Applications of artificial neural networks (ANNs) in food science

Artificial neural networks (ANNs) have been applied in almost every aspect of food science over the past two decades, although most applications are in the development stage. ANNs are useful tools for food safety and quality analyses, which include modeling of microbial growth and from this predicting food safety, interpreting spectroscopic data, and predicting physical, chemical, functional and sensory properties of various food products during processing and distribution. ANNs hold a great deal of promise for modeling complex tasks in process control and simulation and in applications of machine perception including machine vision and electronic nose for food safety and quality control. This review discusses the basic theory of the ANN technology and its applications in food science, providing food scientists and the research community an overview of the current research and future trend of the applications of ANN technology in the field.     

An artificial neural network model for predicting flavour intensity in blackcurrant concentrates

Artificial neural networks (ANNs)—machine learning acquiring knowledge in training and using deduced relationships to predict responses—were studied to rationalise concentrate use in fruit drinks production. Sets of ANNs were developed for predicting flavour intensity in blackcurrant concentrates from gas chromatographic data on flavour components (37) in 133 sorbent extracts from blackcurrant concentrates varying in season, geographical origin and processing technology. Sensory data was collected using ratio scaling on flavour intensities in drinks from concentrates. Relationships between chromatographic and sensory data for concentrates of three seasons (1989, 1990 and 1992) were modelled by ANNs with back propagation using principal component regression scores as input. Predictions were compared with a global model from random concentrates from all three seasons. In predicting overall flavour intensity, ANN models were better fitted than partial least square regression. Ability of artificial neural networks to simulate non-linear relationships observed in human perceptions could explain such improvements.     

Application of artificial neural network (ANN) for the prediction of thermal resistance of knitted fabrics at different moisture content*

Thermal resistance of the fabrics is one of the decisive parameters in terms of comfort; however it can change due to wetting. Therefore, thermal resistance of wetted fabric is important for comfort performance of garments. In recent years, artificial neural networks (ANN) have been used in the textile field for classification, identification, prediction of properties and optimization problems. ANNs can predict the fabric thermal properties by considering the influence of all fabric parameters at the same time. In this study, ANNs were used to predict thermal resistance of wetted fabrics. For this aim, two different architectures were experienced and high regression coefficient (R²) between the predicted (training and testing) and observed thermal resistance values were obtained from both models. The obtained regression coefficient values were over 90% for both models. Then it can be said that ANNs could be used for predicting thermal resistance of wetted fabrics successfully.     

Application of machine learning to the monitoring and prediction of food safety: A review

Machine learning (ML) has proven to be a useful technology for data analysis and modeling in a wide variety of domains, including food science and engineering. The use of ML models for the monitoring and prediction of food safety is growing in recent years. Currently, several studies have reviewed ML applications on foodborne disease and deep learning applications on food. This article presents a literature review on ML applications for monitoring and predicting food safety. The paper summarizes and categorizes ML applications in this domain, categorizes and discusses data types used for ML modeling, and provides suggestions for data sources and input variables for future ML applications. The review is based on three scientific literature databases: Scopus, CAB Abstracts, and IEEE. It includes studies that were published in English in the period from January 1, 2011 to April 1, 2021. Results show that most studies applied Bayesian networks, Neural networks, or Support vector machines. Of the various ML models reviewed, all relevant studies showed high prediction accuracy by the validation process. Based on the ML applications, this article identifies several avenues for future studies applying ML models for the monitoring and prediction of food safety, in addition to providing suggestions for data sources and input variables.     

Antioxidant activity prediction and classification of some teas using artificial neural networks

In order to characterise and to classify some teas a simple, rapid and economical method based on composition, antioxidant activity and artificial neural networks (ANNs) is proposed. For these purpose two types of ANN based applications have been developed: one for predicting the antioxidant activity and a second one for establishing the class of the teas. The complex relationship between the total antioxidant activity (AA) depending on the total flavonoids content (F), total catechins content (C) and total methyl-xanthines content (MX) of commercial teas was revealed by the first designed feed-forward ANN. Secondly, using a probabilistic ANN, successful tea classification in various classes (green tea, black tea and express black tea) was also performed.     

