By using data from a network of sensors in a smart home, we can characterise patient activities and provide support. Examples are: prompts for Alzheimer’s patients or health alerts for heart patients. The sensor network typically consists of diverse devices such as accelerometers, heart monitors, smartphones, sensorised household equipment, and cameras.
Recent work on Process Mining and Modelling has sought to obtain new knowledge and process conformity measures, where processes typically consist of a series of time-stamped activities. As such, sensor networks can be thought of as following processes, where sensor activations demarcate the end of one activity and the start of another. In addition to the sensor activities, residents and patients, in parallel, carry out subsequences of associated activities, toward achieving goals. However, anomalies in the processes may occur, and, once detected, can require intervention.
The research will build on previous novel work, of the supervisors and others, for clustering Process Mining sub-sequences, and the development of Probability Models for recognition of patient activities of daily living in smart homes, here using nth-order Markov Chains to incorporate associations for sensor groups that form clusters within the overall process. These will allow us to improve activity prediction accuracy and timeliness by incorporating new knowledge of the activity process and sensor associations. The literature shows that a huge amount of data is being generated in healthcare, such as in hospitals by staff and machinery, but still, there is not a lot of evidence that process mining is being used in a research context beyond specific case studies. In particular, using sensor data for healthcare is a very limited explored area in the field of process mining.
As such, the project will concentrate on the following research questions:
This Ph.D. research presents a valuable case study for the ongoing research projects at BTIIC and ARC.
The School of Computing’s living lab will play an important role in providing a Markov Chain based digital-twin representation of a smart homes.
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.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University is an equal opportunities employer and welcomes applicants from all sections of the community, particularly from those with disabilities.
Appointment will be made on merit.
The University offers the following levels of support:
The following scholarship options are available to applicants worldwide:
These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) 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.
Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,237 (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.
Due consideration should be given to financing your studies. Further information on cost of living
Tariq, Z., Khan, N., Charles, D., McClean, S., McChesney, I. and Taylor, P., 2020. Understanding contrail business processes through hierarchical clustering: A multi-stage framework. Algorithms, 13(10), p.244.
Tariq, Z., Charles, D., McClean, S., McChesney, I. and Taylor, P., 2021, August. An Event-Level Clustering Framework for Process Mining Using Common Sequential Rules. In International Conference for Emerging Technologies in Computing (pp. 147-160). Springer, Cham.
Shuai Zhang, Sally I. McClean, Bryan W. Scotney (2012): Probabilistic Learning From Incomplete Data for Recognition of Activities of Daily Living in Smart Homes, IEEE Transactions on Information Technology in Biomedicine, 16(3): 454-462.
Zhang, S., McClean, S.I., Scotney, B.W., Hong, X., Nugent, C.D., & Mulvenna, M.D. (2010). An Intervention Mechanism for Assistive Living in Smart Homes. Journal of Ambient Intelligence and Smart Environments (Smart Home Thematic Issue), Volume 2, Issue 3, pp. 233-252.
Munoz-Gama, J., Martin, N., Fernandez-Llatas, C., Johnson, O.A., Sepúlveda, M., Helm, E., Galvez-Yanjari, V., Rojas, E., Martinez-Millana, A., Aloini, D. and Amantea, I.A., 2022. Process mining for healthcare: Characteristics and challenges. Journal of Biomedical Informatics, 127, p.103994.
L Yang, S McClean, M Donnelly, K Burke, K Khan (2022). A multi-components approach to monitoring process structure and customer behaviour concept drift. Expert Systems with Applications
Submission deadline
Monday 26 February 2024
04:00PM
Interview Date
April 2024
Preferred student start date
16 September 2024
Telephone
Contact by phone
Email
Contact by email