Olive Fruit Varieties Research Articles

TinyML Olive Fruit Variety Classification by Means of Convolutional Neural Networks on IoT Edge Devices

Machine learning (ML) within the edge internet of things (IoT) is instrumental in making significant shifts in various industrial domains, including smart farming. To increase the efficiency of farming operations and ensure ML accessibility for both small and large-scale farming, the need for a low-cost ML-enabled framework is more pressing. In this paper, we present an end-to-end solution that utilizes tiny ML (TinyML) for the low-cost adoption of ML in classification tasks with a focus on the post-harvest process of olive fruits. We performed dataset collection to build a dataset that consists of several varieties of olive fruits, with the aim of automating the classification and sorting of these fruits. We employed simple image segmentation techniques by means of morphological segmentation to create a dataset that consists of more than 16,500 individually labeled fruits. Then, a convolutional neural network (CNN) was trained on this dataset to classify the quality and category of the fruits, thereby enhancing the efficiency of the olive post-harvesting process. The goal of this study is to show the feasibility of compressing ML models into low-cost edge devices with computationally constrained settings for tasks like olive fruit classification. The trained CNN was efficiently compressed to fit into a low-cost edge controller, maintaining a small model size suitable for edge computing. The performance of this CNN model on the edge device, focusing on metrics like inference time and memory requirements, demonstrated its feasibility with an accuracy of classification of more than 97.0% and minimal edge inference delays ranging from 6 to 55 inferences per second. In summary, the results of this study present a framework that is feasible and efficient for compressing CNN models on edge devices, which can be utilized and expanded in many agricultural applications and also show the practical insights for implementing the used CNN architectures into edge IoT devices and show the trade-offs for employing them using TinyML.

Classification of Algerian olive oils: Physicochemical properties, polyphenols and fatty acid composition combined with machine learning models

The regulation of olive cultivar and geographical origin is a requirement for the global extra virgin olive oil market, due to its significant impact on consumer choice. Our work involves obtaining a promising marker parameter for cultivar and geographical origin that can be used to verify declared labels. The effects of these factors on the physicochemical parameters and composition of monovarietal extra virgin olive oil (MEVOO) from Algeria were studied. Thirteen olive fruit varieties were analyzed using different physicochemical methods, including phenolic and fatty acid composition. Five classification techniques, random forests (RForest), gradient boosted trees (GBoost), Naïve Bayes (NBayes), logistic regression (LRegression) and decision tree (DTree), were applied and their results were compared. The best validation accuracy of 91.7 % was achieved with DT classification through a feature selection procedure using a genetic algorithm (GA). These results demonstrate the effective use of machine learning techniques to rapidly classify different Algerian varieties based on their compositional fingerprints.

Effect of Ripening on the Phenolic Composition and Mineral Content of Three Varieties of Olive Fruits.

The phenolic composition and mineral content of Cornezuelo, Cornicabra and Picual olive fruit varieties were investigated during olive ripening in two different harvesting seasons (2017/2018 and 2018/2019). Phytochemical profiles were evaluated by high-performance liquid chromatography (HPLC) with diode-array and mass spectrometry detection. Mineral contents were determined by inductively coupled plasma-mass spectrometry (ICP-MS). Twenty-five compounds were characterized and the main ones quantified. These compounds corresponded mostly to secoiridoids, the main ones being oleuropein, oleoside/secologanoside, oleoside-11-methylester, and oleuropein and comselogoside isomers. Total phenolic contents reached the highest values between December and January, coinciding with the usual harvesting date. This trend was observed in both harvesting seasons, although higher phenolic contents were recorded in season 2018/2019. This was due to the different weather conditions, which caused a lower olive production in season 2017/2018. No clear tendency was observed between mineral content and harvest time in any of the studied seasons. The highest concentration of total phenolics was obtained in Cornezuelo variety (840 mg/100 g) in January 2019 (season 2018/2019). Picual and Cornicabra varieties reached concentrations of 670 mg/100 g and 530 mg/100 g, respectively, also in the last harvesting dates of season 2018/2019.

