The electromagnetic induction (EMI) and frequency domain reflectometry (FDR) sensors, which measure the soil apparent electrical conductivity (ECa) in situ, have emerged as efficient and rapid tools for the indirect assessment of soil salinity, conventionally determined by the electrical conductivity of the saturated soil paste extract (ECe). However, the limitations of applying a single soil sensor and the ECa dependence on multiple soil properties, such as soil moisture and texture, can hinder the interpretation of ECe, whereas selecting the most appropriate set of sensors is challenging. To address these issues, this study explored the prediction ability of a noninvasive EM38-MK2 (EMI) and a capacitance dielectric WET-2 probe (FDR) in assessing topsoil salinity and texture within 0–30 cm depth across diverse soil and land-use conditions in Laconia, Greece. To this aim, multiple linear regression models of laboratory-estimated ECe and soil texture were constructed by the in situ measurements of EM38-MK2 and WET-2, and their performances were individually evaluated using statistical metrics. As was shown, in heterogeneous soils with sufficient wetness and high salinity levels, both sensors produced models with high adjusted coefficients of determination (adj. R2 > 0.82) and low root mean square error (RMSE) and mean absolute error (MAE), indicating strong model fit and reliable estimations of topsoil salinity. For the EM38-MK2, model accuracy improved when clay was included in the regression, while for the WET-2, the soil pore water electrical conductivity (ECp) was the most accurate predictor. The drying soil surface was the greatest constraint to both sensors’ predictive performances, whereas in non-saline soils, the silt and sand were moderately assessed by the EM38-MK2 readings (0.49 < adj. R2 < 0.51). The results revealed that a complementary use of the contemporary EM38-MK2 and the low-cost WET-2 could provide an enhanced interpretation of the soil properties in the topsoil without the need for additional data acquisition, although more dense soil measurements are recommended.

This paper presents a novel hybrid and hierarchical architecture of a Convolutional Neural Network (CNN), based on MobileNetV2 and Support Vector Machines (SVM) for the classification of crop diseases (SVMobileNetV2). The system feeds from multispectral images captured by Unmanned Aerial Vehicles (UAVs) alongside data from IoT nodes. The primary objective is to improve classification performance in terms of both accuracy and precision. This is achieved by integrating contemporary Deep Learning techniques, specifically different CNN models, a prevalent type of artificial neural network composed of multiple interconnected layers, tailored for the analysis of agricultural imagery. The initial layers are responsible for identifying basic visual features such as edges and contours, while deeper layers progressively extract more abstract and complex patterns, enabling the recognition of intricate shapes. In this study, different datasets of tropical crop images, in this case banana crops, were constructed to evaluate the performance and accuracy of CNNs in detecting diseases in the crops, supported by transfer learning. For this, multispectral images are used to create false-color images to discriminate disease through spectra related to the blue, green and red colors in addition to red edge and near-infrared. Moreover, we used IoT nodes to include environmental data related to the temperature and humidity of the environment and the soil. Machine Learning models were evaluated and fine-tuned using standard evaluation metrics. For classification, we used fundamental metrics such as accuracy, precision, and the confusion matrix; in this study was obtained a performance of up to 86.5% using current deep learning models and up to 98.5% accuracy using the proposed hybrid and hierarchical architecture (SVMobileNetV2). This represents a new paradigm to significantly improve classification using the proposed hybrid CNN-SVM architecture and UAV-based multispectral images.

The harvesting of dragon fruit remains challenging due to uneven clamping forces, high fruit damage rates, and low redundancy in conventional end-effectors. To address these issues, we developed a novel embracing end-effector with a Variable-Span Arch (VSA) structure. The VSA design enables adaptive clamping force distribution and effective torsional fruit separation, significantly reducing static pressure damage. Theoretical modeling, mechanical testing, and field experiments were conducted to evaluate its performance. Results show that the proposed end-effector achieves a 95% harvesting success rate, with an average picking time of 15 s per fruit, and can output a maximum torque of 18 kgf·cm, which is sufficient for dragon fruit detachment. These findings demonstrate that the VSA-based embracing end-effector offers a low-damage, efficient, and robust solution for dragon fruit harvesting, providing practical guidance for robotic applications in tropical fruit production.

