FindA University Ltd Featured PhD Programmes
University of Sheffield Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
FindA University Ltd Featured PhD Programmes
FindA University Ltd Featured PhD Programmes

Deep Feature Learning for Distributed Rehabilitation Robots with Wearable Tactile Sensing

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

Click here to search FindAPhD.com for PhD studentship opportunities
  • Full or part time
    Dr S Luo
    Dr P Paoletti
  • Application Deadline
    No more applications being accepted
  • Funded PhD Project (Students Worldwide)
    Funded PhD Project (Students Worldwide)

Project Description

The project is supported by the University of Liverpool Doctoral Network in Future Digital Health, which is directed at creating and maintaining a community of AI health care professionals that can realise the benefits that AI can bring to Health Care. The vision is that of a world-class centre providing high-quality doctoral training within the domain of AI for Future Digital Health. Each available PhD project has been carefully co-created in collaboration with a health provider and/or a healthcare commercial interest so that the outcomes of the PhD research will be of immediate benefit. The network will be providing doctoral training, culminating in a PhD, in a collaborative environment that features, amongst other things, peer-to-peer and cohort-to-cohort based learning. On completion students will be well-placed to take up rewarding careers within the domain of AI and Digital Health.
Somatosensory impairment, i.e., loss of the sense of touch, is common after stroke, occurring in 50–80% of stroke survivors [1]. Rehabilitation devices/robots can be employed to help the patients improve the touch sensation after stroke and learn new ways of movement with the potential to help them regain use of their affected limb. In the recent decades, various rehabilitative exoskeleton robots, some of which are commercially available, have been developed that support the rehabilitation of different body parts, e.g., the hand, shoulder, elbow, forearm and wrist through different ranges of motions. For such rehabilitation devices, wearable tactile sensors can be employed to provide posture and activity monitoring of the patients, which brings significant information about rehabilitation practice and clinical efficacy [2,3]. A growing interest in analysing movement in everyday environments, e.g., the home, has given rise to the development of the wearable tactile sensors, with the most current ones being those embedded into clothing, e.g., textile or fabric-based sensors. These sensors have various advantages such as high sensitivity, lightweight, flexibility and being easy to fabricate. However, a major issue with the use of such sensors is the undesired effect of motion artefacts of fabrics that corrupts the sensing of activity and movement signals. This project aims to develop a distributed tactile sensing system for rehabilitation devices and make use of the data collected from the tactile sensors to learn the activities and movements of the body parts using deep neural network models.

The proposed programme will consist of three parts. The first part of work will be directed at development of the distributed tactile sensing system using fabric sensors. A soft fabric based tactile sensor will be developed using the conductive materials, and the developed sensors will be integrated with a Lilypad platform to pre-process and transmit the data. The second part of the project will be dedicated to an investigation of the use of deep learning models [4], such as LSTMs and Deep Belief Networks, on the collected data from the distributed tactile sensors to perceive the movement of the body parts and the environment, especially the properties of interacted objects. The object properties will include, but not limited to, shapes/geometry, weights, textures, poses and stiffness. It has been demonstrated that deep learning models have achieved the state-of-the-art results on various tasks in different fields including computer vision, automated medical diagnosis. The deep learning models not only produce excellent classification results by extracting deep features from raw data, but also determine the relevant features automatically. It is anticipated that several variations of the deep learning models will be investigated in the project. The third part of the project will tackle the stochastic perturbations to the motions caused by the undesired motion of the fabrics and eliminate the errors in learning body movements and perception of object interactions. The developed tactile sensing system will be tested by human subjects wearing the fabrics embedded with the distributed sensors.

The project will be carried out at the state-of-the-art robotics lab smARTLab at the University of Liverpool. The candidate will have access to the resources available in the lab, e.g., the robotics components, robot arms and commercial sensors.

For enquiries please contact Dr Shan Luo, [Email Address Removed] ; Dr Paolo Paoletti, [Email Address Removed].

To apply for this opportunity, please visit: https://www.liverpool.ac.uk/study/postgraduate-research/how-to-apply/

Funding Notes

This project is funded by the University of Liverpool Doctoral Network in Future Digital Health, successful students will receive a studentship of tuition fees paid at the Home/EU rate for 3.5 years and a stipend of £15,009 per annum for 3.5 years. In addition, students will have access to a research support fund of £1,000 per annum for purchasing equipment, consumables and conference costs co-managed by the academic supervisor. Applications from international students are welcomed, however suitable arrangements will need to be made for the difference between the Home/EU and international rate.

References

[1] Carey, L.M. and Matyas, T.A., 2011. Frequency of discriminative sensory loss in the hand after
stroke in a rehabilitation setting. Journal of rehabilitation medicine, 43(3), pp.257-263.
[2] Wang, Y., Wang, L., Yang, T., Li, X., Zang, X., Zhu, M., Wang, K., Wu, D. and Zhu, H., 2014.
Wearable and highly sensitive graphene strain sensors for human motion monitoring. Advanced
Functional Materials, 24(29), pp.4666-4670.
[3] Yang, T., Xie, D., Li, Z. and Zhu, H., 2017. Recent advances in wearable tactile sensors: Materials,
sensing mechanisms, and device performance. Materials Science and Engineering: R: Reports, 115,
pp.1-37.
[4] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-44.



FindAPhD. Copyright 2005-2019
All rights reserved.