Postdoc Research Associate in Multimodal biomedical AI for emotion recognition
Nowadays, the widespread use of wearable sensors, along with the improved capabilities of data collection, have increased the availability of biomedical data, setting the foundations for developing new multimodal artificial intelligence (AI) tools able to capture the complexity of human emotions.
Emotion recognition is a key task in several fields of activities, such as education, marketing, and mental health monitoring.
This position is an exciting opportunity for an enthusiastic machine learning researcher to push the boundaries of multimodal-AI by developing new models that incorporate data across several modalities, including biosensor, imaging, text, social and environmental data.
The post-holder will design and develop new algorithms and associated software
stack for multimodal signal analysis and monitoring. The post holder will focus on technical algorithmic developments such as using unsupervised and self-supervised learning methods for data synchronization, feature extraction and selection, and multimodal information fusion to leverage the complementary nature of different modalities effectively.
The successful applicant will work in an interdisciplinary environment with academic experts from Social Gerontology, Psychology, Design, Smart Composite Material, and Artificial Intelligence.
The School of Biomedical Engineering & Imaging Sciences at King's College London provide a cutting-edge research environment dedicated to developing, clinical translation, and clinical application of medical imaging and computational modelling technologies. It offers an exciting opportunity to perform truly translational research, from basic science through to the clinic.
This post will be offered on a fixed-term contract until 1st May 2025 (with possibility of extension subject to funding)
This is a full-time post
- Development of multimodal AI tools for emotion recognition and monitoring
- Development of analytical tools to extract quantitative information from multiple sources ( images, text , physiological signals, clinical features)
- Development of machine learning tool for prediction and prognosis.
- Perform statistical analyses and modelling on large datasets.
- Data curation and organization in a structured infrastructure.
- Adhere to project’s milestone deadlines.
- Publish methods and findings in international journal.
- Actively collaborate will clinical and industrial partners.
The above list of responsibilities may not be exhaustive, and the post holder will be required to undertake such tasks and responsibilities as may reasonably be expected within the scope and grading of the post.
Skills, knowledge, and experience
1. PhD degree in relevant area*
2. Experience in medical image processing
3. Experience in signal processing
4. Experience in machine/deep learning
5. Experience in statistical analysis
6. Experience in developing good quality software using Python
7. Knowledge of machin/deep learning libraries and applications (SciKit Learn, pytorch, etc, )
8. Knowledge of data science and statistical modelling packages (Pandas, SciPy/Statsmodels)
9. History of publishing research articles in international journals and/or conferences.
Please note that this is a PhD level role but candidates who have submitted their thesis and are awaiting award of their PhDs will be considered. In these circumstances the appointment will be made at Grade 5, spine point 30 with the title of Research Assistant. Upon confirmation of the award of the PhD, the job title will become Research Associate and the salary will increase to Grade 6.
1. Experience in physiological signals processing
2. Independent and interdisciplinary researcher
3. Experience in working in a multi-disciplinary team