articles+ search results

hazel, corylus avellana, hazelnut, storage, aflatoxins, and Agriculture

In the Republic of Croatia, hazel (Corylus avellana L.) is the fruit species with the largest recorded increase in cultivation. Due to its high content of lipids and moisture (at the time of harvest) hazelnuts are susceptible to quality deterioration (rancidity development, mycotoxins contamination etc.) and therefore proper harvest and post-harvest handling is necessary to preserve their quality. Hazelnuts are most often collected from the ground by the appropriate mechanization. After harvesting, proper drying of is a crucial measure. Hazelnuts in the shell should be dried to about 7 - 10% moisture, and the kernel moisture content should be from about 4 - 6%. The maximum drying temperature should never exceed 50 °C. Regarding the storage conditions, the relative humidity is the most important factor and should never exceed 70%, while it is optimal to range from about 55 - 65%. Low temperatures (

machine learning, AUC, peach maturity prediction, artificial neural networks, fruit quality, non-destructive measurements, Chemical technology, and TP1-1185

To date, many machine learning models have been used for peach maturity prediction using non-destructive data, but no performance comparison of the models on these datasets has been conducted. In this study, eight machine learning models were trained on a dataset containing data from 180 ‘Suncrest’ peaches. Before the models were trained, the dataset was subjected to dimensionality reduction using the least absolute shrinkage and selection operator (LASSO) regularization, and 8 input variables (out of 29) were chosen. At the same time, a subgroup consisting of the peach ground color measurements was singled out by dividing the set of variables into three subgroups and by using group LASSO regularization. This type of variable subgroup selection provided valuable information on the contribution of specific groups of peach traits to the maturity prediction. The area under the receiver operating characteristic curve (AUC) values of the selected models were compared, and the artificial neural network (ANN) model achieved the best performance, with an average AUC of 0.782. The second-best machine learning model was linear discriminant analysis with an AUC of 0.766, followed by logistic regression, gradient boosting machine, random forest, support vector machines, a classification and regression trees model, and k-nearest neighbors. Although the primary parameter used to determine the performance of the model was AUC, accuracy, F1 score, and kappa served as control parameters and ultimately confirmed the obtained results. By outperforming other models, ANN proved to be the most accurate model for peach maturity prediction on the given dataset.

industrial IoT, Industry 4.0, prototyping, retrofitting solutions, embedded solutions, low-cost, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, and QD1-999

Industry 4.0 is fast becoming a mainstream goal, and many companies are lining up to join the Fourth Industrial Revolution. Small and medium-sized enterprises, especially in the manufacturing industry, are the most heavily challenged in adopting new technology. One of the reasons why these enterprises are lagging behind is the motivation of the key personnel, the decision-makers. The factories in question often do not have a pressing need for advancing to Industry 4.0 and are wary of the risk in doing so. The authors present a rapid, low-cost prototyping solution for the manufacturing companies with legacy machinery intending to adopt the Industry 4.0 paradigm with a low-risk initial step. The legacy machines are retrofitted through the Industrial Internet of Things, making these machines both connectable and capable of providing data, thus enabling process monitoring. The machine chosen as the digitization target was not connectable, and the retrofit was extensive. The choice was made to present the benefits of digitization to the stakeholders quickly and effectively. Indeed, the solution provides immediate results within manufacturing industrial settings, with the ultimate goal being the digital transformation of the entire factory. This work presents an implementation cycle for digitizing an industrial broaching machine, supported by state-of-the-art literature analysis. The methodology utilized in this work is based on the well-known DMAIC strategy customized for the specifics of this case study.

photoselective nets, light quality, light quantity, sustainability, sustainable food production, value-added, Environmental effects of industries and plants, TD194-195, Renewable energy sources, TJ807-830, Environmental sciences, and GE1-350

Net application in agriculture has a long history. Nets were usually used for the protection of plants against different hazards (hail, wind, birds, pests, excessive sun radiation) and, lately, from insects (nets with smaller mesh size). In recent years, photoselective netting technology has emerged, which adds desired plant responses caused by light quality changes to their basic protective properties. A combination of anti-insect and photoselective net technology (anti-insect photoselective nets) may present a notable contribution to the sustainable food production concept. Notable positive effects of this eco-friendly approach on agroecosystems are mainly achievable due to its non-pesticide pest protection of cultivated plants and, at the same time, promotion of special beneficial morphological and physiological plant responses. Although netting has been extensively studied over the last decade, there is a pronounced lack of publications and analyses that deal with their mode of action on fruit trees, which is especially true for new netting concepts. A better understanding of such mechanisms can lead to improved development and/or utilization of this technology and enhanced generation of value-added products. This review was based on a revision of the literature regarding netting in agriculture, with emphasis on fruit cultivation, and the following databases were used: Web of Science, ScienceDirect, Scopus, and Google Scholar. Although this study aims to comprehend a majority of fruit species, it narrows down to those usually net-protected and, hence, studied, such as apple, peach or nectarine, kiwifruit, blueberry, etc. Nets mainly differ in their mesh size and color, which are the parameters that mostly determine their capacity for light quantity and quality modification. Such light modifications, directly or indirectly (e.g., change in microclimate), initiate different fruit tree responses (in some cases, mechanisms) through which the final effect is realized on their vegetative and generative traits. For instance, some of them include a shade avoidance mechanism (initiated by changes in red to a far-red ratio, blue light levels, etc.), source–sink relationship, and carbohydrate availability (actualized by changes in photosynthesis efficiency, vegetative and generative growth, etc.), plant stress response (actualized by microclimate changes), etc. In most cases, these responses are interconnected, which contributes to the complexity of this topic and emphasizes the importance of a better understanding of it.

