Few-shot crop disease recognition using sequence- weighted ensemble model-agnostic meta-learning.

Diseases pose significant threats to crop production, leading to substantial yield reductions and jeopardizing global food security. Timely and accurate detection of crop diseases is essential for ensuring sustainable agricultural development and effective crop management. While deep learning-based computer vision techniques have emerged as powerful tools for crop disease recognition, these methods are heavily reliant on large datasets, which are often difficult to obtain in practical agricultural settings.

Enhanced denitrification and fouling control in hydrogen-based membrane biofilm reactor using novel flat membrane module.

In hydrogen-based membrane biofilm reactors (H-MBfR), the most critical concerns revolve removal rate and membrane fouling. This study introduces a novel flat membrane module to enhance denitrification efficiency and the operational stability of MBfR. The membrane module featured an additional layer of polyester material on outer side of the membrane.

Laccase immobilized on electrospun polyurethane/regenerated cellulose nanofiber membranes for efficient P-Chlorophenol degradation from wastewater.

Laccase has been the focus of extensive research in the field of pollutant degradation. However, its practical application is currently severely hampered by issues such as poor stability, proneness to inactivation, and recycling challenges. In this study, numerous laccase molecules were efficiently loaded onto the electrospun polyurethane/regenerated cellulose nanofiber membrane via metal ion coordination technique.

Assessing the Impact of Serum Per- and Polyfluoroalkyl Substance Concentrations on Immune Function in an Industrialized Region of China.

This study investigates the presence and health implications of per- and polyfluoroalkyl substances (PFAS) in human serum samples collected from white-collar workers in an industrialized region of China. Our research offers fresh insights into the underexplored area of nonoccupational PFAS exposure among white-collar workers, shedding light on health risks linked to industrial PFAS pollution. Seven PFAS compounds were measured.

Plasma club cell secretory protein reflects early lung injury: comprehensive epidemiological evidence.

Background: It is inaccurate to reflect the level of dust exposure through working years. Furthermore, identifying a predictive indicator for lung function decline is significant for coal miners. The study aimed to explored whether club cell secretory protein (CC16) levels can reflect early lung function changes.

CMTNet: a hybrid CNN-transformer network for UAV-based hyperspectral crop classification in precision agriculture.

Hyperspectral imaging acquired from unmanned aerial vehicles (UAVs) offers detailed spectral and spatial data that holds transformative potential for precision agriculture applications, such as crop classification, health monitoring, and yield estimation. However, traditional methods struggle to effectively capture both local and global features, particularly in complex agricultural environments with diverse crop types, varying growth stages, and imbalanced data distributions. To address these challenges, we propose CMTNet, an innovative deep learning framework that integrates convolutional neural networks (CNNs) and Transformers for hyperspectral crop classification.

EMSAM: enhanced multi-scale segment anything model for leaf disease segmentation.

Accurate segmentation of leaf diseases is crucial for crop health management and disease prevention. However, existing studies fall short in addressing issues such as blurred disease spot boundaries and complex feature distributions in disease images. Although the vision foundation model, Segment Anything Model (SAM), performs well in general segmentation tasks within natural scenes, it does not exhibit good performance in plant disease segmentation.

How is familial idiopathic scoliosis transmitted? Analysis of 26 pedigrees.

Background: Adolescent idiopathic scoliosis (AIS) is a three-dimensional deformity of the spine, affecting 1-3 % of the population, predominantly female patients, especially for severe curves. Its etiology is still debated, but a genetic involvement is certain, alongside with epigenetic and environmental factors. Isolated or sporadic cases are frequent, but AIS also affect families, with a reported heritability up to 38%.

Modeling daily evapotranspiration time series based on Non-Linear Autoregressive Exogenous (NARX) method and climate variables for a data-deficient region.

For flood-prone, developing nations where hydrological data is scarce, an innovative methodological approach is essential. This study aims to explore the potentiality of modelling daily evapotranspiration time series by checking causal relationship among the available climate variables in a flood-prone, data-deficient region like Samar in the Philippines. First, to verify if the available variables (rainfall, air pressure and the four (4) Niño Sea Surface Temperature (SST) Indices) have direct effects to evapotranspiration, a causality test called Convergent Cross-Mapping (CCM) was used.

Rationally Designed Cell Membrane Biomimetic Biosensing Platform for the Binding Analysis of Drugs with Intracellular Kinase Domain of Epidermal Growth Factor Receptor.

Biosensing technologies have demonstrated significant potential in exploring the binding of drugs to receptor tyrosine kinases (RTKs). As a typical transmembrane receptor, there are still several shortcomings in the utilization of the intracellular kinase domain of RTKs, the primary action site of small-molecule inhibitors, resulting in insufficient binding and unclear action sites, which impair the efficiency and accuracy of biosensing. Herein, using epidermal growth factor receptor (EGFR) as an example, we reported a biosensing platform based on cell membrane camouflage technology for evaluating drugs binding to the intracellular kinase domain of EGFR.

