ABSTRACT
This chapter compares smart healthcare monitoring system using LoRaWAN IoT and machine learning methods using medical data. The sensor medical data uploaded on the cloud is analyzed, and data predictions are explained briefly with the machine learning algorithm-based decision tree and random forest algorithm. The 6LoWPAN is the most energy-efficient communication in smart sensor networks, and it is also used to analyze the operation time of the wireless network for the health monitoring system. Patients9 electrocardiogram (ECG) signals for remote real-time monitoring are also analyzed to predict patients’ cardiovascular disease. This chapter highlights the standard design systems of intelligent IoT-based machine learning methods with a dataset taken from the UCI repository. The decision tree feature selection and random forest classifiers are used in this chapter. The proposed model shows an accuracy of about 4% for training data and 5% improvement in accuracy for testing data.
