Exploring Factors Influencing Energy Consumption Behavior Among Higher Education Students Using Deep Learning

This research examines the dynamics of university students’ energy usage behaviour using Internet of Things (IoT) technologies. The assignment meticulously positions a range of sensors in labs and lecture rooms and combines them with gadget learning algorithms to be able to maximize energy consumption. For a month, the Internet of Things sends actual-time notifications to students approximately the need for careful strength management. Before the implementation observations provide a comparative evaluation of student behavior and draw interest to the subtle behavioural adjustments as a result of psychological shifts. Machine studying fashions are built to forecast destiny energy use by way of using the information generated by way of those processes. These fashions include Decision Trees, Random Forests, Support Vector Machines, and Artificial Neural Networks. The consequences display a noteworthy decrease in strength use with the IoT machine in region, highlighting the significance of technological interventions in encouraging environmentally pleasant behaviour. From an academic angle, this advances our expertise of strength behaviour and gives useful information to educational establishments trying to find creative techniques to implementing responsible electricity control.