Vishakha Pareek

Intelligent sensor system design demands the efficient pattern recognition method that uses raw time-series sensor data to identify the target gas with fast and accurate results. The presented work uses gas sensor array response (open sampling setting) for 10 bio-marker gases. The responses are obtained at different concentrations. We propose a 2D convolution neural network (2D-CNN) based adaptive ensemble network for gas identification. The Spatio-temporal correlation of sensor array responses inspired us to design deep-learning-based gas identification networks. The network uses raw time-series gas sensor array data and identifies the target gas mixtures with improved accuracy despite sensor drift. Experimental results show that the proposed methods are an effective technique with identification accuracy approximately 91% for identifying gas mixture for smart sensor system application. The proposed method outperforms and provides higher identification accuracy than comparable various machine learning and deep learning methods.

This work proposes a hybrid 3D Convolutional Neural Network and Restricted Boltzmann Machine (Hybrid 3DCNN-RBM) architecture tailored for gas concentration estimation. The immense success of deep learning in computer vision and natural language processing inspired us to design a deep-learning-based gas concentration estimation network. The proposed network is a joint 3DCNN and RBM network. It uses raw time-series gas sensor array data and provides the concentration of each gas in a mixture of gases. This raw time series data is considered similar to video signal comparing sensor array response as an image, which varies with time. We first time utilized 3DCNN for sensor array data processing and developed a joint network with RBM to design an end-to-end gas concentration estimation model. Although several pattern recognition-based methods have been applied to estimate the gas concentration of the gas mixtures, the effectiveness of these techniques enormously depends on the hand-created feature engineering. Nevertheless, the experiments show that the proposed method is an efficient method for estimating gas concentration in the gas mixture for sensor array data.