Assessing the ability to predict human percepts of odor quality from the detector responses of a conducting polymer composite-based electronic nose

Abstract

The responses of a conducting polymer composite``electronic nose'' detector array were used to predict human perceptual descriptors of odor quality for a selected test set of analytes. The single-component odorants investigated in this work included molecules that are chemically quite distinct from each other, as well as molecules that are chemically similar to each other but which are perceived as having distinct odor qualities by humans. Each analyte produced a different, characteristic response pattern on the electronic nose array, with the signal strength on each detector re¯ecting the relative binding of the odorant into the various conducting polymer composites of the detector array. A``human perceptual space'' was de®ned by reference to English language descriptors that are frequently used to describe odors. Data analysis techniques, including standard regression, nearest-neighbor prediction, principal components regression, partial least squares regression, and feature subset selection, were then used to determine mappings from electronic nose measurements to this human perceptual space. The effectiveness of the derived mappings was evaluated by comparison with average human perceptual data published by Dravnieks. For speci®c descriptors, some models provided cross-validated predictions that correlated well with the human data (above the 0.60 level), but none of the models could accurately predict the human values for more than a few descriptors. #

Pattern analysis for machine olfaction: a review

“…Ridge regression (RR) is a regularization method that stabilizes the OLS solution by adding a multiple of the identity matrix 5 to the estimation of the covariance matrix [48], [69] where is a regularization parameter that controls the amount of shrinkage toward the identity matrix. For , RR is equivalent to OLS, whereas for , the solution becomes a constant model that always predicts the mean concentration of the training data.…”

Sensitivity of Tiacalixarene Films Towards Set of the Aliphatic Alcohols

“…Останнім часом все більша увага приділяється створенню ефективних, надійних, малогабаритних та швидкодіючих газоаналітичних систем, які могли б застосовуватися для контролю навколишнього середовища, в харчовій промисловості, парфумерії, медицині, тощо [1,2]. В них використовуються різні принципи реєстрації параметрів, що базуються на зміні провідності [3], оптичних характеристик [4][5][6], частоти (кварцовий мікробаланс) [7,8], порогової напруги (газові польові транзистори) [9,10], та ін. Проте для всіх їх обов'язковим є наявність чутливої поверхні, на якій відбувається адсорбція молекул газу, що аналізується.…”

A nanostructural model of ethanol adsorption in thin calixarene films

“…Various principles of sensor arrays organization can be used [12], utilizing different physical transducers. Sensor systems based upon the measurement of electroconductive polymers conductivity [13], quartz crystal resonator frequency [14][15][16], and various optical characteristics of thin films (optical absorption, reflection, diffusion or luminescence, using interference or resonance properties) [17][18][19] were reported in literature. At the present time, optical sensor systems are among the most promising from the standpoint of research interest and introduction into wide practice.…”