Multimodal Sensor Fusion and Large-Language-Model-Driven Muscle Fatigue Wearable Monitoring Systems

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

Muscle fatigue is a critical issue in sports performance, rehabilitation, and occupational health. It not only reduces physical efficiency and increases injury risk but also complicates long-term health monitoring and adaptive intervention. Existing approaches mostly rely on single-modality sensors and lack interpretive intelligence, making it difficult to translate raw biosignals into actionable insights.

This PhD project aims to develop an intelligent muscle-fatigue monitoring framework by combining advanced wearable front-end sensors, ambient/contextual sensors, multimodal data-fusion techniques, and state-of-the-art large-language models (LLMs) for interpretive analytics and interaction. The goal is to detect, interpret and predict muscle fatigue states in real time, enabling personalised feedback and adaptive intervention in smart health systems. At the core of the project is the front-end sensor design: we will develop and deploy a high-fidelity wearable sensor platform—comprising surface electromyography (sEMG), inertial measurement units (IMU), mechanomyography or strain sensors, heart-rate/ECG modules, and ambient load/force sensors—where special attention will be paid to sensor placement, comfort, signal quality, low-latency transmission, and long-term wearability. These sensors will capture physiological, biomechanical and contextual signals related to fatigue onset, progression and recovery. The heterogeneous data streams will be synchronised and processed through a fusion pipeline to extract robust features characterising fatigue states.

A novel aspect of this research is the integration of a large language model as a semantic layer. The LLM will ingest fused sensor-derived information plus metadata (user history, task context, load profile) to interpret fatigue status in natural language, generate actionable user feedback (e.g., “Based on your current sensor trends and history, you are likely to reach fatigue threshold in ~X minutes”), and enable semi-automated interaction (via mobile app or wearable interface) to solicit subjective input (“On a scale of 1–10, how fatigued do you feel?”) and deliver tailored suggestions.

The candidate will have opportunities to engage in international collaboration and research exchange with partner institutions such as University College London (UCL), Imperial College London, and the University of Oxford. These collaborations will provide access to advanced robotic laboratories, joint supervision, and cross-institutional research seminars, supporting the student’s development as an independent researcher in human–robot interaction and intelligent healthcare technologies.

The expected outcomes of this research include:

1. Design, prototyping and validation of the front-end wearable sensor system (hardware, placement, wearability, calibration).
2. Multimodal data acquisition and fusion from wearables + ambient/contextual sensors, with feature engineering and machine-learning model training to detect and predict fatigue states. Novel sensor-fusion and predictive algorithms for muscle fatigue detection, emphasising front-end sensor design and data integrity.
3. A proof-of-concept LLM-driven interpretive layer bridging low-level sensor data with high-level fatigue insights and interaction. Real-world validation in scenarios such as sports training, rehabilitation sessions or occupational tasks—evaluating accuracy, user-experience, responsiveness and long-term wearability.
4. Investigation of adaptive capability over time: personalising baseline, adjusting thresholds, evolving sensor and fusion strategies with user behaviour. User studies demonstrating improved fatigue awareness, workload management and injury-risk mitigation.

This project aligns with global trends of human-centred AI, intelligent health monitoring and personalised wearable robotics, offering both fundamental research contributions (front-end sensor design + sensor-fusion + LLM interpretability) and translational impact in sports medicine, rehabilitation technology and occupational health.

Informal enquiries can be directed to Dr Zhenhua Yu (zhenhua.yu@abdn.ac.uk) if the topic within this project is of interest to you, he is happy to discuss further with interested candidates.

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in robotics, mechanical engineering, electronic and electrical engineering, biomedical engineering, computer science, or a closely related discipline.

Candidates should have a strong interest in human–robot interaction, wearable sensing, and intelligent control systems.

Prior experience with Python, MATLAB, or C/C++, and familiarity with ROS (Robot Operating System) will be highly desirable. A good understanding of experimental research methods and data analysis is expected.

We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Degree of Doctor of Philosophy in Computing Science to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project titleon the application form. If you do not include these details, it may not be considered for the project.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you do not need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at researchadmissions@abdn.ac.uk

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen