Deep Learning Framework With Essential Pre-Processing Techniques for Improving Mixed-Gas Concentration Prediction

Abstract

Multiple gas detection in mixed-gas environments is a challenging issue in many engineering industries because some of the gases can raise defect rates and reduce production efficiency. For chemoresistive gas sensors, a precise estimation can be challenging because of the measurement variance and non-linear nature of the gas sensors, especially in a low concentration environment. A simple application of the deep learning models, however, does not yield sufficiently accurate predictions of the concentrations of multiple gases in gas mixtures; thus, it is essential to develop basic strategies for enhancing the accuracy in all possible ways. In this study, we develop a deep learning framework for achieving high accuracy of gas concentration prediction by studying the essential pre-processing techniques, learning task design, and architecture design. For the pre-processing, we study several aspects of processing time-series sensor data and identify the key techniques for complementing deep learning models' limitations. We utilize the mixedgas nature for the learning task design and show that multi-task learning can generate a synergistic effect. Additionally, we show that a further improvement is possible by considering on-off classification as a part of the hybrid learning task. Concerning architecture design, we investigate Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) models after applying the identified pre-processing techniques. CNN outperformed other models in a joint analysis with the learning task. The effectiveness of our framework is confirmed with the UCI gas mixture dataset acquired using a chemical detection platform where 16 chemical sensors are exposed to ethylene, CO, and methane gases. Using the dataset, we study the basic techniques that can be effective to mixed-gas prediction. For the UCI dataset, our deep learning framework achieves a significant improvement in estimation accuracy when compared to the previous studies.

Intelligent Detection and Odor Recognition of Cigarette Packaging Paper Boxes Based on a Homemade Electronic Nose

“…Given that the resistance values captured by each sensor span a broad range, proper normalization of gas sensor data is essential for enhancing the reliability of predictions for future test data, including those that may extend beyond the range of the training dataset. Several normalization methods exist, such as z-score normalization [17], min-max normalization [18], and baseline normalization [19]. While z-score normalization is widely used, it may not effectively handle non-stationary time-series data.…”