Search Results (721)

Tea bud targets are typically located in complex environments characterized by multi-scale variations, high density, and strong color resemblance to the background, which pose significant challenges for rapid and accurate detection. To address these issues, this study presents YOLO-LMTB, a lightweight multi-scale detection model based on the YOLOv11n architecture. First, a Multi-scale Edge-Refinement Context Aggregator (MERCA) module is proposed to replace the original C3k2 block in the backbone. MERCA captures multi-scale contextual features through hierarchical receptive field collaboration and refines edge details, thereby significantly improving the perception of fine structures in tea buds. Furthermore, a Dynamic Hyperbolic Token Statistics Transformer (DHTST) module is developed to replace the original PSA block. This module dynamically adjusts feature responses and statistical measures through attention weighting using learnable threshold parameters, effectively enhancing discriminative features while suppressing background interference. Additionally, a Bidirectional Feature Pyramid Network (BiFPN) is introduced to replace the original network structure, enabling the adaptive fusion of semantically rich and spatially precise features via bidirectional cross-scale connections while reducing computational complexity. In the self-built tea bud dataset, experimental results demonstrate that compared to the original model, the YO-LO-LMTB model achieves a 2.9% improvement in precision (P), along with increases of 1.6% and 2.0% in mAP50 and mAP50-95, respectively. Simultaneously, the number of parameters decreased by 28.3%, and the model size reduced by 22.6%. To further validate the effectiveness of the improvement scheme, experiments were also conducted using public datasets. The results demonstrate that each enhancement module can boost the model’s detection performance and exhibits strong generalization capabilities. The model not only excels in multi-scale tea bud detection but also offers a valuable reference for reducing computational complexity, thereby providing a technical foundation for the practical application of intelligent tea-picking systems. Full article

Drawing from practices at Walmart, we model a supply chain where the manufacturer conducts product R&D while the retailer distributes products to two distinct consumer segments: green-conscious consumers who translate environmental principles into purchasing decisions, and non-green-conscious consumers who are deterred by perceived high costs and information deficits. The retailer engages in green education targeted at non-green-conscious consumers, providing clear product explanations to improve their willingness to pay for sustainable products, though this education is motivated by profit maximization rather than altruistic environmental responsibility. Our analysis reveals that while retailer green education can boost product R&D and adoption under certain conditions, this creates a ‘consumer education paradox’—a situation where green education could further enhance product R&D and adoption, but the retailer forgoes it because doing so does not contribute to profit. This occurs because profit-driven retailers limit education to self-beneficial ranges, creating tension between individual profit maximization and overall environmental performance. We then propose two government subsidy solutions—green product quantity subsidies and product R&D subsidies—to resolve this paradox. Both effectively alleviate the tension, but green innovation subsidies, despite requiring greater government investment, consistently outperform in fostering innovation and adoption, offering superior environmental outcomes. Full article

Coastal zones, as critical intersections of ecosystems, resource utilization, and socioeconomic activities, exhibit complex and diverse land cover types with frequent changes. Acquiring large-scale, high-quality annotated data in these areas is costly and time-consuming, which makes rule-based segmentation methods reliant on extensive annotations impractical. Few-shot semantic segmentation, which enables effective generalization from limited labeled samples, thus becomes essential for coastal region analysis. In this work, we propose an optimized few-shot segmentation method based on the Segment Anything Model (SAM) with a frozen-parameter segmentation backbone to improve generalization. To address the high visual similarity among coastal vegetation classes, we design a cross-matching module integrated with a hyper-correlation pyramid to enhance fine-grained visual correspondence. Additionally, a self-matching module is introduced to mitigate scale variations caused by UAV altitude changes. Furthermore, we construct a novel few-shot segmentation dataset, OUC-UAV-SEG-$2^{\mathrm{i}}$, based on the OUC-UAV-SEG dataset, to alleviate data scarcity. In quantitative experiments, the suggested approach outperforms existing models in mIoU and FB-IoU under ResNet50/101 (e.g., ResNet50’s 1-shot/5-shot mIoU rises by 4.69% and 4.50% vs. SOTA), and an ablation study shows adding CMM, SMM, and SAM boosts Mean mIoU by 4.69% over the original HSNet, significantly improving few-shot semantic segmentation performance. Full article

