Search Results (1,024)

Tomatoes are an important economic crop in China, and crop diseases often lead to a decline in their yield. Deep learning-based visual recognition methods have become an approach for disease identification; however, challenges remain due to complex background interference in the field and the diversity of disease manifestations. To address these issues, this paper proposes the SXA-YOLO (an improvement based on YOLO, where S stands for the SAAPAN architecture, X represents the XIoU loss function, and A denotes the AsDDet module) symmetric perception recognition model. First, a comprehensive symmetry architecture system is established. The backbone network creates a hierarchical feature foundation through C3k2 (Cross-stage Partial Concatenated Bottleneck Convolution with Dual-kernel Design) and SPPF (the Fast Pyramid Pooling module) modules; the neck employs a SAAPAN (Symmetry-Aware Adaptive Path Aggregation Architecture) bidirectional feature pyramid architecture, utilizing multiple modules to achieve equal fusion of multi-scale features; and the detection head is based on the AsDDet (Adaptive Symmetry-aware Decoupled Detection Head) module for functional decoupling, combining dynamic label assignment and the XIoU (Extended Intersection over Union) loss function to collaboratively optimize classification, regression, and confidence prediction. Ultimately, a complete recognition framework is formed through triple symmetric optimization of “feature hierarchy, fusion path, and task functionality.” Experimental results indicate that this method effectively enhances the model’s recognition performance, achieving a P (Precision) value of 0.992 and an mAP50 (mean Average Precision at 50% IoU threshold) of 0.993. Furthermore, for ten categories of diseases, the SXA-YOLO symmetric perception recognition model outperforms other comparative models in both p value and mAP50. The improved algorithm enhances the recognition of foliar diseases in tomatoes, achieving a high level of accuracy. Full article

Alternaria is a widespread genus and a diverse taxonomic group of fungi, whose members exhibit a wide range of ecological roles, from endophytes and saprophytes to potent plant pathogens, and in some cases, to opportunistic pathogens or allergens affecting humans. Their high adaptability to various environmental conditions determines their widespread distribution and resilience. A key feature of the genus Alternaria is its substantial species diversity. According to the Species Fungorum database, it currently comprises 792 registered species, which are grouped into 29 sections. It should be noted that this number reflects the current state of taxonomic classification and is subject to ongoing revision. The ecological role of representatives of this genus is particularly relevant in the context of agriculture, as many species are pathogens and causative agents of Alternaria leaf spot in important agricultural plants such as tomatoes, potatoes, apples, wheat, and others. This disease causes significant economic losses. At the same time, some strains demonstrate potential for use in biotechnology due to their ability to produce biologically active metabolites. This review examines the taxonomy, morphological characteristics, ecological role, pathogenicity, and control methods of fungi of the genus Alternaria, as well as their biotechnological potential. Full article

This study addresses the challenges of early recognition of fruit and vegetable diseases and pests in facility horticultural greenhouses and the difficulty of real-time deployment on edge devices, and proposes a lightweight cross-scale intelligent recognition network, Light-HortiNet, designed to achieve a balance between high accuracy and high efficiency for automated greenhouse pest and disease detection. The method is built upon a lightweight Mobile-Transformer backbone and integrates a cross-scale lightweight attention mechanism, a small-object enhancement branch, and an alternative block distillation strategy, thereby effectively improving robustness and stability under complex illumination, high-humidity environments, and small-scale target scenarios. Systematic experimental evaluations were conducted on a greenhouse pest and disease dataset covering crops such as tomato, cucumber, strawberry, and pepper. The results demonstrate significant advantages in detection performance, with mAP@50 reaching $0.872$, mAP@50:95 reaching $0.561$, classification accuracy reaching $0.894$, precision reaching $0.886$, recall reaching $0.879$, and F1-score reaching $0.882$, substantially outperforming mainstream lightweight models such as YOLOv8n, YOLOv11n, MobileNetV3, and Tiny-DETR. In terms of small-object recognition capability, the model achieved an mAP-small of $0.536$ and a recall-small of $0.589$, markedly enhancing detection stability for micro pests such as whiteflies and thrips as well as early-stage disease lesions. In addition, real-time inference performance exceeding 20 FPS was achieved on edge platforms such as Jetson Nano, demonstrating favorable deployment adaptability. Full article

