Search

Sour rot (SR) is one of the major diseases affecting grapevine berries, causing severe yield losses and deterioration of wine quality. SR is caused by an etiologic complex of microorganisms, including yeasts, bacteria, and filamentous fungi. This systematic review focuses on the etiology, epidemiology, and control of SR. A total of 74 papers published between 1986 and 2023 were assessed in this review. Description of disease symptoms was quite consistent across the papers, including oxidation of the grape skin, disaggregation of the internal tissues, and detachment of the rotten berries from the pedicel. The affected bunches are characterized by the smell of acetic acid and ethyl acetate that attracts fruit flies (Drosophila spp.). However, several knowledge gaps and/or inconsistencies were identified with respect to SR etiology, epidemiology, and control. Overall, 146 microorganisms were isolated from the affected berries (44.5% yeasts, 34.3% bacteria, and 21.2% filamentous fungi); however, the selected papers could not definitively clarify which species are primarily involved in the etiology of the disease. A general inconsistency was also observed in the methods used to assess the incidence and severity of SR in vineyards, making inter-study comparisons extremely challenging. Inconsistencies were also found in the methods used for pathogenicity assessment in artificial inoculation studies. Furthermore, gaps were detected in terms of SR epidemiology, with a focus on environmental conditions affecting the disease development. The SR management options are limited, and efficacy trials often result in poor, variable, and inconsistent levels of control, which might be attributed to the lack of knowledge on disease epidemiology. These knowledge gaps and inconsistencies were analyzed in this review to inform future research activities. [ABSTRACT FROM AUTHOR]

Introduction: Grapes are prone to various diseases throughout their growth cycle, and the failure to promptly control these diseases can result in reduced production and even complete crop failure. Therefore, effective disease control is essential for maximizing grape yield. Accurate disease identification plays a crucial role in this process. In this paper, we proposed a real-time and lightweight detection model called Fusion Transformer YOLO for 4 grape diseases detection. The primary source of the dataset comprises RGB images acquired from plantations situated in North China. Methods: Firstly, we introduce a lightweight high-performance VoVNet, which utilizes ghost convolutions and learnable downsampling layer. This backbone is further improved by integrating effective squeeze and excitation blocks and residual connections to the OSA module. These enhancements contribute to improved detection accuracy while maintaining a lightweight network. Secondly, an improved dual-flow PAN+FPN structure with Real-time Transformer is adopted in the neck component, by incorporating 2D position embedding and a single-scale Transformer Encoder into the last feature map. This modification enables real-time performance and improved accuracy in detecting small targets. Finally, we adopt the Decoupled Head based on the improved Task Aligned Predictor in the head component, which balances accuracy and speed. Results: Experimental results demonstrate that FTR-YOLO achieves the high performance across various evaluation metrics, with a mean Average Precision (mAP) of 90.67%, a Frames Per Second (FPS) of 44, and a parameter size of 24.5M. Conclusion: The FTR-YOLO presented in this paper provides a real-time and lightweight solution for the detection of grape diseases. This model effectively assists farmers in detecting grape diseases. [ABSTRACT FROM AUTHOR]

Copyright of Matica Srpska Journal for Natural Sciences is the property of Matica Srpska, Department of Natural Studies and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Storage & Process is the property of Tianjin Academy of Agricultural Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Edible coatings and active packaging have become more prevalent in response to changing consumption patterns and market trends to enhance the quality and safety of fresh products. In this work, we investigated the effect of aloe vera gel (AVG) coating and paraffin wax-coated paperboard (PWB) packaging on the postharvest quality attributes of both grapes and apples during storage. The fruits were coated with 50% AVG concentrations, and the inner wall of the corrugated paperboard was coated with paraffin wax emulsion. The grapes and apples were stored for 12 and 35 days, respectively, at ambient conditions (25 ± 3°C and 80–85% relative humidity). The physicochemical properties, microbiological attributes, and decay incidence of the fruits were analyzed at intervals during storage. Both fruits treated with AVG and PWB packaging retained better qualities than the control at the final day of the storage period. Particularly, PWB packaging provided considerably superior quality from the control sample in terms of weight loss (≈54% and 32%), firmness (≈48% and 68%), and color difference (≈30% and 28%) for both grapes and apples. These findings would introduce a novel approach for preserving the quality attributes of both climacteric and nonclimacteric fruits for a prolonged storage period at ambient temperature by PWB packaging and AVG coating. [ABSTRACT FROM AUTHOR]

Copyright of Matica Srpska Journal for Natural Sciences is the property of Matica Srpska, Department of Natural Studies and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Morphological operations, one of the techniques for processing the shapes of objects within images, are primarily categorized into erosion and dilation operations. Erosion operation entails shaving off the periphery of objects, thereby eliminating noise-like artifacts within the image and potentially enhancing object boundaries or separating touching objects. Conversely, dilation operation involves expanding the periphery of objects, enabling the filling of small internal void spaces. When morphological operations are implemented in hardware, their execution time is significantly reduced compared to software implementations. This paper proposes a circuit design aimed at implementing morphological operations for binary images using FPGA. The proposed circuit architecture is designed to minimize the relatively expensive RAM resources, while maximizing computational efficiency. The performance of the proposed circuitry is evaluated by assuming implementation on AMD's FPGA platform and is compared against the results obtained from morphological operation circuits implemented using the AMD's Vitis vision library, confirming its effectiveness. [ABSTRACT FROM AUTHOR]

Copyright of Glasnik Zastite Bilja is the property of Zadruzna Stampa D.D. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The wide ampelographic treasure of Italian wine grape varieties is driving research towards suitable approaches for the varietal authenticity control of wine. In this paper, Aglianico, Negroamaro, Primitivo and Uva di Troia red wines, which were produced experimentally by single-grape winemaking from non-aromatic grapes native to southern Italy, were analyzed with respect to berry markers, namely anthocyanins, hydroxycinnamic acids (HPLC-DAD), shikimic acid (HPLC-UV) and glycosidic aroma precursors (GC-MS). The study confirms that, just as for the berries, useful varietal authenticity markers for red wine, even after aging, turn out to be hydroxycinnamic acids, relative amounts of acylated forms of anthocyanins, and shikimic acid, together with some grape glycosidic precursors from terpenes and C13− norisoprenoids. Principal Component Analysis was used as a valuable tool to highlight the results. [ABSTRACT FROM AUTHOR]

