Exploiting the Self-Attention Mechanism in Gas Sensor Array (GSA) Data With Neural Networks

Abstract

Gas sensor array (GSA) data is a sequential series of values that represents the temporal conditions of the existence/absence/mixture of gases and exhibits similarities to the textual stream of natural languages that represents semantic information. We speculate and subsequently prove that there also exist self-attention mechanisms in GSA data that can be exploited for gas classification and recognition. We first convert GSA data into a 1-D token series (called WORDs in this work) through sampling and quantization of the sensor values and then use an enhanced long short-term memory (LSTM) revision network, called LSTM-attention, to extract the self-attention mechanism in the GSA data. We demonstrate that LSTM-attention achieves a much better performance (99.6%) than CNN-based networks as well as other GSA data process techniques on UCI dynamic gases dataset. We also find out that the self-attention mechanism varies with different sampling and quantization levels during data acquisition.