Frequent occurrences of pests and diseases in tomatoes severely restrict yield and quality improvements. Traditional detection methods are labor-intensive and prone to errors, while advancements in deep learning provide a promising solution for rapid and accurate identification. However, existing deep learning-based models often face high computational complexity and a large number of parameters, which hinder their deployment on resource-constrained edge devices. To overcome this limitation, we propose a novel lightweight detection model named YOLOv11n-KL based on the YOLOv11n framework. In this model, the feature extraction capability for small targets and the overall computational efficiency are enhanced through the integration of the Conv_KW and C3k2_KW modules, both of which incorporate the KernelWarehouse (KW) algorithm, and the Detect_LSCD detection head is employed to enable parameter sharing and adaptive multi-scale feature calibration. The results indicate that YOLOv11n-KL achieves superior performance in tomato pest and disease detection, balancing lightweight design and detection accuracy. The model achieves an mAP@0.5 of 92.5% with only 3.0 GFLOPs and 5.2 M parameters, reducing computational cost by 52.4% and improving mAP@0.5 by 0.9% over YOLOv11n. With its low complexity and high precision, YOLOv11n-KL is well-suited for resource-constrained applications. The proposed YOLOv11n-KL model offers an effective solution for detecting tomato pests and diseases, serving as a useful reference for agricultural automation. Full article

Packaging plays a crucial role in extending the shelf life of fresh fruits and vegetables, thereby preserving their quality characteristics throughout the supply chain. Packaging systems treated with natural compounds can replace synthetic packaging systems. This study aimed to evaluate the potential application of active cardboard packaging (ACP) in preserving fruit quality and extending its shelf life. We observed the effect of cardboard packaging containing Punica granatum peel extract (PPGE) and Rumex crispus root extract (RRCE) on the shelf life of strawberries, tomatoes, and table grapes. In vitro and in vivo tests demonstrated the ability of RRCE + PPGE (group A) and PPGE (group B), once incorporated into the packaging at a concentration of 8%, to create a system capable of inhibiting microbial growth, thus prolonging the freshness and marketability of the fruit. Conventional packaging (group C) was taken as control. Strawberry groups A and B showed disease severity (DS) values of 55.9 and 51.8%, significantly lower than the 87.7% found in group C. Similar findings were observed in table grapes and datterini tomatoes. Quality was also assessed by measuring the surface color of homogenized strawberries, grapes and tomatoes, using a spectrophotometer. In strawberries, after 4 days, the colorimetric values in groups A and B were 26.86 and 34.50, respectively, much higher than the 13.99 recorded in untreated strawberries (group C). In table grapes and datterini tomatoes, the same results as those obtained in strawberries were confirmed. This study offers a novel approach to extending the shelf life of fruits and vegetables. We believe this technology, in addition to being an excellent bioactive packaging solution capable of reducing losses and improving quality in the fruit supply chain, is also economically viable since PPGE is derived from pomegranate processing waste and RRCE is obtained from the roots of a weed. Full article

Foodborne diseases remain a public health issue worldwide. Inadequate attention to food safety and hygiene increases the risk of opportunistic pathogens and resistant bacteria spreading to people through the food chain, leading to foodborne diseases. To investigate food safety in our region, this study aims to measure the prevalence of microorganisms on raw food materials randomly purchased from wet markets in Chiang Mai province, Northern Thailand. In this study, microbial cultures, identified by MALDITOF-MS techniques, were used to determine the microflora and antibiotic-resistance organisms on raw vegetables and fruit. Consequently, to confirm antibiotic resistance, the antimicrobial susceptibility techniques were performed. The results found no Salmonella enterica was detected on the overall food samples. For Proteus spp. detection, P. mirabilis were detected at 3.23% in cabbage, 3.57% in Chinese cabbage, and 6.67% in lettuce, while P. vulgaris were detected at 7.14% in Chinese cabbage and 3.57% in peppermint. No Proteus spp. was detected in basils, tomatoes and grapes. In addition, for antibiotic-resistance detection, only ESBL-producing Klebsiella oxytoca was detected in the raw tomato sample (3.57%). According to the study’s findings, people who participate in the food process should be aware of their food safety and hygiene. Full article