Resveratrol (RSV), a naturally occurring phytoalexin, is the most important stilbenoid synthesized by plants as a defense mechanism in response to microbial aggression, toxins, or ultraviolet radiation. RSV came to the attention of researchers both as a potential chemopreventive agent and a possible explanation for the low incidence of cardiovascular disease (CVD) in French people with a high-fat diet. RSV is mainly administered as a food supplement, and its properties are evaluated in vitro or in vivo on various experimental models. RSV modulates signaling pathways that limit the spread of tumor cells, protects nerve cells from damage, is useful in the prevention of diabetes, and generally acts as an anti-aging natural compound. It was highlighted that RSV could ameliorate the consequences of an unhealthy lifestyle caused by an exaggerated caloric intake. This paper reviews the evidence supporting the beneficial effect of RSV for various pathological conditions, e.g., neoplastic diseases, neurodegeneration, metabolic syndrome, diabetes, obesity, CVDs, immune diseases, bacterial, viral, and fungal infections. The study also focused on the chromatographic analysis of trans-RSV (tRSV) in Romanian wine samples, providing a comprehensive overview of tRSV content across different types of wine. [ABSTRACT FROM AUTHOR]

The pH and firmness index (FI) of red globe grapes determine the taste and post-harvest quality of the fruit. In this paper, a method for the detection of pH and firmness of red globe grapes based on transmission spectroscopy technology was proposed. Spectral datas were first collected from 360 full-growth-cycle red globe grape samples, which were pre-processed and modeled by different spectral pre-processing methods as a way to determine the best spectral pre-processing method. Then competitive adaptive reweighted sampling (CARS), successive projection algorithm (SPA), uniformative variable elimination (UVE) and CARS-SPA, UVE-SPA composite data dimensionality reduction methods were used respectively for extracting feature variables from spectra. Finally, partial least squares regression (PLSR) detection models for pH and firmness of red globe grapes were established, respectively. The optimal prediction models for pH and firmness of red globe grape samples were moving-average method (MA)-CARS-SPA-PLSR and MA-UVE-SPA- PLSR. The correlation coefficient of prediction (RP) of the prediction sets of the two models were 0.9882 and 0.9588, and the residual predictive deviation (RPD) were 6.5857 and 3.5167, respectively. The results showed that transmission spectroscopy could be applied to the detection of pH and firmness of red globe grapes, which provided a new idea and a new method for the detection of pH and firmness of red globe grapes in the whole growth cycle. [ABSTRACT FROM AUTHOR]

Mechanized harvesting is the key technology to solving the high cost and low efficiency of manual harvesting, and the key to realizing mechanized harvesting lies in the accurate and fast identification and localization of targets. In this paper, a lightweight YOLOv5s model is improved for efficiently identifying grape fruits and stems. On the one hand, it improves the CSP module in YOLOv5s using the Ghost module, reducing model parameters through ghost feature maps and cost-effective linear operations. On the other hand, it replaces traditional convolutions with deep convolutions to further reduce the model's computational load. The model is trained on datasets under different environments (normal light, low light, strong light, noise) to enhance the model's generalization and robustness. The model is applied to the recognition of grape fruits and stems, and the experimental results show that the overall accuracy, recall rate, mAP, and F1 score of the model are 96.8%, 97.7%, 98.6%, and 97.2% respectively. The average detection time on a GPU is 4.5 ms, with a frame rate of 221 FPS, and the weight size generated during training is 5.8 MB. Compared to the original YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x models under the specific orchard environment of a grape greenhouse, the proposed model improves accuracy by 1%, decreases the recall rate by 0.2%, increases the F1 score by 0.4%, and maintains the same mAP. In terms of weight size, it is reduced by 61.1% compared to the original model, and is only 1.8% and 5.5% of the Faster-RCNN and SSD models, respectively. The FPS is increased by 43.5% compared to the original model, and is 11.05 times and 8.84 times that of the Faster-RCNN and SSD models, respectively. On a CPU, the average detection time is 23.9 ms, with a frame rate of 41.9 FPS, representing a 31% improvement over the original model. The test results demonstrate that the lightweight-improved YOLOv5s model proposed in the study, while maintaining accuracy, significantly reduces the model size, enhances recognition speed, and can provide fast and accurate identification and localization for robotic harvesting. [ABSTRACT FROM AUTHOR]

This paper focuses on the creation of an in vitro collection of grapevine hybrids from the breeding program of the Kazakh Scientific Research Institute of Fruit Growing and Viticulture and investigates the presence of Plasmopara viticola resistance mediated by Rpv3 and Rpv12 loci. We looked at the optimization of in vitro establishment using either shoots taken directly from field-grown plants or from budwood cuttings forced indoors. We further screened for the presence of endophyte contamination in the initiated explants and optimized the multiplication stage. Finally, the presence of the resistance loci against P. viticola was studied. The shoots initiated from the field-sourced explants were the more effective method of providing plant sources for in vitro initiation once all plant accessions met the goal of in vitro establishment. The concentration of phytohormones and the acidity of the culture medium have a great effect on the multiplication rate and the quality of in vitro stock cultures. Out of 17 grapevine accessions, 16 showed the presence of single or combined resistance loci against P. viticola. The grapevine accessions identified as carrying Rpv3 and Rpv12 alleles represent important genetic resources for disease resistance breeding programs. These accessions may further contribute to the creation of new elite cultivars of economic interest. [ABSTRACT FROM AUTHOR]

This paper reports a study aimed at determining the biochemical quality indicators of grapes during long-term storage. The object of research was nine table varieties of ripened grapes. These include white varieties – Tabrizi, Karaburnu, White Shasla, Agadai; pink varieties – Nimrang, Marandi Shamakhi, Taifi pink; red varieties – Kyzyl raisins and Hamburg Muscat. The grapes were stored in refrigerators for 5–6 months, at a temperature of 0–1 °C and air humidity of 87–95 %. The grapes were studied before planting and 30–40 days before the end of storage. Long-term refrigerated storage of grapes using weekly fumigation with sulfur dioxide is accompanied by a decrease in the activity of oxyreductases and a gradual increase in the activity of pectinesterase. This causes changes in the quantity and proportions of nutrients and other chemical components that determine the nutritional and biological value of the final product. It was revealed that during the sale of ripened grapes stored using weekly fumigation with sulfur dioxide, the activity of the studied oxyreductases is slightly restored in pink varieties – Nimrang, Taifi pink, and in white varieties – in Karaburnu and Tabrizi. In the Marandi Shamakhi variety, the activity of enzymes does not change, therefore, for a long time in these grape varieties, especially in the Marandi Shamakhi variety, darkening and softening of the berries are not observed during their sale. Among the studied table grape varieties, Tabrizi, Karaburnu, Nimrang, and Marandi Shamakhi, with long-term refrigerated storage using weekly fumigation with sulfur dioxide, have the longest shelf life; under a controlled gas environment, the results reported here could prove useful in practice. [ABSTRACT FROM AUTHOR]

In viticulture, downy mildew is one of the most common diseases that, if not adequately treated, can diminish production yield. However, the uncontrolled use of pesticides to alleviate its occurrence can pose significant risks for farmers, consumers, and the environment. This paper presents a new framework for the early detection and estimation of the mildew's appearance in viticulture fields. The framework utilizes a protocol for the real-time acquisition of drones' high-resolution RGB images and a cloud-docker-based video or image inference process using object detection CNN models. The authors implemented their framework proposition using open-source tools and experimented with their proposed implementation on the debina grape variety in Zitsa, Greece, during downy mildew outbursts. The authors present evaluation results of deep learning Faster R-CNN object detection models trained on their downy mildew annotated dataset, using the different object classifiers of VGG16, ViTDet, MobileNetV3, EfficientNet, SqueezeNet, and ResNet. The authors compare Faster R-CNN and YOLO object detectors in terms of accuracy and speed. From their experimentation, the embedded device model ViTDet showed the worst accuracy results compared to the fast inferences of YOLOv8, while MobileNetV3 significantly outperformed YOLOv8 in terms of both accuracy and speed. Regarding cloud inferences, large ResNet models performed well in terms of accuracy, while YOLOv5 faster inferences presented significant object classification losses. [ABSTRACT FROM AUTHOR]

The proliferation of classification-capable artificial intelligence (AI) across a wide range of domains (e.g., agriculture, construction, etc.) has been allowed to optimize and complement several tasks, typically operationalized by humans. The computational training that allows providing such support is frequently hindered by various challenges related to datasets, including the scarcity of examples and imbalanced class distributions, which have detrimental effects on the production of accurate models. For a proper approach to these challenges, strategies smarter than the traditional brute force-based K-fold cross-validation or the naivety of hold-out are required, with the following main goals in mind: (1) carrying out one-shot, close-to-optimal data arrangements, accelerating conventional training optimization; and (2) aiming at maximizing the capacity of inference models to its fullest extent while relieving computational burden. To that end, in this paper, two image-based feature-aware dataset splitting approaches are proposed, hypothesizing a contribution towards attaining classification models that are closer to their full inference potential. Both rely on strategic image harvesting: while one of them hinges on weighted random selection out of a feature-based clusters set, the other involves a balanced picking process from a sorted list that stores data features' distances to the centroid of a whole feature space. Comparative tests on datasets related to grapevine leaves phenotyping and bridge defects showcase promising results, highlighting a viable alternative to K-fold cross-validation and hold-out methods. [ABSTRACT FROM AUTHOR]

Copyright of Matica Srpska Journal for Natural Sciences is the property of Matica Srpska, Department of Natural Studies and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The present research is focused on the link between entrepreneurship and rural economic growth in the direction and intensity of the net influence of farmers' entrepreneurial activities on rural economic development in Romania. This research delves into land use for grape production, a key element in Romania's wine processing industry. It examines the dynamics between consumption, production, and import in the wine market, noting in particular the increase in imports after Romania accedes to the European Union. In addition, it considers the impact of viticulture on land use amid food competition concerns. The study aims to elucidate the relationships between wine production, import, and consumption and assesses the capacity of domestic production to meet consumption demands. Using regression analysis of data on wine consumption, production, and import, the research uncovers significant findings. It reveals that a one-unit increase in wine consumption correlates with a 0.13-unit increase in both wine production and imports. This study contributes to a deeper understanding of the interaction between wine consumption, production, and import, helping predictive modeling and identifying sustainable entrepreneurial paths in the grape processing sector in Romania, given the considerable wine production potential. [ABSTRACT FROM AUTHOR]

The determination of grape quality parameters is intricately linked to the mineral composition of the fruit; this relationship is increasingly affected by the impacts of climate change. The conventional chemical methodologies employed for the mineral quantification of grape tissues are expensive and impracticable for widespread commercial applications. This paper utilized Laser-Induced Breakdown Spectroscopy (LIBS) to analyze the mineral constituents within the skin, pulp, and seeds of two distinct Vitis vinifera cultivars: a white cultivar (Loureiro) and a red cultivar (Vinhão). The primary objective was to discriminate the potential variations in the calcium (Ca), magnesium (Mg), and nitrogen (N) concentrations and water content among different grape tissues, explaining their consequential impact on the metabolic constitution of the grapes and, by extension, their influence on various quality parameters. Additionally, the study compared the mineral contents of the white and red grape cultivars across three distinct time points post veraison. Significant differences (p < 0.05) were observed between the Loureiro and Vinhão cultivars in Ca concentrations across all the dates and tissues and for Mg in the skin and pulp, N in the pulp and seeds, and water content in the skin and pulp. In the Vinhão cultivar, Ca differences were found in the pulp across the dates, N in the seeds, and water content in the skin, pulp, and seeds. Comparing the cultivars within tissues, Ca exhibited differences in the pulp, Mg in the skin and pulp, N in the pulp and seeds, and water content in the skin, pulp, and seeds. These findings provide insights into the relationship between the grape mineral and water content, climatic factors, and viticulture practices within a changing climate. [ABSTRACT FROM AUTHOR]

Reconfigurable devices such as field-programmable gate arrays (FPGAs) offer flexible solutions to workload acceleration with high energy efficiency. Despite such a potential advantage, they often reveal hard to program by application programmers. High-level synthesis languages have been developed to provide higher-level abstractions, allowing the developers to define the FPGA behavior using an imperative programming approach based on C/C++ languages. However, such approaches still leave the developer with the responsibility to harness the low-level optimizations required to develop efficient FPGA programs. Along this line, this paper introduces FSPX, a framework helping programmers to develop FPGA-accelerated data stream processing (DSP) applications. The approach provides a high-level Python API to develop the data-flow graph of operators, which is automatically translated into an efficient Vitis source code targeting Xilinx devices. The execution of the bitstreams implementing two benchmark applications showcases the efficiency of using FPGAs for DSP workloads. In general, FSPX provides, with a reasonable time-to-solution, higher performance compared with state-of-the-art DSP frameworks. [ABSTRACT FROM AUTHOR]

