On the performance of gas sensor arrays in open sampling systems using Inhibitory Support Vector Machines

Abstract

a b s t r a c tChemo-resistive transduction presents practical advantages for capturing the spatio-temporal and structural organization of chemical compounds dispersed in different human habitats. In an open sampling system, however, where the chemo-sensory elements are directly exposed to the environment being monitored, the identification and monitoring of chemical substances present a more difficult challenge due to the dispersion mechanisms of gaseous chemical analytes, namely diffusion, turbulence, and advection. The success of such actively changeable practice is influenced by the adequate implementation of algorithmically driven formalisms combined with the appropriate design of experimental protocols. On the basis of this functional joint-formulation, in this study we examine an innovative methodology based on the inhibitory processing mechanisms encountered in the structural assembly of the insect's brain, namely Inhibitory Support Vector Machine (ISVM) applied to training a sensor array platform and evaluate its capabilities relevant to odor detection and identification under complex environmental conditions. We generated -and made publicly available -an extensive and unique dataset with a chemical detection platform consisting of 72 conductometric metal-oxide based chemical sensors in a custom-designed wind tunnel test-bed facility to test our methodology. Our findings suggest that the aforementioned methodology can be a valuable tool to guide the decision of choosing the training conditions for a costefficient system calibration as well as an important step toward the understanding of the degradation level of the sensory system when the environmental conditions change.

Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring

“…Therefore, algorithms based on RC are better suited for open sampling systems, in which the sensors are exposed directly to gas plumes in a turbulent environment, or continuous monitoring and alarm applications, in which large number of volatiles are expected to fluctuate irregularly [47,48]. Previous experimental protocols in open sampling systems also assume control of the gas onset, which happens at specific times from the beginning of the measurement [49,50]. A calibration model based on RC would be sensitive to changes in the sample composition at all times and to turbulence.…”

Deep learning–based real-time query processing for wireless sensor network

“…The settings for CNN followed the settings described in the previous Deep learning analysis section. The data are gas sensor data published by Vergara et al, 9 which can be retrieved from UCI Machine Learning Repository (Gas sensor data; UCI Machine Learning Repository, http://archive.ics.uci.edu/ml/datasets/Gas+ sensor+arrays+in+open+sampling+settings). These are the data of air pollution degree in a tunnel using 72 metal-oxide gas sensors.…”

Computational models to understand decision making and pattern recognition in the insect brain

“…Left: Dataset from an array of 72 metal-oxide gas sensors in presence of carbon monoxide, publicly available at UCI Machine Learning Repository [9]. Right: example of the traditional three phases sampling process applied under controlled conditions (shown on top) and a few time series recorded by a mobile robot in an uncontrolled environment (bottom)[15].…”

“…The nature of the olfactory stimulus is stochastic and non stationary: wind transports gases by turbulent flows that induce complex filaments [9, 10, 11] (see Figure 1). Although pattern recognition of gases is challenging for modern artificial sensors [9, 12], evolution has provided even the simplest nervous systems with the ability to extract all necessary information for survival by exploiting the random nature of the stimuli [13, 14].…”

“…Although pattern recognition of gases is challenging for modern artificial sensors [9, 12], evolution has provided even the simplest nervous systems with the ability to extract all necessary information for survival by exploiting the random nature of the stimuli [13, 14]. …”