Analysing Gas Data using Deep Learning and 2D Gramian Angular Fields

The notion of employing a Deep Learning (DL) for gas classification has kindled revolution in the field that has both improved data collection measures and classification performance. Yet, the current literature, with its vast contributions, has potential in enhancing the current state-of-the-art by employing both DL and novel visualization methods to boost classification performance and speed. Therefore, this paper presents a dual classification system for high-performance gas classification: on 1D time series data and on 2D Gramian Angular Field (GAF) data. For the GAF case, 1D data is converted into 2D counterparts by means of normalization, segmentation, averaging, and color-coding. The Gas Sensor Array (GSA) dataset is used for evaluating the implemented AlexNet model for classifying 2D GAF data and an improved version of GasNet for 1D time-based data. Using a cloud-based architecture, the two models are evaluated and benchmarked with the state-of-the-art. Evaluation results of the modified GasNet model on time series data signifies state-of-the-art accuracy of 96.0%, while AlexNet achieved 81.3% test accuracy of GAF classification with near real-time performance on edge computing platforms.