We integrate programming, experimental methods, statistics, and machine learning to study emotion and its related disorders. We develop methods and tools for recognizing, predicting, and modeling emotion in behavioral and physiological data.
- Data provisioning: datasets, metadata standards, and discovery infrastructure
- Research tools: open-source toolkits for acquisition, preprocessing, and analysis
- Data science: statistical modeling and machine learning for affective signals
- EMGFlow: github.com/WiIIson/EMGFlow-Python-Package
- RespFlow: github.com/affectivedatascience/respflow
- PyFAME: github.com/Gavin-Bosman/PyFAME
- PyOcclusion: github.com/affectivedatascience/PyOcclusion
- RAVDESS: zenodo.org/record/1188976
- PeakAffectDS: hzenodo.org/records/6403363
- FELT: zenodo.org/records/13243600
- Browse pinned repositories below.
- Questions and bug reports belong in the relevant repository Issues.
- Licenses and citation instructions are defined per repository.
- Contributions: see
CONTRIBUTING.md(when present) and repository-specific guidelines.
- Website: affectivedatascience.com
- PI: Steven R. Livingstone, Ontario Tech University
