Search Results (47)

Determining the optimal harvest time is among the most critical economic decisions for peanut (Arachis hypogaea L.) growers, directly influencing yield, quality, and market value. Unlike many other crops, peanuts are indeterminate, continuing to flower and produce pods throughout their life cycle. As a result, pod development and maturation are asynchronous, making harvest timing particularly challenging. Conventional maturity estimation techniques, including the hull scrape method, pod blasting, and visual maturity profiling, are invasive, labor-intensive, time-consuming, and spatially limited. Moreover, differences in cultivar maturity rates and agroclimatic conditions exacerbate inconsistencies in maturity prediction. These challenges highlight the urgent need for scalable, objective, and data-driven methods to support growers in achieving optimal harvest outcomes. This review synthesizes the current understanding of peanut pod maturity and evaluates existing traditional and non-invasive approaches for maturity estimation. It aims to identify the limitations of conventional techniques and explore the integration of advanced sensing technologies, artificial intelligence (AI), and geospatial analytics to enhance precision and scalability in peanut maturity assessment and harvest decision-making. This review examines traditional destructive techniques such as the hull scrape method and pod blasting, followed by emerging non-invasive methods employing proximal and remote sensing platforms. Applications of vegetation indices, multispectral and hyperspectral imaging, and AI-based data analytics are discussed in the context of maturity prediction. Additionally, the potential of multimodal remote sensing data fusion and digital frameworks integrating spatial big data analytics, centralized data management, and cloud-based graphical interfaces is explored as a pathway toward end-to-end decision-support systems. Recent advances in non-invasive sensing and AI-assisted modeling have demonstrated significant improvements in scalability, precision, and automation compared with traditional manual approaches. However, their effectiveness remains constrained by the limited inclusion of agroclimatic, phenological, and cultivar-specific variables. Furthermore, the translation of model outputs into actionable, field-level harvest decisions is still underdeveloped, underscoring the need for integrated, user-centric digital infrastructure. Achieving a robust and transferable digital peanut maturity estimation system will require comprehensive ground-truth data across cultivars, regions, and growing seasons. Multidisciplinary collaborations among agronomists, data scientists, growers, and technology providers will be essential for developing practical, field-ready solutions. Integrating AI, multimodal sensing, and geospatial analytics holds immense potential to transform peanut maturity estimation. Such innovations promise to enhance harvest precision, economic returns, and sustainability while reducing manual effort and uncertainty, ultimately improving the efficiency and quality of life for peanut producers worldwide. Full article

The present study investigated the community composition and dynamics of freshwater biofouling on fiberglass inland waterway vessel (IWV) models coated with two commercial antifouling paints deployed in the Danube River (Serbia) for a total of five months. Biofouling was characterized using visual observations, in situ optical microscopy, the rapid ATP bioluminescence method, dry biomass measurements, and analyses of phototrophic and fungal communities. Based on the results, Hard Racing TecCel demonstrated the highest suppression of biofouling, with the lowest biomass accumulation and reduced algal diversity. At all stages of biofouling, diatoms dominated the phototrophic community, comprising 123 taxa. Achnanthidium minutissimum and Gomphonella olivacea were shown to be persistent hull colonizers, while Cyanobacteriophyta and Chlorophyta had reduced presence. Overall, the results highlight a slower progression of freshwater biofouling compared to marine systems and emphasize the need for the development of tailored antifouling strategies for IWVs to reduce environmental impact and operational costs. Full article

