PhD Studentship: Bootstrapping activity recognition in wearable activity recognition (2018)
What you get
- Only suitable for UK or EU residents
- 3-year scholarship
- £14,553 tax free stipend per year;
- Fees are waived
Type of award
Postgraduate Research
PhD project
Machine learning applied to wearable motion sensor data can be used to infer human activities and provide contextual assistance: for instance as a wearable fitness coach, for home assistance or in industrial settings. Sufficient data, however, must be available to successfully train machine learning models.
Within this project, you will develop advanced machine learning and AI techniques suitable to address these challenges: i) recognising an open-ended set of activities from wearable sensors data, and ii) reduce the effort associated with acquiring training data. Depending on your interests, different approaches can be followed: crowd-sourcing data acquisition, developing new interactive machine learning approaches, or you might exploit the growing availability of multimedia datasets (e.g. Google AVA dataset, Youtube data, the Sussex-Huawei Locomotion dataset, and other) which can be reused and translated across modalities or using recent deep learning techniques.
Eligibility
== Qualifications ==
The ideal candidates will have a master's degree in computer science, computer engineering, mathematics, physics, electrical engineering, or equivalent, with prior experience in machine learning.
The ideal candidates will have a passion to contribute to the development of novel wearables which can improve our quality of life. They will have outstanding technical skills and a strong interest in research at the crossroads of signal processing, machine learning, embedded systems, sensor technologies and their applications.
Applicants should be committed to pursue leading research and publish results in top venues. Additionally, we expect mastery of written and spoken English, self-motivation, an inquiring mind, be able to work independently and in an interdisciplinary environment.
== About the Lab ==
The Wearable Technologies Lab has been established in 2014 and received funding from a variety of sources (Google, Huawei, Unilever, EPRSC, FFG, etc). We are a growing group, with an international team and outlook, and interdisciplinary skills in AI, computing and hardware with a focus on novel wearable technologies.
Some of the research areas you may come in contact during your PhD include applied machine learning, deep learning, signal processing, big data, crowd sourcing, human-computer interaction, etc.
Deadline
31 July 2018 17:00How to apply
Contact Dr. Daniel Roggen (daniel.roggen@ieee.org) with your CV to discuss your application.
Applications are handled online via the University Doctoral School:
http://www.sussex.ac.uk/study/phd/apply.
More informations about the Wearable Technologies Lab and ongoing research:
http://www.sussex.ac.uk/strc/research/wearable
http://scholar.google.co.uk/citations?user=JGjtLtYAAAAJ
Contact us
Contact for informal enquiries and further details of the project: Dr Daniel Roggen, http://www.sussex.ac.uk/profiles/335131
Timetable
Deadline: 15/03/2018
Availability
At level(s):
PG (research)
Application deadline:
31 July 2018 17:00 (GMT)
the deadline has now expired
Countries
The award is available to people from these specific countries: