Student project: AI for modality-agnostic biometric identification using diverse biosignals

What you will do

We are seeking an intern with a strong background in signal processing and machine learning to join our team and conduct a biometric identification study for users of wearable devices. The involved data sets include open ECG datasets, e.g., Physionet and open algorithms used in domains, e.g., face recognition, gait recognition. This role provides an excellent opportunity to apply your technical skills in a real-world research setting and contribute to advancements in biometric identification technology. You will work closely with a multidisciplinary team to develop and test algorithms aiming to identify individuals based on their biosignal uniqueness. 

In short, the internship involves: 

• Feature Engineering: Identify relevant features from ECG signals for biometric identification, leveraging signal processing and spectral analysis techniques. 
• Machine Learning Model Development: Design, train, and evaluate machine learning models for biometric identification, with a focus on model robustness and accuracy. 
• Algorithm Optimization: Optimize algorithms for performance, accuracy, and computational efficiency. This may include using deep learning techniques. 
• Documentation and Reporting: Maintain clear and thorough documentation of methodologies, code, and results. Regularly report findings to the project team and stakeholders. 
• Collaboration and Communication: Work with senior researchers and developers to troubleshoot issues, incorporate feedback, and refine approaches based on experimental results. 

The internship work and activities will be organized with a scrum-like methodology: you will maintain the backlog in coordination with your mentors. You will select prioritized tasks from the backlog, and you will tackle and evaluate them on a biweekly basis. At the end of each biweekly iteration, you will showcase the progress made and will reflect on insights and improvements to focus on. Additional stakeholders may take part in the showcases to get better feedback on the study. 

What we do for you 

• We have a diverse team of experts both from the technical and biomedical sides to supervise and support you. 
• We have a challenging problem where you have the freedom to help develop it in a specific direction. 
• You will join the Digital Twin team of OnePlanet, which employs state-of-the-art knowledge on machine learning for precision medicine. 
• You will be able to exchange views and knowledge with the OnePlanet and Imec community of experts and scientists, widening your professional network. 
• At OnePlanet we embrace diversity and thus give equal opportunities to intern candidates with diverse backgrounds.  
  
  

Who you are

• MSc student enrolled in Electrical/Biomedical Engineering, Computer Science, or a related field. 
• Signal Processing Skills: Experience with ECG and other physiological signals; familiarity with preprocessing techniques like filtering, peak detection, and Fourier transforms. 
• Machine Learning Knowledge: Understanding of machine learning concepts, with hands-on experience in model building and evaluation (e.g., classification models, feature selection, CNNs, RNNs, transformer-like AI models). 
• Programming Skills: Proficiency in Python (NumPy, SciPy, pandas) and machine learning libraries such as scikit-learn, TensorFlow, or PyTorch. 
• Analytical Skills: Ability to analyze large datasets and extract meaningful insights for model improvement. 
• Plus – Basic understanding of agile/scrum. 
• Plus – experience working with personalized healthcare data 
• Plus – Leverage cloud platforms such as Microsoft Azure or HPC environments to manage large datasets and accelerate model training and optimization. 

Interested

Does this position sound like an interesting next step in your career at imec? Don’t hesitate to submit your application by clicking on ‘APPLY NOW’.
Should you have more questions about the job, you can contact Lei Wang (Lei.Wang@imec.nl).