View All Vacancies

PhD Studetnship: Machine Learning for Stress and Fatigue Detection in Ship Crews

School of Engineering

Location:  Boldrewood Campus
Closing Date:  Saturday 31 August 2019
Reference:  1167619DA

Supervisory Team: Dominic Hudson, Dominic Taunton, Sarvapali Ramchurn

It is often reported that 80% of maritime accidents are due to human error, with a large proportion of these attributed to a failure to follow procedures. The usual response to this is to increase training. A recent research project (MARTHA) which looked into fatigue and sleepiness onboard ships, concluded that although all crew showed increased levels of fatigue by the end of a voyage, certain crew member (particularly 2nd Officers) were more susceptible to tiredness and that fatigue and stress were inter-related. 

The aim of this project will be to measure and predict the levels of fatigue and stress in targeted Deck Officers from modern LNG ships. This will be carried out using a range of both intrusive and non-intrusive methods. Intrusive methods will include modern fitness trackers which can record activity, heart rate and track sleep in an unobtrusive manner. Non-intrusive methods will include environmental sensors built into the ship that allow the monitoring of physical activities and environmental parameters (temperature, humidity etc…). This will be combined with vessel tracking data from AIS and ship motions data and environmental data from wave buoys. Machine learning techniques (e.g., deep learning and Bayesian classifiers) can then be used to determine periods of acute stress and poor sleep leading to fatigue. Based on these outputs, optimisation algorithms will be developed to reduce tiredness and stress levels. Moreover, this information can then be used to develop more realistic training programmes which incorporate appropriate stressors, which could potentially reduce the negative effects of stress/ fatigue as the trainees become habituated to the stressors. The project will also investigate the levels of activity and stress when off watch and when not at sea, in particular the periods before and after a long sea voyage. 

The ideal candidate will have a background in Machine learning, Ubiquitous Computing, Artificial Intelligence, and Human Factors or Human-Computer Interaction. Depending on the background of the successful PhD student, suitable training will be provided from specialist modules across Engineering and Health Sciences. In particular Ship Design and Economics and Research Methods for Evidence Based Practice. The student will also be given the opportunity to learn about ship operation and crew training from Shell Shipping. Training in relevant analysis software will also be provided. 

The recent Global Marine Technology Trends 2030 document highlighted the increasing technology onboard ships and the need for highly skilled crew to operate them. Skilled crew requires good training programmes, which need to reinforce the correct human behaviours in stressful situations, especially as humans have finite resources in terms of memory and attention. The design of shipboard systems is usually the responsibility of engineers, but the evaluation of these systems needs to be carried out from the human perspective. This needs a multi-disciplinary approach building on the work already carried out between engineering and psychology in the laboratory and incorporating real in-situ measurement based on occupational health practice. The research has the potential to reduce major shipping accidents, saving lives and reducing environmental impact. Currently, a career at sea is not viewed in the same aspirational way as, say, becoming a commercial airline pilot. Yet the physical, mental and emotional requirements are very similar. The need to recruit highly skilled crew for ship operations will require significant development of training that more adequately prepares people for the ships of the future. 

Entry Requirements

We welcome applications from future experts who have, or expect to shortly have, a very good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent).

Closing date: applications should be received no later than 31 August 2019 for standard admissions, but later applications may be considered depending on the funds remaining in place.

Funding: full tuition plus, for UK students, an enhanced stipend of £15,009 tax-free per annum for up to 3.5 years. 

How To Apply

Candidates should apply as soon as possible to be considered for a place for September 2020 entry. All shortlisted applicants will be invited for interview at the University of Southampton. Note that if, due to your personal circumstances, you are unable to attend for interview in person, please get in touch.

Applications should be made online here selecting “PhD Engineering & Environment (Full time)” as the programme. Please enter Dominic Hudson under the Topic or Field of Research.

Applications should include

Your Curriculum Vitae

Two reference letters

Degree Transcripts to date

Apply online:

The closing date for this job opportunity has now passed, and applications are no longer being accepted for this position

Login to your account


Forgotten your password?

Register for an account

Mindful Employer Disability Confident Leader HR Excellence In Research Stonewall Diversity Champion Athena Swan Silver Award - University of Southampton Committed to being an Inclusive Employer Technician Commitment