Open Positions
Please check our positions below. If you are interested in joining our lab, contact nsquared@fau.de with a short description of your scientific background and what you would like to do, e.g. bachelor/master thesis.
Postdoctoral Researcher
PhD Candidate
Student Assistant
Master's Thesis
Design, construction and validation of a knee extension dynamometer
Goal
For studies in the field of neuromuscular physiology and sports science, you will design, build and test a dynamometer that measures the isometric knee extension force. You will take existing dynamometers used in research and our lab as inspiration and are responsible for the full mechanical design and layout, choice of materials and electronic components. Depending on the progress of the project, you will then test and validate the dynamometer in a small study on a number of participants. A background in mechanical engineering, including Computer Aided Design (CAD) is strongly recommended.
Requirements
- Engineering background (mechanical engineering, medical engineering, etc…)
- Experience in CAD
- Experience with electronics and microcontrollers beneficial
- Ability to work independently and sound time management skills
- Fluent in english
Supervisor
Marius Oßwald, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Case Study: Enabling proprioception through vibration patterns on the upper back
Goal
Providing proprioception and haptic feedback of hand movements through vibration patterns on the upper back. Based on previous work, this project includes the design of a case study to determine the number of poses the user can distinguish and to test different feedback strategies (e.g., placement, type of sensor).
Tasks
- Literature research on haptic and proprioceptive feedback strategies
- Implementation of a visual feedback mechanism based on virtual hand developed in the lab
- Case study design, execution, and evaluation
Requirements
- Solid Python skills
- Prototyping / hardware skills (3D-printing, soldering, microcontroller skills) are beneficial
- Independent and reliable working style
Supervisor
Charlotte Pradel, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Addressing Data and Concept Drift in Neural Interfaces: Monitoring, Mitigation, and Comparative Evaluation
Goal
Data and concept drifts pose significant challenges for machine learning solutions, particularly in systems designed to control assistive devices for generating hand movements. In clinical practice, the majority of prostheses available on the market rely on two electrodes for simple yet highly reliable actuation, thereby mitigating many issues. However, research solutions often incorporate multiple electrodes to capture a more nuanced understanding of the user’s neural activity, albeit with a tendency to degrade over time with usage. Our goal is to enhance and mitigate this phenomenon.
Tasks
- Coming up with solutions to check and monitor data and concept drift,
- implementing real-time solutions to counteract such drifts,
- and in investigating if the counteractions developed are better than a system without said counteractions implemented.
Requirements
- Solid python skills and the willingness to spend time understanding how to create real-time neural interfaces
- Fun at reading technical and complex academic material on machine learning
- Ability to work independently and sound time management skills
Supervisor
Raul Sîmpetru, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Exploring Neural Manifolds in Motor Control: Dimensionality Reduction of Non-Invasive Motor Unit Recordings for Understanding Hand Movements
Goal
Dimensionality reduction can extract and make complex relationships between neural signals understandable by compressing n-D spaces into 2- or 3-D. In neuroscience such human understandable spaces are called neural manifolds. Using brain recordings, it has been shown that movements generally inhabit a low dimensional rotational space (https://doi.org/10/f997z4). We are interested in whether these manifolds are also present in non-invasive recordings of motor units during different hand movements.
Tasks
- Implementing different dimensionality reduction algorithms from the literature (e.g. http://jmlr.org/papers/v22/21-0131.html),
- understanding their strengths and weaknesses first by simulated extreme examples (think cinnamon roll dataset) and later using real EMG signals,
- and in interpreting the results by comparing the extracted lower dimensionality information to the movement executed.
Requirements
- Solid python skills
- Fun at reading technical and complex (sometimes highly complex) academic material on dimensionality reduction and neuroscience
- Ability to work independently and sound time management skills
Supervisor
Raul Sîmpetru, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Bachelor's Thesis
Design, construction and validation of a knee extension dynamometer
Goal
For studies in the field of neuromuscular physiology and sports science, you will design, build and test a dynamometer that measures the isometric knee extension force. You will take existing dynamometers used in research and our lab as inspiration and are responsible for the full mechanical design and layout, choice of materials and electronic components. Depending on the progress of the project, you will then test and validate the dynamometer in a small study on a number of participants. A background in mechanical engineering, including Computer Aided Design (CAD) is strongly recommended.
