Development of a metal oxide semiconductor-based artificial nose as a fast, reliable and non-expensive analytical technique for aroma profiling of milk adulteration

Machine learning assisted biosensing technology: An emerging powerful tool for improving the intelligence of food safety detection

Recently, the application of biosensors in food safety assessment has gained considerable research attention. Nevertheless, the evaluation of biosensors' sensitivity, accuracy, and efficiency is still ongoing. The advent of machine learning has enhanced the application of biosensors in food security assessment, yielding improved results. Machine learning has been preliminarily applied in combination with different biosensors in food safety assessment, with positive results. This review offers a comprehensive summary of the diverse machine learning methods employed in biosensors for food safety. Initially, the primary machine learning methods were outlined, and the integrated application of biosensors and machine learning in food safety was thoroughly examined. Lastly, the challenges and limitations of machine learning and biosensors in the realm of food safety were underscored, and potential solutions were explored. The review's findings demonstrated that algorithms grounded in machine learning can aid in the early detection of food safety issues. Furthermore, preliminary research suggests that biosensors could be optimized through machine learning for real-time, multifaceted analyses of food safety variables and their interactions. The potential of machine learning and biosensors in real-time monitoring of food quality has been discussed.

Recent developments of e-sensing devices coupled to data processing techniques in food quality evaluation: a critical review

A greater demand for high-quality food is being driven by the growth of economic and technological advancements. In this context, consumers are currently paying special attention to organoleptic characteristics such as smell, taste, and appearance. Motivated to mimic human senses, scientists developed electronic devices such as e-noses, e-tongues, and e-eyes, to spot signals relative to different chemical substances prevalent in food systems. To interpret the information provided by the sensors' responses, multiple chemometric approaches are used depending on the aim of the study. This review based on the Web of Science database, endeavored to scrutinize three e-sensing systems coupled to chemometric approaches for food quality evaluation. A total of 122 eligible articles pertaining to the e-nose, e-tongue and e-eye devices were selected to conduct this review. Most of the performed studies used exploratory analysis based on linear factorial methods, while classification and regression techniques came in the second position. Although their applications have been less common in food science, it is to be noted that nonlinear approaches based on artificial intelligence and machine learning deployed in a big-data context have generally yielded better results for classification and regression purposes, providing new perspectives for future studies.

Feasibility study of detecting some milk adulterations using a LED-based Vis-SWNIR photoacoustic spectroscopy system

The aim of this study is to evaluate a previousely developed photoacoustic spectroscopy system with light sources of visible to short-wave near infrared (Vis-SWNIR, 395-940 nm) for detection of adulterations in cow's milk including formalin, urea, hydrogen peroxide, starch, sodium hypochlorite, and detergent powder. The results of principal component analysis (PCA) showed a very good visual differentiation of different adulterations. The artificial neural networks (ANN) showed the highest classification accuracy (97.6 %) in detection of adulteration type and adulteration level (nearly 100 %). It can be generally concluded that the Vis-SWNIR photoacoustic spectroscopy system is a reliable and potent instrument for detecting various types of milk adulterations. Further studies are suggested with including cow's milk of different sources with probable variations in composition to generalize the findings of the present study. With the extension of the light sources to the range of long-wave NIR, the system can be applied as a diagnostic tool for quality evaluation of other liquid foods.

Evaluation the effects of temperature and packaging conditions on the quality of button mushroom during storage using e-nose system

In this study, the effects of different packaging conditions on the quality of button mushrooms and some its chemical properties (pH and TSS) using an e-nose system equipped with ten sensors have been investigated. The button mushrooms were packaged using two types of films in two atmospheric modes. They were stored at 25 and 4 °C for ten days. During the storage, they were tested every other day. The results showed a mild increase in pH levels in all treatments during the ten days. Changes in TSS in ordinary polyethylene film-packed samples and ambient atmosphere at room temperature showed the highest value. Moreover, investigating the sensor response during the storage period showed that the most significant changes in the response of all sensors occurred in samples packed with polyethylene film and ambient atmosphere at 25 °C. Also, the scoring diagram of principal component analysis (PCA) showed that the completely distinct groups were detectable at two temperatures, two packaging films, and two different packaging atmosphere. At the same time, there was an overlap between the groups in six storage times. The support vector machine (SVM-C) and artificial neural network (ANN)classified the samples with 81 and 66% accuracy in six different storage times. The values of R 2 for predicting TSS and pH using PLS (partial least squares regression), MLR (multiple linear regression) and PCR (principal component regression) ranged between 51 and 68 and 54-59%, respectively, however prediction of TSS had a higher accuracy.

