Fusion of artificial senses as a robust approach to food quality assessment

Current applications and future trends of artificial senses in fish freshness determination: A review

Fish is a highly demanding food product and the determination of fish freshness is crucial as it is a fundamental factor in fish quality. Therefore, the fishery industry has been working on developing rapid fish freshness determination methods to monitor freshness levels. Artificial senses that mimic human senses are developed as convenient emerging technologies for fish freshness determination. Computer vision, electronic nose (e-nose), and electronic tongue (e-tongue) are the emerging artificial senses for fish freshness determination. This review article is uniquely worked upon to investigate the current applications of the artificial senses in fish freshness determination while describing the steps, and fundamental principles behind each artificial sense, comparing them with their advantages and limitations, and future trends related to fish freshness determination. Among the artificial senses, computer vision determines the freshness of fish in a completely nondestructive way while the e-tongue determines the freshness of fish in a completely destructive way. There are developed e-noses for fish freshness determination in both destructive and nondestructive ways. By analyzing visual cues such as color, computer vision systems can assess fish quality without the need for physical contact and it makes computer vision suitable for large-scale industrial fish quality assessing applications. Overall, this review study reveals artificial senses as a proven replacement for traditional sensory panels in determining fish freshness precisely and conveniently. As future trends, there is a demand for developing applications for consumers to determine fish freshness based on artificial senses.

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.

Combining Vis-NIR and NIR Spectral Imaging Techniques with Data Fusion for Rapid and Nondestructive Multi-Quality Detection of Cherry Tomatoes

Firmness, soluble solid content (SSC) and titratable acidity (TA) are characteristic substances for evaluating the quality of cherry tomatoes. In this paper, a hyper spectral imaging (HSI) system using visible/near-infrared (Vis-NIR) and near-infrared (NIR) was proposed to detect the key qualities of cherry tomatoes. The effects of individual spectral information and fused spectral information in the detection of different qualities were compared for firmness, SSC and TA of cherry tomatoes. Data layer fusion combined with multiple machine learning methods including principal component regression (PCR), partial least squares regression (PLSR), support vector regression (SVR) and back propagation neural network (BP) is used for model training. The results show that for firmness, SSC and TA, the determination coefficient R2 of the multi-quality prediction model established by Vis-NIR spectra is higher than that of NIR spectra. The R2 of the best model obtained by SSC and TA fusion band is greater than 0.9, and that of the best model obtained by the firmness fusion band is greater than 0.85. It is better to use the spectral bands after information fusion for nondestructive quality detection of cherry tomatoes. This study shows that hyperspectral imaging technology can be used for the nondestructive detection of multiple qualities of cherry tomatoes, and the method based on the fusion of two spectra has a better prediction effect for the rapid detection of multiple qualities of cherry tomatoes compared with a single spectrum. This study can provide certain technical support for the rapid nondestructive detection of multiple qualities in other melons and fruits.

Reformulating Couscous with Sprouted Buckwheat: Physico-Chemical Properties and Sensory Characteristics Assessed by E-Senses

In the frame of reformulating food products for valorizing underutilized crops and enhancing both the nutritional and sensory characteristics of traditional foods, this study explored the potential impact of sprouting on some features of couscous prepared from buckwheat. Specifically, the impact of two sprouting times (48 h and 72 h) and two enrichment levels (25% and 50%) on physical properties (bulk density, hydration properties), cooking behavior (e.g., texture), chemical features (e.g., total phenolic content, rutin and quercetin), antioxidant activity (DPPH assay), and sensory traits (by means of electronic nose, tongue, and eye) was considered. Results showed that the replacement of 50% of pre-gelatinized buckwheat flour with 72 h-sprouted buckwheat flour resulted in a couscous with a higher content of phenolic compounds (including rutin and quercetin) and antioxidant activity; the related values further increased upon cooking. Moreover, except for the hardness and gumminess that were worsened (i.e., their values increased), cohesiveness and resilience improved in the presence of sprouted buckwheat (i.e., their values increased). Finally, the overall sensory traits improved with the addition of 50% sprouted buckwheat, since both bitterness and astringency decreased in the reformulated couscous.

Quality assessment of traditional Chinese medicine based on data fusion combined with machine learning: A review

The authenticity and quality of traditional Chinese medicine (TCM) directly impact clinical efficacy and safety. Quality assessment of traditional Chinese medicine (QATCM) is a global concern due to increased demand and shortage of resources. Recently, modern analytical technologies have been extensively investigated and utilized to analyze the chemical composition of TCM. However, a single analytical technique has some limitations, and judging the quality of TCM only from the characteristics of the components is not enough to reflect the overall view of TCM. Thus, the development of multi-source information fusion technology and machine learning (ML) has further improved QATCM. Data information from different analytical instruments can better understand the connection between herbal samples from multiple aspects. This review focuses on the use of data fusion (DF) and ML in QATCM, including chromatography, spectroscopy, and other electronic sensors. The common data structures and DF strategies are introduced, followed by ML methods, including fast-growing deep learning. Finally, DF strategies combined with ML methods are discussed and illustrated for research on applications such as source identification, species identification, and content prediction in TCM. This review demonstrates the validity and accuracy of QATCM-based DF and ML strategies and provides a reference for developing and applying QATCM methods.

A Comparison between the Egg Yolk Flavor of Indigenous 2 Breeds and Commercial Laying Hens Based on Sensory Evaluation, Artificial Sensors, and GC-MS

The focus of this study was to compare the yolk flavor of eggs from laying hens of Chinese indigenous and commercial, based on detection of volatile compounds, fatty acids, and texture characteristics determination, using sensory evaluation, artificial sensors (electronic nose (E-nose), electronic tongue (E-tongue)), and gas chromatography-mass spectrometry (GC-MS). A total of 405 laying hens (Hy-Line Brown (n = 135), Xueyu White (n = 135), and Xinyang Blue (n = 135)) were used for the study, and 540 eggs (180 per breed) were collected within 48 h of being laid and used for sensory evaluation and the instrument detection of yolk flavor. Our research findings demonstrated significant breed differences for sensory attributes of egg yolk, based on sensory evaluation and instrument detection. The milky flavor, moisture, and compactness scores (p < 0.05) of egg yolk from Xueyu White and Xinyang Blue were significantly higher than that of Hy-Line Brown. The aroma preference scores of Xinyang Blue (p < 0.05) were significantly higher, compared to Hy-Line Brown and Xueyu White. The sensor responses of WIW and W2W from E-nose and STS from E-tongue analysis were significantly higher foe egg yolks of Hy-Line Brown (p < 0.05), compared to that of Xueyu White and Xinyang Blue. Additionally, the sensor responses of umami from E-tongue analysis, was significantly higher for egg yolks of Xueyu White (p < 0.05), compared to that of Hy-Line Brown and Xinyang Blue. Besides, the contents of alcohol and fatty acids, such as palmitic acid, oleic acid, and arachidonic acid, in egg yolk were positively correlated with egg flavor. The texture analyzer showed that springiness, gumminess, and hardness of Hy-Line Brown and Xueyu White (p < 0.05) were significantly higher, compared to Xinyang Blue. The above findings demonstrate that the egg yolk from Chinese indigenous strain had better milky flavor, moisture, and compactness, as well as better texture. The egg yolk flavors were mainly due to presence of alcohol and fatty acids, such as palmitic acid, oleic acid, and arachidonic acid, which would provide research direction on improvement in egg yolk flavor by nutrition. The current findings validate the strong correlation between the results of egg yolk flavor and texture, based on sensory evaluation, artificial sensors, and GC-MS. All these indicators would be beneficial for increased preference for egg yolk flavor by consumers and utilization by food processing industry, as well as a basis for the discrimination of eggs from different breeds of laying hens.

Challenges and Opportunities of Implementing Data Fusion in Process Analytical Technology—A Review

The release of the FDA’s guidance on Process Analytical Technology has motivated and supported the pharmaceutical industry to deliver consistent quality medicine by acquiring a deeper understanding of the product performance and process interplay. The technical opportunities to reach this high-level control have considerably evolved since 2004 due to the development of advanced analytical sensors and chemometric tools. However, their transfer to the highly regulated pharmaceutical sector has been limited. To this respect, data fusion strategies have been extensively applied in different sectors, such as food or chemical, to provide a more robust performance of the analytical platforms. This survey evaluates the challenges and opportunities of implementing data fusion within the PAT concept by identifying transfer opportunities from other sectors. Special attention is given to the data types available from pharmaceutical manufacturing and their compatibility with data fusion strategies. Furthermore, the integration into Pharma 4.0 is discussed.

E-Senses, Panel Tests and Wearable Sensors: A Teamwork for Food Quality Assessment and Prediction of Consumer’s Choices

At present, food quality is of utmost importance, not only to comply with commercial regulations, but also to meet the expectations of consumers; this aspect includes sensory features capable of triggering emotions through the citizen’s perception. To date, key parameters for food quality assessment have been sought through analytical methods alone or in combination with a panel test, but the evaluation of panelists’ reactions via psychophysiological markers is now becoming increasingly popular. As such, the present review investigates recent applications of traditional and novel methods to the specific field. These include electronic senses (e-nose, e-tongue, and e-eye), sensory analysis, and wearables for emotion recognition. Given the advantages and limitations highlighted throughout the review for each approach (both traditional and innovative ones), it was possible to conclude that a synergy between traditional and innovative approaches could be the best way to optimally manage the trade-off between the accuracy of the information and feasibility of the investigation. This evidence could help in better planning future investigations in the field of food sciences, providing more reliable, objective, and unbiased results, but it also has important implications in the field of neuromarketing related to edible compounds.

Fluorescence and UV/visible spectroscopic investigation of orange and mango fruit juice quality in case of Adama Town

Extracted Mango and Orange juices were investigated by using spectroscopic techniques such as UV/Visible and Fluorescence. Three portions of samples (fresh juice) were stored at 22 °C for eight days, stored in a water bath and heated at 40 °C, 60 °C, and 80 °C for ten minutes. The highest wavelengths (455 nm) were observed from the UV/Vis results for fresh Mango juices, while 270 nm and 460 nm were observed for stored Mango juices. Furthermore, wavelengths of 320 nm were observed in heat-treated mango juice (40 °C). No absorption peaks were observed at 60 °C and 80 °C due to temperature effects. Absorption peaks of fresh fruit were observed at 330 nm and 390 nm, while 260 nm and 320 nm reflect stored orange juices absorptions peaks. From heat-treated stored (40 °C and 60 °C) samples, 320 nm and 260 nm absorption peaks were observed, respectively. Wavelength observed (454 nm, 540 nm & 700 nm) peaks represent the fresh mango juice spectra, while 460 nm and 700 nm are for stored Mango juices. The peaks observed in the region of 400–500 nm and at 700 nm represent heat-treated mango juices at 40 °C. Heat stored Mango juices (60 °C & 80 °C) have peaks at 700 nm. Peaks observed at 700 nm, 500 nm, and 455 nm reflect fresh orange juice, while 460–500 nm and 700 nm represent the emission spectra of the samples. The stored orange juice peaks at 460–500 nm and at 700 nm, but heated-stored orange juice peaks only at 700 nm. The pH values for orange and mango juices were 3.52–3.73 and 4.02–4.72, respectively.

Consensual Regression of Soluble Solids Content in Peach by Near Infrared Spectrocopy

In order to reduce the uncertainty of the genetic algorithm (GA) in optimizing the near-infrared spectral calibration model and avoid the loss of spectral information of the unselected variables, a strategy of fusing consensus models is proposed to measure the soluble solids content (SSC) in peaches. A total of 266 peach samples were collected at four arrivals, and their interactance spectra were scanned by an integrated analyzer prototype, and then an internal index of SSC was destructively measured by the standard refractometry method. The near-infrared spectra were pre-processed with mean centering and were selected successively with a genetic algorithm (GA) to construct the consensus model, which was integrated with two member models with optimized weightings. One was the conventional partial least square (PLS) optimized with GA selected variables (PLS_GA), and the other one was the derived PLS developed with residual variables after GA selections (PLS_RV). The performance of PLS_RV models showed some useful spectral information related to peaches’ SSC and someone performed close to the full-spectral-based PLS model. Among these 10 runs, consensus models obtained a lower root mean squared errors of prediction (RMSEP), with an average of 1.106% and standard deviation (SD) of 0.0068, and performed better than that of the optimized PLS_GA models, which achieved a RMSEP of average 1.116% with SD of 0.0097. It can be concluded that the application of fusion strategy can reduce the fluctuation uncertainty of a model optimized by genetic algorithm, fulfill the utilization of the spectral information amount, and realize the rapid detection of the internal quality of the peach.