Severe foliage occlusion and dynamically changing lighting conditions in complex orchard environments pose significant challenges for visual perception systems in automated apple harvesting, including low detection accuracy, poor robustness, and insufficient real-time performance. To address these issues, this study proposes an improved lightweight detection network based on YOLOv11, named YOLO-WBL, along with a precise yield estimation algorithm based on 3D point clouds, termed CLV. The YOLO-WBL network is optimized in three aspects: (1) A C3K2_WT module integrating wavelet transform is introduced into the backbone network to enhance multi-scale feature extraction capability; (2) A weighted bidirectional feature pyramid network (BiFPN) is adopted in the neck network to improve the efficiency of multi-scale feature fusion; (3) A lightweight shared convolution separated batch normalization detection head (Detect-SCGN) is designed to significantly reduce the parameter count while maintaining accuracy. Based on this detection model, the CLV algorithm deeply integrates depth camera point cloud information through 3D coordinate mapping, irregular point cloud reconstruction, and convex hull volume calculation to achieve accurate estimation of individual fruit volume and total yield. Experimental results demonstrate that: (1) The YOLO-WBL model achieves a precision of 93.8%, recall of 79.3%, and mean average precision (mAP@0.5) of 87.2% on the apple test set; (2) The model size is only 3.72 MB, a reduction of 28.87% compared to the baseline model; (3) When deployed on an NVIDIA Jetson Xavier NX edge device, its inference speed reaches 8.7 FPS, meeting real-time requirements; (4) In scenarios with an occlusion rate below 40%, the mean absolute percentage error (MAPE) of yield estimation can be controlled within 8%. Experimental validation was conducted using apple images selected from the dataset under varying lighting intensities and fruit occlusion conditions. The results demonstrate that the CLV algorithm significantly outperforms traditional average-weight-based estimation methods. This study provides an efficient, accurate, and deployable visual solution for intelligent apple harvesting and yield estimation in complex orchard environments, offering practical reference value for advancing smart orchard production. Full article

Maritime ship target tracking plays an important role in applications such as maritime patrol and maritime surveillance. However, complex sea conditions, similar target appearances, and long-distance imaging often lead to target identity confusion and unstable trajectories. To address these issues, in this paper, a ship multi-object tracking algorithm, DeepSORT-OCR, that integrates hull number semantic features is proposed. Based on the YOLO detection framework and the DeepSORT tracking architecture, a CBAM-ResNet network is introduced to enhance the representation of ship appearance features. An Inner-SIoU metric is adopted to improve the geometric matching of slender ship targets, while an LSTM-Adaptive Kalman Filter is employed to model the nonlinear motion patterns of ships and improve trajectory prediction stability. In addition, a Hull Number Feature Extraction module is designed in order to recognize ship hull numbers using OCR and match them with a hull number database. The extracted hull number semantic features are dynamically fused with visual appearance features to strengthen identity constraints during target association. The experimental results show that the proposed method achieves an MOTA of 66.53% on the MOT16 dataset, representing an improvement of 5.13% over DeepSORT. On the self-constructed maritime ship dataset, the method achieves an MOTA of 70.89% and an MOTP of 80.84%. Furthermore, on the hull-number subset, the MOTA further increases to 77.18%, an improvement of 7.31% compared with DeepSORT, while the number of ID switches is significantly reduced. In addition, experiments conducted on pure real data, pure synthetic data, and cross-domain evaluation settings demonstrate the stability and strong generalization capability of the proposed algorithm under different data distributions. The proposed method effectively improves the stability and identity consistency of ship multi-object tracking in complex maritime environments. Full article

Although underwater gliders are highly energy-efficient platforms capable of long-duration and large-scale ocean observation, their lack of self-propulsion requires external assistance for recovery upon mission completion. In harsh and dynamic marine environments, reliably detecting the glider and accurately estimating its three-dimensional position are critical to ensuring the recovery operations are safe and efficient. This paper proposes a perception framework based on deep learning to detect underwater glider hulls and estimate their three-dimensional relative positions using camera–sonar multi-sensor fusion. This approach integrates a hierarchical convolutional neural network (CNN) vision encoder and a transformer-based architecture to estimate the glider’s spatial location and heading direction simultaneously. The hierarchical CNN encoder extracts multi-level, semantically rich visual features, thereby improving robustness to visual degradation and environmental disturbances common in underwater settings. Additionally, the transformer incorporates a variable mixture-of-experts (vMoE) mechanism that adaptively allocates expert networks across layers, enhancing representational capacity while maintaining computational efficiency. The resulting pose estimates enable precise, collision-free ROV navigation for automated recovery and onboard sensor inspection tasks. Experimental results, including ablation studies, validate the effectiveness of the proposed components and demonstrate their contributions to accurate glider hull detection and three-dimensional localization. Overall, the proposed framework provides a scalable, reliable perception solution that allows for the safe, autonomous recovery of underwater gliders with an ROV in realistic ocean environments. Full article

Machine learning (ML) methods have been widely explored for predicting material properties. However, due to the rapid development of ML techniques and the diversity of available models, performance comparisons between traditional and graph-based machine learning models remain limited. Therefore, we evaluate 11 conventional ML models alongside the graph neural network-based Crystal Graph Convolutional Neural Network (CGCNN) for predicting three key properties—formation energy (E_f), band gap (E_g), and energy above hull (E_h)—across a dataset comprising single perovskites, double perovskites, and their combined structures. The results demonstrate that for single perovskites, CGCNN exhibits gains of over 20% in the root mean square error (RMSE) relative to the second-best model (Gradient Boosting Regression), achieving values of 0.205 eV/atom (E_f), 0.718 eV (E_g), and 0.167 eV/atom (E_h). Prediction accuracy for double perovskites is significantly enhanced by training CGCNN on a combined dataset, particularly for E_h, where the coefficient of determination (R²) improves approximately 68.1-fold compared to models trained exclusively on double-perovskite data. Feature importance analysis via one-shot, permutation-based, and recursive feature elimination (RFE) methods reveals that optimal model performance requires retention of at least the top 20 critical features. Furthermore, feature utilization patterns of CGCNN across different prediction tasks are visualized. This work provides actionable guidelines for model selection and feature engineering in perovskite property prediction, establishing a benchmark for future ML-driven materials discovery. Full article

This research presents a large-scale thematic analysis of 66,002 Slovak university thesis abstracts, aimed at identifying, categorizing, and visualizing research trends across multiple academic disciplines. Using BERTopic for unsupervised topic modeling with K-Means clustering, 3000 distinct thematic clusters were extracted through rigorous coherence optimization, with each topic characterized by representative keywords derived from class-based TF-IDF weighting. Text embeddings were generated using SlovakBERT-STS, a domain-adapted Slovak BERT model fine-tuned for semantic textual similarity, producing 768-dimensional vectors that enable precise computation of cosine similarity between topics, resulting in a 3000 × 3000 topic similarity matrix. The optimal topic count was determined through systematic evaluation of K values ranging from 1000 to 10,000, with K = 3000 identified as the optimal configuration based on coherence elbow analysis, yielding a mean coherence score of 0.433. Thematic relationships were visualized through Multidimensional Scaling (MDS) projection to 3-D space, where convex hull geometries reveal semantic boundaries and topic separability. The methodology incorporates dynamic stopword filtering, Stanza-based lemmatization for Slovak morphology, and UMAP dimensionality reduction, achieving a balanced distribution of approximately 22 abstracts per topic. Results demonstrate that fine-grained topic models with 3000 clusters can extract meaningful semantic structure from multi-domain, morphologically complex Slovak academic corpora, despite inherent coherence constraints. The reproducible pipeline provides a framework for large-scale topic discovery, coherence-driven optimization, and geometric visualization of thematic relationships in academic text collections. Full article

Advancements in deep learning have revolutionized materials discovery by enabling predictive modeling of complex material properties. However, single-modal approaches often fail to capture the intricate interplay of compositional, structural, and morphological characteristics. This study introduces a novel multimodal deep learning framework for enhanced material property prediction, integrating textual (chemical compositions), tabular (structural descriptors), and image-based (2D crystal structure visualizations) modalities. Utilizing the Alexandriadatabase, we construct a comprehensive multimodal dataset of 10,000 materials with symmetry-resolved crystallographic data. Specialized neural architectures, such as FT-Transformer for tabular data, Hugging Face Electra-based model for text, and TIMM-based MetaFormer for images, generate modality-specific embeddings, fused through a hybrid strategy into a unified latent space. The framework predicts seven critical material properties, including electronic (band gap, density of states), thermodynamic (formation energy, energy above hull, total energy), magnetic (magnetic moment per volume), and volumetric (volume per atom) features, many governed by crystallographic symmetry. Experimental results demonstrated that multimodal fusion significantly outperforms unimodal baselines. Notably, the bimodal integration of image and text data showed significant gains, reducing the Mean Absolute Error for band gap by approximately 22.7% and for volume per atom by 22.4% compared to the average unimodal models. This combination also achieved a 28.4% reduction in Root Mean Squared Error for formation energy. The full trimodal model (tabular + images + text) yielded competitive, and in several cases the lowest, error metrics, particularly for band gap, magnetic moment per volume and density of states per atom, confirming the value of integrating all three modalities. This scalable, modular framework advances materials informatics, offering a powerful tool for data-driven materials discovery and design. Full article

