prabhu-omkar/cardioedge-esp32

How prabhu-omkar/cardioedge-esp32 works

CardioEdge-ESP32 is an offline ECG monitor and development pipeline: the device samples live or demo ECG, processes and quality-gates beats, classifies accepted beats, then presents rolling verdicts and alerts. In parallel, Python prepares patient-wise datasets using the same DSP core, trains CNN and Random Forest models, and evaluates them. The README documents the end-to-end behavior; source excerpts show key firmware, DSP, dataset, and training details, but not every runtime call, so some links rely on documentation.

Main entry points: main.cpp ESP32 Runtime · core.py Python DSP Binding · common.py ML Data Utilities · ecg_core.cpp ECG DSP Core

Components 27

ESP32 Monitoring

ESP32 Runtime firmware/src/main.cpp
Demo Clips firmware/src/demo_clips.h
Live State firmware/src/state.h

Signal Processing

ECG DSP Core firmware/lib/ecg_core/ecg_core.cpp
DSP Contracts firmware/lib/ecg_core/ecg_config.h
Beat Features firmware/lib/ecg_core/ecg_core.cpp
Signal Quality Gate firmware/lib/ecg_core/ecg_core.cpp
Rhythm and HRV firmware/lib/ecg_core/ecg_core.cpp

Classification

Dual Classifiers firmware/src/classifiers.cpp
Int8 CNN firmware/src/model_cnn.h
Random Forest firmware/src/rf_predict.h

Data and Evaluation

Patient-wise Dataset ml/dataset.py
Python DSP Binding ml/core.py
ML Data Utilities ml/common.py
CNN Training ml/train_cnn.py
RF Training ml/train_rf.py
Model Evaluation ml/evaluate.py
Capture Evaluation ml/eval_capture.py
QRS Evaluation ml/eval_qrs.py
SQA Evaluation ml/sqa_eval.py

User Outputs

OLED Display firmware/src/display.cpp
Phone Dashboard firmware/src/webui.cpp
Dashboard Page firmware/src/dashboard_html.h
Buzzer and LED firmware/src/main.cpp

Other components

ECG Front End
ECG Databases
Monitor User

Connections 30

ECG Front End → ESP32 Runtime: supplies samples README.md
Demo Clips → ESP32 Runtime: provides clips firmware/src/main.cpp
ESP32 Runtime → ECG DSP Core: streams samples README.md
ECG DSP Core → Signal Quality Gate: assesses quality firmware/lib/ecg_core/ecg_core.cpp
ECG DSP Core → Beat Features: extracts beats README.md
Signal Quality Gate → Beat Features: gates classification README.md
ESP32 Runtime → Dual Classifiers: classifies beat firmware/src/main.cpp
Dual Classifiers → Int8 CNN: runs CNN firmware/src/classifiers.cpp
Dual Classifiers → Random Forest: runs forest firmware/src/classifiers.cpp
ESP32 Runtime → Rhythm and HRV: applies rhythm logic README.md
ESP32 Runtime → Live State: updates snapshot firmware/src/main.cpp
ESP32 Runtime → OLED Display: refreshes display README.md
ESP32 Runtime → Phone Dashboard: serves dashboard README.md
Phone Dashboard → Dashboard Page: serves page firmware/src/webui.cpp
ESP32 Runtime → Buzzer and LED: drives alarm README.md
Monitor User → OLED Display: views verdicts README.md
Monitor User → Phone Dashboard: views live data README.md
ECG Databases → Patient-wise Dataset: provides records ml/dataset.py
Patient-wise Dataset → Python DSP Binding: processes recordings ml/dataset.py
Python DSP Binding → ECG DSP Core: calls shared DSP README.md
Patient-wise Dataset → ML Data Utilities: writes split data README.md
ML Data Utilities → CNN Training: loads training splits ml/train_cnn.py
ML Data Utilities → RF Training: loads training splits ml/train_rf.py
ML Data Utilities → Model Evaluation: loads test splits ml/evaluate.py
CNN Training → Int8 CNN: exports device model ml/train_cnn.py
RF Training → Random Forest: exports forest model README.md
Model Evaluation → SQA Evaluation: measures gate effects ml/evaluate.py
Model Evaluation → Python DSP Binding: evaluates inference ml/evaluate.py
Capture Evaluation → Python DSP Binding: evaluates captures ml/eval_capture.py
QRS Evaluation → Python DSP Binding: evaluates detection ml/eval_qrs.py

Drawn by GitDiagram on November 14, 2026 from the repository's file tree, README and source files. Read as Markdown ·