How poornachandra-29/eeg-to-text works
This repository combines two products: EEG-to-text decoding and sentiment experiments, and NeuroRead, a research-grounded participant-analysis application. The documented experimental workflow prepares ZuCo and sentiment datasets, trains decoding/classification models, then evaluates decoding or the zero-shot sentiment pipeline. NeuroRead ingests scientific literature, analyzes participant measurements, grounds interpretations in retrieved evidence, and produces reports or serves a dashboard. Several NeuroRead orchestration links are visible in excerpts; unsampled model-training and evaluation internals are represented only at their documented boundaries.
Main entry points: main.py NeuroRead CLI · server.py Dashboard API · construct_dataset_mat_to_pickle_v1.py Dataset preparation · synthesizer.py Evidence retrieval
Components 24
EEG Experiments
- Dataset preparation
util/construct_dataset_mat_to_pickle_v1.py - EEG dataset
data.py - EEG decoder
model_decoding.py - Decoder training
train_decoding.py - Decoder evaluation
eval_decoding.py - Sentiment classifier
model_sentiment.py - Sentiment evaluation
eval_sentiment.py
Research Literature
- Paper discovery
neuroread_rag/discovery/aggregator.py - Literature ingestion
neuroread_rag/ingestion/pipeline.py - Hybrid index
neuroread_rag/ingestion/vector_store.py - Evidence retrieval
neuroread_rag/retrieval/synthesizer.py
Participant Analysis
- MAT processing
neuroread_rag/participant_analysis/mat_processor.py - Participant analysis
neuroread_rag/participant_analysis/analyzer.py
Grounded Results
- Scientific grounding
neuroread_rag/interpretation/grounding_engine.py - Recommendations
neuroread_rag/recommendations/recommender.py
Reports and Dashboard
- Report generation
neuroread_rag/reporting/report_generator.py - Dashboard API
neuroread_rag/server.py - Web dashboard
neuroread_rag/frontend/app.js - NeuroRead CLI
neuroread_rag/main.py
Other components
- Researcher
- ZuCo data
- Sentiment data
- Academic sources
- Participant data
Connections 31
- Researcher → Dataset preparation: prepares datasets
README.md - ZuCo data → Dataset preparation: supplies MAT files
README.md - Sentiment data → Dataset preparation: supplies labels
README.md - Dataset preparation → EEG dataset: creates dataset
README.md - EEG dataset → Decoder training: feeds training
train_decoding.py - Decoder training → EEG decoder: trains
train_decoding.py - Researcher → Decoder evaluation: runs evaluation
README.md - EEG decoder → Decoder evaluation: evaluated by
README.md - Sentiment data → Sentiment classifier: trains classifier
README.md - Sentiment classifier → Sentiment evaluation: used in pipeline
README.md - EEG decoder → Sentiment evaluation: decoded input
README.md - Researcher → NeuroRead CLI: selects participant
neuroread_rag/main.py - Academic sources → Paper discovery: queried for papers
neuroread_rag/discovery/aggregator.py - Paper discovery → Literature ingestion: supplies papers
neuroread_rag/ingestion/pipeline.py - Literature ingestion → Hybrid index: indexes literature
neuroread_rag/ingestion/pipeline.py - Participant data → MAT processing: loads participant data
- MAT processing → Participant analysis: produces measurements
- NeuroRead CLI → Participant analysis: runs analysis
neuroread_rag/main.py - NeuroRead CLI → Literature ingestion: runs ingestion
neuroread_rag/main.py - NeuroRead CLI → Hybrid index: opens index
neuroread_rag/main.py - NeuroRead CLI → Evidence retrieval: creates synthesizer
neuroread_rag/main.py - Evidence retrieval → Hybrid index: retrieves evidence
neuroread_rag/retrieval/synthesizer.py - NeuroRead CLI → Scientific grounding: grounds findings
neuroread_rag/main.py - Scientific grounding → Evidence retrieval: uses synthesis
neuroread_rag/interpretation/grounding_engine.py - NeuroRead CLI → Report generation: generates report
neuroread_rag/main.py - Report generation → Recommendations: renders recommendations
neuroread_rag/reporting/report_generator.py - NeuroRead CLI → Dashboard API: launches server
neuroread_rag/main.py - Dashboard API → Web dashboard: serves dashboard
neuroread_rag/server.py - Dashboard API → Evidence retrieval: retrieves search results
neuroread_rag/server.py - Dashboard API → Scientific grounding: initializes grounding
neuroread_rag/server.py - Dashboard API → Report generation: initializes report
neuroread_rag/server.py