Direct authentication and composition quantitation of red wines based on Tri-step infrared spectroscopy and multivariate data fusion

A robust data fusion strategy integrating Tri-step infrared spectroscopy (IR) with electronic nose (E-nose) was established for rapid qualitative authentication and quantitative evaluation of red wines using Cabernet Sauvignon as an example. The chemical fingerprints of four types of wines were thoroughly interpreted by Tri-step IR, and the defined spectral fingerprint region of alcohol and sugar was 1200-950 cm^-1. The wine types were authenticated by IR-based principal component analysis (PCA). Furthermore, ten quantitative models by partial least squares (PLS) were built to evaluate alcohol and total sugar contents. In particular, the model based on the fusion datasets of spectral fingerprint region and E-nose was superior to the others, in which RMSEP reduced by 47.95% (alcohol) and 79.90% (total sugar), r_p increased by 11.95% and 43.47%, and RPD >3.0. The developed methodology would be applicable for mass screening and rapid multi-chemical-component quantification of wines in a more comprehensive and efficient manner.

Fast GC E-Nose and Chemometrics for the Rapid Assessment of Basil Aroma

The aim of this work is to assess the potentialities of the synergistic combination of an ultra-fast chromatography-based electronic nose as a fingerprinting technique and multivariate data analysis in the context of food quality control and to investigate the influence of some factors, i.e., basil variety, cut, and year of crop, in the final aroma of the samples. A low = level data fusion approach coupled with Principal Component Analysis (PCA) and ANOVA—Simultaneous Component Analysis (ASCA) was used in order to analyze the chromatographic signals acquired with two different columns (MXT-5 and MXT-1701). While the PCA analysis results highlighted the peculiarity of some basil varieties, differing either by a higher concentration of some of the detected chemical compounds or by the presence of different compounds, the ASCA analysis pointed out that variety and year are the most relevant effects, and also confirmed the results of previous investigations.

An Overview of Sensory Characterization Techniques: From Classical Descriptive Analysis to the Emergence of Novel Profiling Methods

Sensory science provides objective information about the consumer understanding of a product, the acceptance or rejection of stimuli, and the description of the emotions evoked. It is possible to answer how consumers perceive a product through discriminative and descriptive techniques. However, perception can change over time, and these fluctuations can be measured with time-intensity methods. Instrumental sensory devices and immersive techniques are gaining headway as sensory profiling techniques. The authors of this paper critically review sensory techniques from classical descriptive analysis to the emergence of novel profiling methods. Though research has been done in the creation of new sensory methods and comparison of those methods, little attention has been given to the timeline approach and its advantages and challenges. This study aimed to gather, explain, simplify, and discuss the evolution of sensory techniques.

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.

The State of Lifelong Learning in Service Robots:

Service robots are appearing more and more in our daily life. The development of service robots combines multiple fields of research, from object perception to object manipulation. The state-of-the-art continues to improve to make a proper coupling between object perception and manipulation. This coupling is necessary for service robots not only to perform various tasks in a reasonable amount of time but also to continually adapt to new environments and safely interact with non-expert human users. Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings. Besides, in most of the cases, there is a reliance on large amounts of training data. Therefore, the knowledge of such robots is fixed after the training phase, and any changes in the environment require complicated, time-consuming, and expensive robot re-programming by human experts. Therefore, these approaches are still too rigid for real-life applications in unstructured environments, where a significant portion of the environment is unknown and cannot be directly sensed or controlled. In such environments, no matter how extensive the training data used for batch learning, a robot will always face new objects. Therefore, apart from batch learning, the robot should be able to continually learn about new object categories and grasp affordances from very few training examples on-site. Moreover, apart from robot self-learning, non-expert users could interactively guide the process of experience acquisition by teaching new concepts, or by correcting insufficient or erroneous concepts. In this way, the robot will constantly learn how to help humans in everyday tasks by gaining more and more experiences without the need for re-programming. In this paper, we review a set of previously published works and discuss advances in service robots from object perception to complex object manipulation and shed light on the current challenges and bottlenecks.

Evaluating low- mid- and high-level fusion strategies for combining Raman and infrared spectroscopy for quality assessment of red meat

The implementation of Raman and infrared spectroscopy with three data fusion strategies to predict pH and % IMF content of red meat was investigated. Raman and FTIR systems were utilized to assess quality parameters of intact red meat. Quantitative models were built using PLS, with model performances assessed with respect to the determination coefficient (R²), root mean square error and normalized root mean square error (NRMSEP). Results obtained on validation against an independent test set show that the high-level fusion strategy had the best performance in predicting the observed pH; with R_P² and NRMSEP values of 0.73 and 12.9% respectively, whereas low-level fusion strategy showed promise in predicting % IMF (NRMSEP = 8.5%). The fusion of data from more than one technique at low and high level resulted in improvement in the model performances; highlighting the possibility of information enhancement.

Electronic Eye Based on RGB Analysis for the Identification of Tequilas

The present work reports the development of a biologically inspired analytical system known as Electronic Eye (EE), capable of qualitatively discriminating different tequila categories. The reported system is a low-cost and portable instrumentation based on a Raspberry Pi single-board computer and an 8 Megapixel CMOS image sensor, which allow the collection of images of Silver, Aged, and Extra-aged tequila samples. Image processing is performed mimicking the trichromatic theory of color vision using an analysis of Red, Green, and Blue components (RGB) for each image's pixel. Consequently, RGB absorbances of images were evaluated and preprocessed, employing Principal Component Analysis (PCA) to visualize data clustering. The resulting PCA scores were modeled with a Linear Discriminant Analysis (LDA) that accomplished the qualitative classification of tequilas. A Leave-One-Out Cross-Validation (LOOCV) procedure was performed to evaluate classifiers' performance. The proposed system allowed the identification of real tequila samples achieving an overall classification rate of 90.02%, average sensitivity, and specificity of 0.90 and 0.96, respectively, while Cohen's kappa coefficient was 0.87. In this case, the EE has demonstrated a favorable capability to correctly discriminated and classified the different tequila samples according to their categories.

Quality Assessment of Different Species and Differently Prepared Slices of Zedoray Rhizome by High-Performance Liquid Chromatography and Colorimeter with the Aid of Chemometrics

In this study, high-performance liquid chromatography (HPLC) and colorimeter were applied to evaluate the quality of different species and differently prepared slices of Zedoray Rhizome samples with the aid of chemometric tools. Fifty batches of Zedoray Rhizome samples from different species and forty-two batches of Zedoray Rhizome samples from differently prepared slices were collected. The quantitative method was developed using HPLC to simultaneously determine the contents of twelve chemical ingredients in Zedoray Rhizome. The colour parameters L, a, and b were measured by a colorimeter. Then, the collected data were analyzed by the principal component analysis and Pearson correlation analysis. The results showed that the proposed method was capable of accurately determining the contents of the twelve chemical ingredients and the colour parameters for the collected samples. There was a dramatic difference in the contents of the chemical ingredients and in the colour parameters among different species and differently prepared slices of Zedoray Rhizome samples. This study reveals that combining HPLC, colorimeter, and chemometric tools can provide a new approach to comprehensively evaluate the quality of Zedoray Rhizome samples.