As a global staple ensuring food security, maize incurs 15–20% annual yield loss from pests/diseases. Conventional manual detection is inefficient (>7.5 h/ha) and subjective, while existing YOLO models suffer from >8% missed detections of small targets (e.g., corn armyworm larva) in complex fields due to feature loss and poor multi-scale fusion. We propose YOLO-FDLU, a YOLO11s-based framework: LAD (Light Attention-Downsampling)-Conv preserves small-target features; C3k2_DDC (DilatedReparam–DilatedReparam–Conv) enhances cross-scale fusion; Detect_FCFQ (Feature-Corner Fusion and Quality Estimation) optimizes bounding box localization; UIoU (Unified-IoU) loss reduces high-IoU regression bias. Evaluated on a 25,419-sample dataset (6 categories, 3 public sources + 1200 compliant web images), it achieves 91.12% Precision, 92.70% mAP@0.5, 78.5% mAP@0.5–0.95, and 20.2 GFLOPs/15.3 MB. It outperforms YOLOv5-s to YOLO12-s, supporting precision maize pest/disease monitoring.

This paper presents a digital approach for the identification of apple varieties bred in Kazakhstan using deep learning methods and transfer learning. The main objective of this study is to develop and evaluate an algorithm for automatic varietal classification of apples based on color images obtained under controlled conditions. Five representative cultivars were selected as research objects: Aport Alexander, Ainur, Sinap Almaty, Nursat, and Kazakhskij Yubilejnyj. The fruit samples were collected in the pomological garden of the Kazakh Research Institute of Fruit and Vegetable Growing, ensuring representativeness and taking into account the natural variability of the cultivars. Two convolutional neural network (CNN) architectures—GoogLeNet and SqueezeNet—were fine-tuned using transfer learning with different optimization settings. The data processing pipeline included preprocessing, training and validation set formation, and augmentation techniques to improve model generalization. Network performance was assessed using standard evaluation metrics such as accuracy, precision, and recall, complemented by confusion matrix analysis to reveal potential misclassifications. The results demonstrated high recognition efficiency: the classification accuracy exceeded 95% for most cultivars, while the Ainur variety achieved 100% recognition when tested with GoogLeNet. Interestingly, the Nursat variety achieved the best results with SqueezeNet, which highlights the importance of model selection for specific apple types. These findings confirm the applicability of CNN-based deep learning for varietal recognition of Kazakhstan apple cultivars. The novelty of this study lies in applying neural network models to local Kazakhstan apple varieties for the first time, which is of both scientific and practical importance. The practical contribution of the research is the potential integration of the developed method into industrial fruit-sorting systems, thereby increasing productivity, objectivity, and precision in post-harvest processing. The main limitation of this study is the relatively small dataset and the use of controlled laboratory image acquisition conditions. Future research will focus on expanding the dataset, testing the models under real production environments, and exploring more advanced deep learning architectures to further improve recognition performance.

Accurate and consistent measurements of geometric features such as fruit length and width are essential for the quality assessment of Namdokmai Sithong mangoes. Traditional manual methods are labor-intensive and prone to inconsistency. This study presented an automated system for geometric feature extraction of Namdokmai Sithong mangoes using a YOLOv8-based object detection model. The framework automated the process of measuring key morphological traits, specifically fruit length and width, to improve accuracy and consistency in quality assessment. The model identified an anatomically meaningful reference point for guiding axis-based measurements by detecting the mango and its peduncle. HSV-based image segmentation combined with morphological operations and edge detection effectively calculated the major (length) and minor (top and bottom width) axes of the fruit. Evaluation on 30 test images showed that the proposed method achieved error rates below 5% in over 90% of samples, with average deviations for fruit length typically under 1.5%. The system was implemented as a standalone Python (version 3.12.8) application and demonstrated high potential for use in real-time, automated fruit grading scenarios.

The rapid and accurate identification of pathogenic spores is essential for the early diagnosis of diseases in modern agriculture. Gray mold disease, caused by Botrytis cinerea, is a significant threat to several crops and is traditionally controlled using fungicides or, alternatively, by UV-C radiation. Classically, the determination of conidial germination percentage, a key indicator for assessing pathogen viability, has been a manual, time-consuming, and error-prone process. This study proposes an approach based on deep learning, using one-stage detectors to automate the detection and counting of germinated and non-germinated conidia in microscopy images. We trained and assessed the performance of three models under several metrics: YOLOv8, YOLOv11, and RetinaNET. The results show that these three architectures provide an efficient and accurate solution for the recognition of gray mold conidia viability. Selecting the best model, we performed the task of detecting and counting conidia for determining the germination percentage on samples treated with different UV-C radiation dosages. The results show that these deep-learning models achieved counting accuracies that closely matched those obtained with conventional manual methods, yet they delivered results far more rapidly. Because they operate continuously without fatigue or operator bias, these models begin to open possibilities, after widening field tests and datasets, for efficient and fully automated monitoring pipelines for disease management in the agro-industry.

