Education

Internships, Master’s Thesis,
Bachelor & Semester Projects

We offer projects related to (i) the development of new methods in healthcare data; (ii) the derivation of theoretical models, and (iii) the conception and execution of experimental studies for the understanding of SCI secondary conditions. Projects apply advanced machine learning, sensing technology, and robotics towards digital twins in digital health care and rehabilitation. Interested students may check our open student projects or check our research projects and contact the responsible person directly for further questions.

Your own project ideas?

It is always possible to find a project for motivated students with their own ideas in the fields of assistive health care and rehabilitation technologies, advanced machine learning modelling, and applied robotics in health care. Please contact Dr Diego Paez if you would like to pursue a project which is not listed below.

Sirop Links

Currently, the following student projects are available. Please contact the responsible supervisor and apply with your CV and transcripts.

Master Thesis: Development of a Customized Knee Orthosis for Osteoarthritis

Osteoarthritis (OA) presents a significant challenge in healthcare, necessitating innovative solutions to alleviate pain, enhance mobility. This thesis documents the research and development journey of an OA knee orthosis within the Spinal Cord and Artificial Intelligence Lab (SCAI-Lab) at ETH Zurich. This thesis is a close collaboration between the ORTHO-TEAM Group and the SCAI-Lab at ETH Zurich. The collaboration offers a unique exchange of expertise and resources between industry and academia. Together, we aim to make meaningful progress in the field of and empower students to make valuable contributions to their academic pursuits.

Keywords

Osteo Arthritis, Orthosis, Biomechanics, AI, Medical Data, Healthcare

Labels

Master Thesis , ETH Zurich (ETHZ)

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-03-30 , Earliest start: 2026-03-01 , Latest end: 2026-09-30

Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne , Empa , University of Basel , University of Berne , Zurich University of Applied Sciences , Università della Svizzera italiana , Hochschulmedizin Zürich , Lucerne University of Applied Sciences and Arts , Institute for Research in Biomedicine , CSEM - Centre Suisse d'Electronique et Microtechnique

Organization Spinal Cord Injury & Artificial Intelligence Lab

Hosts Paez Diego, Dr. , Paez Diego, Dr.

Topics Medical and Health Sciences , Engineering and Technology

(Master Thesis / Internship) - Personalized Low Latency Interactive AI

We are seeking one highly motivated student to join our innovative project focused on developing a cutting-edge voice recognition and personalization platform for wheelchair users. This project aims to deliver low-latency, context-aware, and personalized AI interactions in noisy, multi-user environments using edge devices powered by NVIDIA Orin. The system leverages advanced models and distilled LLMs, combined with biosignal tracking, to provide asynchronous interactions that are well-organized and accessible to doctors, while ensuring user privacy.

Keywords

Voice recognition, AI personalization, low latency, SLMs and distilled LLMs, Edge-Computing, audio processing

Labels

Semester Project , Internship , Master Thesis

PLEASE LOG IN TO SEE DESCRIPTION

More information

Open this project...

Published since: 2026-03-05 , Earliest start: 2026-04-01 , Latest end: 2026-12-31

Applications limited to ETH Zurich , EPFL - Ecole Polytechnique Fédérale de Lausanne , CSEM - Centre Suisse d'Electronique et Microtechnique , CERN , Berner Fachhochschule , IBM Research Zurich Lab , Hochschulmedizin Zürich , University of Zurich , Zurich University of Applied Sciences , Lucerne University of Applied Sciences and Arts

Organization Sensory-Motor Systems Lab

Hosts Paez Diego, Dr.

