Abstract:
The research focuses on the development of learning innovations involving the Internet of Things (AIoT) to enhance the competencies of engineering students. It presents the design of an automatic water resource control system for a fingerroot farm using AIoT. This system is configured with three input variables: temperature, soil moisture, and sunlight intensity, to control the output variable, pulse width modulation (PWM), which is used to operate a water pump. A mathematical model was developed using multiple linear regression (MLR) and optimized with particle swarm optimization (PSO). This model was then trained using an adaptive neuro-fuzzy inference system (ANFIS) to apply rules for generating Arduino program code through the embedded fuzzy logic library (eFLL). The resulting values are displayed on the Node-RED dashboard, and performance is evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), and R - squared metrics. This research aims to integrate AIoT into engineering education by designing practical training workshops on microcontrollers (Arduino), focusing on AIoT applications. The objective is to enhance students' competencies in knowledge, skills, habits, and attitudes. The study found that the experimental group, taught using the AIoT inquiry-based learning process, demonstrated a significant improvement in their competencies effectively.