Evaluation of near-infrared hyperspectral imaging for the assessment of potato processing aptitude.

The potato (Solanum tuberosum L.) is the world's fifth most important staple food with high socioeconomic relevance. Several potato cultivars obtained by selection and crossbreeding are currently on the market. This diversity causes tubers to exhibit different behaviors depending on the processing to which they are subjected. Therefore, it is interesting to identify cultivars with specific characteristics that best suit consumer preferences. In this work, we present a method to classify potatoes according to their cooking or frying as crisps aptitude using NIR hyperspectral imaging (HIS) combined with a Partial Least Squares Discriminant Analysis (PLS-DA). Two classification approaches were used in this study. First, a classification model using the mean spectra of a dataset composed of 80 tubers belonging to 10 different cultivars. Then, a pixel-wise classification using all the pixels of each sample of a small subset of samples comprised of 30 tubers. Hyperspectral images were acquired using fresh-cut potato slices as sample material placed on a mobile platform of a hyperspectral system in the NIR range from 900 to 1,700 nm. After image processing, PLS-DA models were built using different pre-processing combinations. Excellent accuracy rates were obtained for the models developed using the mean spectra of all samples with 90% of tubers correctly classified in the external dataset. Pixel-wise classification models achieved lower accuracy rates between 66.62 and 71.97% in the external validation datasets. Moreover, a forward interval PLS (iPLS) method was used to build pixel-wise PLS-DA models reaching accuracies above 80 and 71% in cross-validation and external validation datasets, respectively. Best classification result was obtained using a subset of 100 wavelengths (20 intervals) with 71.86% of pixels correctly classified in the validation dataset. Classification maps were generated showing that false negative pixels were mainly located at the edges of the fresh-cut slices while false positive were principally distributed at the central pith, which has singular characteristics.

Classification of Beef longissimus thoracis Muscle Tenderness Using Hyperspectral Imaging and Chemometrics.

Nowadays, the meat industry requires non-destructive, sustainable, and rapid methods that can provide objective and accurate quality assessment with little human intervention. Therefore, the present research aimed to create a model that can classify beef samples from longissimus thoracis muscle according to their tenderness degree based on hyperspectral imaging (HSI). In order to obtain different textures, two main strategies were used: (a) aging type (wet and dry aging with or without starters) and (b) aging times (0, 7, 13, 21, and 27 days). Categorization into two groups was carried out for further chemometric analysis, encompassing group 1 (ngroup1 = 30) with samples with WBSF ˂ 53 N whereas group 2 (ngroup2 = 28) comprised samples with WBSF values ≥ 53 N. Then, classification models were created by applying the partial least squares discriminant analysis (PLS-DA) method. The best results were achieved by combining the following pre-processing algorithms: 1st derivative + mean center, reaching 70.83% of correctly classified (CC) samples and 67.14% for cross validation (CV) and prediction, respectively. In general, it can be concluded that HSI technology combined with chemometrics has the potential to differentiate and classify meat samples according to their textural characteristics.

Phytochemicals determination and classification in purple and red fleshed potato tubers by analytical methods and near infrared spectroscopy.

BACKGROUND: Over the last two decades, the attractive colours and shapes of pigmented tubers and the increasing concern about the relationship between nutrition and health have contributed to the expansion of their consumption and a specialty market. Thus, we have quantified the concentration of health promoting compounds such as soluble phenolics, monomeric anthocyanins, carotenoids, vitamin C, and hydrophilic antioxidant capacity, in a collection of 18 purple- and red-fleshed potato accessions. RESULTS: Cultivars and breeding lines high in vitamin C, such as Blue Congo, Morada and Kasta, have been identified. Deep purple cultivars Violet Queen, Purple Peruvian and Vitelotte showed high levels of soluble phenolics, monomeric anthocyanins, and hydrophilic antioxidant capacity, whereas relatively high carotenoid concentrations were found in partially yellow coloured tubers, such as Morada, Highland Burgundy Red, and Violet Queen. CONCLUSION: The present characterisation of cultivars and breeding lines with high concentrations of phytochemicals is an important step both to support the consideration of specialty potatoes as a source of healthy compounds, and to obtain new cultivars with positive nutritional characteristics. Moreover, by using near infrared spectroscopy a non-destructive identification and classification of samples with different levels of phytochemicals is achieved, offering an unquestionable contribution to the potato industry for future automatic discrimination of varieties.

A review of the application of near-infrared spectroscopy for the analysis of potatoes.

Potato (Solanum tuberosum L.) is one of the most important crops in the world being considered as a staple food in many developing countries. The potato industry like other vegetable and fruit industries is subject to the current demand of quality products. In order to meet this challenge, the food industry is relying on the adoption of nondestructive and environmentally friendly techniques to determine quality of products. Near-infrared spectroscopy (NIRS) is currently one of the most advanced nondestructive technologies regarding instrumentation and application, and it also complies with the environment requirements as it does not generate emissions or waste. This paper reviews research progress on the analysis of potatoes by NIRS both in terms of determination of constituents and classification according to the different constituents of the tubers. A brief description of the fundamentals of NIRS technology and its advantages over other quality assessment techniques is included. Finally, future prospects of the development of NIRS technology at the industrial level are explored.

Ability of NIRS technology to determine pesticides in liquid samples at maximum residue levels.

BACKGROUND: Pesticide residues remaining on food represent a potential risk to consumer's health. Determination of these pesticide residues involves tedious procedures of analysis with regard to time and laboratory work. Near-infrared spectroscopy (NIRS) is a possible alternative to these methods. The aim of this research was to evaluate the ability of NIRS to classify two pesticides used for controlling apple fruit pests according to their concentration. Different solutions were prepared, based on the dose recommended by the pesticide producers for apple pest treatments. Spectra were acquired on a spectrophotometer from liquid samples belonging to these solutions. RESULTS: Calibration models were developed from liquid samples, following the soft independent modelling of class analogy (SIMCA) analysis method. These models classified between 99 and 100% of the validation samples belonging to different pesticide concentration solutions even at the maximum residue limit level of these products in apple fruit. CONCLUSIONS: NIRS technology shows a high potential for identifying pesticides in liquid samples, according to their concentration, at the levels required by the legislation.

Evaluation of mechanical tomato harvesting using wireless sensors.

The harvesting of processing tomatoes is fully mechanised and it is well known that during harvest, fruits are subjected to mechanical stress causing physical injuries, including skin punctures, pulp and cell rupture. Some wireless sensors have been used for research during recent years with the main purpose of reducing the quality loss of tomato fruits by diminishing the number and intensity of impacts. In this study the IRD (impact recorder device) sensor was used to evaluate several tomato harvesters. The specific objectives were to evaluate the impacts during mechanical harvest using a wireless sensor, to determine the critical points at which damage occurs, and to assess the damage levels. Samples were taken to determine the influence of mechanical harvest on texture, or on other quality characteristics including percentage of damages. From the obtained data it has been possible to identify the critical points where the damages were produced for each one of the five harvester models examined. The highest risk of damage was in zone 1 of the combine--from the cutting system to the colour selector--because the impacts were of higher intensity and hit less absorbing surfaces than in zone 2--from colour selector to discharge. The shaker and exit from the shaker are two of the harvester elements that registered the highest intensity impacts. By adjusting, in a specific way each harvester model, using the results from this research, it has been possible to reduce the tomato damage percentage from 20 to 29% to less than 10%.