Metabolome classification via GC/MS and UHPLC/MS of olive fruit varieties grown in Egypt reveal pickling process impact on their composition

The role of variety and effects of pickling on Egyptian olive fruit metabolome was determined using mass spectrometry-based metabolomics targeting nutrients and bioactive metabolities. The analyzed fresh olive fruit varieties included Manzanilo, Picual, Koroneiki, and Coratina, while the pickled samples included the Manzanilo and Picual varieties. Profiling of primary and secondary metabolites resulted in the detection of 201 metabolites. Variation between varieties was mostly observed among sugars, sugar alcohols, secoiridoids, and flavonoids. An abundance of carbohydrates and O-glycosides in Picual and Manzanilo versus enrichment of secoiridoids in Picual and Coratina olives viz. dehyro-oleuropein could account for the difference in palatability and health benefits among varieties. Herein, 13 new compounds are reported in the tested varieties, of which 10 appeared exclusively in pickled samples. Generally, pickled samples were characterized by the relative abundance of secoiridoids regarded as important markers for the pickling process. Metabolites profiling provided greater insight into the pickling process as a preservation method and accounted for the improved organoleptic characters in pickled fruits.

The effect of olive fruit maturation in Spanish style fermentation with a controlled temperature

The influence of maturation of different olive fruit varieties and the effect of these olives fermented at room temperature in a spontaneous fermentation were studied. Also, table olives from Carrasqueña variety harvested in two consecutive weeks in green stage of maturation, were fermented at different thermal temperature by heat transfer to the brine. Initially, an olive growth characterization was carried out. The largest variety was “Manzanilla Cacereña” and presented less texture and the lowest total phenolic and antioxidant activity. However, “Carrasqueña” variety, which had the highest firmness, showed a slower size. The color index of “Manzanilla Sevillana” was rather higher than the color index of the other varieties. After fermentation process, the highest color index and free acidity in “Manzanilla Sevillana” table olive could be caused by the highest temperature of the brine achieved. In general, the varieties studied had a good texture during fermentation. On the other hand, the effect of thermal applications in table olive color was higher when the olives were harvested later and by thermal application. Finally, the effect of thermal application depended on initial maturation stage achieving an increase of phenols with determined temperatures and conditions.

Parasitism of Psytallia concolor (Hymenoptera: Braconidae) on Bactrocera oleae (Diptera: Tephritidae) infesting different olive varieties

Psytallia concolor (Szepligeti) is a koinobiont endoparasitoid of many Tephritidae larvae, including Bactrocera oleae (Rossi), and has been used in Mediterranean areas for biological control of olive fruit fly by inundative release. The present study evaluates the influence of olive fruit variety (Amfissis, Arbequina, Branquita de Elvas, Carolea, Kalamon, Koroneiki, Leccino, Manzanilla, Mastoidis, Moroccan Picholine and Picholine) on P. concolor parasitism efficiency and performance in the field during two successive years. The results showed that the percentage of parasitism was significantly higher (>30%) in Mastoidis and Koroneiki (light-weight varieties 4.21 mg) as well as the length of the developed adult parasitoids (>3.5 cm) in Mastoidis and Manzanilla were significantly higher than these individuals developed from other varieties such as Koroneiki and Kalamon. Finally, the optimal host fruit for P. concolor development seems to be Mastoidis variety with great biological parameters and percentage of parasitism.

Blending Local olive oils with Arbequina or Picual oils produces high quality, distinctive EVOOs

Arbequina and Picual are the most common olive fruit varieties cultivated in Galicia (NW Spain). However, in recent years, the interest of oil producers in autochthonous Local olive fruits has increased substantially since its oil has differentiated and peculiar characteristics, especially with respect to the aromatic and phenolic composition. The blending of Local oil (in low percentages) with Arbequina or Picual oils is assessed in this study. Quality‐related indices, fatty acid composition, as well as minor compounds, such as volatiles and phenolics, were determined for both monovarietal and blending oils. Results obtained showed that the blending has the advantage of producing high quality virgin olive oil with predictable phenolic and aromatic profiles.Practical application: The development of high quality and distinctive extra virgin olive oils in NW Spain based on blends with a minor oil of differentiated and peculiar characteristics, especially with respect to the aromatic and phenolic composition, could produce highly marketable EVOO, with qualities that could be selected à la carte.Galician virgin olive oil producers want to promote the production and marketing of high quality extra virgin olive oils with peculiar sensory and health characteristics. To reach this goal, it is of great interest to recover old autochthonous Local olive varieties, which may bring added value to the most common Galician olive oils elaborated from Arbequina and Picual cultivars. Results obtained in this study showed that the previous knowledge of quality‐related indices, fatty acid composition, as well as minor composition, such as phenolic and volatile profiles of monovarietal EVOOs, could be a good strategy to produce high quality extra virgin olive oils à la carte.

