Low-cost air pollution wireless sensors are emerging in densely distributed networks that provide more spatial resolution than typical traditional systems for monitoring ambient air quality. This paper presents an air quality measurement system that is composed of a distributed sensor network connected to a cloud system forming a wireless sensor network (WSN). Sensor nodes are based on low-power ZigBee motes, and transmit field measurement data to the cloud through a gateway. An optimized cloud computing system has been implemented to store, monitor, process, and visualize the data received from the sensor network. Data processing and analysis is performed in the cloud by applying artificial intelligence techniques to optimize the detection of compounds and contaminants. This proposed system is a low-cost, low-size, and low-power consumption method that can greatly enhance the efficiency of air quality measurements, since a great number of nodes could be deployed and provide relevant information for air quality distribution in different areas. Finally, a laboratory case study demonstrates the applicability of the proposed system for the detection of some common volatile organic compounds, including: benzene, toluene, ethylbenzene, and xylene. Principal component analysis, a multilayer perceptron with backpropagation learning algorithm, and support vector machine have been applied for data processing. The results obtained suggest good performance in discriminating and quantifying the concentration of the volatile organic compounds.

This paper introduces a miniaturized personal electronic nose (39 mm × 33 mm), which is managed through an app developed on a smartphone. The electronic nose (e-nose) incorporates four new generation digital gas sensors. These MOx-type sensors incorporate a microcontroller in the same package, being also smaller than the previous generation. This makes it easier to integrate them into the electronics and improves their performance. In this research, the application of the device is focused on the detection of atmospheric pollutants in order to complement the information provided by the reference stations. To validate the system, it has been tested with different concentrations of NOx including some tests specifically developed to study the behavior of the device in different humidity conditions. Finally, a mobile application has been developed to provide classification services. In this regard, a neural network has been developed, trained, and integrated into a smartphone to process the information retrieved from e-nose devices.

Current legislation in Spain indicates that table olives must be free of off-odors and off-flavors and without symptoms of ongoing alteration or abnormal fermentations. In this regard, the International Olive Council (IOC) has developed a protocol for the sensory classification of table olives according to the intensity of the predominantly perceived defect (PPD). An electronic nose (e-nose) was used to assess the abnormal fermentation defects of Spanish-style table olives that were previously classified by a tasting panel according to the IOC protocol, namely zapateria, butyric, putrid, and musty or humidity. When olives with different defects were mixed, the putrid defect had the greatest sensory impact on the others, while the butyric defect had the least sensory dominance. A total of 49 volatile compounds were identified by gas chromatography, and each defect was characterized by a specific profile. The e-nose data were analyzed using principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA). The different defects were clearly separated from each other and from the control treatment, independently of PPD intensity. Moreover, the e-nose differentiated control olives from table olives with combined sensory defects despite the dilution effect resulting from the combination. These results demonstrate that e-nose can be used as an olfactory sensor for the organoleptic classification of table olives and can successfully support the tasting panel.

BACKGROUND: Olive oil continues to be the main destination for olives. The production of table olives is increasing. 'Californian-style' processes are among the most frequently employed to produce oxidized olives. Sensory evaluation requires the development of an instrumental detection method that can be used as an adjunct to traditional tasting panels.RESULTS: An electronic nose (E-nose) was used to classify two varieties of olives following exposure to different sterilization. Principal component analysis (PCA) revealed that both varieties had different volatile profiles. Sensory panel evaluations were similar for both. Partial least squares-discriminant analysis (PLS-DA) obtained from the E-nose was able to separate the two varieties and explained 82% of total variance. Moreover, volatile profiles correctly classified olives according to sterilization times recorded up to 121 °C . The only exception was at F 0 ≥ 22 min, at which a plot of PCA outcomes failed to differentiate scores. E-nose data showed similar results to those produced from the volatile analysis when grouping samples were sterilized to F 0 ≥ 18 min, at the same time distinguishing these samples from those subjected to less intense thermal treatments. A partial least squares (PLS) chemometric approach was evaluated for quantifying important olive quality parameters. With regards to validation parameters, R 2 P pertaining to perceived defect was 0.88, whilst R 2 P pertaining to overall assessment was 0.78. CONCLUSIONS: E-nose offers a fast, inexpensive and non-destructive method for discriminating between varieties and thermal treatments up to a point at which cooking defects are highly similar (from F 0 = 18 onwards).

This study addresses the development of a wireless gas sensor network with low cost, small size, and low consumption nodes for environmental applications and air quality detection. Throughout the article, the evolution of the design and development of the system is presented, describing four designed prototypes. The final proposed prototype node has the capacity to connect up to four metal oxide (MOX) gas sensors, and has high autonomy thanks to the use of solar panels, as well as having an indirect sampling system and a small size. ZigBee protocol is used to transmit data wirelessly to a self-developed data cloud. The discrimination capacity of the device was checked with the volatile organic compounds benzene, toluene, ethylbenzene, and xylene (BTEX). An improvement of the system was achieved to obtain optimal success rates in the classification stage with the final prototype. Data processing was carried out using techniques of pattern recognition and artificial intelligence, such as radial basis networks and principal component analysis (PCA).