Case Study 3: Predicting Stress from Wearables
From store.empatica.com
Learning Objectives
- gain proficiency handling very large datasets
- learn about special issues in processing and cleaning of sensor data
- use high-dimensional data to predict a biomedical outcome
Case Study Goals
- Determine whether sensor data are useful in predicting stress
- Determine which types of sensor data are most useful in predicting stress, alone or in combination
- Determine whether we can detect stress only using the wrist-worn wearable
Data
- Data for this case study are available on the UCI Machine Learning Repository site for the Wearable Stress and Affect Detection data.
Assignments and Reports
Report and reproducible code (Group assignment due 6/16): produce a 8 page (maximum) report using R markdown that clearly addresses the case study goals. This report should follow the format of a standard scientific report and should include sections for the introduction, methods, results, and discussion. The methods section should clearly identify the approach to model selection and evaluation, and the results section should clearly specify the final model selected, along with evidence the model provides a good fit to the data. Code should be fully reproducible.
Peer review of reports (Individual assignment due 6/18): using the peer review rubric provided, provide constructive feedback on the other group’s report you have been assigned
Revised report and response to reviews (Group assignment due 6/22): groups may submit revised reports and must submit a point-by-point response to the review comments provided
Resources
Schmidt et al, Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection
Video Lectures (See Sakai)
[Predicting Stress from Wearable Sensors]
[Dealing with File Types]
[Alignment of Data]
[Data Considerations]
[Validation of Sensors]
[Common Pitfalls to Avoid]