Phytopathogenic viruses severely impact major crops, leading to significant social and economic losses. Among them, begomoviruses pose a serious threat to key cultivars in subtropical and tropical regions despite ongoing efforts to limit their spread. Early detection of these pathogens in field crops and associated weeds is essential for the timely implementation of management strategies to mitigate viral disease outbreaks. In this study, we applied a sensitive loop-mediated isothermal amplification (LAMP) assay for the detection of tomato yellow leaf curl virus (TYLCV), tomato latent virus (TLV), and tomato mottle Taino virus (ToMoTV) in agro-inoculated Nicotiana benthamiana and Solanum lycopersicum. Importantly, LAMP assays also enabled the identification of these viruses in both symptomatic and asymptomatic field-grown tomato plants, detecting a higher number of infected plants than dot blot hybridization and PCR. Field surveys further revealed mixed infections of TYLCV, TLV, and ToMoTV within individual tomato plants, uncovering a complex epidemiological scenario. Full article

Glycosylation plays a critical role in maintaining cardiac structure and function, yet its modulation during aging and hypertrophic cardiomyopathy (HCM) in feline hearts remains uncharacterized. This study provides a systematic analysis of lectin-binding patterns in feline myocardium across different age groups and disease states. Post-mortem feline hearts (n = 64), classified by age (newborn to senior) and diagnostic status (healthy vs. HCM-affected), were evaluated using tissue microarrays stained with five plant-derived lectins—Concanavalin A (ConA), Wheat Germ Agglutinin (WGA), RCA (Ricinus communis Agglutinin I), Tomato (Lycopersicon esculentum Agglutinin), and Griffonia (Bandeiraea) simplicifolia Lectin I (BS)—alongside Draq5 nuclear counterstaining. Lectin histochemistry revealed distinct, region-specific glycosylation patterns, with notable remodelling in both aged and HCM-affected hearts. These glycan alterations reflect underlying molecular and structural changes associated with cardiac aging and pathology. Although lectin histochemistry has been used to examine cardiac glycosylation in species such as mice, rats, zebrafish, and humans, comparable data for felines have been lacking, even if domestic cat represents a spontaneous model for human HCM. This study provides the first essential step in characterizing the feline cardiac glycosylation. The observed shifts in lectin-binding profiles reveal specific remodelling associated with aging and HCM in cats. These results provide a foundation for future studies assessing the utility of glycan motifs as potential post-mortem markers of disease progression in felines. Full article

The hemibiotrophic bacterial pathogen Pseudomonas syringae (Pst) infects a range of plant species and causes enormous economic losses. Despite its agronomic significance, the molecular mechanisms underlying tomato–Pst interactions remain largely uncharacterized. To elucidate these mechanisms, we conducted a comprehensive transcriptomic analysis using infected tomato leaves inoculated with virulent strains Pst DC3000 at relatively early time points. RNA-sequencing of nine libraries identified stage-specific expression patterns, with DEG counts ranging from 484 to 1267 upregulated and from 560 to 844 downregulated genes. Enrichment analysis highlighted significant alterations in metabolic pathways, plant–pathogen interaction networks, and hormone signaling cascades, with marked transcriptional reprogramming observed between the pre- and post-infection stages. A longitudinal analysis of gene expression dynamics identified 15 consistently upregulated and 9 downregulated genes across all post-inoculation time points. Notably, in several candidate genes, a homologous gene of AtNSP2, SlNSP-Like was confirmed to be involved in disease resistance in tomato leaves. SlNSP-Like is localized in the cytoplasm and nucleus, and the transient overexpression of SlNSP-Like tomato plant exhibits significant resistance to Pst DC3000. This study provides valuable insights into the molecular dialogue between tomato and Pst, and the identified regulatory genes and pathways serve as promising targets for breeding disease-resistant tomato cultivars and developing management strategies against bacterial spot disease. Full article

