Recent Advances in Data Mining Techniques and Their Applications in Hyperspectral Image Processing for the Food Industry

Hyperspectral imaging for estimating leaf, flower, and fruit macronutrient concentrations and predicting strawberry yields

Managing the nutritional status of strawberry plants is critical for optimizing yield. This study evaluated the potential of hyperspectral imaging (400-1,000 nm) to estimate nitrogen (N), phosphorus (P), potassium (K), and calcium (Ca) concentrations in strawberry leaves, flowers, unripe fruit, and ripe fruit and to predict plant yield. Partial least squares regression (PLSR) models were developed to estimate nutrient concentrations. The determination coefficient of prediction (R2P) and ratio of performance to deviation (RPD) were used to evaluate prediction accuracy, which often proved to be greater for leaves, flowers, and unripe fruit than for ripe fruit. The prediction accuracies for N concentration were R2P = 0.64, 0.60, 0.81, and 0.30, and RPD = 1.64, 1.59, 2.64, and 1.31, for leaves, flowers, unripe fruit, and ripe fruit, respectively. Prediction accuracies for Ca concentrations were R2P = 0.70, 0.62, 0.61, and 0.03, and RPD = 1.77, 1.63, 1.60, and 1.15, for the same respective plant parts. Yield and fruit mass only had significant linear relationships with the Difference Vegetation Index (R2 = 0.256 and 0.266, respectively) among the eleven vegetation indices tested. Hyperspectral imaging showed potential for estimating nutrient status in strawberry crops. This technology will assist growers to make rapid nutrient-management decisions, allowing for optimal yield and quality.

Prediction of acrylamide content in potato chips using near-infrared spectroscopy

Acrylamide (ACR), a neurotoxin with carcinogenic properties that can affect fertility, is commonly found in fried and baked foods such as potato chips. This study was carried out to predict the ACR content in fried and baked potato chips using near-infrared (NIR) spectroscopy. Effective wavenumbers were identified using competitive adaptive reweighted sampling (CARS) and the successive projections algorithm (SPA). Six wavenumbers (12799 cm^-1, 12007 cm^-1, 10944 cm^-1, 10943 cm^-1, 5801 cm^-1, and 4332 cm^-1) were selected using the ratio (λ_i/λ_j) and difference (λ_i-λ_j) of any two wavenumbers from the CARS and SPA results. First, partial least squares (PLS) models were established based on full spectral wavebands (12799-4000 cm^-1), and the prediction models were subsequently redeveloped based on effective wavenumbers to predict ACR content. Results showed that the full and selected wavenumbers-based PLS models obtained the coefficient of determination (R²) of 0.7707 and 0.6670, respectively, and the root mean square errors of prediction (RMSEP) of 53.0442 μg/kg and 64.3810 μg/kg, respectively, in the prediction sets. The results of this work demonstrate the suitability of NIR spectroscopy as a non-destructive method for predicting ACR content in potato chips.

ResNet Model Automatically Extracts and Identifies FT-NIR Features for Geographical Traceability of Polygonatum kingianum

Medicinal plants have incredibly high economic value, and a practical evaluation of their quality is the key to promoting industry development. The deep learning model based on residual convolutional neural network (ResNet) has the advantage of automatic extraction and the recognition of Fourier transform near-infrared spectroscopy (FT-NIR) features. Models are difficult to understand and interpret because of unknown working mechanisms and decision-making processes. Therefore, in this study, artificial feature extraction methods combine traditional partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) models to understand and compare deep learning models. The results show that the ResNet model has significant advantages over traditional models in feature extraction and recognition. Secondly, preprocessing has a great impact on the feature extraction and feature extraction, and is beneficial for improving model performance. Competitive adaptive reweighted sampling (CARS) and variable importance in projection (VIP) methods screen out more feature variables after preprocessing, but the number of potential variables (LVs) and successive projections algorithm (SPA) methods obtained is fewer. The SPA method only extracts two variables after preprocessing, causing vital information to be lost. The VIP feature of traditional modelling yields the best results among the four methods. After spectral preprocessing, the recognition rates of the PLS-DA and SVM models are up to 90.16% and 88.52%. For the ResNet model, preprocessing is beneficial for extracting and identifying spectral image features. The ResNet model based on synchronous two-dimensional correlation spectra has a recognition accuracy of 100%. This research is beneficial to the application development of the ResNet model in foods, spices, and medicinal plants.

Alternative data mining/machine learning methods for the analytical evaluation of food quality and authenticity - A review

In recent years, the variety and volume of data acquired by modern analytical instruments in order to conduct a better authentication of food has dramatically increased. Several pattern recognition tools have been developed to deal with the large volume and complexity of available trial data. The most widely used methods are principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), soft independent modelling by class analogy (SIMCA), k-nearest neighbours (kNN), parallel factor analysis (PARAFAC), and multivariate curve resolution-alternating least squares (MCR-ALS). Nevertheless, there are alternative data treatment methods, such as support vector machine (SVM), classification and regression tree (CART) and random forest (RF), that show a great potential and more advantages compared to conventional ones. In this paper, we explain the background of these methods and review and discuss the reported studies in which these three methods have been applied in the area of food quality and authenticity. In addition, we clarify the technical terminology used in this particular area of research.