This paper addresses the problem of automatically reconstructing three-dimensional coronary vessel trees from a series of X-ray angiography images, a task which remains difficult, particularly with respect to solutions requiring no additional user input. This study analyses the performance of a visual hull-based algorithm, producing the actual positions of heart arteries in the coordinate system, which is an approach not sufficiently explored in XRA images analysis. The proposed algorithm first creates a bounding cube using a novel heuristic and then iteratively projects the cube onto preprocessed 2D images, removing points too far from the depicted arteries. The method performance is first evaluated on a synthetic dataset through a series of experiments, and for a set of common clinical angles, 3D Dice of 75.25% and 78.61% reprojection Dice is obtained, which rivals the state-of-the-art machine learning methods. The findings suggest that the method offers a promising and interpretable alternative to black box methods on the synthethic dataset in question. Full article

To improve environmental sustainability and operational safety in maritime industries, the development of efficient methods for removing biofouling from submerged surfaces is critical. This study investigates the erosion mechanisms of cavitation jets as a non-contact, high-efficiency method for detaching marine organisms, including bacteria and larvae, from ship hulls and underwater infrastructure. Through erosion experiments on coated specimens, variations in jet morphology, and flow visualization using the Schlieren method, we examined how factors such as jet incident angle and nozzle configuration influence removal performance. The results reveal that erosion occurs not only at the direct jet impact zone but also in regions where cavitation bubbles exhibit intense motion, driven by pressure fluctuations and shock waves. Notably, single-hole jets with longer potential cores produced more concentrated erosion, while multi-jet interference enhanced bubble activity. These findings underscore the importance of understanding bubble distribution dynamics in the flow field and provide insight into optimizing cavitation jet configurations to expand the effective cleaning area while minimizing material damage. This study contributes to advancing biofouling removal technologies that promote safer and more sustainable maritime operations. Full article

LiDAR and camera sensors are widely utilized in autonomous vehicles (AVs) and robotics due to their complementary sensing capabilities—LiDAR provides precise depth information, while cameras capture rich visual context. However, effective multi-sensor fusion remains challenging due to discrepancies in resolution, data format, and viewpoint. In this paper, we propose a robust pattern matching algorithm that leverages singular value decomposition (SVD) and gradient descent (GD) to align geometric features—such as object contours and convex hulls—across LiDAR and camera modalities. Unlike traditional calibration methods that require manual targets, our approach is targetless, extracting matched patterns from projected LiDAR point clouds and 2D image segments. The algorithm computes the optimal transformation matrix between sensors, correcting misalignments in rotation, translation, and scale. Experimental results on a vehicle-mounted sensing platform demonstrate an alignment accuracy improvement of up to 85%, with the final projection error reduced to less than 1 pixel. This pattern-based SVD-GD framework offers a practical solution for maintaining reliable cross-sensor alignment under calibration drift, enabling real-time perception systems to operate robustly without recalibration. This method provides a practical solution for maintaining reliable sensor fusion in autonomous driving applications subject to long-term calibration drift. Full article

High-throughput image analysis is a key tool for the efficient assessment of quantitative plant phenotypes. A typical approach to the computation of quantitative plant traits from image data consists of two major steps including (i) image segmentation followed by (ii) calculation of quantitative traits of segmented plant structures. Despite substantial advancements in deep learning-based segmentation techniques, minor artifacts of image segmentation cannot be completely avoided. For several commonly used traits including plant width, height, convex hull, etc., even small inaccuracies in image segmentation can lead to large errors. Ad hoc approaches to cleaning ’small noisy structures’ are, in general, data-dependent and may lead to substantial loss of relevant small plant structures and, consequently, falsified phenotypic traits. Here, we present a straightforward end-to-end approach to direct computation of phenotypic traits from image data using a deep learning regression model. Our experimental results show that image-to-trait regression models outperform a conventional segmentation-based approach for a number of commonly sought plant traits of plant morphology and health including shoot area, linear dimensions and color fingerprints. Since segmentation is missing in predictions of regression models, visualization of activation layer maps can still be used as a blueprint to model explainability. Although end-to-end models have a number of limitations compared to more complex network architectures, they can still be of interest for multiple phenotyping scenarios with fixed optical setups (such as high-throughput greenhouse screenings), where the accuracy of routine trait predictions and not necessarily the generalizability is the primary goal. Full article