Olive-Mill Wastewater Bacterial Communities Display a Cultivar Specific Profile

Culture-dependent and -independent approaches were employed to identify the bacterial community structure from olive-mill wastewater produced from three olive-fruit varieties. The 233 bacterial isolates recovered were phylogenetically related to 38 members of Firmicutes, Actinobacteria, α-Proteobacteria, β-Proteobacteria, γ-Proteobacteria, and Bacteroidetes. Employing a novel microarray-based approach (PhyloChip) a high bacterial diversity was revealed consisting of 18 different phyla with representatives from 99 different families. The bacterial diversity in olive-mill wastewater from the three olive tree varieties was dominated by α-, β-, γ-, δ-, ε-Proteobacteria, Firmicutes, Bacteroidetes, Chloroflexi, Cyanobacteria, and Actinobacteria. This in-depth analysis of the indigenous microbiota indicated a cultivar-specific bacterial profile. Interestingly, the common bacterial taxa present in all three varieties examined were restricted indicating that the bacterial communities present in the olive-mill wastewater are greatly influenced by the olive-fruit variety.

MODIFICATION AND EVALUATION OF HAND-HELD HARVESTERS FOR OLIVE FRUITS.

The main objective of this study is to modify the real effectiveness of two imported hand-held harvester types namely; olive lancer with a vertical straight rotor head and olive comb harvester with a fruit collecting bag to increase the harvesting productivity and efficiency with high quality olive fruits; in addition to reduce the high cost and risks of manual harvesting method. Both harvester types were evaluated before and after modification compared with manual harvesting method of olive fruits in terms of labor productivity, harvesting efficiency, harvested fruit quality, energy requirements and harvesting cost. The obtained results may be summarized as follows: Modification and use of the olive lancer type harvester for harvesting Shimlaly and Tofahy olive fruit varieties gave a remarkable increment percentage in labor productivity by about 5-7 times higher with respect to manual harvesting method. Also, it can be save the harvesting manpower requirements by about 90-130% and reduce the total harvesting cost by about 185-245% comparing with manual harvesting cost. The use of hand-held modified olive comb harvester increased the labor productivity by about 1-2.5 times, saved the harvesting manpower requirements by about 190-260% and saved the harvesting cost by about 135-195%, for harvesting Shimlaly and Tofahy olive varieties, respectively comparing with manual harvesting method. These results means that the use of hand-held olive harvesters could be reduced the amount of labors or time needed to carry out the olive harvesting operation in the best period and obtain the best harvested fruits quality. In addition to make the introduction of hand-held olive harvesters easier, feasible and more economical especially when used for other purposes to run devices such as scissors and saws to mechanize tree pruning.

Multivariate analysis of HT/GC-(IT)MS chromatographic profiles of triacylglycerol for classification of olive oil varieties

The ability of multivariate analysis methods such as hierarchical cluster analysis, principal component analysis and partial least squares-discriminant analysis (PLS-DA) to achieve olive oil classification based on the olive fruit varieties from their triacylglycerols profile, have been investigated. The variations in the raw chromatographic data sets of 56 olive oil samples were studied by high-temperature gas chromatography with (ion trap) mass spectrometry detection. The olive oil samples were of four different categories ("extra-virgin olive oil", "virgin olive oil", "olive oil" and "olive-pomace" oil), and for the "extra-virgin" category, six different well-identified olive oil varieties ("hojiblanca", "manzanilla", "picual", "cornicabra", "arbequina" and "frantoio") and some blends of unidentified varieties. Moreover, by pre-processing methods of chemometric (to linearise the response of the variables) such as peak-shifting, baseline (weighted least squares) and mean centering, it was possible to improve the model and grouping between different varieties of olive oils. By using the first three principal components, it was possible to account for 79.50% of the information on the original data. The fitted PLS-DA model succeeded in classifying the samples. Correct classification rates were assessed by cross-validation.

Sterol and alcohol components of seed, pulp and whole olive fruit oils. Their use to characterise olive fruit variety by multivariates

AbstractSterols, triterpene dialcohols, long‐chain aliphatic alcohols and higher triterpene alcohols were determined in three fruit oil kinds (seed, pulp and whole fruit oils). Seven major Italian olive fruit varieties from the same environment were considered. Results of this research suggested that the compositional data concerning the above analytical fractions were effective in discriminating between seed and pulp oils. The seed oil fraction did not substantially modify the sterol and alcohol composition of the whole fruit oil (mixture of seed and pulp oils), the percentage weight of the seed (∼2%) being far lower than that of the pulp (∼85%) (whole fruit weight basis). Based on the concentrations of the above components and using appropriate statistical parametric or non‐parametric multivariate techniques, the genetic origin (olive variety) of the three fruit oil kinds was characterised.© 2002 Society of Chemical Industry

Chemical authentication of extra virgin olive oil varieties by supervised chemometric procedures.