Historical Evolution and Food Control Achievements of Near Infrared Spectroscopy, Electronic Nose, and Electronic Tongue-Critical Overview

Amid today's stringent regulations and rising consumer awareness, failing to meet quality standards often results in health and financial compromises. In the lookout for solutions, the food industry has seen a surge in high-performing systems all along the production chain. By virtue of their wide-range designs, speed, and real-time data processing, the electronic tongue (E-tongue), electronic nose (E-nose), and near infrared (NIR) spectroscopy have been at the forefront of quality control technologies. The instruments have been used to fingerprint food properties and to control food production from farm-to-fork. Coupled with advanced chemometric tools, these high-throughput yet cost-effective tools have shifted the focus away from lengthy and laborious conventional methods. This special issue paper focuses on the historical overview of the instruments and their role in food quality measurements based on defined food matrices from the Codex General Standards. The instruments have been used to detect, classify, and predict adulteration of dairy products, sweeteners, beverages, fruits and vegetables, meat, and fish products. Multiple physico-chemical and sensory parameters of these foods have also been predicted with the instruments in combination with chemometrics. Their inherent potential for speedy, affordable, and reliable measurements makes them a perfect choice for food control. The high sensitivity of the instruments can sometimes be generally challenging due to the influence of environmental conditions, but mathematical correction techniques exist to combat these challenges.

DNA barcoding and mini-barcoding in authenticating processed animal-derived food: A case study involving the Chinese market

This study used DNA barcoding and DNA mini-barcoding to test a variety of animal-derived food products sold in the Chinese market for potential mislabeling. Samples (52) including meat, poultry, and fish purchased from retail and online sources were examined. Regions of cytochrome C oxidase I (COI) gene (~650 bp) and 16S rRNA (~220 bp) were used as full- and mini-barcode markers, respectively. Approximately 94% (49 of 52) of the samples generated barcode sequences. The failure rate for full COI full-barcodes was 44%, but we obtained the 16S rRNA mini-barcode from 87% of the COI-failed cases. Overall, the survey revealed that 23% (12 of 52) of animal-derived products were mislabeled and, in most cases, contain undeclared species. Thus, regulatory measures and continuous monitoring for mislabeling of animal-derived products should be conducted.

Information integration of force sensing and machine vision for in-shell shrivelled walnut detection based on the golden-section search optimal discrimination threshold

BACKGROUND

The shrivelled defect of walnuts has a serious effect on walnut quality and is a common internal defect of in-shell walnuts. However, only depending on a single detection technique such as machine vision to detect in-shell shrivelled walnuts is challenging. Meanwhile, the threshold has a great impact on the accuracy of the discrimination analysis. Therefore, the golden-section was used to search the optimal discrimination threshold and the information integration of force sensing and machine vision was used to identify the shrivelled walnut and the sound walnut.

RESULTS

A discrimination model for in-shell shrivelled walnut based on information integration of force sensing and machine vision was built. The optimal threshold was determined as 0.3464 by the golden-section method, and the optimal threshold was used to discriminate the in-shell shrivelled walnut and the sound walnut. The discriminant accuracy of in-shell shrivelled and sound walnuts were 96.97% and 85.29%, respectively, and the total discriminant accuracy reached 93.00% based on the discrimination model.

CONCLUSION

The results indicated the information integration of force sensing and machine vision based on the golden-section search optimal discrimination threshold is a potential method to discriminate shrivelled walnuts and sound walnuts, which also makes a basis for on-line detection of in-shell shrivelled walnut. © 2019 Society of Chemical Industry.

Recent developments of artificial intelligence in drying of fresh food: A review

Intellectualization is an important direction of drying development and artificial intelligence (AI) technologies have been widely used to solve problems of nonlinear function approximation, pattern detection, data interpretation, optimization, simulation, diagnosis, control, data sorting, clustering, and noise reduction in different food drying technologies due to the advantages of self-learning ability, adaptive ability, strong fault tolerance and high degree robustness to map the nonlinear structures of arbitrarily complex and dynamic phenomena. This article presents a comprehensive review on intelligent drying technologies and their applications. The paper starts with the introduction of basic theoretical knowledge of ANN, fuzzy logic and expert system. Then, we summarize the AI application of modeling, predicting, and optimization of heat and mass transfer, thermodynamic performance parameters, and quality indicators as well as physiochemical properties of dried products in artificial biomimetic technology (electronic nose, computer vision) and different conventional drying technologies. Furthermore, opportunities and limitations of AI technique in drying are also outlined to provide more ideas for researchers in this area.