Hyperspectral imaging: a novel approach for plant root phenotyping

BACKGROUND

Root phenotyping aims to characterize root system architecture because of its functional role in resource acquisition. RGB imaging and analysis procedures measure root system traits via colour contrasts between roots and growth media or artificial backgrounds. In the case of plants grown in soil-filled rhizoboxes, where the colour contrast can be poor, it is hypothesized that root imaging based on spectral signatures improves segmentation and provides additional knowledge on physico-chemical root properties.

RESULTS

Root systems of Triticum durum grown in soil-filled rhizoboxes were scanned in a spectral range of 1000-1700 nm with 222 narrow bands and a spatial resolution of 0.1 mm. A data processing pipeline was developed for automatic root segmentation and analysis of spectral root signatures. Spectral- and RGB-based root segmentation did not significantly differ in accuracy even for a bright soil background. Best spectral segmentation was obtained from log-linearized and asymptotic least squares corrected images via fuzzy clustering and multilevel thresholding. Root axes revealed major spectral distinction between center and border regions. Root decay was captured by an exponential function of the difference spectra between water and structural carbon absorption regions.

CONCLUSIONS

Fundamentals for root phenotyping using hyperspectral imaging have been established by means of an image processing pipeline for automated segmentation of soil-grown plant roots at a high spatial resolution and for the exploration of spectral signatures encoding physico-chemical root zone properties.

Rapid detection of frozen-then-thawed minced beef using multispectral imaging and Fourier transform infrared spectroscopy

In recent years, fraud detection has become a major priority for food authorities, as fraudulent practices can have various economic and safety consequences. This work explores ways of identifying frozen-then-thawed minced beef labeled as fresh in a rapid, large-scale and cost-effective way. For this reason, freshly-ground beef was purchased from seven separate shops at different times, divided in fifteen portions and placed in Petri dishes. Multi-spectral images and FTIR spectra of the first five were immediately acquired while the remaining were frozen (-20°C) and stored for 7 and 32days (5 samples for each time interval). Samples were thawed and subsequently subjected to similar data acquisition. In total, 105 multispectral images and FTIR spectra were collected which were further analyzed using partial least-squares discriminant analysis and support vector machines. Two meat batches (30 samples) were reserved for independent validation and the remaining five batches were divided in training and test set (75 samples). Results showed 100% overall correct classification for test and external validation MSI data, while FTIR data yielded 93.3 and 96.7% overall correct classification for FTIR test set and external validation set respectively.

Quality evaluation of fish and other seafood by traditional and nondestructive instrumental methods: Advantages and limitations

Although being one of the most vulnerable and perishable products, fish and other seafoods provide a wide range of health-promoting compounds. Recently, the growing interest of consumers in food quality and safety issues has contributed to the increasing demand for sensitive and rapid analytical technologies. Several traditional physicochemical, textural, sensory, and electrical methods have been used to evaluate freshness and authentication of fish and other seafood products. Despite the importance of these standard methods, they are expensive and time-consuming, and often susceptible to large sources of variation. Recently, spectroscopic methods and other emerging techniques have shown great potential due to speed of analysis, minimal sample preparation, high repeatability, low cost, and, most of all, the fact that these techniques are noninvasive and nondestructive and, therefore, could be applied to any online monitoring system. This review describes firstly and briefly the basic principles of multivariate data analysis, followed by the most commonly traditional methods used for the determination of the freshness and authenticity of fish and other seafood products. A special focus is put on the use of rapid and nondestructive techniques (spectroscopic techniques and instrumental sensors) to address several issues related to the quality of these products. Moreover, the advantages and limitations of each technique are reviewed and some perspectives are also given.

Hyperspectral imaging with multivariate analysis for technological parameters prediction and classification of muscle foods: A review

Muscle foods are very important for a well-balanced daily diet. Due to their perishability and vulnerability, there is a need for quality and safety evaluation of such foods. Hyperspectral imaging (HSI) coupled with multivariate analysis is becoming increasingly popular for the non-destructive, non-invasive, and rapid determination of important quality attributes and the classification of muscle foods. This paper reviews recent advances of application of HSI for predicting some significant muscle foods parameters, including color, tenderness, firmness, springiness, water-holding capacity, drip loss and pH. In addition, algorithms for the rapid classification of muscle foods are also reported and discussed. It will be shown that this technology has great potential to replace traditional analytical methods for predicting various quality parameters and classifying muscle foods.