Machine Learning Empowered IoT Devices, Analysis of Indoor and Outdoor Temperature and Health Risks

The Internet of Things (IoT) is a widely used technology due to its high applicability. Since it is capable of generating data at high velocity, this data can also be beneficial in machine learning. This paper pre-processed data about temperature generated through IoT devices, followed by analysis, consequences on health, and ML applications. In order to establish a maximum indoor and outdoor temperature threshold for health, this study aims to identify and evaluate the evidence regarding the direct and indirect health effects of Indoor and Outdoor temperatures, as well as the temperature thresholds at which those effects are noticed. Additionally, the data generated by IoT devices are fed into machine learning models for classification as indoor or outdoor based on the given temperature and comparative analysis of predictability for the given dataset. The analysis of data generated by the IOT device is done using available tools in Python. Some valuable insights about data related to temperature and its associated parameters are extracted, and their effect is estimated. Different machine learning models have been applied to the given dataset and measured using available metrics. Overall, this paper contains the analytical part of the data to measure the health risks based on the indoor and outdoor temperature and their classification using the best supporting Machine Learning models.