Monitoring and Mapping of Machine Learning Supported Sensor Data for Digital Transformation Transfer Laboratory

Abstract

Along with technological innovations, the internet of things, artificial intelligence and big data,
as a result of all these, the "digital age" or "digitalization" processes we have discussed have entered our
lives. These concepts emerged in the Industry 4.0 period, which represents the fourth stage of the
industrial revolution, and continue to exist today. The internet of things (IoT) refers to all systems that can
transfer data over a network. In the world of the Internet of Things, the role of human-to-human
commands and even human-computer interaction has been minimized. In this context, sensor technology
forms the basis of IoT. Sensors detect variables in their environment and transfer this data to other
devices or a data storage center. By analyzing large data sets, machine learning algorithms discover
patterns and relationships and can thus predict future events. The Python programming language, in
particular, offers a wide set of libraries and tools for machine learning applications. Therefore, when IoT,
sensor technology, machine learning and Python programming language come together, it becomes
possible to effectively measure, analyze and map environmental parameters. This can be used as an
important tool for monitoring and managing environmental conditions in various industries. This study
combines sensor technology and machine learning methods to measure and map the temperature and
humidity values of a specific area, an approach associated with the concept of the Internet of Things
(IoT). After different temperature and humidity values are taken from different locations, a mapping is
created for the area where the data is taken. In addition to the temperature and humidity values taken from
certain locations, the temperature and humidity values of locations where no data is taken are estimated
and mapped with the support of machine learning methods.