DGS-Yolov7-Tiny: a lightweight pest and disease target detection model suitable for edge computing environments.

Pest detection is vital for maintaining crop health in modern agriculture. However, traditional object detection models are often computationally intensive and complex, rendering them unsuitable for real-time applications in edge computing. To overcome this limitation, we proposed DGS-YOLOv7-Tiny, a lightweight pest detection model based on YOLOv7-Tiny that was specifically optimized for edge computing environments.

A Portable and Thermally Degradable Hydrogel Sensor Based on Eu-Doped Carbon Dots for Visual and Ultrasensitive Detection of Ferric Ion.

Degradable fluorescent sensors present a promising portable approach for heavy metal ion detection, aiming to prevent secondary environmental pollution. Additionally, the excessive intake of ferric ions (Fe), an essential trace element for human health, poses critical health risks that urgently require effective monitoring. In this study, we developed a thermally degradable fluorescent hydrogel sensor (Eu-CDs@DPPG) based on europium-doped carbon dots (Eu-CDs).

Investigation of Cuttings Transport in a Reverse Circulation Drill Bit during Direction Drilling Using Two-Phase Flow Simulation.

Effective removal of cuttings from the central channel of the drill tool is critical for directional drilling using pneumatic down-the-hole hammers, yet the flow behavior of cuttings in reverse circulation drill bits remains unclear. This study establishes a validated Computational Fluid Dynamics (CFD) model that quantifies borehole cleaning efficiency through Eulerian-Eulerian two-phase flow simulation, enabling precise optimization of reverse circulation performance and cutting transport capacity under varying structural and operational conditions. The reliability of the simulation results is validated by a series of experiments.

Prediction model for chemical explosion consequences via multimodal feature fusion.

Chemical explosion accidents represent a significant threat to both human safety and environmental integrity. The accurate prediction of such incidents plays a pivotal role in risk mitigation and safety enhancement within the chemical industry. This study proposes an innovative Bayes-Transformer-SVM model based on multimodal feature fusion, integrating Quantitative Structure-Property Relationship (QSPR) and Quantitative Property-Consequence Relationship (QPCR) principles.

Ecological distribution, dissemination potential, and health risks of antibiotic resistance genes and mobile genetic elements in soils across diverse land-use types in China.

Antibiotic resistance genes (ARGs) have emerged as critical environmental contaminants, while mobile genetic elements (MGEs) act as key vectors facilitating their horizontal transfer, collectively posing growing challenges to ecosystem and public health. This study presents a comprehensive metagenomic investigation of ARGs and MGEs across 180 soil samples from five major land use types in China: farmland, forest, grassland, urban planting, and bare land. Among 862 identified ARG subtypes, 28 were detected in over 95 % of samples, indicating the presence of ecologically dominant and widely disseminated resistance elements.

BLTTNet: feature fusion based on BiLSTM-Transfomer-TCN for prediction of remaining useful life of aircraft engines.

Remaining useful life (RUL) prediction of aircraft engines is of great significance for the safety and reliability of aircraft operations. However, the high feature dimension and noise of the raw data cause difficulties for existing methods in extracting long sequence time features and allocating weights. In this study, we propose a RUL prediction network named BLTTNet with enhanced feature extraction ability to address these difficulties.

Singular Value Decomposition (SVD) Method for LiDAR and Camera Sensor Fusion and Pattern Matching Algorithm.

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.

Review of Research Progress on Dry Granulation Technology for Blast Furnace Slag.

Blast furnace slag, a high-temperature molten by-product generated during the ironmaking process in the metallurgical industry, has garnered significant attention for its resource utilization technologies. Compared to the traditional water-quenching method, dry granulation offers notable advantages. This paper systematically compares and analyzes the performance parameters of three typical dry treatment processes: mechanical crushing, air-quenching granulation, and centrifugal granulation.

Experimental study on the low-temperature performance and evaluation methods of crack sealants for asphalt pavements in seasonal frozen regions.

