Register now After registration you will be able to apply for this opportunity online.
Characterization and classification of diseases using ML/AI approaches using wearable-based physical activity data
This project is motivated by the emerging potential of digital biomarkers derived from passive sensing data to assess and characterize disease characteristics. Widespread wearables and smartwatches enable non-invasive, passive, objective, and continuous measurement of physical activity throughout 24 hours. Combined with cutting-edge ML/AI approaches, this 24-hour passive sensing data may reveal distinct physical activity profiles associated with illnesses, which can be used for the classification of different types of diseases. Distinct physical activity profiles may represent different manifestations of the health states including circadian rest-activity rhythm among diseases. To this end, we aim to conduct retrospective data analysis to conduct an in-depth investigation of wearable-based physical activity data by varying resolutions and build ML/AI models for disease classifications.
Keywords: Digital health, digital biomarker, machine learning, artificial intelligence, data science, classification.
Candidate profile: We are searching for highly motivated, collaborative, proactive, and self-directed students with an interest in digital health and data science. A successful candidate would have the following skill sets:
1) Proficient or advanced in R or Python.
2) Theoretical and programming knowledge of statistical modeling.
3) Theoretical and programming knowledge of different ML/AI approaches.
4) Prior experience in data management, data manipulation, data cleaning, and data analysis.
Master thesis task:
1) Systematically investigate and explore different resolutions of wearable-based accelerometer data to characterize physical activity
2) Investigate different ML/AI approaches for disease classifications based on wearable-based physical activity data
Start: Immediately
Methodology: Retrospective data analysis
Duration: 6 months
Candidate profile: We are searching for highly motivated, collaborative, proactive, and self-directed students with an interest in digital health and data science. A successful candidate would have the following skill sets: 1) Proficient or advanced in R or Python. 2) Theoretical and programming knowledge of statistical modeling. 3) Theoretical and programming knowledge of different ML/AI approaches. 4) Prior experience in data management, data manipulation, data cleaning, and data analysis.
Master thesis task: 1) Systematically investigate and explore different resolutions of wearable-based accelerometer data to characterize physical activity 2) Investigate different ML/AI approaches for disease classifications based on wearable-based physical activity data
Start: Immediately
Methodology: Retrospective data analysis
Duration: 6 months
ML/AI approach for disease classification based on in-depth characterization of wearable-based physical activity data
ML/AI approach for disease classification based on in-depth characterization of wearable-based physical activity data
Interested students are invited to send an email with their CV and motivation letter to Jinjoo Shim at jshim@ethz.ch.
Interested students are invited to send an email with their CV and motivation letter to Jinjoo Shim at jshim@ethz.ch.