Graphical abstract

Electronic nose for detection of food adulteration: a review

The food products may attract unscrupulous vendors to dilute it with inexpensive alternative food sources to achieve more profit. The risk of high value food adulteration with cheaper substitutes has reached an alarming stage in recent years. Commonly available detection methods for food adulteration are costly, time consuming and requires high degree of technical expertise. However, a rapid and suitable detection method for possible adulterant is being evolved to tackle the aforesaid issues. In recent years, electronic nose (e-nose) system is being evolved for falsification detection of food products with reliable and rapid way. E-nose has the ability to artificially perceive aroma and distinguish them. The use of chemometric analysis together with gas sensor arrays have shown to be a significant procedure for quality monitoring in food. E-nose techniques with numerous provisions are reliable and favourable for food industry in food fraud detection. In the present review, the contributions of gas sensor based e-nose system are discussed extensively with a view to ascertain the adulteration of food products.

Application of E-nose technique to predict sugarcane syrup quality based on purity and refined sugar percentage

Rapid test methods with portable devices along with standard chemical tests are necessary to determine raw syrup quality in the sugarcane agro-industries. On this account, a special e-nose device was developed to test the sugarcane syrup and its association with the odor emitted from it to determine the amount of sucrose (purity) in the sugarcane syrup. Samples were obtained from the farms of Hakim-Farabi agro-industry, including four varieties (CP57, CP69, IRC99-02, and CP48). Experiments included chemical tests to determine the percentage of purity (PTY) and refined sugar (RS) plus an electronic nose test. Partial least squares (PLS), principle component regression (PCR), multiple linear regression (MLR), and artificial neural network (ANN) methods were used to evaluate the correlation between the gained signals from the sensor array and chemical analysis results of the samples. In the case of PTY, among 8 sensors, MQ3, MQ5, and MQ9 had the highest response compared to the others, while regarding RS, all the sensors except for MQ8 indicated a great contribution. Also, all models for PTY and RS showed a good prediction performance. The results revealed that ANN model, with topology 8-1-2, outperformed others for prediction of the quality indices of sugarcane, with high correlation coefficients (R² = 0.96 for RS; 0.99 for PTY), and relatively low RMSE values of 0.33 for RS; 0.4 for RTY. Finally, findings indicated that e-nose technique has the potential to become an authentic tool to assess chemical features of sugarcane syrup from e-nose system signals.

Machine Learning-Reinforced Noninvasive Biosensors for Healthcare

The emergence and development of noninvasive biosensors largely facilitate the collection of physiological signals and the processing of health-related data. The utilization of appropriate machine learning algorithms improves the accuracy and efficiency of biosensors. Machine learning-reinforced biosensors are started to use in clinical practice, health monitoring, and food safety, bringing a digital revolution in healthcare. Herein, the recent advances in machine learning-reinforced noninvasive biosensors applied in healthcare are summarized. First, different types of noninvasive biosensors and physiological signals collected are categorized and summarized. Then machine learning algorithms adopted in subsequent data processing are introduced and their practical applications in biosensors are reviewed. Finally, the challenges faced by machine learning-reinforced biosensors are raised, including data privacy and adaptive learning capability, and their prospects in real-time monitoring, out-of-clinic diagnosis, and onsite food safety detection are proposed.

Application of Artificial Intelligence in Food Industry—a Guideline

Artificial intelligence (AI) has embodied the recent technology in the food industry over the past few decades due to the rising of food demands in line with the increasing of the world population. The capability of the said intelligent systems in various tasks such as food quality determination, control tools, classification of food, and prediction purposes has intensified their demand in the food industry. Therefore, this paper reviews those diverse applications in comparing their advantages, limitations, and formulations as a guideline for selecting the most appropriate methods in enhancing future AI- and food industry–related developments. Furthermore, the integration of this system with other devices such as electronic nose, electronic tongue, computer vision system, and near infrared spectroscopy (NIR) is also emphasized, all of which will benefit both the industry players and consumers.

