Concentration estimation of formaldehyde using metal oxide semiconductor gas sensor array-based e-noses

Abstract

Purpose -The purpose of this paper is to present a novel concentration estimation model for improving the accuracy and robustness of low-cost electronic noses (e-noses) with metal oxide semiconductor sensors in indoor air contaminant monitoring and overcome the potential sensor drift. Design/methodology/approach -In the quantification model, a piecewise linearly weighted artificial neural network ensemble model (PLWE-ANN) with an embedded self-calibration module based on a threshold network is studied. Findings -The nonlinear estimation problem of sensor array-based e-noses can be effectively transformed into a piecewise linear estimation through linear weighted neural networks ensemble activated by a threshold network. Originality/value -In this paper, a number of experimental results have been presented, and it also demonstrates that the proposed model has very good accuracy and robustness in real-time indoor monitoring of formaldehyde.

Nanostructured WO3 based gas sensors: a short review

“…Air pollution is caused by toxic, ignitable, hazards and certain gas particles are suspended in the atmosphere which is harmful to the living environment. Hence, gas sensing technology has been developing in the fields of science and industry to monitor air quality (Righettoni et al, 2012;Hossain et al, 2016;Rana et al, 2017;Reimann and Schutze, 2012;Ghosh et al, 2019), food quality (Kuswandi et al, 2011;Poghossian et al, 2019;Ponzoni et al, 2012), electronic nose (Loutfi et al, 2015;Faleh et al, 2018;Haddi et al, 2011;Zhang et al, 2014) and medical diagnosis (Nasiri and Clarke, 2019;Bielecki et al, 2018;Koo et al, 2016). The various types of gas sensors are available based on the working principle of the sensing element, such as resistive gas sensors, electrochemical gas sensors, capacitancebased gas sensors, calorimetric gas sensors, optical gas sensors, surface acoustic sensors, micro-cantilever sensors, photoionization gas sensors, infrared gas sensors and plasmon resonance sensors have been developed Vijayakumar et al, 2021).…”

Highly selective acetone detector based on a separation channel and semiconductor gas sensor

“…Semiconductor gas sensors are considered to be a promising real-time breath detector, because of their small size, low cost, high sensitivity, and ease of operation [26][27][28][29].…”

Comparison of machine learning algorithms for concentration detection and prediction of formaldehyde based on electronic nose

“…The contaminants released from modern decoration materials can cause indoor air pollution. Among the various air pollutants, formaldehyde takes a larger proportion in the gas mixture (Zhang et al , 2014a, 2014b). With people on average spending at least 80 per cent of their daily time indoor (de Nazelle et al , 2013), the indoor air pollution exposure is a major cause of a new class of illnesses, identified as building-related illnesses and sick building syndromes (Zampolli et al , 2004).…”

“…The rapid development of sensor technology has facilitated the measurement of portable devices (Bender et al , 2003; Jiang et al , 2011) based on variety of sensors. There are typically two categories of devices, one is the device using expensive sensors with high accuracy like photoionization detector sensors (Ševčik and Krýsl, 1973; Devine et al , 2014), while another is the device that uses cheap sensors with a relatively low accuracy like metal oxide semiconductor (MOS) gas sensors (Zhang et al , 2014a, 2014b). The devices using expensive sensors can meet the precision level of 1 ppb.…”