k-NN and k-NN-ANN Combined Classifier to Assess MOX Gas Sensors Performances Affected by Drift Caused by Early Life Aging

Abstract

The drift of metal oxide semiconductor (MOX) chemical sensors is one of the most important topics in this field. The work aims to test the performance of MOX gas sensors over the aging process. Firstly, sensors were tested with ethanol to understand their behavior and response changes. In parallel, beers with different alcoholic content were analyzed to assess what happened in a real application scenario. With ethanol analysis, it was possible to quantify drift of the baseline of the sensors and changes that could affect their responses over time (from day 1 to day 51). Conversely, the beer dataset has been exploited to evaluate how two different classifiers perform the classification task based on the alcohol content of the samples. A hybrid k-nearest neighbors artificial neural network (k-NN-ANN) approach and “standard” k-NN were used to evaluate to distinguish among the samples when the measures were affected by drift. To achieve this goal, data acquired from day one to day six were used as training to predict data collected up to day 51. Overall, performances of the two methods were similar, even if the best result in terms of accuracy is reached by k-NN-ANN (96.51%).

Volatile Olfactory Profiles of Umbrian Extra Virgin Olive Oils and Their Discrimination through MOX Chemical Sensors

“…The Small Sensor System (S3) is a device that has amply demonstrated the advantages of the application of this technology in recent years. This technology is based on semiconductor metal oxide gas sensors (MOX) [ 34 , 35 ], used with considerable success in several sectors, ranging from food safety [ 36 ], quality control [ 37 , 38 , 39 ], environmental monitoring and human health, in particular due to its high sensitivity, fast responses and low costs [ 40 ]. The innovative S3 device consists of an array, made of different semiconductor metal oxide gas sensors, flow, temperature and humidity sensors.…”

Review–Modern Data Analysis in Gas Sensors

“…A multilayered perceptron SimResNet-9 was implemented in another article 134 which improved accuracy of the model from 88.0% to 93.7%. A hybrid KNN-ANN network proposed in a prior study 135 that achieved 96.51% of accuracy for drifted gas sensor data classification.…”

Nanowire Gas Sensor to Support Optical and Volatile Changes in the Production Chain of Fruit Jams

“…S3, an acronym for Small Sensor Systems, is an instrument that was built in collaboration with the University of Brescia and with Nano Sensor Systems Srl (www.nasys.it, accessed on 1 July 2022), a start-up of the University of Brescia. S3 [11] is composed of three fundamental parts (Figure 2):…”