Road repair materials employed in the seasonal frozen regions of Northeastern China always often demonstrate poor long-term performance under extreme climate conditions. This is primarily attributed to the detrimental effects of short-term aging and frequent freeze-thaw cycles on the adhesive properties of sealants. Existing standards fail to adequately account for these complex environmental factors, leading to unsatisfactory repair outcomes.

Coupling Dy toroics in macrocycles.

A Dy complex with centrosymmetric edge-to-edge assembly of Dy triangles showing toroidal arrangement of the magnetic moments was encapsulated in a macrocycle.

Deep Learning-Assisted 3D Pressure Sensors for Control of Unmanned Aerial Vehicles.

Accurately and reliably detecting and recognizing human body movements in real time, relaying appropriate commands to the machine, have substantial implications for virtual reality, remote control, and robotics applications. Nonetheless, most contemporary wearable analysis and control systems attain action recognition by setting sensor thresholds. In routine usage, the stringent trigger conditions facilitate inadvertent contact, resulting in a poorer user experience.

Deep Learning Image Compression Method Based On Efficient Channel-Time Attention Module.

Remote monitoring of transmission lines plays a vital role in ensuring the stable operation of power systems, especially in regions with weak or unstable network signals, where efficient data transmission and storage are essential. However, traditional image compression methods face significant limitations in both quality and efficiency when applied to high-resolution imagery in such scenarios.To address these challenges, this paper proposes a deep learning-based image compression approach incorporating an Efficient Channel-Temporal Attention Module (ETAM).

Ecological Risk and Early Warning of PCBs in Central Jilin Province's Black Soil Zone, China.

To investigate the levels of polychlorinated biphenyls (PCBs) in the black soils of Northeast China, we collected 59 surface soil samples from the central black soil region of Jilin Province. We analyzed the concentrations and sources of seven PCBs in the black soil, assessed the ecological risks associated with PCB contamination, and provided a risk assessment for PCBs in this soil type. The mean concentrations of the seven PCBs (PCB28, PCB52, PCB101, PCB118, PCB138, PCB153, and PCB180) were as follows: 1.

Spatiotemporal influence analysis model for cultural landscapes based on a virtual geographic environment.

A cultural landscape can have a lasting impact on the surrounding region, significantly influencing its culture, customs, and development patterns. It is therefore important to understand the spatiotemporal influence range of a particular cultural landscape. The scope of influence is affected by subjective factors regarding the views, hobbies, communication, and cognitive abilities of all individuals involved in landscape interaction.

Multiview stereo reconstruction of UAV remote sensing images based on adaptive propagation with multiregional refinement.

Based on computer vision and image processing technologies, 3D reconstruction of ground or building targets can be achieved from drone images. However, current algorithms still have significant room for improvement in dense reconstruction of weak-textured areas. In order to enhance the reconstruction effect in weak texture regions, this paper proposes a multi-view stereo method for unmanned aerial vehicle (UAV) remote sensing images based on adaptive propagation and multi-region refinement, called APMRR-MVS.

Obstacle Avoidance Strategy and Path Planning of Medical Automated Guided Vehicles Based on the Bionic Characteristics of Antelope Migration.

Automated Guided Vehicles (AGVs) face dynamic and static obstacles in the process of transporting patients in medical environments, and they need to avoid these obstacles in real time. This paper proposes a bionic obstacle avoidance strategy based on the adaptive behavior of antelopes, aiming to address this problem. Firstly, the traditional artificial potential field and dynamic window algorithm are improved by using the bionic characteristics of antelope migration.

Dynamic failure mechanisms and hazard evaluation of rock collapse induced by extreme rainfall in Changbai County highways.

Rock collapses induced by extreme rainfall frequently occur along highways in Changbai County, posing serious threats to traffic safety and regional sustainable development. This study introduces a slope-unit zoning approach into the hazard assessment of collapses, integrating UDEC (Universal Distinct Element Code) numerical simulation and GIS (Geographic Information System) technology to reveal the failure mechanism and affected areas of slopes under extreme rainfall conditions. By employing the AHP-CV (Analytic Hierarchy Process-Coefficient of Variation) combined weighting method, the weights of nine critical indicators, including elevation, slope, slope direction, and NDVI (Normalized Difference Vegetation Index), were quantified.

Interpretable Machine Learning for Explaining and Predicting Collapse Hazards in the Changbai Mountain Region.

This study analyzes collapse hazards for complex interactions between geology, meteorology, and human activities in the Changbai Mountain region, focusing on how to cope with these features through machine learning. Using a dataset of 651 collapse events, this study evaluates four machine learning methods, Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), to deal with complex nonlinear data structures. To overcome the limitations of a single-feature selection method, a variance inflation factor is introduced to optimize the selection of collapse risk factors.

Spin polarized nodal loop state at Fermi level in the monolayer PrClS.

The investigation of two-dimensional materials exhibiting half-metallicity and topological features has become a rapidly growing area of interest, driven by their immense potential in nanoscale spintronics and quantum electronics. In this work, we present a comprehensive study of a two-dimensional PrClS monolayer, revealing its remarkable electronic and mechanical properties. Under its ferromagnetic ground state, the PrClS monolayer is shown to exhibit half-metallic behavior with 100% spin polarization originating from the spin-up channel.

ADAMT: Adaptive distributed multi-task learning for efficient image recognition in Mobile Ad-hoc Networks.

Distributed machine learning in mobile adhoc networks faces significant challenges due to the limited computational resources of devices, non-IID data distribution, and dynamic network topology. Existing approaches often rely on centralized coordination and stable network conditions, which may not be feasible in practice. To address these issues, we propose an adaptive distributed multi-task learning framework called ADAMT for efficient image recognition in resource-constrained mobile ad hoc networks.

Assessment of urban seismic social vulnerability based on game theory combination and TOPSIS model: a case study of Changchun City.

Earthquakes, as one of the common natural phenomena in China, can directly lead to the collapse of buildings and trigger secondary effects such as landslides and tsunamis, often resulting in significant property losses and casualties. Therefore, conducting seismic risk assessments for regions holds great practical significance. Current disaster research typically requires a comprehensive consideration of the probabilities of disaster-causing factors, the instability of disaster-prone environments, and the vulnerability of disaster-bearing entities.

OM-VST: A video action recognition model based on optimized downsampling module combined with multi-scale feature fusion.

Video classification, as an essential task in computer vision, aims to identify and label video content using computer technology automatically. However, the current mainstream video classification models face two significant challenges in practical applications: first, the classification accuracy is not high, which is mainly attributed to the complexity and diversity of video data, including factors such as subtle differences between different categories, background interference, and illumination variations; and second, the number of model training parameters is too high resulting in longer training time and increased energy consumption. To solve these problems, we propose the OM-Video Swin Transformer (OM-VST) model.

Risk assessment of land subsidence in Shanghai municipality based on AHP and EWM.

Urban land subsidence (LS) results in a reduction in ground elevation, compromising infrastructure integrity, disrupting the hydrological cycle, and posing significant risks to economic, demographic, and environmental security. This phenomenon is characterized by a certain degree of latency. In recent years, as Shanghai has undergone rapid urban expansion and high-density development, the issue of LS has become increasingly pronounced.

Assessment of ecological risks and spatiotemporal monitoring of heavy metal contamination in cultivated soils of the Liaohe River Basin, Jilin Province, China.

Ensuring the quality and safety of soil is crucial for achieving ecological sustainability. This study systematically analyzed and evaluated the ecological risks, early warning mechanisms, and mitigation strategies for heavy metals in the Liaohe River Basin of Jilin Province, employing methods such as multiple index models, environmental capacity prediction models, and spatiotemporal cube models. The results indicate that local soil heavy metals range from non-polluted to moderately polluted (0.

Stoichiometric analysis and control strategy of partial nitrification for treating dewatering liquid from food-waste methane fermentation.

Methane fermentation is critical for food-waste management; however, effective treatment of its high-ammonium dewatering liquid remains a major challenge. Anammox, a promising candidate for liquid treatment, requires effective pretreatment, such as partial nitrification (PN), to reduce ammonium and generate sufficient nitrite to optimize efficiency. In this study, an airlift reactor was employed to process the dewatering liquid from food-waste methane fermentation.