From laboratory to field: cross-domain few-shot learning for crop disease identification in the field.

Few-shot learning (FSL) methods have made remarkable progress in the field of plant disease recognition, especially in scenarios with limited available samples. However, current FSL approaches are usually limited to a restrictive setting where base classes and novel classes come from the same domain such as PlantVillage. Consequently, when the model is generalized to new domains (field disease datasets), its performance drops sharply.

Estimation of potato canopy leaf water content in various growth stages using UAV hyperspectral remote sensing and machine learning.

To ensure national food security amidst severe water shortages, agricultural irrigation must be reduced through scientific innovation and technological progress. Efficient monitoring is essential for achieving water-saving irrigation and ensuring the sustainable development of agriculture. UAV hyperspectral remote sensing has demonstrated significant potential in monitoring large-scale crop leaf water content (LWC).

Synergistic Treatment Approach for Pulmonary Fibrosis: Prednisone and Cyclophosphamide Regulation of Circular RNA MORF4L1 and MicroRNA-29a-3p Targeting BRD4.

This study aimed to explore the effect of prednisone (PDN) combined with cyclophosphamide (CTX) on bleomycin-induced pulmonary fibrosis (PF) in rats via circular RNA mortality factor 4 like 1 (MORF4L1)/microRNA (miR)-29a-3p/Bromodomain protein 4 (BRD4) axis. A rat model of PF was induced by bleomycin and treated with PDN combined with CTX, and the lentiviral vectors that interfered with MORF4L1, miR-29a-3p, or BRD4 expression were injected into the tail vein at the same time. The mRNA expressions of MORF4L1, miR-29a-3p, BRD4, and fibrosis-associated proteins including fibronectin, connective tissue growth factor, and collagen I were detected by real-time quantitative polymerase chain reaction.

A multi-source domain feature adaptation network for potato disease recognition in field environment.

Accurate identification of potato diseases is crucial for reducing yield losses. To address the issue of low recognition accuracy caused by the mismatch between target domain and source domain due to insufficient samples, the effectiveness of Multi-Source Unsupervised Domain Adaptation (MUDA) method in disease identification is explored. A Multi-Source Domain Feature Adaptation Network (MDFAN) is proposed, employing a two-stage alignment strategy.

Enhancement of livestock wastewater treatment by a novel wooden-modified biocarrier.

Intensive livestock wastewater poses threat to ecosystem. A novel wooden-modified biocarrier was applied in this study to enhance the livestock wastewater treatment in anoxic-aerobic systems. Compared to the ordinary polyethylene (PE) biocarrier, the novel wooden-modified biocarrier improved the biomass owing to its rough surface and porous side wall, and had better nitrogen removal ability.

Biomimetic heat-localized and solar absorption-enhanced hollow structural nanofibrous membrane for clean water production from saline water and dye wastewater.

The rational design of material structures can be an effective approach to enhance the performance of solar-driven clean water production. In this study, a hollow structural nanofibrous membrane was developed by mimicking the hollow structure of polar bear hair using coaxial electrospinning. The shell layer consisted of carbon nanoparticles (C NPs) decorated CuO nanosheets (C@CuO), that exhibited photothermal conversion capacity.

Effects of a novel sawdust-modified carrier on performance, bioaccumulation and microbial community of sequencing batch reactor.

The impact of a novel sawdust-modified carrier on the performance of aerobic sequencing batch reactor (SBR) was examined. Compared with the conventional polyethylene (PE) carrier, the sawdust-modified carrier had coarse surface and porous side wall, which was beneficial for the rapid formation of biofilm. The biomass of sawdust-modified carrier was 3.

Asymmetrically Wettable, PET/PA6, Hollow, Segmented-Pie, Microfiber Nonwovens for a Synthetic Leather Base.

PET/PA6, hollow, segmented-pie, microfiber nonwovens (PET/PA6 HSMNs) play an important role in a microfiber, synthetic leather base. Most of the current PET/PA6 HSMNs generally lack in hygiene performance. Moreover, there is an urgent need for the asymmetric wettability of PET/PA6 HSMNs to ensure the comfort of clothing.

Novel Biomimetic "Spider Web" Robust, Super-Contractile Liquid Crystal Elastomer Active Yarn Soft Actuator.

In nature, spider web is an interwoven network with high stability and elasticity from silk threads secreted by spider. Inspired by the structure of spider webs, light-driven liquid crystal elastomer (LCE) active yarn is designed with super-contractile and robust weavability. Herein, a novel biomimetic gold nanorods (AuNRs) @LCE yarn soft actuator with hierarchical structure is fabricated by a facile electrospinning and subsequent photocrosslinking strategies.

Few-shot disease recognition algorithm based on supervised contrastive learning.

Diseases cause crop yield reduction and quality decline, which has a great impact on agricultural production. Plant disease recognition based on computer vision can help farmers quickly and accurately recognize diseases. However, the occurrence of diseases is random and the collection cost is very high.