Efficiency of Linear and Non-Linear Classifiers for Gas Identification from Electrocatalytic Gas Sensor

Abstract

Electrocatalytic gas sensors belong to the family of electrochemical solid state sensors. Their responses are acquired in the form of I-V plots as a result of application of cyclic voltammetry technique. In order to obtain information about the type of measured gas the multivariate data analysis and pattern classification techniques can be employed. However, there is a lack of information in literature about application of such techniques in case of standalone chemical sensors which are able to recognize more than one volatile compound. In this article we present the results of application of these techniques to the determination from a single electrocatalytic gas sensor of single concentrations of nitrogen dioxide, ammonia, sulfur dioxide and hydrogen sulfide. Two types of classifiers were evaluated, i.e. linear Partial Least Squares Discriminant Analysis (PLS-DA) and nonlinear Support Vector Machine (SVM). The efficiency of using PLS-DA and SVM methods are shown on both the raw voltammetric sensor responses and pre-processed responses using normalization and auto-scaling.

Determination Of Gas Mixture Components Using Fluctuation Enhanced Sensing And The LS-SVM Regression Algorithm

“…Awareness of concentration, or even presence, of hazardous gases is crucial for protecting life and health of human beings in numerous cases [1][2][3][4][5][6]. In real-world applications we deal with a mixture of various gases and have to develop detection methods that are robust to the presence of background gases or humidity.…”

“…The sensor response to changes of the ambient atmosphere (gas concentration) is usually nonlinear, and therefore we decided to apply a nonlinear algorithm, which should assure better detection under conditions of nonlinearity. We proposed to apply the Support Vector Machine (SVM) algorithm as in other similar cases, such as for electro-catalytic gas sensors [6] or in Raman spectroscopy [8], where the input data form a vector of partially correlated values. The correlation is unknown and can change for data observed at various gas compositions.…”

Fall Detector Using Discrete Wavelet Decomposition And SVM Classifier

“…Therefore, the total sum of data from each 3D sensor was used as the input signal for the feature extraction block. Based on the previous work, the feature extraction was performed using the DWT (Discrete Wavelet Transform), while the data classification was performed using the linear SVM (Support Vector Machine) [16,17]. In the iterative process used for all of the sensors, the wavelet, the number of decomposition levels and the number of descriptors for each decomposition level were chosen.…”

Potentiometric Oxygen Sensor with Solid State Reference Electrode

“…There is a continuing need for the development of fast, sensitive, rugged, reliable, and low-cost sensors for applications in harsh industrial environments [2,3]. The real challenge is to develop highly sensitive and selective sensors with long-term stability in such aggressive environments [4].…”