FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Development of EEG-based Motor-Imagery BCI Application


   Centre for Digital Innovation

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr Yar Muhammad  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

A brain-computer interface (BCI) is a system that interprets brain signals generated by the user, allowing specific commands from the brain to be sent to an external device.

Such interface enables severely disabled people to interact with their environment without the need for any activation of their normal pathways involved in motor commands. According to the World Health Organization, there is a significant population of people with limited motor abilities who are not able or find it hard to operate the devices without assistance.

The main challenge for BCI is to identify human intent accurately given meagre Signal-to-Noise Ratio (SNR) brain signals. Poor generalization capability and low classification performance limit the broad real-world application of BCI.

This doctoral project will focus to achieve a cross-population generalized classifier. There is a need to develop a better architecture for classifier which should target the better generalized accuracy. The transfer learning technique will be used together with deep learning and on top of that Motor Imagery BCI application will be developed.

Background

Brain-Computer Interface (BCI) systems (cf. Fig. 1) interpret the human brain patterns into commands to communicate with the outer world [1]. BCI supports several novel applications that are vital to people’s daily life, particularly to people with psychological/physical disabilities.

BCI empowers the disabled, elders, and other people with limited motion ability to control wheelchairs, home appliances, and robots. According to the World Health Organization [2] there is a significant population of people with limited motor abilities who are not able or find it hard to operate the devices without assistance.

The main challenge for BCI is to identify human intent accurately given meagre Signal-to-Noise Ratio (SNR) brain signals. Poor generalization capability and low classification performance limit the broad real-world application of BCI.

Deep Learning (DL) allows to learn distinct high-level representations from raw brain signals without manual feature selection. It also achieves high accuracy.

Even though traditional BCI systems have made remarkable progress [3, 4], BCI research still faces major challenges such as brain signals are simply corrupted by different biological and environmental artifacts [3], BCI faces the low SNR of non-stationary electrophysiological brain signals [5] and feature engineering highly depends on human expertise in the specific domain [6]. DL has two benefits: i) it works directly on raw brain signals, ii) DL can capture both representative high-level features and latent dependencies through deep structures.

The transfer learning is the enhancement of learning in a new task through the transfer of knowledge from a related task that has already been learned. However, most machine learning algorithms are designed to address single tasks [7].

 Innovativeness and Importance

 The potential for improvements to quality of life and the commercial value of BCI systems is unquestionable. However, it is becoming clearer that for BCI systems to be adopted for a wider general use, the accuracy of classifying the brain activity of the subjects operating the system needs to be near 100%. Achieving 100% generalized accuracy is very difficult by the fact that brain waves are documented to be highly individualized to the subject [8].

One of the key limitations of BCI is its long calibration time. Typically, a big amount of training data needs to be collected at the beginning of each session to tune the parameters of the system for the target user due to between-sessions/-subjects non-stationarity. To mitigate this limitation, transfer learning can be potentially one useful solution. Transfer learning extracts information from different domains (raw data, features, or classification domain) to compensate the lack of labelled data from the test subject.

This doctoral project will focus on achieving a cross-population generalized classifier. There is a need to develop a better architecture for classifier which should target the better generalized accuracy. The transfer learning technique will be used together with DL and on top of that Motor Imagery BCI application will be developed.

Plan and Description

Year 1:

  • Review and benchmark existing classifiers and transfer learning technique
  • Develop an initial algorithm/approach/method to deal with and provide an initial classifier
  • Paper submission based on initial developed approach/method and classifier

Year 2:

  • Refine the previous proposed classifier to improving the accuracy, efficiency, and performance.
  • Submission an extending version of paper with additional refinements and results

 Year 3:

  • Development of real-time EEG-based motor imagery BCI application based on proposed classifier
  • Submission of a paper outlining a novel approach/method for EEG-based BCI application to interprets brain signals.

Year 4:

  • Implement the developed application in real-time in real-world environment
  •  Thesis writing

Entry Requirements

Applicants should hold or expect to obtain a good honours degree (2:1 or above) in a relevant discipline. A masters level qualification in a relevant discipline is desirable, but not essential, as well as a demonstrable understanding of the research area. Further details of the expected background may appear in the specific project details. International students will be subject to the standard entry criteria relating to English language ability, ATAS clearance and, when relevant, UK visa requirements and procedures.

How to Apply

Applicants should apply online for this opportunity at: https://e-vision.tees.ac.uk/si_prod/userdocs/web/apply.html?CourseID=1191

Please use the Online Application (Funded PHD) application form. When asked to specify funding select “other” and enter ‘RDS’ and the title of the PhD project that you are applying for. You should ensure that you clearly indicate that you are applying for a Funded Studentship and the title of the topic or project on the proposal that you will need to upload when applying. If you would like to apply for more than one project, you will need to complete a further application form and specify the relevant title for each application to a topic or project.

Applications for studentships that do not clearly indicate that the application is for a Funded Studentship and state the title of the project applied for on the proposal may mean that your application may not be considered for the appropriate funding.

For academic enquiries, please contact Dr Yar Muhammad [Email Address Removed]  

For administrative enquiries before or when making your application, contact [Email Address Removed].  


Funding Notes

The Fees-Paid PhD studentship will cover all tuition fees for the period of a full-time PhD Registration of up to four years. Successful applicants who are eligible will be able to access the UK Doctoral Loan scheme https://www.gov.uk/doctoral-loan to support with living costs. The Fully Funded PhD Studentship covers tuition fees for the period of a full-time PhD Registration of up to four years and provide an annual tax-free stipend of £15,000 for three years, subject to satisfactory progress. Applicants who are employed and their employer is interested in funding a PhD, can apply for a Collaborative Studentship

References

[1] F. Lotte et al. 2018. A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J NEURAL ENG
[2] World Health Organization 2011. “World report on disability”. (https://www.who.int/disabilities/world_report/2011/en/ 13.11.2019)
[3] S. Abdulkader et al. 2015. Brain computer interfacing: Applications and challenges. Egypt. Inform. J.
[4] A. Bashashati et al. 2007. A survey of signal processing algorithms in brain–computer interfaces based on electrical, brain signals. J NEURAL ENG.
[5] W. Samek et al. 2012. Brain-computer interfacing in discriminative and stationary subspaces. In EMBC
[6] Xiang Zhang, Lina Yao, Xianzhi Wang, Jessica Monaghan, David Mcalpine, Yu Zhang. 2019. “A Survey on Deep Learning based Brain Computer Interface: Recent Advances and New Frontiers”.
[7] E. S. Olivas, J. D. M. Guerrero, M. M. Sober, J. R. Magdalena-Benedito and A. J. S. López. 2009. “Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques”
[8] Abhang, P. A., Gawali, B. W., & Mehrotra, S. C. 2016. “Technological Basics of EEG Recording and Operation of Apparatus. Introduction to EEG- and Speech-Based Emotion Recognition”.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs