How anushreeankola/multichannel-eeg-based-principal-component-sentiment-disorder-detection-model works
This is a research prototype for detecting sentiment from multichannel EEG. The documented workflow derives information from EEG signals, reduces dimensions with PC-RoDx, identifies sentiment with DEAn, and uses HOPe to optimize the models. The README describes these capabilities but provides no source excerpts tying them to particular files, so file assignments and unshown implementation details are omitted.
Main entry points: PrincipalComponet.R PC-RoDx
Components 6
EEG analysis
- EEG dataset
- Signal inference
- PC-RoDx
PrincipalComponet.R - DEAn sentiment
Model optimization
- HOPe
Other components
- Sentiment result
Connections 7
- EEG dataset → Signal inference: provides signals
README.md - Signal inference → PC-RoDx: reduces dimensions
README.md - Signal inference → DEAn sentiment: supports analysis
README.md - PC-RoDx → HOPe: is optimized by
README.md - DEAn sentiment → HOPe: is optimized by
README.md - DEAn sentiment → Sentiment result: detects sentiment
README.md - HOPe → Sentiment result: optimizes detection
README.md