comparison between univariate and multivariate methods in regression analysis ofsensor arrays

Array-based sensor platforms are inspired by the mammalian olfactory system. multiple sensorelements in these devices selectively interact with target analytes, producing a distinct pattern ofresponse and enabling analyte identification. it provides a multidimensional data set that needs tobe processed by multivariate analysis methods. in quantitative analyses, the relation of sensorarray responses and different concentration of analyte can be obtained by univariate andmultivariate regression methods. in the univariate approach, response vector of each concentrationconvert to a value by calculating the euclidean norm. while in multivariate regression methods,the relationship is built between the sensor array responses and analyte concentration. many timesthese two methods used interchangeably in analyzing the sensor arrays data [1]. however, it is achallenge that univariate and multivariate methods can quantifying the species in complex mixturethe same or not. to compare two univariate and multivariate method in analysis the sensor arrays,the operation of a sensor array based strip in four different real matrix (cell culture, milk, , orangejuice and tap water) were considered to evaluate the dependency of color values (r, g and b) onthe concentration (ph values) [2]. since the studied real samples may be complex, the standardaddition method was applied for ph determination. to do so, for each real sample solution, theresponse of the strip was measured by dipping it in the sample solution. the euclidean norm andpls calibration models were built for each real sample systems. to evaluate the ability of themethods, the correlation coefficient (r2) between predicted and the actual phs calculated formultivariate methods and between the euclidian norm and phs for univariate method wascompared. also, the models were used to predict the ph of unknown sample and compare by theobtained ph of unknown samples calculated by euclidean norm method. however, the r2 obtainedfrom pls model and euclidean norm methods are so close to each other, (cell culture: 0.97, 0.99;milk: 0.94, 0.96; orange juice: 0.97, 0.98; and tap water: 0.97, 0.97, related to pls model andeuclidean norm, respectively.), but their ability in prediction the ph of unknown sample aresignificantly different (recovery for cell culture: 0.98.9, 103.5; milk: 90.5, 80.93; orange juice:91.8, 31.8; and tap water: 104.4, 81.2, related to pls model and euclidean norm, respectively). itcan be concluded that chemometrics method can be a better candidate for prediction the unknownconcentration in sensor arrays data.