Accurate postharvest quality evaluation of soybeans is essential for preserving product value and meeting industry standards. Traditional inspection methods are often inconsistent, labor-intensive, and unsuitable for high-throughput operations. This study presents a non-destructive soybean classification approach using a simplified reflectance-mode hyperspectral imaging system equipped with a single light source, eliminating the complexity and maintenance demands of dual-light configurations used in prior studies. A spectral–spatial data fusion strategy was developed to classify harvested soybeans into four categories: normal, split, diseased, and foreign materials such as stems and pods. The dataset consisted of 1140 soybean samples distributed across these four categories, with spectral reflectance features and spatial texture attributes extracted from each sample. These features were combined to form a unified feature representation for use in classification. Among multiple machine learning classifiers evaluated, Linear Discriminant Analysis (LDA) achieved the highest performance, with approximately 99% accuracy, 99.05% precision, 99.03% recall and 99.03% F1-score. When evaluated independently, spectral features alone resulted in 98.93% accuracy, while spatial features achieved 78.81%, highlighting the benefit of the fusion strategy. Overall, this study demonstrates that a single-illumination HSI system, combined with spectral–spatial fusion and machine learning, offers a practical and potentially scalable approach for non-destructive soybean quality evaluation, with applicability in automated industrial processing environments.

The precise identification of plant diseases is essential for improving agricultural productivity and reducing reliance on human expertise. Deep learning frameworks, belonging to the YOLO series, have demonstrated significant potential in the real-time detection of plant diseases. There are various factors influencing model performance; activation functions play an important role in improving both accuracy and efficiency. This study proposes αSiLU, a modified activation function developed to optimize the performance of YOLOv11n for plant disease-detection tasks. By integrating a scaling factor α into the standard SiLU function, αSiLU improved the effectiveness of feature extraction. Experiments are conducted on two different plant disease datasets—tomato and cucumber—to demonstrate that YOLOv11n models equipped with αSiLU outperform their counterparts using the conventional SiLU function. Specifically, with α = 1.05, mAP@50 increased by 1.1% for tomato and 0.2% for cucumber, while mAP@50–95 improved by 0.7% and 0.2% each. Additional evaluations across various YOLO versions confirmed consistently superior performance. Furthermore, notable enhancements in precision, recall, and F1-score were observed across multiple configurations. Crucially, αSiLU achieves these performance improvements with minimal effect on inference speed, thereby enhancing its appropriateness for application in practical agricultural contexts, particularly as hardware advancements progress. This study highlights the efficiency of αSiLU in the plant disease-detection task, showing the potential in applying deep learning models in intelligent agriculture.

It is critical to provide proper environmental conditions in poultry houses to maintain birds’ health, boost productivity, and improve the overall economic viability of the poultry industry. Among the myriad of environmental elements, indoor air quality has been a determining factor that directly affects poultry well-being. Elevated concentrations of harmful gases—in particular Carbon Dioxide (CO2), Methane (CH4), and Ammonia (NH3)—decomposition products of poultry litter, feed wastage, and biological processes have draconian effects on bird health, feed efficiency, the growth rate, reproduction efficiency, and mortality rate. Despite their importance, traditional air quality monitoring systems are often operated manually, labor intensive, and cannot detect sudden environmental changes due to the lack of real-time sensing. To overcome these limitations, this paper presents an interdisciplinary approach combining cloud computing, Artificial Intelligence (AI), and Internet of Things (IoT) technologies to measure real-time poultry gas concentrations. Real-time sensor feeds are transmitted to a cloud-based platform, which stores, displays, and processes the data. Furthermore, a machine learning (ML) model was trained using historical sensory data to predict the next-day gas emission levels. A web-based platform has been developed to enable convenient user interaction and display the gas sensory readings on an interactive dashboard. Also, the developed system triggers automatic alerts when gas levels cross safe environmental thresholds. Experimental results of CO2 concentrations showed a significant diurnal trend, peaking in the afternoon, followed by the evening, and reaching their lowest levels in the morning. In particular, CO2 concentrations peaked at approximately 570 ppm during the afternoon, a value that was significantly elevated (p < 0.001) compared to those recorded in the evening (~560 ppm) and morning (~555 ppm). This finding indicates a distinct diurnal pattern in CO2 accumulation, with peak concentrations occurring during the warmer afternoon hours.