Toward the Development of Combined Artificial Sensing Systems for Food Quality Evaluation: A Review on the Application of Data Fusion of Electronic Noses, Electronic Tongues and Electronic Eyes

Devices known as electronic noses (ENs), electronic tongues (ETs), and electronic eyes (EEs) have been developed in recent years in the in situ study of real matrices with little or no manipulation of the sample at all. The final goal could be the evaluation of overall quality parameters such as sensory features, indicated by the “smell”, “taste”, and “color” of the sample under investigation or in the quantitative detection of analytes. The output of these sensing systems can be analyzed using multivariate data analysis strategies to relate specific patterns in the signals with the required information. In addition, using suitable data-fusion techniques, the combination of data collected from ETs, ENs, and EEs can provide more accurate information about the sample than any of the individual sensing devices. This review’s purpose is to collect recent advances in the development of combined ET, EN, and EE systems for assessing food quality, paying particular attention to the different data-fusion strategies applied.

Data Classification Methodology for Electronic Noses Using Uniform Manifold Approximation and Projection and Extreme Learning Machine

The classification and use of robust methodologies in sensor array applications of electronic noses (ENs) remain an open problem. Among the several steps used in the developed methodologies, data preprocessing improves the classification accuracy of this type of sensor. Data preprocessing methods, such as data transformation and data reduction, enable the treatment of data with anomalies, such as outliers and features, that do not provide quality information; in addition, they reduce the dimensionality of the data, thereby facilitating the tasks of a machine learning classifier. To help solve this problem, in this study, a machine learning methodology is introduced to improve signal processing and develop methodologies for classification when an EN is used. The proposed methodology involves a normalization stage to scale the data from the sensors, using both the well-known min−max approach and the more recent mean-centered unitary group scaling (MCUGS). Next, a manifold learning algorithm for data reduction is applied using uniform manifold approximation and projection (UMAP). The dimensionality of the data at the input of the classification machine is reduced, and an extreme learning machine (ELM) is used as a machine learning classifier algorithm. To validate the EN classification methodology, three datasets of ENs were used. The first dataset was composed of 3600 measurements of 6 volatile organic compounds performed by employing 16 metal-oxide gas sensors. The second dataset was composed of 235 measurements of 3 different qualities of wine, namely, high, average, and low, as evaluated by using an EN sensor array composed of 6 different sensors. The third dataset was composed of 309 measurements of 3 different gases obtained by using an EN sensor array of 2 sensors. A 5-fold cross-validation approach was used to evaluate the proposed methodology. A test set consisting of 25% of the data was used to validate the methodology with unseen data. The results showed a fully correct average classification accuracy of 1 when the MCUGS, UMAP, and ELM methods were used. Finally, the effect of changing the number of target dimensions on the reduction of the number of data was determined based on the highest average classification accuracy.

The Research of Chronic Gastritis Diagnosis with Electronic Noses

In order to solve the problem of existing diagnostic methods for chronic gastritis which are complex and traumatic, a novel noninvasive method for diagnosis of chronic gastric based on e-nose and deep convolutional neural network is proposed. Firstly, in order to collect samples, a respiratory gas sampling device was established and the response curve of respiratory gas is generated. Then, a deep convolutional neural network for the diagnosis of chronic gastritis is proposed to recognize and classify the respiratory gas response curve. The DCNN model attained good results with accuracy, sensitivity, and specificity of 85.00%, 90.00%, and 80.00%, respectively, for chronic gastric prediction. The proposed method provides a new way for the clinical auxiliary diagnoses of chronic gastric.

Differentiation of aspirated nasal air from room air using analysis with a differential mobility spectrometry-based electronic nose: a proof-of-concept study

Over the last few decades, breath analysis using electronic nose technology has become a topic of intense research, as it is both non-invasive and painless, and is suitable for point-of-care use. To date, however, only a few studies have examined nasal air. As the air in the oral cavity and the lungs differs from the air in the nasal cavity, it is unknown whether aspirated nasal air could be exploited with electronic nose technology. Compared to traditional electronic noses, differential mobility spectrometry uses an alternating electrical field to discriminate the different molecules of gas mixtures, providing analogous information. This study reports the collection of nasal air by aspiration and the subsequent analysis of the collected air using a differential mobility spectrometer. We collected nasal air from ten volunteers into breath collecting bags and compared them to bags of room air and the air aspirated through the device. Distance and dissimilarity metrics between the sample types were calculated and statistical significance evaluated with Kolmogorov-Smirnov test. After leave-one-day-out cross-validation, a shrinkage linear discriminant classifier was able to correctly classify 100% of the samples. The nasal air differed (p < 0.05) from the other sample types. The results show the feasibility of collecting nasal air by aspiration and subsequent analysis using differential mobility spectrometry, and thus increases the potential of the method to be used in disease detection studies.