PREDICTION OF MECHANICAL PROPERTIES OF CUMIN SEED USING ARTIFICIAL NEURAL NETWORKS

In this paper, two artificial neural networks (ANNs) are applied to acquire the relationship between the mechanical properties and moisture content of cumin seed, using the data of quasi-static loading test. In establishing these relationship, the moisture content, seed size, loading rate and seed orientation were taken as the inputs of both models. The force and energy required for fracturing of cumin seed, under quasi-static loading were taken as the outputs of two models. The activation function in the output layer of models obeyed a linear output, whereas the activation function in the hidden layers were in the form of a sigmoid function. Adjusting ANN parameters such as learning rate and number of neurons and hidden layers affected the accuracy of force and energy prediction. Comparison of the predicted and experimented data showed that the ANN models used to predict the relationships of mechanical properties of cumin seed have a good learning precision and good generalization, because the root mean square errors of the predicated data by ANNs were rather low (4.6 and 7.7% for the force and energy, respectively).

PRACTICAL APPLICATIONS

Cumin seed is generally used as a food additive in the form of powder for imparting flavor to different food preparations and for a variety of medicinal properties. Physical properties of cumin seeds are essential for the design of equipment for handling, harvesting, aeration, drying, storing, grinding and processing. For powder preparation especially the fracture behavior of the seeds are essential. These properties are affected by numerous factors such as size, form and moisture content of the grain and deformation speed. A neural network model was developed that can be used to predict the relationships of mechanical properties. Artificial neural network models are powerful empirical models approach, which can be compared with mathematical models.     

黄酒糟的增值利用技术及应用前景探讨

为充分发挥黄酒糟在食品加工工业中增值利用的技术,与黄酒生产企业分享技术进步而产生的经济效益,较为全面地介绍了以黄酒糟为原料生产糟烧酒、香糟卤、食醋、复合氨基酸调味剂和蛋白质等产品的工艺流程和技术要点,探讨了黄酒糟在食品加工工业中的增值应用前景。     

Using artificial neural networks to develop prediction models for sensory-instrumental relationships; an overview

The possibility of using neural networks for modelling instrumental-sensory relationships is investigated. The advantages and disadvantages of using artificial neural networks (ANNs) are considered and compared with those of the multivariate linear methods of principal components regression (PCR) and partial least squares regression (PLS). In particular the problem of modelling nonlinear relationships is considered. It is concluded that ANNs cannot replace PCR and PLS for linear relationships but do offer potential for modelling nonlinear relationships.     

利用AFIS与神经网络预测纱线强力

评述了AFIS纤维测试系统以及人工神经网络的特点，提出了利用它们进行纱线强力预测的工作原理和网络构建方法，并提供了实例。     

Using artificial neural networks with graphical user interface to predict the strength of carded cotton yarns

Artificial neural networks (ANNs) are used in prediction fields. Yarn strength is one of the most important properties, because it reflects the quality of the yarn. The prediction process of yarn strength is very important from the technology side because many of generated forces in the spun yarns could be given by yarn strength. Data were collected from the United Commercial Industrial Company, Damascus, Syria. Then, artificial neural network algorithm was architected. Several neural networks were architected one of these has been chosen, which contained acceptable network error rate. To deal easily with ANN, a simple graphical user interface has been created. This ANN has been tested on a new sample. Results were compared with the actual results as well as the relationship of Solovev which is allocated to predict the strength cotton yarn. ANN has given more acceptable results than Solovev’s relationship.     