Topics Engineering and Technology

(Master Thesis / Internship) - Video to 3D Pose Estimation & Mesh Recovery to Understand Walking Aids Effects in Cerebral Palsy

In this project, we aim to understand and quantitatively evaluate the use of walking aids through monocular video assessment in children with pathological gait. The objective is to enable clinically relevant decision support in remote or resource-limited settings, where traditional motion capture systems are not readily available. To achieve this, we employ a markerless analysis framework that integrates both \textit{3D pose estimation} and \textit{3D mesh recovery} from monocular video recordings, allowing detailed reconstruction of body kinematics and surface-level body geometry. Using our proposed pipeline, the effects of orthotic devices on gait patterns in children with cerebral palsy (CP) will be evaluated. The framework leverages a CP-specific dataset to benchmark multiple state-of-the-art 2D and 3D pose estimation models, as well as 3D human mesh recovery approaches, in order to determine the most accurate representation of pathological gait. The best-performing models will then be fine-tuned for the CP population, followed by multivariate time-series analysis of joint-level kinematics. This analysis will compare gait characteristics across three conditions: healthy individuals, children with CP without orthosis, and children with CP using orthotic devices, enabling a comprehensive assessment of how assistive devices influence gait biomechanics.

Keywords

3D Pose Estimation, Cerebral Palsy, Gait Analysis, Orthosis, Stable Diffusion, Deep Learning

Labels

Internship , Master Thesis , ETH Zurich (ETHZ)

Description

This project addresses a clinically relevant challenge in pediatric gait analysis by leveraging deep learning–based markerless motion capture methods, including both 3D pose estimation and 3D mesh recovery. The work is hosted at the SCAI-Lab (D-HEST) in collaboration with the AIT Lab (D-INFK), both of which focus on advancing artificial intelligence methods for biomedical applications. Main Objectives: - Develop a robust benchmarking pipeline for evaluating multiple 2D-to-3D pose estimation and 3D mesh recovery models on a cerebral palsy (CP) gait dataset. - Systematically benchmark combinations of 2D keypoint detectors and 3D reconstruction models to identify the best-performing architecture for pathological gait reconstruction. - Fine-tune the best-performing model identified during benchmarking using CP-specific clinical video data to improve robustness and accuracy in pathological gait scenarios. - Evaluate reconstruction accuracy using established metrics such as the Procrustes Aligned Mean Per Joint Position Error (PA-MPJPE) for skeletal pose estimation and the Mean Per Vertex Position Error (MPVPE) for 3D mesh reconstruction. - Perform multivariate time-series analysis of joint angles and kinematic trajectories to quantify the biomechanical impact of orthotic devices by comparing healthy gait, CP gait without orthosis, and CP gait with orthosis. Technical Highlights: - Evaluation of multiple 2D keypoint detection backbones (e.g., Detectron2, AlphaPose, MediaPipe) combined with state-of-the-art 3D lifting and 3D mesh recovery models. - Selection of the most accurate reconstruction pipeline through quantitative benchmarking using pose and mesh reconstruction metrics such as PA-MPJPE and MPVPE. - Domain-specific fine-tuning of the selected best-performing model on CP gait recordings to adapt pretrained networks to atypical kinematics and compensatory gait patterns. - Application of clustering and deep learning approaches (e.g., MVTS models, LSTM-FCNN, and MLP) for multivariate gait time-series analysis and pattern discovery. - Integration of kinematic feature extraction and temporal modeling to identify clinically relevant gait deviations and the biomechanical influence of orthotic support. - Potential for scientific publication depending on the results. Ideal Candidate: We are looking for a motivated Master’s student with experience in data processing (particularly video or motion capture data) and deep learning using PyTorch. Students with backgrounds in Computer Science, Information Technology, Electrical Engineering, or Health Sciences and Technology are especially encouraged to apply. The project requires a 6-month full-time commitment.

