Imaging, Data and Communications

We are seeking an ambitious and proactive PhD student to characterise sleep in young children with neurodevelopmental conditions by analysing electroencephalogram (EEG) recordings as part of our interdisciplinary research team. You will do research in EEG signal processing, deep learning, and causal AI as part of the team delivering the project EPIC (Enabling the early and equitable diagnosis of epilepsy in infants in the community, http://edin.ac/epic-infant), an EPSRC-funded research project developing advanced signal analysis and artificial intelligence for the identification of childhood epilepsy in community settings. 

Sleep difficulties are common in children with neurodevelopmental conditions and can have profound effects on cognition, behaviour, emotional wellbeing, learning and family life. Yet, measuring sleep objectively remains difficult, and much remains unknown about what causes and effects link sleep and neurodevelopmental conditions. To shed light on this important clinical question, this PhD project will develop and apply new computational analysis of EEG recordings to achieve a richer understanding of sleep in children with neurodevelopmental conditions. You will develop algorithms to extract meaningful information from paediatric EEG recordings, including features that capture sleep organisation, variability, and atypical patterns. You will also examine how causal AI can be used to separate genuine sleep-related causes and effects from confounding factors. Our aim is not only to create algorithms that are accurate in detecting abnormalities in sleep but that are also interpretable, robust, and fair. 

You must have a strong technical background in signal processing and/or AI, be proactive and eager to work in a highly interdisciplinary environment at the frontier of AI for healthcare, paediatric neuroscience, and clinically relevant signal processing. This is an exciting opportunity to contribute to research with strong potential for future real-world impact. 

Early application is strongly encouraged – the PhD studentship will be awarded once a suitable candidate is found. Start date is flexible.

The PhD student will be integrated in the EPSRC-funded project EPIC: http://edin.ac/epic-infant.  

Informal enquiries to javier.escudero@ed.ac.uk are welcome but please note the eligibility criteria.

Minimum criteria: 

• a 2:1 undergraduate degree (or equivalent).

• the University’s English language requirements.

  It is essential that a successful candidate has a strong background in signal processing, deep learning or artificial intelligence (AI). 

  They must also have an interest in clinical applications.

Desirable criteria:

• experience processing brain activity. 

Tuition fees + stipend are available for Home/EU and International students.

Further information and other funding options.

This PhD project aims to develop a flexible, laser-based gas monitoring platform integrated within soft robotic systems for real-time detection of hazardous gases in inaccessible environments. The research will focus on advanced laser spectroscopic sensing techniques implemented in fibre-based architectures, enabling compact, lightweight, and highly sensitive gas detection. Target gases include ammonia (NH₃), hydrogen (H₂), and methane (CH₄), all of which are critical in fuel transportation and energy infrastructure due to their flammability and toxicity.

The project will explore wavelength-selective laser spectroscopic sensing for high specificity and sensitivity, alongside fibre design optimization to enhance gas diffusion, signal strength, and mechanical resilience. Integration of the sensing fibre into soft robotic platforms will be a key challenge, requiring innovative approaches to ensure flexibility, durability, and minimal performance degradation under deformation.

The envisioned system will enable soft robots to navigate confined or hazardous environments, such as pipelines, storage facilities, or industrial plants, where human access is limited or unsafe. By embedding distributed sensing capabilities directly into the robot’s structure, the platform will provide continuous, real-time monitoring of gas leaks or accumulation.

This interdisciplinary research combines photonics, soft robotics, and sensing technologies, aiming to deliver robust, scalable solutions for industrial safety and environmental monitoring. The outcomes have the potential to significantly enhance autonomous inspection systems in energy and transportation sectors.

Primary objectives:

1. Develop fibre-based laser sensing systems for selective detection of NH₃, H₂, and CH₄
2. Design and optimize optical fibres for enhanced gas-light interaction and sensitivity
3. Integrate flexible, miniature sensing fibres into soft robotic platforms
4. Achieve real-time gas monitoring in confined or inaccessible environments
5. Improve robustness and durability of sensing systems under dynamic motions
6. Validate system in realistic operational scenarios relevant to industrial safety

Required skills: 

1. Background in optics or electrical engineering
2. Experienced in optical design and signal processing
3. Basic understanding of soft robotics or flexible systems
4. Programming skills for data acquisition and analysis (e.g., Python, MATLAB)
5. Signal processing and data interpretation skills
6. Ability to work in an interdisciplinary research environment

Please note that this advert will close as soon as a suitable candidate is found.

• a 2:1 undergraduate degree (or equivalent) in Electronic and Computer Science or Mechanical Engineering, possibly supported by an MSc Degree.
• the University’s English language requirements

Applications are welcomed from self-funded students, or students who are applying for scholarships from the University of Edinburgh or elsewhere

Further information and other funding options.