level. Dive into details by clicking on the dots or