Goal

The primary goal of this project is to quantitatively evaluate the impact of orthotic devices on gait patterns in children with cerebral palsy (CP) using markerless motion capture techniques based on 3D pose estimation and 3D human mesh recovery. By reconstructing both skeletal joint trajectories and surface-level body geometry from monocular video, the project aims to provide clinically interpretable biomechanical insights into how orthotic interventions influence pathological gait. To achieve this objective, the following sub-goals are defined: - Develop a markerless motion analysis pipeline. This involves designing a robust pipeline that integrates 2D keypoint detection, 3D pose lifting, and 3D mesh recovery models to reconstruct full-body kinematics from monocular clinical videos. - Benchmark pose and mesh reconstruction models. Combinations of 2D detection backbones and 3D pose and mesh recovery frameworks will be systematically evaluated to identify the most accurate configuration for CP gait analysis. - Perform quantitative accuracy evaluation. Reconstruction performance will be assessed using established metrics such as the Procrustes Aligned Mean Per Joint Position Error (PA-MPJPE) for skeletal pose estimation and the Mean Per Vertex Position Error (MPVPE) for 3D mesh reconstruction. - Fine-tune models for CP gait. The top-performing models identified during benchmarking will be adapted to CP-specific gait characteristics through fine-tuning on annotated clinical datasets, improving robustness to atypical kinematics and compensatory movement patterns. - Generate joint angle time-series. Reconstructed 3D keypoints will be transformed into joint angle trajectories over time, producing clinically interpretable kinematic signals representing the gait cycle. - Perform multivariate time-series analysis. Statistical and deep learning approaches, such as clustering, multivariate time-series models, LSTM-FCNN, and MLP classifiers, will be applied to analyze gait dynamics and compare biomechanical patterns across three groups: healthy individuals, children with CP without orthosis, and children with CP using orthotic devices. - Enable clinically interpretable insights. The analysis will identify kinematic deviations and biomechanical improvements associated with orthotic use, providing quantitative evidence to support clinical decision-making and treatment planning. - Document and disseminate findings. The results will be compiled into a comprehensive research manuscript with the goal of preparing a submission to a relevant peer-reviewed scientific conference or journal.

Contact Details

More information

Open this project...

Published since: 2026-03-05 , Earliest start: 2026-04-01 , Latest end: 2026-12-31

Applications limited to CSEM - Centre Suisse d'Electronique et Microtechnique , CERN , EPFL - Ecole Polytechnique Fédérale de Lausanne , ETH Zurich , IBM Research Zurich Lab , Lucerne University of Applied Sciences and Arts , University of Zurich , Wyss Translational Center Zurich , Zurich University of Applied Sciences , Zurich University of the Arts , Empa , Department of Quantitative Biomedicine , Swiss Institute of Bioinformatics , Università della Svizzera italiana

Organization Spinal Cord Injury & Artificial Intelligence Lab

Hosts Paez Diego, Dr.

Topics Medical and Health Sciences , Information, Computing and Communication Sciences

Semester / Master Thesis: Event Segmentation and Detection in Time-Series for Monitoring Activities of Daily Living in SCI Individuals

This thesis explores precise event segmentation in time-series/video data from wearable sensors to monitor daily activities in spinal cord injury individuals.

Keywords

Machine Learning, Classification, Event Detection, Pattern Recognition, Human Activity Monitoring, Time-series Segmentation

Labels

Semester Project , Internship , Master Thesis

Description

**Background** Spinal cord injuries (SCI) pose significant challenges, impacting millions globally and often leading to reduced mobility and difficulties in daily activities. Monitoring activities of daily living (ADLs) is crucial for assessing overall health. Wearable sensors like IMU sensors, pressure mats, and cameras provide wealth of data showing promise for monitoring daily life, however, intelligently segmenting daily behaviors and activities remains a hurdle. This thesis focuses on researching event segmentation and detection techniques on time-series data from diverse signal modalities and video data. Precise segmentation aims to reveal patterns, anomalies, and critical events, serving as key indicators for individuals' well-being. Accurate event detection holds potential for personalized healthcare, enabling timely interventions and tailored care plans. **Useful References** Find useful resources in the attached .pdf file. **Your Tasks** 1. Dive into existing research on activity recognition, with a focus on event detection and data segmentation. 2. Construct a robust pipeline using sliding ADL classification models. After processing the measurements, fine-tune the model output for precise ADL segmentation. 3. Implement state-of-the-art event detection and data segmentation methods for time-series data such as evolutionary state graph [1]. Compare these advanced techniques with the traditional sliding approach for ADL monitoring. 4. Evaluate the outputs of the ADL segmentation pipeline for outpatient monitoring, focusing on identifying and establishing benchmarks for unknown classes in the data. 5. Craft a concise report summarizing the project’s findings. 6. Preparation of a manuscript showcasing the project's findings, for journal submission (optional). **Your Benefits** Gain unique access and first-hand experience in one of the leading institutions on long-term health management - At the Swiss Paraplegic Center at Nottwil and ETH Zurich. **Your Profile** - Strong experience with Python - Understanding of multi-modal machine learning methods. - Knowledge of virtual environments (conda / docker) - Structured and reliable working style - Ability to work independently on a challenging topic