machine learning, imbalanced datasets, peach maturity, variable importance, interpretable machine learning, random forest, Electronics, and TK7800-8360

Peaches (Prunus persica (L.) Batsch) are a popular fruit in Europe and Croatia. Maturity at harvest has a crucial influence on peach fruit quality, storage life, and consequently consumer acceptance. The main goal of this study is to develop a machine learning model that will detect the most important features for predicting peach maturity by first training models and then using the importance ratings of these models to detect nonlinear (and linear) relationships. Thus, the most important peach features at a given stage of its ripening could be revealed. To date, this method has not been used for this purpose, and at the same time, it has the potential to be applied to other similar peach varieties. A total of 33 fruit features are measured on the harvested peaches, and three imbalanced datasets are created using firmness thresholds of 1.84, 3.57, and 4.59 kg·cm−2. These datasets are balanced using the SMOTE and ROSE techniques, and the Random Forest machine learning model is trained on them. Permutation Feature Importance (PFI), Variable Importance (VI), and LIME interpretability methods are used to detect variables that most influence predictions in the given machine learning models. PFI shows that the h° and a* ground color parameters, COL ground color index, SSC/TA, and TA inner quality parameters are among the top ten most contributing variables in all three models. Meanwhile, VI shows that this is the case for the a* ground color parameter, COL and CCL ground color indexes, and the SSC/TA inner quality parameter. The fruit flesh ratio is highly positioned (among the top three according to PFI) in two models, but it is not even among the top ten in the third.

apple, fruit quality, photo-selective nets, postharvest, superficial scald, and Agriculture

The present study was conducted with aim to test the effect of red photo-selective nets (Agritech S.r.l., Eboly, Italy) on 'Granny Smith' apple postharvest quality. The fruits have been harvested on optimal harvest date from orchard near city of Zadar where red photo-selective nets were used. Afterwards fruits were stored in regular air storage at 0°C for 4 months and then kept for 7 days at room temperature (shelf life). After harvest, cold storage and shelf life fruits grown under red net had significantly lower total soluble solid (SSC) content. After cold storage, superficial scald index and share of fruits with strong and very strong superficial scald severity were significantly higher in fruits grown under red net while for share of fruits with low superficial scald severity situation was opposite. After shelf life, fruits grown under red net had significantly higher titratable acidity (TA), but lower weight loss and SSC/TA ratio. It can be concluded that, due to greater susceptibility to superficial scald, prevention measures (optimal harvest time, 1-MCP and CA storage) should be applied when red photo-selective net is used on superficial scald-susceptible apple varieties.

fruit morphology, radicle emergence, seed germination, stratification, Sorbus domestica L., Forestry, and SD1-669.5

Background and Purpose: The current study aims to evaluate the effect of the fruit size of service tree (Sorbus domestica L.) on physio-morphological properties of seeds and the seed germination process. Materials and Methods: The fruit samples varying in size and divided on the basis of weight into small (5-10 g), medium (11-15 g) and large (16-20 g) were collected from the area of Vukomeričke gorice (45°34′45″N 16°00′11″E), Zagreb County, Croatia. Results: In all fruits, a significant, positive and very high correlation was found between the fruit length and width (r=0.92). There was a negative and significant correlation between the fruit weight and the fruit shape index (r=-0.47). The number of filled seeds in fruit was significantly higher in large fruits (2.62 seeds) than in medium and small fruits (1.81 and 1.46, respectively). Seeds from large fruits had significantly greater length of radicle (3.89 mm) than those from medium and small fruits (3.27 and 2.88, respectively) after 120 days of stratification at 3°C. The mean germination time of seeds for all fruits in total was 107 days. The seeds with the highest weight had significantly lower rate of moisture absorption. After stratification the seeds of large fruits had the highest germination percentage (83.7%). Conclusions: The findings obtained will likely impact the propagation of this plant species in the future, because the results of the study favour the usage of seeds obtained from large fruits since they showed highest germination rate.

ensemble techniques, data mining, classification and discrimination, linear regression, applied mathematics general, prediction theory, Mathematics, and QA1-939

The main motivation to conduct the study presented in this paper was the fact that due to the development of improved solutions for prediction risk of bleeding and thus a faster and more accurate diagnosis of complications in cirrhotic patients, mortality of cirrhosis patients caused by bleeding of varices fell at the turn in the 21th century. Due to this fact, an additional research in this field is needed. The objective of this paper is to develop one prediction model that determines most important factors for bleeding in liver cirrhosis, which is useful for diagnosis and future treatment of patients. To achieve this goal, authors proposed one ensemble data mining methodology, as the most modern in the field of prediction, for integrating on one new way the two most commonly used techniques in prediction, classification with precede attribute number reduction and multiple logistic regression for calibration. Method was evaluated in the study, which analyzed the occurrence of variceal bleeding for 96 patients from the Clinical Center of Nis, Serbia, using 29 data from clinical to the color Doppler. Obtained results showed that proposed method with such big number and different types of data demonstrates better characteristics than individual technique integrated into it.