Converting electronic nose into opto-electronic nose by mixing MoS2 quantum dots with organic reagents: Application to recognition of aldehydes and ketones and determination of formaldehyde in milk

A new colorimetric sensor array based on mixing of Molybdenum disulfide quantum dots (MoS₂ QDs) and organic reagents is introduced in this study. MoS₂ QDs shows a specific and higher affinity to oxygen functionalized volatile compounds like aldehydes and ketones. Therefore, this designed sensor array is used for classification of eight different aldehydes and ketones based on Linear Discriminate Analysis (LDA) at first. The classification accuracy of 96% and 83% was obtained for training and prediction phases, respectively. Then the introduced colorimetric sensor array is used for the semi-quantitative and quantitative analysis of formaldehyde in milk samples. Formaldehyde is an adulteration that is added to the milk for increasing the storage time. Cow milk samples were provided directly from dairy farmer and from supermarkets and were spiked by formaldehyde in the concentration range of 1-25 ppm. The response of sensor array to these samples were analyzed by partial least squares regression (PLS-R) method and were calibrated for concentration of formaldehyde. The PLSR results (R² = 0.94 and RMSEC = 2.36) shows that proposed sensor is useable in direct analysis of formaldehyde in milk as a complex matrix.

Nanoengineering Approaches Toward Artificial Nose

Significant scientific efforts have been made to mimic and potentially supersede the mammalian nose using artificial noses based on arrays of individual cross-sensitive gas sensors over the past couple decades. To this end, thousands of research articles have been published regarding the design of gas sensor arrays to function as artificial noses. Nanoengineered materials possessing high surface area for enhanced reaction kinetics and uniquely tunable optical, electronic, and optoelectronic properties have been extensively used as gas sensing materials in single gas sensors and sensor arrays. Therefore, nanoengineered materials address some of the shortcomings in sensitivity and selectivity inherent in microscale and macroscale materials for chemical sensors. In this article, the fundamental gas sensing mechanisms are briefly reviewed for each material class and sensing modality (electrical, optical, optoelectronic), followed by a survey and review of the various strategies for engineering or functionalizing these nanomaterials to improve their gas sensing selectivity, sensitivity and other measures of gas sensing performance. Specifically, one major focus of this review is on nanoscale materials and nanoengineering approaches for semiconducting metal oxides, transition metal dichalcogenides, carbonaceous nanomaterials, conducting polymers, and others as used in single gas sensors or sensor arrays for electrical sensing modality. Additionally, this review discusses the various nano-enabled techniques and materials of optical gas detection modality, including photonic crystals, surface plasmonic sensing, and nanoscale waveguides. Strategies for improving or tuning the sensitivity and selectivity of materials toward different gases are given priority due to the importance of having cross-sensitivity and selectivity toward various analytes in designing an effective artificial nose. Furthermore, optoelectrical sensing, which has to date not served as a common sensing modality, is also reviewed to highlight potential research directions. We close with some perspective on the future development of artificial noses which utilize optical and electrical sensing modalities, with additional focus on the less researched optoelectronic sensing modality.

Gas Sensors Based on Chemi-Resistive Hybrid Functional Nanomaterials

Chemi-resistive sensors based on hybrid functional materials are promising candidates for gas sensing with high responsivity, good selectivity, fast response/recovery, great stability/repeatability, room-working temperature, low cost, and easy-to-fabricate, for versatile applications. This progress report reviews the advantages and advances of these sensing structures compared with the single constituent, according to five main sensing forms: manipulating/constructing heterojunctions, catalytic reaction, charge transfer, charge carrier transport, molecular binding/sieving, and their combinations. Promises and challenges of the advances of each form are presented and discussed. Critical thinking and ideas regarding the orientation of the development of hybrid material-based gas sensor in the future are discussed.

Multicapillary Gas Chromatography-Temperature Modulated Metal Oxide Semiconductor Sensors Array Detector for Monitoring of Volatile Organic Compounds in Closed Atmosphere Using Gaussian Apodization Factor Analysis

A unique metal oxide semiconductor sensor (MOS) array detector with eight sensors was designed and fabricated in a PTFE chamber as an interface for coupling with multicapillary gas chromatography. This design consists of eight transfer lines with equal length between the multicapillary columns (MCC) and sensors. The deactivated capillary columns were passed through each transfer line and homemade flow splitter to distribute the same gas flow on each sensor. Using the eight ports flow splitter design helps us to equal the length of carrier gas path and flow for each sensor, minimizing the dead volume of the sensor's chamber and increasing chromatographic resolution. In addition to coupling of MCC to MOS array detector and other considerations in hardware design, modulation of MOS temperature was used to increase sensitivity and selectivity, and data analysis was enhanced with adapted Gaussian apodization factor analysis (GAFA) as a multivariate curve resolution algorithm. Continues air sampling and injecting system (CASI) design provides a fast and easily applied method for continues injection of air sample with no additional sample preparation. The analysis cycle time required for each run is less than 300 s. The high sample load and sharp injection with the fast separation by MCC decrease the peak widths and improve detection limits. This homemade customized instrument is an alternative to other time-consuming and expensive technologies for continuous monitoring of outgassing in air samples.