Evaluation of Coffee Roasting Degree by Using Electronic Nose and Artificial Neural Network for Off-line Quality Control

An electronic nose (EN) based on an array of 10 metal oxide semiconductor sensors was used, jointly with an artificial neural network (ANN), to predict coffee roasting degree. The flavor release evolution and the main physicochemical modifications (weight loss, density, moisture content, and surface color: L*, a*), during the roasting process of coffee, were monitored at different cooking times (0, 6, 8, 10, 14, 19 min). Principal component analysis (PCA) was used to reduce the dimensionality of sensors data set (600 values per sensor). The selected PCs were used as ANN input variables. Two types of ANN methods (multilayer perceptron [MLP] and general regression neural network [GRNN]) were used in order to estimate the EN signals. For both neural networks the input values were represented by scores of sensors data set PCs, while the output values were the quality parameter at different roasting times. Both the ANNs were able to well predict coffee roasting degree, giving good prediction results for both roasting time and coffee quality parameters. In particular, GRNN showed the highest prediction reliability. Practical Application: Actually the evaluation of coffee roasting degree is mainly a manned operation, substantially based on the empirical final color observation. For this reason it requires well-trained operators with a long professional skill. The coupling of e-nose and artificial neural networks (ANNs) may represent an effective possibility to roasting process automation and to set up a more reproducible procedure for final coffee bean quality characterization.     

Recent Applications of Advanced Control Techniques in Food Industry

Process control has become increasingly important for the food industry since the last decades due to its capability of increasing yield, minimizing production cost, and improving food quality. New developments for control strategies such as artificial neural networks and model-based controls as well as their applications have brought several new prospects to the food industry. Food processes are mostly nonlinear and show different process dynamics with various raw materials and different processing conditions. Therefore, advanced process control techniques are highly invaluable compared to classical control approaches. In this review, advanced control strategies, particularly model-based controllers, fuzzy logic controllers, and neural network-based controllers, are firstly described with their main characteristics. A number of applications of the advanced control strategies are then discussed according to different food processing industries such as baking, drying, fermentation/brewing, dairy, and thermal/pressure food processing.     

Does the product test really make a difference? Evidence from the launch of a new wine

Although both the concept and the product tests are considered important in predicting the acceptance of new food products into the market, there is scant research in the relevant literature comparing the predictive power of both tests, simultaneously, for the same product. To shed light on this line of research, this study compares the explanatory capacities of concept and product testing in the introduction of a new wine. To achieve this, a structural equation model, integrating sensory benefits, social norms and emotional dimensions with two consumer samples (one for the concept testing and another for the product testing) was proposed and tested. The results obtained showed that the modeĺs explanatory capacity did not increase significantly when the new wine was tested (product testing) in comparison to when only information about the wine was presented (concept testing). In both cases, the variables that explain purchase intention are the same. These results have important practical implications and open new research lines that can contribute to the theories that try to explain the acceptance of new foods.     

Artificial neural networks for prediction of antioxidant capacity of cruciferous sprouts

The aim of this work was to show that artificial neural networks (ANNs) are the convenient tool for modeling the biological properties of food. For this reason, as a good example, known contents of bioactive compounds of cruciferous sprouts were taken for the prediction of their trolox equivalent antioxidant capacity–one of the most important biological properties of food. The input data reflected the contents of the following compounds in cruciferous seeds in the course of germination: total phenolic compounds (TPC), inositol hexaphosphate (InsP₆), glucosinolates (GLS), soluble proteins (SP), ascorbic acid (AH₂), and total tocopherols (T_tot). Additionally, the trolox equivalent antioxidant capacity of germinated cruciferous seeds (TEAC_exp) was determined. The used ANN which was trained on the learning set, generalized the obtained prediction ability in respect to the data contained in validating and testing sets. The predicted TAEC values calculated by ANN were satisfactory correlated with experimental TAEC values. Therefore, the ANN seems to find application in the quality analysis of functional properties of food of plant origin for the prediction of the trolox equivalent antioxidant capacity.     

