Computational approaches to enhance wearable sensor-based human activity recognition

Summary

Artificial Intelligence, and specifically machine learning techniques, have been used to infer human activities by interpreting data from low level wearable, mobile and ambient sensors.

Nonetheless, sensor-based human activity recognition (AR) lags similar fields, such as machine vision, largely due to a lack of large-scale, high-quality, multimodal, and labelled datasets. This has impeded progress in developing robust and generalised machine learning approaches for AR.

Within this PhD project the successful candidate will investigate computational approaches to make it easier to train models capable of recognising a wide range of human activities. The project will undertake research in advanced machine learning and AI techniques to recognise a growing set of activities from a range of various sensor modalities, and reduce the effort associated with acquiring annotated training data.

Depending on the research interests of the candidate, various focused research challenges can be addressed:

Approaches to assist with labelling AR data;

  • Development of models which require less labelled data (contrastive learning, self-supervised learning, and self-training).
  • Producing tools which can facilitate crowd labelling or active label cleaning.
  • Investigating the role of data augmentation for training.

Personalisation of models to address cross-subject variability;

  • Combining semi-population and user adaptation to personalise models trained on a population.
  • Investigating the potential of transfer learning, and evaluating it in a range of under-represented populations.

Approaches to utilise multi-modal data;

  • Approaches to utilise a diverse range of sensing modalities.
  • Methods of combining multi-model sensing approaches through feature fusion and classifier ensembles.

Approaches for on device modelling of AR on embedded platforms;

  • Computational constraints reduction,
  • Model optimization, through federated and distributed learning
  • Optimisation of sensor configuration (e.g. placement and sampling rate).

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

  • First Class Honours (1st) Degree
  • Masters at 70%
  • Experience using research methods or other approaches relevant to the subject domain
  • Work experience relevant to the proposed project
  • Publications - peer-reviewed

Funding and eligibility

The University offers the following levels of support:

Vice Chancellors Research Studentship (VCRS)

Full award (full-time PhD fees + DfE level of maintenance grant + RTSG for 3 years).

This scholarship will cover full-time PhD tuition fees and provide the recipient with £18,000 (tbc) maintenance grant per annum for three years (subject to satisfactory academic performance).

This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Vice-Chancellor’s Research Bursary (VCRB)

Part award (full-time PhD fees + 50% DfE level of maintenance grant + RTSG for 3 years).

This scholarship will cover full-time PhD tuition fees and provide the recipient with £8,000 maintenance grant per annum for three years (subject to satisfactory academic performance). This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Vice-Chancellor’s Research Fees Bursary (VCRFB)

Fees only award (PhD fees + RTSG for 3 years).

This scholarship will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance). This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Department for the Economy (DFE)

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £18,000 (tbc) per annum for three years (subject to satisfactory academic performance).

This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

  • Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance.
  • Republic of Ireland (ROI) nationals who satisfy three years’ residency in the UK prior to the start of the course MAY receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify).
  • Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding.
  • Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Due consideration should be given to financing your studies. Further information on cost of living

Recommended reading

Cruciani, F., Nugent, C.D., Quero, J.M., Cleland, I., McCullagh, P., Synnes, K., Hallberg, J., Personalizing activity recognition with a clustering based semi-population approach, 2020, IEEE Access, 8, 9258905, , 10.1109/ACCESS.2020.3038084.

Razzaq, M.A., Cleland, I., Nugent, C., Lee, S., Semimput: Bridging semantic imputation with deep learning for complex human activity recognition, 2020, Sensors (Switzerland), 20, 10, 2771, 10.3390/s20102771.

Ni, Qin, Timothy Patterson, Ian Cleland, and Chris Nugent. "Dynamic detection of window starting positions and its implementation within an activity recognition framework." Journal of biomedical informatics 62 (2016): 171-180.

Cruciani, F., Vafeiadis, A., Nugent, C., Cleland, I., McCullagh, P., Votis, K., ... & Hamzaoui, R. (2020). Feature learning for human activity recognition using convolutional neural networks. CCF Transactions on Pervasive Computing and Interaction, 2(1), 18-32.

Ni, Q., Cleland, I., Nugent, C., García Hernando, A.B., de la Cruz, I.P., Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home, 2019, Pervasive and Mobile Computing, 56, 1, , 10.1016/j.pmcj.2019.03.006.

Patterson, T., Khan, N., McClean, S., Nugent, C., Zhang, S., Cleland, I., Ni, Q., Sensor-Based Change Detection for Timely Solicitation of User Engagement, 2017, IEEE Transactions on Mobile Computing, 16, 10, 7784795, 10.1109/TMC.2016.2640959.

Cleland, I., Kikhia, B., Nugent, C., Boytsov, A., Hallberg, J., Synnes, K., McClean, S., Finlay, D., Optimal placement of accelerometers for the detection of everyday activities., 2013, Sensors (Basel, Switzerland), 13, 7, , 10.3390/s130709183.

The Doctoral College at Ulster University

Key dates

Submission deadline
Monday 27 February 2023
04:00PM

Interview Date
week commencing 17 April 2023

Preferred student start date
18 Sept 23

Applying

Apply Online  

Contact supervisor

Dr Ian Cleland

Other supervisors

Back to Top