Application of Electronic Nose Systems on Animal-Source Food

Electronic nose, which is designed to perceive artificially the odour-active molecules in a sample headspace, has seen an increased use in the food industry as a rapid and reliable tool for quality assessment, classification, and authentication of several food items. The use of chemometrics and pattern recognition methods, together with gas sensors, emerged to be a very powerful analytical approach. In this chapter, an overview of the recent achievements in the field of electronic nose applications on animal-source food is given. Moreover, the authors deal with the recent research trends to overcome the actual sensor shortcomings, including sensor fusion techniques and their applications to evaluate animal-source foods and novel electronic nose systems.

Electronic noses: Powerful tools in meat quality assessment

Main factors that are considered by consumers when choosing meat products are colour and aroma, of which the latter is a more reliable indicator of quality. However, a simple sensory evaluation of hedonistic qualities is often not sufficient to determine whether protein is past its shelf life, and consumption of spoiled meat can lead to serious health hazards. Some volatile compounds can be used as spoilage indicators, and so a device equipped with a sensor sensitive to particular odorants would prove useful. Unfortunately, no such single compound has yet been identified, as the changes taking place in a sample of meat during storage are contingent on numerous factors. On the other hand, a combination of volatile compounds may form a unique 'fingerprint' which can be analysed pattern recognition algorithms with an electronic nose. It can supplement established techniques of meat quality assessment by providing results that correlate well with hedonic perception in a short time and at a low cost.

A Framework for the Multi-Level Fusion of Electronic Nose and Electronic Tongue for Tea Quality Assessment

Electronic nose (E-nose) and electronic tongue (E-tongue) can mimic the sensory perception of human smell and taste, and they are widely applied in tea quality evaluation by utilizing the fingerprints of response signals representing the overall information of tea samples. The intrinsic part of human perception is the fusion of sensors, as more information is provided comparing to the information from a single sensory organ. In this study, a framework for a multi-level fusion strategy of electronic nose and electronic tongue was proposed to enhance the tea quality prediction accuracies, by simultaneously modeling feature fusion and decision fusion. The procedure included feature-level fusion (fuse the time-domain based feature and frequency-domain based feature) and decision-level fusion (D-S evidence to combine the classification results from multiple classifiers). The experiments were conducted on tea samples collected from various tea providers with four grades. The large quantity made the quality assessment task very difficult, and the experimental results showed much better classification ability for the multi-level fusion system. The proposed algorithm could better represent the overall characteristics of tea samples for both odor and taste.

Case Studies in Modelling, Control in Food Processes

This chapter discusses the importance of modelling and control in increasing food process efficiency and ensuring product quality. Various approaches to both modelling and control in food processing are set in the context of the specific challenges in this industrial sector and latest developments in each area are discussed. Three industrial case studies are used to demonstrate the benefits of advanced measurement, modelling and control in food processes. The first case study illustrates the use of knowledge elicitation from expert operators in the process for the manufacture of potato chips (French fries) and the consequent improvements in process control to increase the consistency of the resulting product. The second case study highlights the economic benefits of tighter control of an important process parameter, moisture content, in potato crisp (chips) manufacture. The final case study describes the use of NIR spectroscopy in ensuring effective mixing of dry multicomponent mixtures and pastes. Practical implementation tips and infrastructure requirements are also discussed.

Potential application of machine vision technology to saffron (Crocus sativus L.) quality characterization

Saffron quality characterization is an important issue in the food industry and of interest to the consumers. This paper proposes an expert system based on the application of machine vision technology for characterization of saffron and shows how it can be employed in practical usage. There is a correlation between saffron color and its geographic location of production and some chemical attributes which could be properly used for characterization of saffron quality and freshness. This may be accomplished by employing image processing techniques coupled with multivariate data analysis for quantification of saffron properties. Expert algorithms can be made available for prediction of saffron characteristics such as color as well as for product classification.