Grape pomace is the most important residual after wine making, and it is considered to be a very abundant source for the extraction of a wide range of polyphenols. These polyphenols exhibit a variety of bioactivities, such as antioxidant, anti-inflammatory, and anti-cancer. They are also beneficial in alleviating metabolic syndrome and regulating intestinal flora, etc. These health effects are most likely contributed by polyphenol metabolite, which are formed by the grape pomace phenolics after a complex metabolic process in vivo. Therefore, understanding the phenolic composition of grape pomace and its metabolism is the basis for an in-depth study of the biological activity of grape pomace polyphenols. In this paper, we first summarize the composition of phenolics in grape pomace, then review the recent studies on the metabolism of grape pomace phenolics, including changes in phenolics in the gastrointestinal tract, their pharmacokinetics in the systemic circulation, the tissue distribution of phenolic metabolites, and the beneficial effects of metabolites on intestinal health, and finally summarize the effects of human health status and dietary fiber on the metabolism of grape polyphenols. It is expected to provide help for the in-depth research on the metabolism and biological activity of grape pomace polyphenol extracts, and to provide theoretical support for the development and utilization of grape pomace. [ABSTRACT FROM AUTHOR]

This paper illustrates the non-target impact of imidacloprid (IM) residues on the grape global metabolome and biomarker identification with high-resolution mass spectrometry. IM was applied at the recommended dose (SD), and ten times SD (10 RD). The global metabolome analysis revealed that 21 metabolites were up- and down-regulated with IM SD treatment. In 10 RD, 9 metabolites were upregulated, and 28 were downregulated. Pathway enrichment analysis revealed the primary and secondary pathway disruption in grapes. Berry quality was affected with decrease in flavonoids by 32.97% in 10 RD; phenols were reduced by 53.93 in SD, 50.8% in 10 RD. The non-target and target study revealed the degradation of IM in grapes to desnitro-IM and IM-urea which were identified as a potential biomarker for IM residues in grapes, which would benefit the authentication of organic product. Overall, imidacloprid showed a significant impact on the grape metabolome and quality. [ABSTRACT FROM AUTHOR]

A farm management information system (MIS) entails record keeping based on a database management system, typically using a client-server architecture, i.e., an information system, IS, coupled with a variety of tools/methods/models for the support of operational management. The current review adopts a multivocal approach to consider academic and commercial developments in MISs for orchard management, based primarily on the refereed literature but extending to grey literature and interviews of Australian mango orchard managers. Drivers for orchard MIS development include increasing the orchard size and management complexity, including regulatory requirements around labour, chemical spray use and fertilisation. The enablers include improvements in within-orchard communications, distributed (web) delivery systems using desktop and mobile devices, and sensor systems and predictive models, e.g., for pest management. Most orchard MIS-related publications target the commodities of apple, grape, mango and olive in the context of management of plant health (pest and disease), plant development, irrigation and labour management. Harvest forecast and MIS modules are only now beginning to emerge, in contrast to a long history of use in grain production. The commercial systems trend towards an incorporation of financial information, an integration of data from multiple sources and a provision of dashboards that are tailored to the user. Requirements for industry adoption of a MIS are discussed in terms of technical and design features, with a focus on usability and scalability. [ABSTRACT FROM AUTHOR]

In today's food industry, fortifying food products with several nutrients is a priority, and animal nutrition represents a key strategy for achieving this goal. Nevertheless, the scarcity and high costs of conventional feedstuffs lead to investigation of industrial by-products as alternative solutions in livestock nutrition. White grape pomace, a byproduct of the winery industry, is well-known for its rich resveratrol content. Nevertheless, in addition to this, it can present significant quantities of other nutrients and antioxidant compounds, which exert beneficial effects when incorporated into ruminants' nutrition. Our study revealed a remarkable concentration of the white grape pomace nutrients, with important minerals, particularly manganese (106.35 mg/kg). The fatty acids profile showed a high composition of polyunsaturated fatty acids (65.05 g/100 g FAME), with a great amount of omega 3 fatty acids (62.66 g/100 g FAME). Concerning the antioxidant compounds, white grape pomace exhibited a concentration of 12.49 mg/g GAE for total polyphenols and 3.27 mg/kg for total flavonoids. Also, our study highlighted its high antioxidant potential, especially assessed through the DPPH radical scavenging assay (74.26 mM eq. Trolox), ABTS radical scavenging assay (75.07 mM eq. Trolox), and total antioxidant capacity (286.26 mM eq. ascorbic acid). [ABSTRACT FROM AUTHOR]

Fungal pathogens Plasmopara viticola (Berk. & M.A. Curtis) Berl. & De Toni (downy mildew) and Erysiphe necator Schwein. (powdery mildew) represent the biggest threats for grape growers worldwide. Under suitable conditions, these pathogens can spread very quickly through vineyards and cause significant damage. The most ecological way to reduce the possibility of infection in vineyards is growing interspecific genotypes which are able to suppress these pathogens and stop the spread of infection. With this in mind, 9 international and 11 Czech grapevine genotypes were analysed in order to genotype the resistance loci present in them. As a tool a set of SSR markers linked to known loci of resistance to downy and powdery mildew was used. Namely, presence of four loci responsible for resistance to Plasmopara viticola (Rpv3, Rpv4, Rpv7, and Rpv10) and two for Erysiphe necator (Ren3 and Ren9) were analysed with respective SSR markers. By this way the degree of resistance gene pyramiding was newly assessed in all analysed cultivars and their perspectives in grapevine breeding are discussed. [ABSTRACT FROM AUTHOR]

As a type of representative bunch-type fruit, the collision-free and undamaged harvesting of grapes is of great significance. To obtain accurate 3D spatial semantic information, this paper proposes a method for multi-feature enhanced semantic segmentation model based on Mask R-CNN and PointResNet(improved PointNet++). Firstly, a depth camera is used to obtain RGBD images. The RGB images are then inputted into the Mask-RCNN network for fast detection of grape bunches. The color and depth information are fused and transformed into point cloud data, followed by the estimation of normal vectors. Finally, the nine-dimensional point cloud, which include spatial location, color information, and surface structure information, are inputted into the PointResNet network to achieve semantic segmentation of grape bunches, peduncles, and leaves. This process obtains the extraction of spatial semantic information from the surrounding area of the bunches. The experimental results show that by incorporating normal vector and color features, the overall accuracy of point cloud segmentation increases to 96.5%, with a mean accuracy of 90.3%. This represents a significant improvement of 7.9% and 16.6% compared to using only positional features. The results demonstrate that the model method presented in this paper can effectively provide precise 3D semantic information to the robot while ensuring both speed and accuracy. This lays the groundwork for subsequent collision-free and undamaged picking. • 2D detection locates grape bunches, extracting regions of interest. • 3D point cloud segmentation identifies grape parts—bunches, peduncles, leaves. • Improved point cloud segmentation network adapts to grape scenes. • Enhanced features for better accuracy. • Experiments show superior recognition using 3D point clouds. [ABSTRACT FROM AUTHOR]

