The model use the correlation between physical activities and ECG. The activities detected are : Still , Walk and Running. We also used GradCAM++ to highlight the features affected by each activity To download the dataset : www.kaggle.com/datasets/marcjuniornkengue/human-activity-recognition-using-ecg
- The original dataset : [Pulse Transit Time] (https://physionet.org/content/pulse-transit-time-ppg/1.1.0)
- The authors of the original article about GRAD-CAM++: Aditya Chattopadhay; Anirban Sarkar; Prantik Howlader; Vineeth N Balasubramanian : Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks