Search Results (33)

Changes in preservation conditions act as an important environmental filter driving shifts in microbial communities. However, the precise identities, functional traits, and ecological mechanisms of the dominant agents driving stage-specific deterioration remain insufficiently characterized. This study investigated microbial communities and dominant fungal degraders in waterlogged versus dried bamboo slips using amplicon sequencing, multivariate statistics, and microbial isolation. Results revealed compositionally distinct communities, with dried slips sharing only a small proportion of operational taxonomic units (OTUs) with waterlogged slips, while indicating the persistence of a subset of taxa across preservation states. A key discovery was the dominance of Fonsecaea minima (92% relative abundance) at the water-solid-air interface of partially submerged slips. Scanning electron microscopy (SEM) and pyrolysis-gas chromatography/mass spectrometry (Py-GC/MS) indicate that this fungus forms melanin-rich, biofilm-like surface structures, suggesting enhanced surface colonization and stress resistance. In contrast, the fungal community isolated from dried slips was characterized by Apiospora saccharicola associated with detectable xylanase activity. Meanwhile, the xerophilic species Xerogeomyces pulvereus dominated (99% relative abundance) the storage box environment. Together, these results demonstrate that preservation niches select for fungi with distinct functional traits, highlighting the importance of stage-specific preservation strategies that consider functional traits rather than taxonomic identity alone. Full article

The topic of archaeological apothekes, i.e., storage areas not intended for display and not accessible to the public (depositi in Italian), has only recently received the attention it deserves, for reasons related to the history of research methodology. The archiving of archaeological material poses specific problems compared to other categories of material with which the process is generally associated, such as artistic artefacts. Excavation finds consist mainly (and increasingly) of a mass of anonymous, repetitive pottery fragments, not destined to be accessible to the public. The management of these storage facilities poses two sets of problems linked with its archiving: on one hand, its (digital) documentation; on the other hand, its physical arrangement. Both aspects have often been contemplated, but as separate entities by different specialists (archaeologists, conservators, etc.). An adequate approach requires however both aspects to be considered together, for archaeological material only achieves its full value when its context of origin is secure. Only proper management of digital and physical archives can ensure a full understanding of the historical significance of archaeological material. These challenges also apply to the Archaeological Mission of Phaistos, in Crete, where Italian have been active since 1900. The reorganisation of the warehouses in 2024–2025 provided an opportunity to adequately address both the digital archiving of the material and the layout of the warehouses, tackling at the same time the particularly pressing issue in this case of the reuse of ‘legacy data’, which poses problems of standardization. This led also to a new perspective, using old labels and boxes as metadata to reconstruct the methods of archaeological research. The main results however were the creation of a holistic approach to the management of archaeological material and its (written, graphic, photographic, and topographic) documentation through the adoption and implementation of PyArchInit (version 4.9.5), a plug-in of QGIS (version 3.40.7 Bratislava). Full article

Accurate prediction of blast-induced air overpressure (AOp) is vital for environmental management and safety in mining and construction. Traditional empirical models are simple but fail to capture complex meteorological effects, while accurate black-box machine learning models lack interpretability, creating a significant dilemma for practical engineering. This study resolves this by applying explainable AI (XAI) to develop a transparent, “white-box” model that explicitly quantifies how meteorological parameters, wind speed, direction, and air temperature influence AOp. Using a dataset from an urban excavation site, the methodology involved comparing a standard USBM empirical model and a Multivariate Non-linear Regression (MNLR) model against a Symbolic Regression (SR) model implemented with the PySR tool. The SR model demonstrated superior performance on an independent test set, achieving an R² of 0.771, outperforming both the USBM (R² = 0.665) and MNLR (R² = 0.698) models, with accuracy rivaling a previous “black-box” neural network. The key innovation is SR’s ability to autonomously generate an explicit, interpretable equation, revealing complex, non-linear relationships between AOp and meteorological factors. This provides a significant engineering contribution: a trustworthy, transparent tool that enables engineers to perform reliable, meteorologically informed risk assessments for safer blasting operations in sensitive environments like urban areas. Full article

Harvesting winter jujubes is a key step in production, yet traditional manual approaches are labor-intensive and inefficient. To overcome these challenges, we propose SCC-YOLO, a lightweight method for winter jujube detection, 3D localization, and cross-platform deployment, aiming to support intelligent harvesting. In this study, RGB-D cameras were integrated with an improved YOLOv11 network optimized by ShuffleNetV2, CBAM, and a redesigned C2f_WTConv module, which enables joint spatial–frequency feature modeling and enhances small-object detection in complex orchard conditions. The model was trained on a diversified dataset with extensive augmentation to ensure robustness. In addition, the original localization loss was replaced with DIoU to improve bounding box regression accuracy. A robotic harvesting system was developed, and an Eye-to-Hand calibration-based 3D localization pipeline was implemented to map fruit coordinates to the robot workspace for accurate picking. To validate engineering applicability, the SCC-YOLO model was deployed on both desktop (PyTorch and ONNX Runtime) and mobile (NCNN with Vulkan+FP16) platforms, and FPS, latency, and stability were comparatively analyzed. Experimental results showed that SCC-YOLO improved mAP by 5.6% over YOLOv11, significantly enhanced detection precision and robustness, and achieved real-time performance on mobile devices while maintaining peak throughput on high-performance desktops. Field and laboratory tests confirmed the system’s effectiveness for detection, localization, and harvesting efficiency, demonstrating its adaptability to diverse deployment environments and its potential for broader agricultural applications. Full article

Strawberry, as an important global economic crop, its disease prevention and control directly affects yield and quality. Traditional detection means rely on manual observation or traditional machine learning algorithms, which have defects such as low efficiency, high false detection rate, and insufficient adaptability to tiny disease spots and complex environment. To solve the above problems, this study proposes a strawberry disease recognition method based on improved YOLOv8. By systematically acquiring 3146 image data covering seven types of typical diseases, such as gray mold and powdery mildew, a high-quality dataset containing different disease stages and complex backgrounds was constructed. Aiming at the difficulties in disease detection, the YOLOv8 model is optimized in two stages: on the one hand, the ultra-small scale detection head (32 × 32) is introduced to enhance the model’s ability to capture early tiny spots; on the other hand, the convolution and attention fusion module (CAFM) is combined to enhance the feature robustness in complex field scenes through the synergy of local feature extraction and global information focusing. Experiments show that the mAP50 of the improved model reaches 0.96 and outperforms mainstream algorithms such as YOLOv5 and Faster R-CNN in both recall and F1 score. In addition, the interactive system developed based on the PyQT5 framework can process images, videos and camera inputs in real time, and the disease areas are presented intuitively through visualized bounding boxes and category labels, which provides farmers with a lightweight and low-threshold field management tool. This study not only verifies the effectiveness of the improved algorithm but also provides a practical reference for the engineering application of deep learning in agricultural scenarios, which is expected to promote the further implementation of precision agriculture technology. Full article

Efficient and explainable vehicle damage inspection is essential due to the increasing complexity and volume of vehicular incidents. Traditional manual inspection approaches are not time-effective, prone to human error, and lead to inefficiencies in insurance claims and repair workflows. Existing deep learning methods, such as CNNs, often struggle with generalization, require large annotated datasets, and lack interpretability. This study presents a robust and interpretable deep learning framework for vehicle damage classification, integrating Vision Transformers (ViTs) and ensemble detection strategies. The proposed architecture employs a RetinaNet backbone with a ViT-enhanced detection head, implemented in PyTorch using the Detectron2 object detection technique. It is pretrained on COCO weights and fine-tuned through focal loss and aggressive augmentation techniques to improve generalization under real-world damage variability. The proposed system applies the Weighted Box Fusion (WBF) ensemble strategy to refine detection outputs from multiple models, offering improved spatial precision. To ensure interpretability and transparency, we adopt numerous explainability techniques—Grad-CAM, Grad-CAM++, and SHAP—offering semantic and visual insights into model decisions. A custom vehicle damage dataset with 4500 images has been built, consisting of approximately 60% curated images collected through targeted web scraping and crawling covering various damage types (such as bumper dents, panel scratches, and frontal impacts), along with 40% COCO dataset images to support model generalization. Comparative evaluations show that Hybrid ViT-RetinaNet achieves superior performance with an F1-score of 84.6%, mAP of 87.2%, and 22 FPS inference speed. In an ablation analysis, WBF, augmentation, transfer learning, and focal loss significantly improve performance, with focal loss increasing F1 by 6.3% for underrepresented classes and COCO pretraining boosting mAP by 8.7%. Additional architectural comparisons demonstrate that our full hybrid configuration not only maintains competitive accuracy but also achieves up to 150 FPS, making it well suited for real-time use cases. Robustness tests under challenging conditions, including real-world visual disturbances (smoke, fire, motion blur, varying lighting, and occlusions) and artificial noise (Gaussian; salt-and-pepper), confirm the model’s generalization ability. This work contributes a scalable, explainable, and high-performance solution for real-world vehicle damage diagnostics. Full article

The automated detection and classification of immature macauba (Acrocomia aculeata) fruits is critical for improving post-harvest processing and quality control. In this study, we present a comparative evaluation of two state-of-the-art YOLO architectures, YOLOv11x and YOLOv12x, trained on the newly constructed VIC01 dataset comprising 1600 annotated images captured under both background-free and natural background conditions. Both models were implemented in PyTorch and trained until the convergence of box regression, classification, and distribution-focal losses. Under an IoU (intersection over union) threshold of 0.50, YOLOv11x and YOLOv12x achieved an identical mean average precision (mAP₅₀) of 0.995 with perfect precision and recall or TPR (true positive rate). Averaged over IoU thresholds from 0.50 to 0.95, YOLOv11x demonstrated superior spatial localization performance (mAP_50–95 = 0.973), while YOLOv12x exhibited robust performance in complex background scenarios, achieving a competitive mAP_50–95. Inference throughput averaged 3.9 ms per image for YOLOv11x and 6.7 ms for YOLOv12x, highlighting a trade-off between speed and architectural complexity. Fused model representations revealed optimized layer fusion and reduced computational overhead (GFLOPs), facilitating efficient deployment. Confusion-matrix analyses confirmed YOLOv11x’s ability to reject background clutter more effectively than YOLOv12x, whereas precision–recall and F1-score curves indicated both models maintain near-perfect detection balance across thresholds. The public release of the VIC01 dataset and trained weights ensures reproducibility and supports future research. Our results underscore the importance of selecting architectures based on application-specific requirements, balancing detection accuracy, background discrimination, and computational constraints. Future work will extend this framework to additional maturation stages, sensor fusion modalities, and lightweight edge-deployment variants. By facilitating precise immature fruit identification, this work contributes to sustainable production and value addition in macauba processing. Full article

As a crucial characteristic waterfowl breed, the egg-laying performance of Lion-Headed Geese serves as a core indicator for precision breeding. Under large-scale flat rearing and selection practices, high phenotypic similarity among individuals within the same pedigree coupled with traditional manual observation and existing automation systems relying on fixed nesting boxes or RFID tags has posed challenges in achieving accurate goose–egg matching in dynamic environments, leading to inefficient individual selection. To address this, this study proposes YOLO-Goose, an improved YOLOv8s-based method, which designs five high-contrast neck rings (DoubleBar, Circle, Dot, Fence, Cylindrical) as individual identifiers. The method constructs a lightweight model with a small-object detection layer, integrates the GhostNet backbone to reduce parameter count by 67.2%, and employs the GIoU loss function to optimize neck ring localization accuracy. Experimental results show that the model achieves an F1 score of 93.8% and mAP50 of 96.4% on the self-built dataset, representing increases of 10.1% and 5% compared to the original YOLOv8s, with a 27.1% reduction in computational load. The dynamic matching algorithm, incorporating spatiotemporal trajectories and egg positional data, achieves a 95% matching rate, a 94.7% matching accuracy, and a 5.3% mismatching rate. Through lightweight deployment using TensorRT, the inference speed is enhanced by 1.4 times compared to PyTorch-1.12.1, with detection results uploaded to a cloud database in real time. This solution overcomes the technical bottleneck of individual selection in flat rearing environments, providing an innovative computer-vision-based approach for precision breeding of pedigree Lion-Headed Geese and offering significant engineering value for advancing intelligent waterfowl breeding. Full article

B-box (BBX) genes, as zinc finger transcription factors (TFs), play essential roles in regulating plant growth and development. In this study, we identified 23 BBX genes in the pomegranate (Punica granatum L.) genome. These genes were classified into five groups based on the distribution of conserved domains and phylogenetic relationships. Each PgBBX group exhibited similar molecular weights, theoretical isoelectric points (pI), gene structures, and conserved motif distributions compared with BBX members in Arabidopsis and Chinese white pear in corresponding groups. Syntenic analysis revealed segmental duplications of eight PgBBX gene pairs within the pomegranate genome. Additionally, twenty-seven and thirty-one orthologous BBX pairs were identified between PgBBX and AtBBX, and PgBBX and PbBBX, respectively. Promoter analysis revealed the presence of five types of cis-acting elements responding to light, phytohormones, stress, developmental signaling, and potential transcription factors (TFs). GO enrichment analysis confirmed that most PgBBX genes function as TF involved in plant growth and development. RNA-seq data indicated that PgBBX5 was primarily expressed in leaves and flowers, with increased expression in different fruit tissues during ripening. Moreover, PgBBX5 showed a high degree of sequence similarity with anthocyanin-related homologs, including AtBBX24, PhBBX24, FaBBX24, MdCOL4, and PyBBX24. During the ripening of ‘Tunisia’ fruits, PgBBX5 expression was positively correlated with the dynamic changes in anthocyanin content and the expression of key anthocyanin biosynthetic and transport genes. Furthermore, subcellular localization suggested that PgBBX5 encodes a nuclear-localized protein. This study provides a comprehensive characterization of the PgBBX family, offering valuable insights into the mechanisms underlying anthocyanin accumulation during pomegranate fruit ripening. Full article

Achieving superior circularly polarized luminescence brightness (B_CPL) is an important subject and continuous challenge for chiroptical materials. Herein, by applying a binary molecular design for the synthesis of chiral organo-Tb³⁺ molecules, a novel pair of mononuclear chiral tris-pyrazolate-Tb³⁺ enantiomers, [Tb(PMIP)₃(R,R-Ph-PyBox)] (2) and [Tb(PMIP)₃(S,S-Ph-PyBox)] (5), have been synthesized and characterized. The three 1-phenyl-3-methyl-4-(isobutyryl)-5-pyrazolone (HPMIP) ligands play the role of efficient luminescence sensitizers and strong light-harvesting antennas, while the enantiopure 2,6-bis(4-phenyl-2-oxazolin-2-yl) pyridine ligand (R,R/S,S-Ph-PyBox) is employed as the strong point-chiral inducer. With the proper combination of the HPMIP and Chiral-Ph-PyBox within the Tb³⁺ enantiomers, strong (PMIP)⁻-centered π-π^* electronic absorption (ε_{263 nm} = 38,400–39,500 M⁻¹ cm⁻¹) and brilliant high-purity ligand-sensitized Tb³⁺-centered green luminescence (Φ_PL = 47–48%) were observed. In addition, a clear circularly polarized luminescence (CPL) activity (|g_lum| = 0.096–0.103) was also observed, resulting in a strong B_CPL (610–623 M⁻¹ cm⁻¹) for the two Tb³⁺ enantiomers from the hypersensitive transitions. Our results offer an effective path to develop high-performance chiroptical organo-Tb³⁺ luminophores. Full article