The Normalized Difference Vegetation Index (NDVI) is a valuable indicator of plant vigor that is frequently used in agronomic practices to make timely and targeted decisions with the aim of increasing the productivity of the system. NDVI measurements of large-scale fields are typically performed using remote sensing from satellite and aerial imaging devices. However, due to their low spatial and temporal resolution, these technologies may have limitations in precision viticulture. This paper investigates the potential of a proximal sensing system to characterize the vine foliage that makes use of data collected by a farmer robot equipped with an Intel RealSense D435 camera. The camera includes two infrared (IR) sensors in stereoscopic configuration and one RGB sensor, which provide, for each observation, both infrared and visible red channel information, thus making possible pixel-per-pixel NDVI calculation. Solutions to IR filtering and radiometric calibration issues are proposed that significantly improve measurement accuracy and reliability. Since the camera also provides stereo-based 3D scene reconstruction, depth information can be used to separate the plant canopy from the background before NDVI measurement. At the same time, range data can be employed to extract geometric properties of the crop, such as plant height and/or volume. The system is validated in the field in a commercial vineyard at different phenological stages, from the formation of the berries to leaf discoloration and fall. Experimental results show good agreement compared with ground truth provided by a GreenSeeker, with a mean absolute percentage error in the NDVI estimation of 4.6% and a R 2 of 0.87 tested over the whole grapevine cycle. Therefore, the proposed sensing system could be a feasible solution to automated NDVI estimation at plant-scale. [Display omitted] • Consumer-grade imaging system using a RealSense RGB-D camera for NDVI estimation. • Robotic platform for automated in-field monitoring at plant scale in viticulture. • Proximal sensing system to characterize the vine foliage. • Solutions to IR filtering and radiometric calibration issues under natural light. • Validation in the field in a commercial vineyard at different phenological stages. [ABSTRACT FROM AUTHOR]

Harpins play a key role in inducing disease resistance in crops, and identifying their core functional regions and establishing a system for their efficient expression would be very valuable. In this study, large amounts of soluble fusion proteins of harpin HrpZ and its subpeptides were obtained via the optimized induction conditions (28 ℃C with 0.5 mmol.L-1 IPTG for 6 h) in Escherichia coli BL21 (DE3). Hypersensitive response (HR) assays demonstrated that the C-terminal 66 aa of HrpZ (HrpZ_C_2_2) elicited a strong HR in tobacco (Nicotiana benthamiana) and grape (Flame Seedless) leaves. Additionally, treatment with HrpZ, and particularly HrpZ_C_2_2, significantly reduced the disease incidence and severity index of field vine leaves and those inoculated with downy mildew. The determination of the physiological parameters indicated that HrpZ, and especially HrpZ_C_2_2, improved the photosynthesis- and chlorophyll fluorescence-related parameters, enhanced the activity of defense-related enzymes, including SOD, POD, CAT and PAL, and increased the H2O2 level. Collectively, we efficiently expressed a core peptide of HrpZ and elucidated its strong ability to elicit a HR and resistance to downy mildew. This research provides insight into understanding the structure and function of HrpZ and will advance the application of HrpZ_C_2_2 to increase the resistance of grapevine to downy mildew. [ABSTRACT FROM AUTHOR]

Purpose: This study examined the influence of various storage conditions on Thompson seedless (Vitis vinifera) grapes quality. Research method: Grapes were stored under four conditions: control (room temperature i.e., 20-22°C, no SO2), T1 with SO2 sheets at room temperature i.e., 20-22°C, T2 with SO2 sheets in cold storage at 1°C and T3 without SO2 sheets in cold storage at 1°C. Changes in acidity, total soluble solids (TSS), total anthocyanin content, total phenols, sugars (glucose and fructose), transresveratrol, decay %, weight loss % and antioxidant activity were monitored over 60 days. Findings: The findings revealed a synergistic effect between SO2 and cold storage. Grapes stored with both SO2 sheets and cold storage (T1) exhibited the slowest decline in anthocyanin, phenols and antioxidant activity of 211.06 mg/L, 2102.39 mg/L and 7.19 mM DPPH, respectively after 60 days. T1 grapes found to have slower reduction in sugars and transresveratrol concentration i.e., 15.47 to 15.37 g/100mL and 695 to 516 µg/g, respectively compared to control samples 15.47 to 14.81 g/100mL and 695 to 500 µg/g, respectively. Research limitations: The study focused solely on storage conditions of Thompson seedless variety grapes, limiting the generalizability of the findings to different grape varieties and maturity levels. Originality/value: These results highlighted the importance of proper storage techniques, particularly the combined use of SO2 and cold storage, for maintaining grape quality and extending shelf life. [ABSTRACT FROM AUTHOR]

Grapefruit and stem detection play a crucial role in automated grape harvesting. However, the dense arrangement of fruits in vineyards and the similarity in color between grape stems and branches pose challenges, often leading to missed or false detections in most existing models. Furthermore, these models' substantial parameters and computational demands result in slow detection speeds and difficulty deploying them on mobile devices. Therefore, we propose a lightweight TiGra-YOLOv8 model based on YOLOv8n. Initially, we integrated the Attentional Scale Fusion (ASF) module into the Neck, enhancing the network's ability to extract grape features in dense orchards. Subsequently, we employed Adaptive Training Sample Selection (ATSS) as the label-matching strategy to improve the quality of positive samples and address the challenge of detecting grape stems with similar colors. We then utilized the Weighted Interpolation of Sequential Evidence for Intersection over Union (Wise-IoU) loss function to overcome the limitations of CIoU, which does not consider the geometric attributes of targets, thereby enhancing detection efficiency. Finally, the model's size was reduced through channel pruning. The results indicate that the TiGra-YOLOv8 model's mAP(0.5) increased by 3.33% compared to YOLOv8n, with a 7.49% improvement in detection speed (FPS), a 52.19% reduction in parameter count, and a 51.72% decrease in computational demand, while also reducing the model size by 45.76%. The TiGra-YOLOv8 model not only improves the detection accuracy for dense and challenging targets but also reduces model parameters and speeds up detection, offering significant benefits for grape detection. [ABSTRACT FROM AUTHOR]

