Predictive Emergency Service Operations Planning [Self-Funded Students Only]

Aims: The objective of this project is the exploration of the frontier between demand forecasting and operations planning to devise predictive, intelligent, and adaptive strategies in the context of emergency services (e.g., policing, fire services, medical services). More specifically, the research will follow and combine two main lines. The first concerns the furthering of spatiotemporal prediction models of the demand that adjust to the idiosyncrasies of the application framework by exploring the implication of context-specific variables (e.g., micro/macroeconomy, population distribution, environmental characteristics) while leveraging societal issues (i.e., the bias in the historical demand distribution due to racial or economic factors). The second regards the definition of optimisation models specifically tailored to the necessities of emergency services to devise predictive action plans. This research will be hosted in the Security, Crime and Intelligence Innovation Institute with connections to UK/international police force partners and other emergency services. As such, the models will be tested on real-world datasets.

Methods: This project draws from the disciplines of Machine Learning (ML) and Operational Research. In broad strokes, the project will be structured as follows. i) Analysis of the context and problem to solve. ii) Literature review for the identification of improvement opportunities with regards to the problem addressed. iii) Definition of mathematical models that solve the problem and expand on the literature. In this regard, the project is focused on (but not limited to) classical ML models, neural and deep models, and mathematical programming models. iv) Development and validation of the solution methodology.

Deliverables: The results of the project will be mostly published as journal papers or as conference papers when appropriate. Dissemination will be carried out at national/international top-tier conferences through talks or posters. Successful models will be implemented and developed into working software to be used by emergency services.

Keywords: Forecasting, Deep Learning, Machine Learning, Location Analysis, Vehicle Routing Optimisation, Districting Design, Operational Research.

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject.  Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas. This project is also available to students with a strong background in Statistics, Machine Learning and/or Operational Research.

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.

How to apply:

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below

This project is accepting applications all year round, for self-funded candidates via https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics 

In order to be considered candidates must submit the following information: 

• Supporting statement 
• CV 
• In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
• Qualification certificates and Transcripts
• Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
• References x 2 
• Proof of English language (if applicable)

For more information about this project, please contact [Email Address Removed]

If you have any questions or need more information, please contact [Email Address Removed]