This work has focused on discriminating extra virgin olive oils from Sabina (Lazio, Italy) by olive fruit variety (cultivar). A set of oils from five of the most widespread cultivars (Carboncella, Frantoio, Leccino, Moraiolo, and Pendolino) in this geographical area was analyzed for chemical composition using only the Official Analytical Methods, recognized for the quality control and commercial classification of this product. The obtained data set was converted into a computer-compatible format, and principal component analysis (PCA) and a method based on the Fisher F ratio were used to reduce the number of variables without a significant loss of chemical information. Then, to differentiate these samples, two supervised chemometric procedures were applied to process the experimental data: linear discriminant analysis (LDA) and artificial neural network (ANN) using the back-propagation algorithm. It was found that both of these techniques were able to generalize and correctly predict all of the samples in the test set. However, these results were obtained using 10 variables for LDA and 6 (the major fatty acid percentages, determined by a single gas chromatogram) for ANN, which, in this case, appears to provide a better prediction ability and a simpler chemical analysis. Finally, it is pointed out that, to achieve the correct authentication of all samples, the selected training set must be representative of the whole data set.

Sugar and polyol compositions of some European olive fruit varieties (Olea europaea L.) suitable for table olive purposes

An experimental investigation was carried out on olive fruits of Douro, Hojiblanca, Cassanese, Taggiasca and Thasos cultivars, to assess free sugar and polyol compositions and their changes during ripening and processing. TMS ethers of sugars from olive pulp were analysed by GC and GC‐MS and identification of each sugar component was obtained by comparison of retention times and mass spectra with those of authentic compounds. Quantitation of sugars was performed on mixture whose tautomeric equilibria were stable. Glucose, fructose and galactose were the main sugars found in olive pulp. Appreciable quantities of mannitol were also present. Sucrose and inositol were present in very low concentrations. A significant correlation (r=0.941) between mannitol and oil contents was found. Sugar content decreased from green to cherry and black colour, according to the stage of ripeness of fruits. In processed olive-fruits, sugar contents varied among olive cultivars according to processing conditions. # 2001 Elsevier Science Ltd. All rights reserved.

Characterization of Olive Ripeness by Green Aroma Compounds of Virgin Olive Oil

The evolution of the volatile compounds responsible for virgin olive oil green aroma has been studied in samples obtained from four olive fruit varieties (Arbequina and Picual, Spain; Koroneiki, Greece; and Coratina, Italy), picked at three different stages of ripeness during two consecutive crops. The volatile compounds hexanal, (E)-3-hexenal, (Z)-3-hexenal, (E)-2-hexenal, hexyl acetate, (Z)-3-hexenyl acetate, hexan-1-ol, (E)-3-hexen-1-ol, (Z)-3-hexen-1-ol, and (E)-2-hexen-1-ol were considered in this study. The sensory significance of these volatile compounds has been stated by their odor activity value (OAV), while their synergic relationships with green sensory attributes have been analyzed by principal component analysis. The stages of ripeness of each variety, with the whole set of volatile compounds, were characterized by cluster analysis. Detailed information corresponding to each volatile compound for each stage of ripeness, after fuzzy filtering of the quantitative data, has also been established. Alcohols produced from linolenic acid (E)-3-hexen-1-ol, (Z)-3-hexen-1-ol, and (E)-2-hexen-1-ol, and hexanal and hexyl acetateboth produced from linoleic acidare major contributors to the ripeness characterization. The results were verified by applying multiple regression to the quantitative values of volatile compounds of a test set of eight Arbequina samples picked each fortnight from unripened to over-ripened olives. From the results of this study it can be concluded that the unripe stage is the best characterized, although the result in prediction for three stages of ripeness was an adjusted R2 value of 0.98. Keywords: Olea europea L.; virgin olive oil; volatiles; green sensory note; ripeness; statistics; fuzzy logic

Flavonoids in three olive (Olea europaea) fruit varieties during maturation

AbstractThe objective of the present paper was the characterisation of olive fruit varieties through the formation and variation during maturation of their flavonols, flavones and anthocyanins. An olive variety with a constant cyanidin‐3‐rutinoside:cyanidin‐3‐glucoside ratio of 1 exhibited lower contents of luteolin‐7‐glucoside and quercetin‐3‐rutinoside than varieties in which the only anthocyanin detected was cyanidin‐3‐rutinoside.