The International Maritime Organization (IMO) is the regulator for the safety and pollution prevention of ships. They have set an ambitious target of driving International Shipping to achieve net-zero greenhouse gas (GHG) emissions in 2050 by the process of decarbonization of shipping. Decarbonization of shipping is integral to sustainability, as it can reduce GHG emissions and provide a clean environment in a world that is conducive to the good health and well-being of our future kith and kin. Decarbonization of shipping may be achieved using alternate low-carbon fuels, a more efficient ship operation to save energy, or redesigning the ship’s hull. The purpose of this article is to conduct a bibliometric analysis of the research papers conducted in the past decade on the initiatives adopted by the shipping industry to work towards the net-zero goal. This study utilizes the Scopus database, renowned for its extensive collection of scientific papers. Moreover, to analyze and visualize the data, the bibliometric software tools VOSviewer 1.6.20, Bibliometrix 4.4.0, and Harzings’ 8.17.4863 have been used. These tools facilitated the assessment of the research output in this bibliometric study. Our findings reveal a steady increase in publications over the years, with a notable rise in research interest from 2015 onward. The most frequently discussed topics include greenhouse gases, emission control, and energy efficiency, with notable contributions from the United Kingdom, China, and Scandinavian countries. The study also highlights the leading journals publishing about this research area. Future research directions include exploring alternative fuels and more inclusive policy frameworks for maritime decarbonization. Full article

The foxtail millet exhibits a diverse range of hull colors, which are crucial indicators for assessing its nutritional and economic value. However, the molecular regulatory mechanisms that govern the hull color of foxtail millet are largely unknown at present. This gap in knowledge significantly impedes efforts to enhance the quality traits of foxtail millet. This study utilized a population of 250 F₆ recombinant inbred lines (RILs) generated from a cross between two foxtail millet varieties: Yugu18 (with light yellow seeds) and Hongjiugu19 (with red seeds). Four methods, the visual grouping method (I), the visual colorimetric method (II), the Lab determination method (III), and the RGB determination method (IV), were employed to determine the hull color of each line across four environments and QTL identification were conducted subsequently. It showed that there were 10, 12, 69 and 56 QTLs were detected for hull color through four methods, and these QTLs were integrated into 4, 6, 27 and 25 unique QTLs, respectively. There were three, four, four and four major QTLs. Of which, three major QTLs (qHC1.1, qHC1.2 and qHC9.3) on chromosomes 1 and 9 could be detected by all 4 methods. qHC9.1 was detected by all four methods except for method I. There were also one, one, seven and four minor identity QTLs identified across the 4 methods. Four minor QTLs (qHC3.1, qHC3.3, qHC4.1 and qHC5.1) can be stably detected only in method III, and two minor QTLs (qHC8.2 and qHC9.2) can be stably detected only in method IV. Generally, method I is fast, efficient and cost-effective, which is suitable for the rapid detection of hull color. Method II is also low-cost; however, it can detect more QTL for hull color, making it suitable for identifying major QTL loci in large populations. Methods III and IV can map more minor QTL and are more accurate in hull color characterization. This study identified four important hull color QTL for foxtail millet, which largely align with those reported in previous research. These findings establish a foundation for characterizing hull color indices and further advancing QTL mapping for grain color. Full article

The linear heating and formation of steel plates is one of the most critical technologies in shipbuilding. Excellent technology not only provides good hydrodynamics for the hull but also affects the whole hull construction cycle and cost. In the heating and formation of a steel plate, the material, size, and thickness of the steel plate; heating temperature; heating position; and many other factors affect the formation of a steel plate. It is a very difficult process to know the influence relationship between various factors. In this study, a steel plate model is established by the Gaussian regression method, which can predict the steel plate deformation according to the selected steel plate material, size and thickness, heating temperature, and heating position. The accuracy of the model was evaluated, and the Gaussian process regression model has a better accuracy compared to other machine learning algorithm models. Finally the model visualization; designing the UI; selecting the steel plate material, size, and thickness; and inputting the heating temperature, the deformation magnitude, and stress magnitude of the steel plate can be obtained. The model can provide guidance to field workers for the heating and formation of hull steel plates and achieve efficient and fast formation of target steel plates. Full article