Due to the enclosed environment of greenhouse grape production, the supply of CO2 required for photosynthesis is often insufficient, leading to photosynthetic downregulation and reduced yield. Currently, the optimal CO2 concentration for grape production in greenhouses is unknown, and the precise control of actual CO2 levels remains a challenge. This study aims to investigate the effects of different CO2 concentrations on the photosynthetic characteristics and yield of grapes, to validate the feasibility of a CO2 gas irrigation system, and to identify the optimal CO2 concentration for greenhouse grape production. In this study, a CO2 gas irrigation systemcombining CO2 enrichment and gas irrigation techniques was used with a 5-year-old Eurasian grape variety (Vitis vinifera L.) 'Flame Seedless.' Four CO2 concentration treatments were applied: 500 ppm (500 ± 30 µmol·mol-1), 700 ppm (700 ± 30 µmol·mol-1), 850 ppm (850 ± 30 µmol·mol-1), and 1,000 ppm (1,000 ± 30 µmol·mol-1). As CO2 concentration increased, chlorophyll a, chlorophyll b, and carotenoids in grape leaves all reached maximum values at 700 ppm and 850 ppm during the same irrigation cycle, while the chlorophyll a/b ratio was lower than at other concentrations. The net photosynthetic rate (Pn) and water use efficiency (WUE) of grape leaves were the highest at 700 ppm. The transpiration rate and stomatal conductance at 700 ppm and 850 ppmwere significantly lower than those at other concentrations. The light saturation point and apparent quantum efficiency reached their maximum at 850 ppm, followed by 700 ppm. Additionally, the maximum net photosynthetic rate, carboxylation efficiency, electron transport rate, and activities of SOD, CAT, POD, PPO, and RuBisCO at 700 ppm were significantly higher than at other concentrations, with the highest yield recorded at 14.54 t·hm-2. However, when the CO2 concentration reached 1,000 ppm, both photosynthesis and yield declined to varying degrees. Under the experimental conditions, the optimal CO2 concentration for greenhouse grape production was 700 ppm, with excessive CO2 levels gradually inhibiting photosynthesis and yield. The results provide a theoretical basis for the future application of CO2 fertilization and gas irrigation techniques in controlled greenhouse grape production. [ABSTRACT FROM AUTHOR]

This study investigates how grapevines (Vitis vinifera L.) respond to shading induced by artificial nets, focusing on physiological and metabolic changes. Through a multidisciplinary approach, grapevines' adaptations to shading are presented via biochemical analyses and hyperspectral data that are then combined with systems biology techniques. In the study, conducted in a 'Moscatel Galego Branco' vineyard in Portugal's Douro Wine Region during post-veraison, shading was applied and predawn leaf water potential ( Ψ p d ) was then measured to assess water stress. Biochemical analyses and hyperspectral data were integrated to explore adaptations to shading, revealing higher chlorophyll levels (chlorophyll a-b 117.39% higher) and increased Reactive Oxygen Species (ROS) levels in unshaded vines (52.10% higher). Using a self-learning artificial intelligence algorithm (SL-AI), simulations highlighted ROS's role in stress response and accurately predicted chlorophyll a (R2: 0.92, MAPE: 24.39%), chlorophyll b (R2: 0.96, MAPE: 17.61%), and ROS levels (R2: 0.76, MAPE: 52.17%). In silico simulations employing flux balance analysis (FBA) elucidated distinct metabolic phenotypes between shaded and unshaded vines across cellular compartments. Integrating these findings provides a systems biology approach for understanding grapevine responses to environmental stressors. The leveraging of advanced omics technologies and precise metabolic models holds immense potential for untangling grapevine metabolism and optimizing viticultural practices for enhanced productivity and quality. [ABSTRACT FROM AUTHOR]

The light plays a key role in regulating anthocyanin biosynthesis in plants. However, the molecular basis of anthocyanin synthesis in grape skins irradiated at night with supplemental white light (W), red light (R), blue light (B), and blue light for 3 h, 6 h, 9 h, and 12 h (B3, B6, B9, and B12) is not known. In the present study, the total anthocyanin content in grape skins was significant under different light (DL) and blue-light time (DT) treatments, and the best result was obtained with B9. Analysis of RNA-seq data determined that the key genes in the anthocyanin synthesis pathway, PAL, CHS, DFR, GT, CFIP, VIT_14s0068g00920, VIT_06s0009g02860, and VIT_06s0004g08150, were significantly up-regulated under night-time supplemental light treatments, which led to the significant expression of the phenylpropanoid biosynthesis, phenylalanine metabolism, flavonoid biosynthesis, flavone and flavonol biosynthesis, and the anthocyanin biosynthesis pathway, which were significantly expressed, promoting the accumulation of anthocyanin. The B caused significant expression of PAL (VIT_08s0040g01710), CFIP (VIT_13s0067g03820, VIT_13s0067g02870) and DFR (VIT_18s0001g12800), which may be one of the reasons for the better effect of B compared to W anthocyanin enrichment in grape skins. The DT treatment resulted in significant expression of GT (VIT_11s0052g01600), Peroxidase, VIT_09s0018g01190, and VIT_11s0037g00570. In addition, many TFs such as bHLH, MYB, ERF, WRKY, C2H2, MYB-related, and NAC were found to be involved in the synthesis of anthocyanins under light regulation. These results provide new insights into plants' nocturnal supplemental-light regulation of anthocyanin accumulation. [ABSTRACT FROM AUTHOR]

The spotted wing drosophila, Drosophila suzukii (Matsumura), is currently distributed in the main soft-skinned fruits production areas in China and 59 other countries, presenting a significant threat to importing nations. Optimal phytosanitary treatments, including fumigation, irradiation, and cold treatment, have been developed to prevent the international movement of this invasive fly. To determine the most cold-tolerant stage and facilitate the development of the technical schedules requested by the Technical Panel on Phytosanitary Treatment (TPPT), cold treatments of D. suzukii immature stages in 'Red Globe' grapes were conducted. Dose–mortality data at 0 °C and 2 °C from repeated trials were subjected to analysis of covariance, linear regression, and probit analysis. Results identified 3 d old pupae as the most cold-tolerant stage, followed by 1 d old pupae, 4 d old larvae, and 6 h old eggs with similar tolerance. The 2 d old larvae were the most sensitive stage. In subsequent confirmatory tests, 3 d old pupae were subjected to cold treatment at 0 °C for 9 and 10 days, and at 2 °C for 10 and 12 days, based on the probit estimation of the probit-9 value. No adult emergence occurred in the confirmatory tests except for one deformed adult from a 2 °C 10 d treatment. Therefore, the recommended treatment schedule requires fruit temperatures below 0.00 °C (or 1.62 °C) for no less than 10 (or 12) continuous days, with treatment efficacy not less than 99.9960% (or 99.9955%) at a 95% confidence level, respectively. These schedules are intended for submission to TPPT for the development of phytosanitary treatment standards. [ABSTRACT FROM AUTHOR]