This study addressed the core challenge of intelligent pest and disease monitoring and early warning in smart horticultural production by proposing a multimodal deep learning framework based on multi-parameter environmental sensor arrays. The framework integrates visual information with electrical signals to overcome the inherent limitations of conventional single-modality approaches in terms of real-time capability, stability, and early detection performance. A long-term field experiment was conducted over 18 months in the Hetao Irrigation District of Bayannur, Inner Mongolia, using three representative horticultural crops—grape (Vitis vinifera), tomato (Solanum lycopersicum), and sweet pepper (Capsicum annuum)—to construct a multimodal dataset comprising illumination intensity, temperature, humidity, gas concentration, and high-resolution imagery, with a total of more than $2.6\times {10}^6$ recorded samples. The proposed framework consists of a lightweight convolution–Transformer hybrid encoder for electrical signal representation, a cross-modal feature alignment module, and an early-warning decision module, enabling dynamic spatiotemporal modeling and complementary feature fusion under complex field conditions. Experimental results demonstrated that the proposed model significantly outperformed both unimodal and traditional fusion methods, achieving an accuracy of $0.921$, a precision of $0.935$, a recall of $0.912$, an F1-score of $0.923$, and an area under curve (AUC) of $0.957$, confirming its superior recognition stability and early-warning capability. Ablation experiments further revealed that the electrical feature encoder, cross-modal alignment module, and early-warning module each played a critical role in enhancing performance. This research provides a low-cost, scalable, and energy-efficient solution for precise pest and disease management in intelligent horticulture, supporting efficient monitoring and predictive decision-making in greenhouses, orchards, and facility-based production systems. It offers a novel technological pathway and theoretical foundation for artificial-intelligence-driven sustainable horticultural production. Full article

Packaging can help prolong the shelf life of perishable agrifoods. In the present investigation, edible coatings were tested to reduce food waste caused by filamentous fungi and increase the shelf-life of high-value products such as strawberries, tomatoes, and blueberries. Different combinations of sodium alginate and calcium chloride, and various immersion times were tested on tomato as a model. The ability to activate edible coatings with food-grade compounds/extracts, such as sodium bicarbonate or Moringa oleifera extract (MLE), was explored. The extract was also tested in vitro against some of the main postharvest pathogens, such as Botrytis cinerea, Alternaria alternata, Rhizopus stolonifer, Colletotrichum acutatum, and Penicillium expansum. The most suitable composition for the edible coating proved to be 2% sodium alginate and 2% calcium chloride. MLE proved not to reduce fungal growth, except for A. alternata and C. acutatum. Concerning active coatings, particularly those containing MLE, there was a reduction in the incidence of rots on strawberries (−45%) and tomatoes (−59%) as compared to the uncoated control. Furthermore, a reduction in the severity of rots was recorded in all tested fruits (−73% in tomato, −88% in strawberries, −47% in blueberries) as compared to the uncoated control. The active edible coatings could play a role in reducing rots, contributing to the extension of the shelf-life of the selected products. Full article

Modern agriculture relies heavily on chemical inputs to sustain productivity, yet their intensive use poses environmental and health risks. Sustainable strategies based on biostimulants have emerged as promising alternatives to reduce agrochemical dependence. Among these compounds, humic substances (HS) stand out for their ability to modulate plant growth and activate defense responses. This study aimed to evaluate the effects of HS from different sources—vermicompost (Vc) and peat (Pt)—on the salicylic acid (SA)-mediated defense pathway in tomato plants (Solanum lycopersicum cv. Micro-Tom) infected with Oidium sp. The HS were characterized by solid-state ¹³C CPMAS NMR to determine the relative distribution of carbon functional groups and structural domains, including alkyl, O-alkyl, aromatic, and carbonyl carbon fractions, as well as hydrophobicity-related indices. Enzymatic activities of lipoxygenase, peroxidase, phenylalanine ammonia lyase, and beta 1,3-glucanase were determined spectrophotometrically, and RT-qPCR quantified gene transcription levels involved in SA signaling and defense (MED25, MED16, MED14, NPR1, ICS, PAL, LOX1.1, MYC2, JAZ, jar1, CAT, POX, SOD, APX, ERF, PR-1, PR-2, PR-4 e PR-5). Both HS significantly reduced disease severity and activated key SA-related defense genes, including the regulatory gene NPR1 and the effector genes PR1, PR2 and PR5, with Pt providing greater protection. Notably, HS amplified defense-related gene expression and enzymatic activities specifically under infection, showing a stronger induction than in non-infected plants. These results demonstrate that structural differences among HS drive distinct and enhanced defense responses under pathogen challenge, highlighting their potential as sustainable tools for improving plant immunity in agricultural systems. Full article

