Implementation of AI Using a Case Study of Hydrogen Gas From an AI- Mining Prototype

Artificial Intelligence (AI) in this research aims to provide a new perspective on AI in education by using a case study in the form of prototype sensor data on hydrogen gas. Those data were analyzed by Long Short-Term Memory (LSTM). This study uses a high-touch and high-tech approach with design thinking on the implementation of LSTM for hydrogen gas sensor data. The results obtained in this study are needed to improve the analysis of sensor data from hydrogen gas, which is single data and is taken in real-time. The analysis was carried out by sequential modeling. The result was successful because the Root Mean Square Error(RMSE) was around 7.9%. LSTM also works for other time series data. So, it can be concluded that LSTM, part of AI, can be introduced as new knowledge for time series data analysis.