Analysis of IoT based multi-parameter patient monitoring system using machine learning

One of the applications of machine learning is analysis of a multi-parameter patient monitoring system. A python 3.7 or higher-based system is developed which can be used in paramedicine to execute different ML algorithms with available datasets such as ECG, heartbeat signal, Blood oxygen saturation (SPO2), temperature, and generates different signals from the data set. This Machine learning-based Multi-Parameter Monitoring (MPM) system is designed in which parameters are monitored by utilizing corresponding sensors and analyzing the parameters using different ML algorithms. In the proposed system sensors and hardware parts are omitted and outputs of sensors are directly taken from the available sources for implementation. The project focuses on improving the performance of a multi-parameter patient monitoring system using machine learning classifier algorithms such as Support Vector Machine (SVM), Random Forest, and Naive Bayes classifiers. Although, other ML classifier algorithm are also available, but from practical implementation point of view these three algorithms provide good results. For data analysis, these three-machine learning-based classifier algorithms are used, and datasets are collected online and arranged in a particular sequence. These datasets are trained, tested, and analyzed using machine learning. At last, the results of all classifiers are compared with each other. Based on this comparison, the one with good result is used to decide patient's health condition.