In traffic scenes, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight convolutional layer using GhostConv and incorporates an enhanced C2f module to improve the network’s detection performance. Additionally, it integrates the Coordinate Attention module to better capture key points of the targets. Next, the bounding box loss function CIoU loss at the output of YOLOv5 is replaced with WiseIoU loss to enhance adaptability to various detection scenarios, thereby further improving accuracy. Finally, we develop a pedestrian count detection system using PyQt5 to enhance human–computer interaction. Experimental results on the INRIA public dataset showed that our algorithm achieved a detection accuracy of 98.4%, representing a 10.1% improvement over the original YOLOv5s algorithm. This advancement significantly enhances the detection of small objects in images and effectively addresses misdetection and omission issues in complex environments. These findings have important practical implications for ensuring traffic safety and optimizing traffic flow. Full article

Theano, TensorFlow, Keras, Torch, PyTorch, and other software frameworks have remarkably stimulated the popularity of deep learning (DL). Apart from all the good they achieve, the danger of such frameworks is that they unintentionally spur a black-box attitude. Some practitioners play around with building blocks offered by frameworks and rely on them, having a superficial understanding of the internal mechanics. This paper constitutes a concise tutorial that elucidates the flows of signals and gradients in deep neural networks, enabling readers to successfully implement a deep network from scratch. By “from scratch”, we mean with access to a programming language and numerical libraries but without any components that hide DL computations underneath. To achieve this goal, the following five topics need to be well understood: (1) automatic differentiation, (2) the initialization of weights, (3) learning algorithms, (4) regularization, and (5) the organization of computations. We cover all of these topics in the paper. From a tutorial perspective, the key contributions include the following: (a) proposition of R and S operators for tensors—rashape and stack, respectively—that facilitate algebraic notation of computations involved in convolutional, pooling, and flattening layers; (b) a Python project named hmdl (“home-made deep learning”); and (c) consistent notation across all mathematical contexts involved. The hmdl project serves as a practical example of implementation and a reference. It was built using NumPy and Numba modules with JIT and CUDA amenities applied. In the experimental section, we compare hmdl implementation to Keras (backed with TensorFlow). Finally, we point out the consistency of the two in terms of convergence and accuracy, and we observe the superiority of the latter in terms of efficiency. Full article

This paper investigates the seismic performance of thin-walled stiffened steel square box columns, modeling bridge piers subjected to unidirectional cyclic lateral loading with a constant axial load, focusing on local, global, and local-global interactive buckling phenomena. Initially, the finite element model was validated against existing experimental results. The study further explored the degradation in strength and ductility of both thin-walled and compact columns under cyclic loading. Thin-walled, stiffened steel square box columns exhibited buckling near the base, forming a half-sine wave shape. The research also addresses discrepancies from different material models used to analyze steel tubular bridge piers. Analysis using a modified two-surface plasticity model (2SM) yielded results closer to experimental data than a multi-linear kinematic hardening model, particularly for compact sections. The 2SM, which accounts for cycling within the yield plateau and strain hardening regime, demonstrated enhanced accuracy over the multi-linear kinematic hardening model. Additionally, a parametric study was conducted to assess the impact of key design parameters—such as width-to-thickness ratio (R_f), column slenderness ratio (λ), and magnitude of axial load (P/P_y)—on the performance of thin-walled stiffened steel square box columns. Design equations were then developed to predict the strength and ductility of bridge piers. These equations closely matched experimental results, achieving an accuracy of 95% for ultimate strength and 97% for ductility. Full article

cis-1-amino-2-indanol is an important building block in many areas of chemistry. Indeed, this molecule is currently used as skeleton in many ligands (BOX, PyBOX…), catalysts and chiral auxiliaries. Moreover, it has been incorporated in numerous bioactive structures. The major issues during its synthesis are the control of cis-selectivity, for which various strategies have been devised, and the enantioselectivity of the reaction. This review highlights the various methodologies implemented over the last few decades to access cis-1-amino-2-indanol in racemic and enantioselective manners. In addition, the various substitution patterns on the aromatic ring and their preparations are listed. Full article