Plant diseases are currently a major threat to agricultural economies and food availability, having a negative environmental impact. Despite being a promising line of research, current approaches struggle with poor cross-site generalization, limited labels and dataset bias. Real-field complexities, such as environmental variability, heterogeneous varieties or temporal dynamics as are often overlooked. Numerous studies have been conducted to address these challenges, proposing advanced learning strategies and improved evaluation protocols. Synthetic data generation and self-supervised learning reduce dataset bias, while domain adaptation, hyperspectral, and thermal signals improve robustness across sites. However, a large portion of current methods are developed and validated mainly on clean laboratory datasets, which do not capture the variability of real-field conditions. Existing AI models often lead to imperfect detection results when dealing with field images complexities, such as dense vegetation, variable illumination or changing symptom expression. Although augmentation techniques can approximate real-world conditions, incorporating field data represents a substantial enhancement in model reliability. Federated transfer learning offers a promising approach to enhance plant disease detection, by enabling collaborative training of models across diverse agricultural environments, using in-field data but without disclosing the participants data to each others. In this study, we collaboratively trained a hybrid Graph–SNN model using federated learning (FL) to preserve data privacy, optimized for efficient use of participant resources. The model achieved an accuracy of 0.9445 on clean laboratory data and 0.6202 exclusively on field data, underscoring the considerable challenges posed by real-world conditions. Our findings demonstrate the potential of FL for privacy preserving and reliable plant disease detection under real field conditions. Full article

Background: Diet quality significantly influences metabolic health, obesity, and non-communicable disease risk. Functional foods and nutraceuticals, rich in bioactive compounds, may enhance health outcomes beyond basic nutrition, particularly when combined with Mediterranean-style dietary patterns. Objectives: This feasibility study evaluated the integration of functional foods and nutraceuticals into a Mediterranean-based dietary intervention in adults with metabolic risk factors, focusing on feasibility, tolerability, and preliminary clinical effects. Methods: Functional food prototypes, including Calabrian tomato, pomegranate, bergamot, blueberry, and hazelnut products, along with two nutraceutical formulations, were developed, characterized for bioactive content, and assessed for palatability, bioavailability, and safety. Adults aged ≥50 years participated in a 4-week intervention, consuming daily servings of functional foods and either a whey protein-based or essential amino acid-based nutraceutical. Compliance, acceptability, anthropometry, body composition, muscle strength, and biochemical markers were assessed pre- and post-intervention. Results: Functional foods and nutraceuticals were well-tolerated, with high adherence (>80%). Bioactive compounds were detectable in serum post-consumption, confirming bioavailability. Preliminary findings suggested that integrating functional foods and nutraceuticals into a Mediterranean-style dietary intervention is feasible, safe, and acceptable in older adults with metabolic risk factors. These results support the potential clinical benefit of combined dietary strategies and provide a rationale for a larger randomized controlled trial to evaluate efficacy on metabolic, musculoskeletal, and hepatic outcomes. Full article

This study presents the design and development of an intelligent end-effector integrated into a custom 7-degree-of-freedom (DOF) robotic arm for monitoring the health status of tomato plants during their growth stages. The robotic system combines five rotational and two prismatic joints, enabling both horizontal reach and vertical adaptability to inspect plants of varying heights without repositioning the robot’s base. The integrated vision module employs a YOLOv5 neural network trained with 7864 images of tomato leaves, including both healthy and diseased samples. Image preprocessing included normalization and data augmentation to enhance robustness under natural lighting conditions. The optimized model achieved a detection accuracy of 90.2% and a mean average precision (mAP) of 92.3%, demonstrating high reliability in real-time disease classification. The end-effector, fabricated using additive manufacturing, incorporates a Raspberry Pi 4 for onboard processing, allowing autonomous operation in agricultural environments. The experimental results validate the feasibility of combining a custom 7-DOF robotic structure with a deep learning-based detector for continuous plant monitoring. This research contributes to the field of agricultural robotics by providing a flexible and precise platform capable of early disease detection in dynamic cultivation conditions, promoting sustainable and data-driven crop management. Full article