Heart Arrhythmia Detection & Monitoring Using Machine Learning & ECG Wearable Device

Heart arrhythmia disease is a heart condition in which the electrical pulses that control the heartbeat become abnormal and leads to an irregular rhythm. In this work, we propose a device that monitors and detects heart arrhythmia, using electrocardiogram signal, machine learning, and Raspberry_PI microcontroller. The proposed methodology has two stages, the first stage is to train the Artificial Neural Network (ANN) model using available databases. After feature extraction, the sample pool is used to train the ANN model using different machine learning tools to obtain the highest accuracy. The second stage is to upload the model into our microcontroller and start predicting real stream ECG signal coming from the sensor. The microcontroller sends the signal and the prediction results to the mobile application and stores it on the cloud for easy access by the user or the physician.