Here we present the palynological composition of a single sample of the elusive purple honey collected in southern North Carolina and discuss how it fits within a nearby statewide South Carolina melissopalynological study. 302 samples were collected by nineteen beekeepers participating in this year-long project, submitting honey samples while honeybees were actively collecting nectar. The absence of pollen of Pueraria (kudzu) in the purple honey dismisses the often-suggested link between the unique tint of the purple honey and kudzu's purple pollen. A second hypothesis hinting that the tint could be linked to ripened berries is not reinforced by our investigation as pollen of Ericaceae (eg blueberries) and Rosaceae (eg blackberries) were not found in the purple honey sample but were commonly found in classic golden honey analyzed. The presence of Vitis pollen supports the possibility that bees forage on wild muscadine grapes (Vitis rotundifolia) which was available in the foraging area. This study cannot discredit the possibility that bees were foraging on berry juices or other sugar sources containing purple pigments because these sources contain little or no pollen. A third hypothesis proposes a link between purple honey and the sourwood tree, Oxydendrum arboretum. This hypothesis is supported by this investigation as the dominant pollen type recovered in the purple honey was sourwood, with 19% in relative abundance, a significant percentage for this plant. We suggest chemical analysis of purple honey samples be conducted to determine if berry juice or sourwood is the more likely source of the pigmentation. [ABSTRACT FROM AUTHOR]

It is crucial for winegrowers to make informed decisions about the optimum time to harvest the grapes to ensure the production of premium wines. Global warming contributes to decreasing acidity and increasing sugar levels in grapes, resulting in bland wines with high contents of alcohol. Predicting quality in viticulture is thus pivotal. To assess the average ripeness, typically a sample of one hundred berries representative for the entire vineyard is collected. However, this process, along with the subsequent detailed must analysis, is time consuming and expensive. This study focusses on predicting essential quality parameters like sugar and acid content in Vitis vinifera (L.) varieties 'Chardonnay', 'Riesling', 'Dornfelder', and 'Pinot Noir'. A small near-infrared spectrometer was used measuring non-destructively in the wavelength range from 1 100 nm to 1 350 nm while the reference contents were measured using high-performance liquid chromatography. Chemometric models were developed employing partial least squares regression and using spectra of all four grapevine varieties, spectra gained from berries of the same colour, or from the individual varieties. The models exhibited high accuracy in predicting main quality-determining parameters in independent test sets. On average, the model regression coefficients exceeded 93% for the sugars fructose and glucose, 86% for malic acid, and 73% for tartaric acid. Using these models, prediction accuracies revealed the ability to forecast individual sugar contents within an range of ± 6.97 g/L to ± 10.08 g/L, and malic acid within ± 2.01 g/L to ± 3.69 g/L. This approach indicates the potential to develop robust models by incorporating spectra from diverse grape varieties and berries of different colours. Such insight is crucial for the potential widespread adoption of a handheld near-infrared sensor, possibly integrated into devices used in everyday life, like smartphones. A server-side and cloud-based solution for pre-processing and modelling could thus avoid pitfalls of using near-infrared sensors on unknown varieties and in diverse wine-producing regions. [ABSTRACT FROM AUTHOR]

The aim of this study is the aromatic characterization of new table grape varieties, namely Guzun (V. vinifera), Melona (V. vinifera), Cotton Candy (V. vinifera), IVC SA3 (V. labrusca), and IVC SB1 (V. labrusca). The qualitative and quantitative analysis of odorant molecules present in the berries allows for the definition of the aroma profile of the grape. This analysis benefits from the progress of analytical techniques and sensory methodologies. Gas chromatography/mass detection enable the efficient detection of the substances present and their concentrations. Through the coupling of gas chromatography with sensory detection (gas chromatography-olfactometry), it is possible to correlate the compounds detected by gas chromatography with olfactory stimuli, exploiting the human olfactory system. Aroma, a significant flavor component, is an important attribute of table grape that contributes to defining their quality. This characteristic is highly valued by consumers, and consequently, the market asks for table grapes with a particular or new aroma. Aromatic characterization is a crucial step in the study of the table grape varieties to evaluate their potential at the commercial level or, for instance, in breeding programs focusing on organoleptic properties. [ABSTRACT FROM AUTHOR]

Fusarium species are agriculturally important fungi with a broad host range and can be found as endophytic, pathogenic, or opportunistic parasites in many crop plants. This study aimed to identify Fusarium species in bare-rooted, dormant plants in Turkish grapevine nurseries using molecular identification methods and assess their pathogenicity. Asymptomatic dormant plants were sampled from grapevine nurseries (43) in different regions of the country, and fungi were isolated from plant roots and internal basal tissues. The Fusarium strains were identified by performing gene sequencing (TEF1-α, RPB2) and phylogenetic analyses. Pathogenicity tests were carried out by inoculating mycelial agar pieces of strains onto the stem or conidial suspensions into the rhizosphere of vines (1103 Paulsen rootstock). Laboratory tests revealed that Fusarium species were highly prevalent in Turkish grapevine nurseries (41 out of 43). Gene sequencing and phylogenetic analyses unraveled that 12 Fusarium species (F. annulatum, F. brachygibbosum, F. clavum, F. curvatum, F. falciforme, F. fredkrugeri, F. glycines, F. nanum, F. nematophilum, F. nirenbergiae, F. solani, and Fusarium spp.) existed in the ready-to-sale plants. Some of these species (F. annulatum, F. curvatum and F. nirenbergiae) consistently caused wood necrosis of seedling stems, rotting of the basal zone and roots, and reduced root biomass. Although the other nine species also caused some root rot and root reduction, their virulence was not as severe as the pathogenic ones, and they were considered opportunistic parasites or endophytic species. This study suggests that Fusarium species might play an important role in root-basal rot, wood canker symptoms, and young vine decline in Turkish grapevine nurseries and that these species need to be considered for healthy seedling production. [ABSTRACT FROM AUTHOR]