基于电子鼻与LightGBM算法判别葡萄酒品种的研究

针对葡萄酒的鉴别问题,通过电子鼻采集7种葡萄酒的气味信息,应用LightGBM算法对葡萄酒的气味特征进行学习,并运用TPE超参数优化算法对LightGBM算法超参数进行自适应寻优,以5折交叉验证为指标评估模型的性能。试验结果表明LightGBM建立的判别模型对葡萄酒样本的判别准确率为96.62%,优于传统的支持向量机、随机森林、神经网络,验证了LightGBM在葡萄酒品种鉴别中的优越性。     

A Comprehensive Review on Food Applications of Terahertz Spectroscopy and Imaging

Food product safety is a public health concern. Most of the food safety analytical and detection methods are expensive, labor intensive, and time consuming. A safe, rapid, reliable, and nondestructive detection method is needed to assure consumers that food products are safe to consume. Terahertz (THz) radiation, which has properties of both microwave and infrared, can penetrate and interact with many commonly used materials. Owing to the technological developments in sources and detectors, THz spectroscopic imaging has transitioned from a laboratory‐scale technique into a versatile imaging tool with many practical applications. In recent years, THz imaging has been shown to have great potential as an emerging nondestructive tool for food inspection. THz spectroscopy provides qualitative and quantitative information about food samples. The main applications of THz in food industries include detection of moisture, foreign bodies, inspection, and quality control. Other applications of THz technology in the food industry include detection of harmful compounds, antibiotics, and microorganisms. THz spectroscopy is a great tool for characterization of carbohydrates, amino acids, fatty acids, and vitamins. Despite its potential applications, THz technology has some limitations, such as limited penetration, scattering effect, limited sensitivity, and low limit of detection. THz technology is still expensive, and there is no available THz database library for food compounds. The scanning speed needs to be improved in the future generations of THz systems. Although many technological aspects need to be improved, THz technology has already been established in the food industry as a powerful tool with great detection and quantification ability. This paper reviews various applications of THz spectroscopy and imaging in the food industry.     

基于人工神经网络的毛精纺纱线质量预报技术

介绍了毛精纺纺纱过程与人工神经网络的特点 ,提出人工神经网络在纺纱质量预报中的工作原理与实现方法 ,并提供了国内外的应用实例 ,指出人工神经网络技术在毛精纺纱线质量预报中的广泛应用前景。     

人工神经网络技术与纺纱质量预报

评述了人工神经网络和纺纱过程的特点 ,提出人工神经网络在纺纱质量预报中的工作原理和网络构建方法 ,并提供了国内外的应用实例和网络的实现方法 ,指出人工神经网络技术在纺纱质量预报中的广泛应用前景     

A new approach for prediction of sewing performance of fabrics in apparel manufacturing using artificial neural networks

Abstract

This paper investigates the use of extended normalized radial basis function (ENRBF) neural networks to predict the sewing performance of fabrics in apparel manufacturing. In order to evaluate the performance of the ENRBF neural networks that could be emulated as human decision in the prediction of sewing performance of fabrics more effectively, it could be compared with the traditional back-propagation (BP) neural networks in terms of prediction errors. There are 109 data sets cover fabric properties measured by using a computerized measuring system, and the sewing performance of each fabric's specimen assessed by the domain experts. Of these 109 input—output data pairs, 94 were used to train the proposed ENRBF and BP neural networks for the prediction of the unknown sewing performance of a given fabric, and 15 were used to test the proposed ENRBF and BP neural networks, respectively. After 10,000 iterations of training of the ENRBF and BP neural networks, both of them converged to the minimum error level. A comparison was made between actual fabric performances during sewing, the experts' advices, and the results of predicting fabric performances during sewing for both networks. It was found that the ENRBF and BP neural networks indicate similar error levels, but the prediction made by the ENRBF neural network is better than the prediction made by the BP neural network in some areas. Both the systems provided better advice than the experts in some areas, when compared to actual sewing performance.