Combinatorial selectivity with an array of phthalocyanines functionalized TiO2/ZnO heterojunction thin film sensors

The development of electronic noses requires the control of the selectivity pattern of each sensor of the array. Organic chemistry offers a manifold of possibilities to this regard but in many cases the chemical sensitivity is not matched with the response of electronic sensor. The combination of organic and inorganic materials is an approach to transfer the chemical sensitivities of the sensor to the measurable electronic signals. In this paper, this approach is demonstrated with a hybrid material made of phthalocyanines and a bilayer structure of ZnO and TiO2. Results show that the whole spectrum of sensitivity of phthalocyanines results in changes of the resistance of the sensor, and even the adsorption of compounds, such as hexane, which cannot change the resistance of pure phthalocyanine layers, elicits changes of the sensor resistance. Furthermore, since phthalocyanines are optically active, the sensitivity in dark and visible light are different. Thus, operating the sensor in dark and light two different signals per sensors can be extracted. As a consequence, an array of 3 sensors made of different phthalocyanines results in a virtual array of six sensors. The sensor array shows a remarkable selectivity respect to a set of test compounds. Principal component analysis scores plot illustrates that hydrogen bond basicity and dispersion interaction are the dominant mechanisms of interaction.

Optimization of training and measurement protocol for eNose analysis of urine headspace aimed at prostate cancer diagnosis

More than one million new cases of prostate cancer (PCa) were reported worldwide in 2020, and a significant increase of PCa incidence up to 2040 is estimated. Despite potential treatability in early stages, PCa diagnosis is challenging because of late symptoms’ onset and limits of current screening procedures. It has been now accepted that cell transformation leads to release of volatile organic compounds in biologic fluids, including urine. Thus, several studies proposed the possibility to develop new diagnostic tools based on urine analysis. Among these, electronic noses (eNoses) represent one of the most promising devices, because of their potential to provide a non-invasive diagnosis. Here we describe the approach aimed at defining the experimental protocol for eNose application for PCa diagnosis. Our research investigates effects of sample preparation and analysis on eNose responses and repeatability. The dependence of eNose diagnostic performance on urine portion analysed, techniques involved for extracting urine volatiles and conditioning temperature were analysed. 192 subjects (132 PCa patients and 60 controls) were involved. The developed experimental protocol has resulted in accuracy, sensitivity and specificity of 83% (CI95% 77–89), 82% (CI95% 73–88) and 87% (CI95% 75–94), respectively. Our findings define eNoses as valuable diagnostic tool allowing rapid and non-invasive PCa diagnosis.

Sensing Performance of Thermal Electronic Noses: A Comparison between ZnO and SnO2 Nanowires

In recent times, an increasing number of applications in different fields need gas sensors that are miniaturized but also capable of distinguishing different gases and volatiles. Thermal electronic noses are new devices that meet this need, but their performance is still under study. In this work, we compare the performance of two thermal electronic noses based on SnO2 and ZnO nanowires. Using five different target gases (acetone, ammonia, ethanol, hydrogen and nitrogen dioxide), we investigated the ability of the systems to distinguish individual gases and estimate their concentration. SnO2 nanowires proved to be more suitable for this purpose with a detection limit of 32 parts per billion, an always correct classification (100%) and a mean absolute error of 7 parts per million.

Development of a Low-Cost Electronic Nose for Detection of Pathogenic Fungi and Applying It to Fusarium oxysporum and Rhizoctonia solani

Electronic noses can be applied as a rapid, cost-effective option for several applications. This paper presents the results of measurements of samples of two pathogenic fungi, Fusarium oxysporum and Rhizoctonia solani, performed using two constructions of a low-cost electronic nose. The first electronic nose used six non-specific Figaro Inc. metal oxide gas sensors. The second one used ten sensors from only two models (TGS 2602 and TGS 2603) operating at different heater voltages. Sets of features describing the shapes of the measurement curves of the sensors’ responses when exposed to the odours were extracted. Machine learning classification models using the logistic regression method were created. We demonstrated the possibility of applying the low-cost electronic nose data to differentiate between the two studied species of fungi with acceptable accuracy. Improved classification performance could be obtained, mainly for measurements using TGS 2603 sensors operating at different voltage conditions.

Non-Invasive Detection and Staging of Colorectal Cancer Using a Portable Electronic Nose

Electronic noses (e-nose) offer potential for the detection of cancer in its early stages. The ability to analyse samples in real time, at a low cost, applying easy–to-use and portable equipment, gives e-noses advantages over other technologies, such as Gas Chromatography-Mass Spectrometry (GC-MS). For diseases such as cancer with a high mortality, a technology that can provide fast results for use in routine clinical applications is important. Colorectal cancer (CRC) is among the highest occurring cancers and has high mortality rates, if diagnosed late. In our study, we investigated the use of portable electronic nose (PEN3), with further analysis using GC-TOF-MS, for the analysis of gases and volatile organic compounds (VOCs) to profile the urinary metabolome of colorectal cancer. We also compared the different cancer stages with non-cancers using the PEN3 and GC-TOF-MS. Results obtained from PEN3, and GC-TOF-MS demonstrated high accuracy for the separation of CRC and non-cancer. PEN3 separated CRC from non-cancerous group with 0.81 AUC (Area Under the Curve). We used data from GC-TOF-MS to obtain a VOC profile for CRC, which identified 23 potential biomarker VOCs for CRC. Thus, the PEN3 and GC-TOF-MS were found to successfully separate the cancer group from the non-cancer group.