Grapevine trunk diseases are a threat to table- and grape-wine cultivation worldwide. Phaeomoniella chlamydospora (Pch) is a vascular fungus recognized as one of the most important pathogens associated with grapevine trunk diseases. The relationships between xylem vessel features and Pch susceptibility of 10 table- and 17 wine-grape genotypes, as well as 3 rootstocks, were investigated by image analysis of 50 µm cross-sections and artificial Pch inoculation on one-year-old vine cuttings. Vessels were grouped in the diameter classes 1–30, 31–60, 61–90, 91–120, and >120 µm. Among the table-grape varieties, 'Sable', 'Timco', and 'Red Globe' showed higher densities of large vessels (>120 μm) than 'Italia', 'Sugar Crisp', and 'Sugraone'. Among the wine-grape varieties, 'Minutolo', 'Montepulciano', 'Primitivo' CDTa19, and 'Verdeca' showed higher densities of large vessels than 'Aglianico', 'Nero di Troia', 'Sangiovese', and 'Susumaniello'. In the rootstocks, the vessel diameters were 50.8, 54.0, and 60.9 μm for '34 E.M.', '140 Ruggieri', and '1103 Paulsen', in that order. For table-grape varieties, Pch was re-isolated from 13.3% for 'Sugar Crisp' and 'Sugraone' cuttings up to 93.3% for 'Timco'. For wine-grape varieties, Pch re-isolation ranged from 51.1% ('Bombino nero', 'Negroamaro' D15, and 'Sangiovese') to 81.1% ('Montepulciano'), while for the rootstocks, the values were from 33 to 51%. A principal component analysis (PCA) revealed a positive correlation between the frequencies of large vessels and Pch re-isolation. In addition, in wine grapes and rootstocks, higher Pch re-isolation frequencies in the lateral parts of cuttings were correlated (r = 0.79) to a higher frequency of large vessels. The results highlight relationships between grapevine xylem vessel sizes and susceptibility to P. chlamydospora that are worthy of further research. [ABSTRACT FROM AUTHOR]

Potassium (K) is essential for the development of grapevines (Vitis vinifera), accumulating into berries during maturation. Elevated K has been associated with high sugar and low acidity in juice. Characterising the accumulation patterns of K and other components in pericarps treated with various experimental factors may indicate potential regulators of berry K levels. A soil fertiliser trial using nutrient solutions with two K supply rates was conducted on potted Shiraz vines during berry ripening. Doubled-K supply increased L-malic acid content in the early-ripening phase, and increased K and magnesium concentrations in the late-ripening phase. Doubled-K supply reduced the ratio of K to sodium in later ripening phases, suggesting that the accumulation of K relative to sodium was limited in more mature berries supplied with extra K. Pericarp water percentage, sugar, K and ATP were correlated in both treatments, indicating links between hydration, solute transport and energy in maturing berries. In a separate rootstock trial over the two growing seasons, Shiraz scions grafted onto 420-A rootstock produced berries with lower K concentration and content than those grafted onto Ramsey or Ruggeri-140 rootstocks and own-rooted vines. This study demonstrated that the K supply and berry ripening phase impacted the berry K level. Increased potassium (K) concentration in grape (Vitis vinifera) berries is associated with loss of acidity and high sugar content in juice. This study demonstrated that the K supply to Shiraz and berry ripening phase could impact the berry attributes and chemical composition at harvest, associated with the linkages between water, sugar, K and ATP. From this study, we suggest that grape berry maturation and composition management may be beneficial. [ABSTRACT FROM AUTHOR]

In speech coding, denoising of the speech signal is essential as well as crucial. The filters for minimizing errors through denoising employ the autoregressive moving average (ARMA) approach, introducing higher computational complexity in speech coder design. This research work presents the design and implementation of an effective perceptual weighting filter (PWF) for speech coding. The high-level synthesis of the fixed-point PWF filter is optimized by multiple optimization techniques along with detailed design space exploration using the weighted sum (WS) method. To enhance the performance, an FPGA-based hardware accelerator is proposed using hardware/software (HW/SW) co-design in an embedded environment. Simulative analysis in Vivado HLS and final accelerator design in the Vitis IDE tool validate the proposed architecture by using real-time speech samples, demonstrating a 50% reduction in area and a 99% execution improvement. This makes it well-suited for use in modern speech codecs, enhancing the efficiency. [ABSTRACT FROM AUTHOR]

Feature selection, reducing number of input variables to develop classification model, is an important process to reduce computational and modeling complexity and affects the performance of image process. In this paper, we have proposed new statistical approaches for feature selection based on sample selection. We have applied our new approaches to grapevine leaves data that possess properties of shape, thickness, featheriness, and slickness that are investigated in images. To analyze such kind of data by using image process, thousands of features are created and selection of features plays important role to predict the outcome properly. In our numerical study, convolutional neural networks have been used as feature extractors and then obtained features from the last average pooling layer to detect the type of grapevine leaves from images. These features have been reduced by using our suggested four statistical methods: simple random sampling, ranked set sampling, extreme ranked set sampling, moving extreme ranked set sampling. Then, selected features have been classified with artificial neural network and we obtained the best accuracy of 97.33% with our proposed approaches. Based on our empirical analysis, it has been determined that the proposed approach exhibits efficacy in the classification of grapevine leaf types. Furthermore, it possesses the potential for integration into various computational devices. [ABSTRACT FROM AUTHOR]

Grape leaf disease is a primary factor affecting grape yield and impeding the growth of the industrial economy. Currently, high-quality datasets are required for deep recognition models to effectively identify grape leaf diseases. In reality, the acquired image inevitably has the appearance of being low quality and unclear due to the influence of equipment and environment. The super-resolution method is an effective way to solve the problem. However, due to the complex model structure and learning strategies, existing super-resolution methods are computationally expensive and neglect the balance between global and local feature extraction. In this paper, a novel multiple attention transformer super-resolution (MATSR) method is proposed to solve these problems. Specifically, the method uses convolution to extract low-level features, which are then fed into the multiple attention shuffle transformer (MAST) module. The module consists of the shuffle transformer for global feature extraction, the constructed channel spatial attention block (CSAB) for local feature extraction, and the built reduisal feature block (RFB) for aggregating these two features. Meanwhile, considering the importance of the balance of global and local features for grape leaf disease recognition, a dynamic learning strategy is designed to balance these two features. Further, the abstract feature extraction layer combined the learned features with the low-level features. Finally, these abstracted features are fed into the pixels shuffle layer for super-resolution upsampling. Numerous comparative experiments are carried out on the collected high-resolution grape leaf disease images as well as the apple leaf pathological images. The results demonstrate the proposed method achieved the best PSNR of 38.152 dB and SSIM of 0.96 at scale ×2, and 35.896 dB and SSIM of 0.934 at scale ×3, respectively. Furthermore, four recognition models are experimented on the super-resolution grape disease dataset, among which ShuffleNet and Inception achieve the best accuracy of 98.28 % and 98.53 %, respectively. Therefore, this study can effectively aid grape growers in accurately identifying diseases and taking proactive measures. [ABSTRACT FROM AUTHOR]