Search Results (48,226)

Understory-cultivated Panax ginseng possesses high pharmacological and economic value; however, its visual quality grading predominantly relies on subjective manual assessment, constraining industrial scalability. To address challenges including fine-grained morphological variations, boundary ambiguity, and complex natural backgrounds, this study proposes Ginseng-YOLO, a lightweight and deployment-friendly object detection model for automated ginseng grade classification. The model is built on the YOLOv11n (You Only Look Once11n) framework and integrates three complementary components: (1) C2-LWA, a cross-stage local window attention module that enhances discrimination of key visual features, such as primary root contours and fibrous textures; (2) ADown, a non-parametric downsampling mechanism that substitutes convolution operations with parallel pooling, markedly reducing computational complexity; and (3) Slide Loss, a piecewise IoU-weighted loss function designed to emphasize learning from samples with ambiguous or irregular boundaries. Experimental results on a curated multi-grade ginseng dataset indicate that Ginseng-YOLO achieves a Precision of 84.9%, a Recall of 83.9%, and an mAP@50 of 88.7%, outperforming YOLOv11n and other state-of-the-art variants. The model maintains a compact footprint, with 2.0 M parameters, 5.3 GFLOPs, and 4.6 MB model size, supporting real-time deployment on edge devices. Ablation studies further confirm the synergistic contributions of the proposed modules in enhancing feature representation, architectural efficiency, and training robustness. Successful deployment on the NVIDIA Jetson Nano demonstrates practical real-time inference capability under limited computational resources. This work provides a scalable approach for intelligent grading of forest-grown ginseng and offers methodological insights for the design of lightweight models in medicinal plants and agricultural applications. Full article

General large language models (LLMs) often suffer from semantic misinterpretation, information redundancy, and hallucinated content when applied to educational question-answering tasks. These issues hinder their effectiveness in supporting students’ specialized course learning and self-directed study. To address these challenges, this study proposes an intelligent tutoring model that integrates a knowledge graph with a large language model (KG-CQ). Focusing on the Data Structures (C Language) course, the model constructs a course-specific knowledge graph stored in a Neo4j graph database. It incorporates modules for knowledge retrieval, domain-specific question answering, and knowledge extraction, forming a closed-loop system designed to enhance semantic comprehension and domain adaptability. A total of 30 students majoring in Educational Technology at H University were randomly assigned to either an experimental group or a control group, with 15 students in each. The experimental group utilized the KG-CQ model during the answering process, while the control group relied on traditional learning methods. A total of 1515 data points were collected. Experimental results show that the KG-CQ model performs well in both answer accuracy and domain relevance, accompanied by high levels of student satisfaction. The model effectively promotes self-directed learning and provides a valuable reference for the development of knowledge-enhanced question-answering systems in educational settings. Full article

With the continuous maturation of prefabricated buildings, the errors and efficiency issues in the design of prefabricated buildings have gradually drawn the attention of architectural designers. The characteristics of standardized design for prefabricated buildings also provide a foundation for the application of computer-learning methods in the field of architectural design, thereby improving design quality and efficiency. This study combined BIM technology to construct the information data on prefabricated buildings, applied the transfer-learning method to build the training model, and utilized the traditional architectural design collision concept to construct a prediction model applicable to the collision detection of prefabricated building design. The training set and test set were constructed in a 9:1 ratio, and the loss function and accuracy function were calculated. The error rate of the model was verified to be within 10% through trial calculations based on engineering cases. The results show that, in the selected engineering cases, the collision detection accuracy of the model reached 90.3%, with an average absolute error (MAE) of 0.199 and a root mean square error (RMSE) of 0.245. The prediction error rate was controlled within 10%, representing an approximately 65% improvement in efficiency compared to traditional manual inspections. This method significantly improves the efficiency and accuracy of collision detection, providing reliable technical support for the optimization of prefabricated building design. Full article

Satellite monitoring of agricultural crops plays a crucial role in ensuring food security and in the sustainable management of agricultural resources, particularly in regions dominated by rainfed farming, such as the Turkestan region of Kazakhstan. Many satellite monitoring tasks rely on remote identification of different types of cultivated crops. In developing the proposed method, we accounted for the temporal characteristics of crop growth and development in various climatic zones of rainfed agriculture, analyzed the dynamics of the Normalized Difference Vegetation Index (NDVI) together with ground-based data, and identified effective time periods and patterns for successful crop recognition. This study aims to develop and comparatively assess two methods for the automatic identification of cultivated crops in rainfed zones using Sentinel-2 satellite data for the years 2018 and 2022. The first method is based on detailed classification of pre-digitized field boundaries, providing high accuracy in satellite-based mapping. The second method represents a fully automated approach applied to large rainfed areas, emphasizing operational efficiency and scalability. The results obtained from both methods were validated against official national statistics, ground-based field surveys, and farm-level data. The findings indicate that the field-boundary-based method delivers significantly higher accuracy (average accuracy of 91.1%). While the automated rainfed-zone approach demonstrates lower accuracy (78%), it still produces acceptable results for large-scale monitoring, confirming its suitability for rapid assessment of sown areas. This research highlights the trade-off between the accuracy achieved through detailed field boundary digitization and the efficiency provided by an automated, scalable approach, offering valuable tools for agricultural production management. Full article

Understanding the multi-crack coupling fracture behavior in brittle materials is particularly critical for aging dam infrastructure, where 78% of structural failures originate from crack network coalescence. In this study, we introduce the concepts of crack distance ratio (DR) and size ratio (SR) to describe the relationship between crack position and length and employ the discrete element method (DEM) for extensive numerical simulations. Specifically, a crack density function is introduced to assess microscale damage evolution, and the study systematically examines the macroscopic mechanical properties, failure modes, and microscale damage evolution of rock-like materials under varying DR and SR conditions. The results show that increasing the crack distance ratio and crack angle can inhibit the crack formation at the same tip of the prefabricated crack. The increase in the size ratio will promote the formation of prefabricated cracks on the same side. The increase in the distance ratio and size ratio significantly accelerate the rapid increase in crack density in the second stage. The crack angle provides the opposite effect. In the middle stage of loading, the growth rate of crack density decreases with the increase in crack angle. Overall, the size ratio has a greater influence on the evolution of microscopic damage. This research provides new insights into understanding and predicting the behavior of materials under complex stress conditions, thus contributing to the optimization of structural design and the improvement of engineering safety. Full article

Change detection technology holds significant importance in disciplines such as urban planning, land utilization tracking, and hazard evaluation, as it can efficiently and accurately reveal dynamic regional change processes, providing crucial support for scientific decision-making and refined management. Although deep learning methods based on computer vision have achieved remarkable progress in change detection, they still face challenges including reducing dynamic background interference, capturing subtle changes, and effectively fusing multi-temporal data features. To address these issues, this paper proposes a novel change detection model called OFNet. Building upon existing Siamese network architectures, we introduce an optical flow branch module that supplements pixel-level dynamic information. By incorporating motion features to guide the network’s attention to potential change regions, we enhance the model’s ability to characterize and discriminate genuine changes in cross-temporal remote sensing images. Additionally, we innovatively propose a dual-domain attention mechanism that simultaneously models discriminative features in both spatial and frequency domains for change detection tasks. The spatial attention focuses on capturing edge and structural changes, while the frequency-domain attention strengthens responses to key frequency components. The synergistic fusion of these two attention mechanisms effectively improves the model’s sensitivity to detailed changes and enhances the overall robustness of detection. Experimental results demonstrate that OFNet achieves an IoU of 83.03 on the LEVIR-CD dataset and 82.86 on the WHU-CD dataset, outperforming current mainstream approaches and validating its superior detection performance and generalization capability. This presents a novel technical method for environmental observation and urban transformation analysis tasks. Full article

Against the backdrop of the growing popularity of blockchain technology, this study investigates blockchain adoption strategies for the fresh food supply chain (FFSC) under a carbon cap-and-trade (CAT) policy. Taking a two-echelon supply chain consisting of a supplier and a retailer as an example, we designed four blockchain adoption modes based on the supplier’s strategy (adopt or not) and the retailer’s strategy (adopt or not). Combining influencing factors such as consumers’ low-carbon preference, consumers’ freshness preference, and carbon trading price (CTP), we established four game-theoretic models. Using backward induction, we derived the equilibrium strategies for the supplier and retailer under different modes and analyzed the impact of key factors on these equilibrium strategies. The analysis yielded four key findings: (1) BB mode (both adopt blockchain) is the optimal adoption strategy for both FFSC parties when carbon prices are high, and consumers exhibit strong dual preferences. It most effectively mitigates the negative price impact of rising carbon prices by synergistically enhancing emission reduction efforts and freshness preservation efforts, thereby increasing overall profits and achieving a Pareto improvement in the benefits for both parties. (2) Consumers’ low-carbon preference and freshness preference exhibit an interaction effect. These two preferences mutually reinforce each other’s incentive effect on FFSC efforts (emission reduction/freshness preservation). Blockchain’s information transparency makes these efforts more perceptible to consumers, forming a synergistic “emission reduction-freshness preservation” cycle that further drives sales and profit growth. (3) The adoption of blockchain by either the supplier or the retailer significantly lowers the cost threshold for the other party to adopt blockchain, thereby increasing their willingness to adopt. (4) CAT and consumer preferences jointly influence the adoption strategies of suppliers and retailers. Additionally, the adoption strategies of FFSC participants are also affected by the other party’s blockchain adoption status. Drawing on the above conclusions, this study provides actionable guidance for suppliers and retailers in selecting optimal blockchain adoption strategies. Full article

Digital ink Chinese characters (DICCs) written by international students often contain various errors and irregularities, making the recognition of these characters a highly challenging pattern recognition problem. This paper designs a graph convolutional network with agent attention (GCNAA) for recognizing DICCs written by international students. Each sampling point is treated as a vertex in a graph, with connections between adjacent sampling points within the same stroke serving as edges to create a Chinese character graph structure. The GCNAA is used to process the data of the Chinese character graph structure, implemented by stacking Block modules. In each Block module, the graph agent attention module not only models the global context between graph nodes but also reduces computational complexity, shortens training time, and accelerates inference speed. The graph convolution block module models the local adjacency structure of the graph by aggregating local geometric information from neighboring nodes, while graph pooling is employed to learn multi-resolution features. Finally, the Softmax function is used to generate prediction results. Experiments conducted on public datasets such as CASIA-OLWHDB1.0-1.2, SCUT-COUCH2009 GB1&GB2, and HIT-OR3C-ONLINE demonstrate that the GCNAA performs well even on large-category datasets, showing strong generalization ability and robustness. The recognition accuracy for DICCs written by international students reaches 98.7%. Accurate and efficient handwritten Chinese character recognition technology can provide a solid technical foundation for computer-assisted Chinese character writing for international students, thereby promoting the development of international Chinese character education. Full article

Class imbalance is a persistent limitation in polyp segmentation, commonly resulting in biased predictions and reduced accuracy in identifying clinically relevant structures. This study systematically evaluated 12 loss functions, including standard, weighted, and compound formulas, applied to colon polyp segmentation using the UNet-VGG16 fixed architecture on the Kvasir-SEG dataset. The encoder was frozen to isolate the effect of loss functions under the same training conditions. A fixed random seed was used in all experiments to ensure reproducibility and control variance during training. The results reveal that the combined loss functions, namely WBCE combined with Dice and Tversky combined with Focal, achieved the top Dice scores of 0.8916 and 0.8917, respectively. Tversky plus Focal also provided the highest sensitivity of 0.8885, and WBCE obtained the best average IoU of 0.8120. Tversky loss showed the lowest error rate of 4.99, indicating stable optimization. These results clarify the influence of loss function selection on segmentation performance in scenarios characterized by considerable class imbalance. Full article

False data injection attack (FDIA) by tampering with the sensor measurements is a big threat to the system’s observability. Power system state estimation (PSSE) is a critical observing function challenged by FDIAs in terms of its resiliency. Therefore, in this paper, we analyze the effectiveness of moving target defense (MTD) in enhancing the resiliency of PSSE against FDIAs. To begin with, the resiliency factor of PSSE against FDIAs is quantified using the relative estimation error against the injected measurement error. Then, the MTD is strategically designed to improve the resiliency factor by changing the line parameter and measurement case, for which the analytical results are provided. Furthermore, the infrastructure and operation costs caused by MTD are optimized to construct a cost-effective MTD. Finally, extensive simulations are conducted to validate the effectiveness of MTD in enhancing PSSE’s resiliency against FDIAs, which show that the MTD can improve the system’s resiliency factor by 10–20% and the generation cost can be reduced by about 10 USD/MWh after MTD. Full article

