Gas Classification and Concentration Prediction in Open Environments Using Class Anchor Clustering-Initialized Temporal Convolutional Network

Abstract

Identifying target gases and predicting their concentrations in open environments are critical tasks, particularly due to fluctuating environmental conditions and the presence of unknown gases. This study aims to address these challenges by developing a model that improves both gas classification and concentration prediction. We introduce two key components: Quantile-Dynamic Associated Features (Q-DAF) and the Class Anchor Clustering-Initialized Temporal Convolutional Network (CAC-InitTCN). Q-DAF dynamically enhances gas signal feature extraction, optimizing the ability of CAC-InitTCN to handle complex and changing gas environments. CAC-InitTCN is designed to efficiently process time-series data, allowing it to manage gas concentration fluctuations while mitigating the interference of unknown gases. CAC-InitTCN was evaluated on two distinct datasets, achieving classification accuracy rates of 93.62% and 98.05%, respectively. In gas concentration prediction tasks, the model demonstrated RMSE values of 0.2102 and 0.0392, and R2 scores of 0.9085 and 0.9784, after data normalization. These results demonstrate the capability of CAC-InitTCN in handling real-time gas fluctuations and recognizing unknown gases, making it a promising approach for open-environment gas detection.