Mobility Data Management, Analysis and Visualisation
Lead Research Organisation:
University of Leeds
Department Name: Mechanical Engineering
Abstract
There are currently many people in the UK and around the world suffering from issues which have directly affected their mobility functions. This proposed project is part of a larger project to design and develop intelligent and autonomous systems of assistive robotic devices intended to restore normal and natural locomotion for a wide range of patients including the growing aging population.
The main aim of the proposed PhD project is to explore methodologies for analysing long term data collected from mobility patients.
Accurate gait analysis in real-time and real-environments are essential both for patient management and well-being and for design, development and improvement of intelligent customised assistive robotic devices. It is well known that the conventional methods to assess human gait are expensive, complex and limited to laboratory environments. Systematic reviews have identified the limitations and drawbacks of current wearable sensors and available analytical methods. A major challenge here is capturing accurate, validated, verifiable and relevant mobility data from patients in real-time and in real-environments with unobtrusive methods and then to properly manage, analyse, interpret and visualise the data.
In the proposed research, a range of methods such as statistical analysis and the use of artificial neural networks will be explored. It is considered that a range of data is already available based on patients' activities of daily living.
The main aim of the proposed PhD project is to explore methodologies for analysing long term data collected from mobility patients.
Accurate gait analysis in real-time and real-environments are essential both for patient management and well-being and for design, development and improvement of intelligent customised assistive robotic devices. It is well known that the conventional methods to assess human gait are expensive, complex and limited to laboratory environments. Systematic reviews have identified the limitations and drawbacks of current wearable sensors and available analytical methods. A major challenge here is capturing accurate, validated, verifiable and relevant mobility data from patients in real-time and in real-environments with unobtrusive methods and then to properly manage, analyse, interpret and visualise the data.
In the proposed research, a range of methods such as statistical analysis and the use of artificial neural networks will be explored. It is considered that a range of data is already available based on patients' activities of daily living.
Organisations
People |
ORCID iD |
Abbas Dehghani-Sanij (Primary Supervisor) | |
John Mitchell (Student) |
Studentship Projects
Project Reference | Relationship | Related To | Start | End | Student Name |
---|---|---|---|---|---|
EP/T517860/1 | 30/09/2020 | 29/09/2025 | |||
2435960 | Studentship | EP/T517860/1 | 30/09/2020 | 31/03/2024 | John Mitchell |