Goal

Contact Details

More information

Open this project...

Published since: 2026-02-24 , Earliest start: 2025-03-01 , Latest end: 2026-09-30

Applications limited to Balgrist Campus , EPFL - Ecole Polytechnique Fédérale de Lausanne , ETH Zurich , Empa , University of Zurich , CERN , Corporates Switzerland , CSEM - Centre Suisse d'Electronique et Microtechnique , IBM Research Zurich Lab , Fernfachhochschule , Hochschulmedizin Zürich , NCCR Democracy , Zurich University of the Arts , Zurich University of Applied Sciences

Organization Spinal Cord Injury & Artificial Intelligence Lab

Hosts Paez Diego, Dr.

Topics Information, Computing and Communication Sciences , Engineering and Technology

Internships (practical or research) in data collection and processing for clinical studies involving spinal cord injury (SCI)

This hands-on work (internship or semester project) within a clinical setting will bring you close to intelligent health management while exploring multiple data and sensor systems. You will experience multimodal data of robotics rehabilitation, general clinical practice, and detailed clinical studies applied in classification and dimensionality reduction.

Keywords

HR, ECG, BP, wearables, Medical and health science, healthcare

Labels

Internship , Lab Practice

Description

Goal

Contact Details

More information

Open this project...

Published since: 2026-02-24 , Earliest start: 2026-03-02 , Latest end: 2026-12-31

Organization Spinal Cord Injury & Artificial Intelligence Lab

Hosts Paez Diego, Dr.

Topics Medical and Health Sciences

Crowd Simulation for RL Robot Navigation

This project focuses on improving RL-based social navigation by creating a simulation framework with diverse and realistic human behaviors. Current RL methods often train on simplified crowds where all pedestrians behave similarly, which limits generalization in real-world environments.

Keywords

RL, Robot Navigation

Labels

Master Thesis

Description

Goal

Contact Details

More information

Open this project...

Published since: 2026-01-26 , Earliest start: 2026-09-01 , Latest end: 2026-09-30

Applications limited to ETH Zurich

Organization Spinal Cord Injury & Artificial Intelligence Lab

Hosts Alyassi Rashid , Alyassi Rashid , Alyassi Rashid

Topics Engineering and Technology

Education

Internships, Master’s Thesis, Bachelor & Semester Projects

Your own project ideas?

Sirop Links

Master Thesis: Development of a Customized Knee Orthosis for Osteoarthritis

Keywords

Labels

PLEASE LOG IN TO SEE DESCRIPTION

More information

(Master Thesis / Internship) - Personalized Low Latency Interactive AI

Keywords

Labels

PLEASE LOG IN TO SEE DESCRIPTION

More information

(Master Thesis / Internship) - Video to 3D Pose Estimation & Mesh Recovery to Understand Walking Aids Effects in Cerebral Palsy

Keywords

Labels

Description

Goal

Contact Details

More information

Semester / Master Thesis: Event Segmentation and Detection in Time-Series for Monitoring Activities of Daily Living in SCI Individuals

Keywords

Labels

Description

Goal

Contact Details

More information

Internships (practical or research) in data collection and processing for clinical studies involving spinal cord injury (SCI)

Keywords

Labels

Description

Goal

Contact Details

More information

Crowd Simulation for RL Robot Navigation

Keywords

Labels

Description

Goal

Contact Details

More information

Internships, Master’s Thesis,
Bachelor & Semester Projects