This paper presents an Internet of Things (IoT) approach to Human Activity Recognition (HAR) using remote monitoring of vital signs in the context of a healthcare system for self-managed chronic heart patients. Our goal is to create a HAR-IoT system using learning algorithms to infer the activity done within 4 categories (lie, sit, walk and run) as well as the time consumed performing these activities and, finally giving feedback during and after the activity. Alike in this work, we provide a comprehensive insight on the cloud-based system implemented and the conclusions after implementing two different learning algorithms and the results of the overall system for larger implementations.