Downhole torsional vibrations, especially high-frequency torsional oscillations (HFTOs) and stick–slip phenomena, pose a serious threat to drilling operations, often resulting in tool damage, prolonged non-productive time, and significant cost increases. Traditional monitoring methods cannot promptly capture complex vibration patterns, so there is an urgent need for advanced early warning systems. This study proposes the DS-DW-TimesNet model, which improves the TimesNet framework by incorporating downsampling technology for efficient data compression, dilated convolution that can expand the temporal receptive field, and a learnable weight normalization method that can stabilize the training process, thereby enhancing the capabilities of feature extraction and long-sequence modeling. Verified using field data from the Fuman Oilfield, the results show that in terms of the mean absolute error (MAE) for 210 s predictions, this model is 77.2% and 21.8% lower than LSTM and Informer, respectively, and the inference speed is increased by 78.5% (reaching 48 milliseconds). It can provide reliable 210 s early warning windows for high-frequency torsional oscillations and 150 s early warning windows for stick–slip, exceeding industry standards and helping to improve the safety and efficiency of drilling operations. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that severely impacts motor function, necessitating early detection for effective management. However, current diagnostic methods are expensive and resource-intensive, limiting their accessibility. This study proposes a non-invasive, gait-based screening approach for PD using time-series analysis of video-derived motion data. Gait patterns indicative of PD are analyzed using videos containing walking sequences of PD subjects. The video data are processed via computer vision and human pose estimation techniques to extract key body points. Classification is performed using K-Nearest Neighbors (KNN) and Long Short-Term Memory (LSTM) networks in conjunction with time-series techniques, including Dynamic Time Warping (DTW), Bag of Patterns (BoP), and Symbolic Aggregate Approximation (SAX). KNN classifies based on similarity measures derived from these methods, while LSTM captures complex temporal dependencies. Additionally, Shapelet-based Classification is independently explored for its ability to serve as a self-contained classifier by extracting discriminative motion patterns. On a self-collected dataset (43 instances: 8 PD and 35 healthy), DTW-based classification achieved 88.89% accuracy for both KNN and LSTM. On an external dataset (294 instances: 150 healthy and 144 PD with varying severity), KNN and LSTM achieved 71.19% and 57.63% accuracy, respectively. The proposed approach enhances PD detection through a cost-effective, non-invasive methodology, supporting early diagnosis and disease monitoring. By integrating machine learning with clinical insights, this study demonstrates the potential of AI-driven solutions in advancing PD screening and management. Full article

Due to the huge network address space of IPv6, the overhead of IPv6 space detection is very large. Thus, how to improve the detection efficiency is a hot research topic. Firstly, the basic process of IPv6 network space detection is illustrated, and then the detection algorithms are categorized into two primary categories: optimization scanning-based detection algorithms and address generation-based detection algorithms. According to the timelines proposed by the algorithms, the ideas of these algorithms are discussed separately. Finally, a comprehensive comparison and analysis of these detection algorithms are conducted from multiple dimensions. Future research directions are discussed, including: collection of active IPv6 addresses and allocation patterns, discovery of IPv6 address detection patterns based on machine learning, improvement of the detection response rate, and moral issues caused by network detection. Full article

In recent years, solar energy has emerged as a pillar of sustainable development. However, maintaining panel efficiency under extreme environmental conditions remains a persistent hurdle. This study introduces an automated defect detection pipeline that leverages deep learning and computer vision to identify five standard anomaly classes: Non-Defective, Dust, Defective, Physical Damage, and Snow on photovoltaic surfaces. To build a robust foundation, a heterogeneous dataset of 8973 images was sourced from public repositories and standardized into a uniform labeling scheme. This dataset was then expanded through an aggressive augmentation strategy, including flips, rotations, zooms, and noise injections. A YOLOv11-based model was trained and fine-tuned using both fixed and adaptive learning rate schedules, achieving a mAP@0.5 of 85% and accuracy, recall, and F1-score above 95% when evaluated across diverse lighting and dust scenarios. The optimized model is integrated into an interactive dashboard that processes live camera streams, issues real-time alerts upon defect detection, and supports proactive maintenance scheduling. Comparative evaluations highlight the superiority of this approach over manual inspections and earlier YOLO versions in both precision and inference speed, making it well suited for deployment on edge devices. Automating visual inspection not only reduces labor costs and operational downtime but also enhances the longevity of solar installations. By offering a scalable solution for continuous monitoring, this work contributes to improving the reliability and cost-effectiveness of large-scale solar energy systems. Full article