Requirements
- Engineering background (mechanical engineering, medical engineering, etc…)
- Experience in CAD
- Experience with electronics and microcontrollers beneficial
- Ability to work independently and sound time management skills
- Fluent in english
Supervisor
Marius Oßwald, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Addressing Data and Concept Drift in Neural Interfaces: Monitoring, Mitigation, and Comparative Evaluation
Goal
Data and concept drifts pose significant challenges for machine learning solutions, particularly in systems designed to control assistive devices for generating hand movements. In clinical practice, the majority of prostheses available on the market rely on two electrodes for simple yet highly reliable actuation, thereby mitigating many issues. However, research solutions often incorporate multiple electrodes to capture a more nuanced understanding of the user’s neural activity, albeit with a tendency to degrade over time with usage. Our goal is to enhance and mitigate this phenomenon.
Tasks
- Coming up with solutions to check and monitor data and concept drift,
- implementing real-time solutions to counteract such drifts,
- and in investigating if the counteractions developed are better than a system without said counteractions implemented.
Requirements
- Solid python skills and the willingness to spend time understanding how to create real-time neural interfaces
- Fun at reading technical and complex academic material on machine learning
- Ability to work independently and sound time management skills
Supervisor
Raul Sîmpetru, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Exploring Neural Manifolds in Motor Control: Dimensionality Reduction of Non-Invasive Motor Unit Recordings for Understanding Hand Movements
Goal
Dimensionality reduction can extract and make complex relationships between neural signals understandable by compressing n-D spaces into 2- or 3-D. In neuroscience such human understandable spaces are called neural manifolds. Using brain recordings, it has been shown that movements generally inhabit a low dimensional rotational space (https://doi.org/10/f997z4). We are interested in whether these manifolds are also present in non-invasive recordings of motor units during different hand movements.
Tasks
- Implementing different dimensionality reduction algorithms from the literature (e.g. http://jmlr.org/papers/v22/21-0131.html),
- understanding their strengths and weaknesses first by simulated extreme examples (think cinnamon roll dataset) and later using real EMG signals,
- and in interpreting the results by comparing the extracted lower dimensionality information to the movement executed.
Requirements
- Solid python skills
- Fun at reading technical and complex (sometimes highly complex) academic material on dimensionality reduction and neuroscience
- Ability to work independently and sound time management skills
Supervisor
Raul Sîmpetru, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Research Lab
Case Study: Enabling proprioception through vibration patterns on the upper back
Goal
Providing proprioception and haptic feedback of hand movements through vibration patterns on the upper back. Based on previous work, this project includes the design of a case study to determine the number of poses the user can distinguish and to test different feedback strategies (e.g., placement, type of sensor).
Tasks
- Literature research on haptic and proprioceptive feedback strategies
- Implementation of a visual feedback mechanism based on virtual hand developed in the lab
- Case study design, execution, and evaluation
Requirements
- Solid Python skills
- Prototyping / hardware skills (3D-printing, soldering, microcontroller skills) are beneficial
- Independent and reliable working style
Supervisor
Charlotte Pradel, M.Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.
Enhancing Movement Intent Detection Systems: Data Acquisition, Optimization and Validation
Goal
ML-based movement intent detection systems are highly subjective to the individual user. To address this, we aim to conduct hyperparameter searches to maximize performance for the individual user while ensuring effective generalization across different users.
Tasks
- Recording baseline data from hand and leg movements using bleeding edge EMG bracelet systems,
- Implementing hyperparameter optimization techniques utilizing Optuna,
- Validate results through real-time experiments.
Requirements
- Solid python skills and the willingness to spend time understanding how to create real-time neural interfaces,
- Fun at reading technical and complex academic material on machine learning,
- Ability to work independently and sound time management skills.
Supervisor
Vlad Cnejevici, M. Sc. and Raul Sîmpetru, M. Sc.
Application
Please provide a short CV, transcript of records and a brief description of one of your last projects to nsquared@fau.de.