Effective Gas Level Prediction Based on Sensor Array Using Deep Learning in Mixed Gases: A Comparative Analysis of CNN-1D, LSTM, and GRU Models
Sampson Addae, Jungyoon Kim, Mi-Sun Kang
Abstract
Estimating the concentration levels of gas components in a mixture is vital for taking preventive actions and ensuring public safety in various environments, including industrial settings, urban areas, and confined spaces where gas leaks or accumulation can pose significant health and safety risks. This is because general gas sensors for target pollutants are easily affected by other gases. In this study, we assessed the effectiveness of combining data segmentation, feature extraction, and normalization on the performance of three deep learning models: one-dimensional Convolutional Neural Network (CNN-1D), Long Short-term Memory (LSTM), and Gated Recurrent Unit (GRU) network for predicting gas levels in two combinations: ethylene-methane and ethylene-carbon monoxide (CO). We evaluated performance using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>). Among the models evaluated, the GRU network outperformed the CNN-1D and LSTM in terms of averaged MAE (0.1578), RMSE (0.0481) and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> (0.96375). Comparative analysis with existing studies confirmed that our proposed GRU model outperformed others so that we propose its use in gas concentration estimation tasks.