Blockchain technology has become a game changer in sectors like accounting and auditing. Its usage is still restricted due to a lack of insight into what drives people to adopt it for financial services like accounting and auditing. This research delves into the factors that influence the adoption of blockchain systems in accounting and auditing services by utilizing an enhanced edition of the Theory of Planned Behavior. In this study, alongside the previously established elements like Attitude, subjective norm, and Perceived Behavioral Control, self-perception and personal moral values are included to reflect how identity and ethics impact decision-making processes. Data were gathered via an online survey (N = 751) conducted on the Prolific platform, and the hypotheses were tested using Structural Equation Modeling. The hypotheses were examined through the Structural Equation Modeling method. The findings indicate that each of the five predictors plays a significant role in influencing Behavioral Intention, with personal moral values being the influential factor followed by subjective norm and Perceived Behavioral Control. Attitude plays an important role in shaping adoption choices and showcases the complexity involved in such decisions. As such, it is crucial to take into account ethical factors when encouraging the use of blockchain technology. This study adds to the existing knowledge of the Theory of Planned Behavior framework, offering insights for companies aiming to boost the implementation of blockchain systems in professional settings. Future research avenues and real-world implications are explored with an emphasis placed on developing targeted strategies that align technological adoption with personal values and organizational objectives. Full article

Ecosystems are nonlinear systems that can shift between multiple stable states. Ecosystem service bundles (ESBs) integrate the supply and trade-offs of multiple services, yet the conditions for achieving high-supply and balanced states remain unclear from a nonlinear, threshold-based perspective. In this study, six representative ecosystem services in Fujian Province were quantified, and ESBs were identified using a Self-Organizing Map (SOM). By integrating the Multiclass Explainable Boosting Machine (MC-EBM) with the API interpretable algorithm, we propose a framework for exploring ESB driving mechanisms from a nonlinear, threshold-based perspective, addressing two key questions: (1) Which factors dominate ESB formation? (2) What thresholds of these factors promote high-supply, balanced ESBs? Results show that (i) the proportion of water bodies, distance to construction land, annual solar radiation, annual precipitation, population density, and GDP density are the primary driving factors; (ii) higher proportions of water bodies enhance and balance multiple services, whereas intensified human activities significantly reduce supply levels, and ESBs are highly sensitive to climatic variables; (iii) at the 1 km × 1 km grid scale, optimal threshold ranges of the dominant factors substantially increase the likelihood of forming high-supply, balanced ESBs. The MC-EBM effectively reveals ESB formation mechanisms, significantly outperforming multinomial logistic regression in predictive accuracy and demonstrating strong generalizability. The proposed approach provides methodological guidance for multi-service coordination across regions and scales. Corresponding land management strategies are also proposed, which deepen understanding of ESB formation and offer practical references for enhancing ecosystem service supply and reducing trade-offs. Full article

Anxiety disorders represent a significant global health challenge, yet a substantial treatment gap persists, motivating the development of scalable digital health solutions. This study investigates the potential of integrating passive physiological data from consumer wearable devices with subjective self-reported surveys to predict state–trait anxiety. Leveraging the multi-modal, longitudinal LifeSnaps dataset, which captured “in the wild” data from 71 participants over four months, this research develops and evaluates a machine learning framework for this purpose. The methodology meticulously details a reproducible data curation pipeline, including participant-specific time zone harmonization, validated survey scoring, and comprehensive feature engineering from Fitbit Sense physiological data. A suite of machine learning models was trained to classify the presence of anxiety, defined by the State–Trait Anxiety Inventory (S-STAI). The CatBoost ensemble model achieved an accuracy of 77.6%, with high sensitivity (92.9%) but more modest specificity (48.9%). The positive predictive value (77.3%) and negative predictive value (78.6%) indicate balanced predictive utility across classes. The model obtained an F1-score of 84.3%, a Matthews correlation coefficient of 0.483, and an AUC of 0.709, suggesting good detection of anxious cases but more limited ability to correctly identify non-anxious cases. Post hoc explainability approaches (local and global) reveal that key predictors of state anxiety include measures of cardio-respiratory fitness (VO₂Max), calorie expenditure, duration of light activity, resting heart rate, thermal regulation and age. While additional sensitivity analysis and conformal prediction methods reveal that the size of the datasets contributes to overfitting, the features and the proposed approach is generally conducive for reasonable anxiety prediction. These findings underscore the use of machine learning and ubiquitous sensing modalities for a more holistic and accurate digital phenotyping of state anxiety. Full article

Complex marine infrared images, which suffer from background interference, blurred features, and indistinct contours, hamper detection accuracy. Meanwhile, the limited computing power, storage, and energy of maritime devices require target detection models suitable for real-time detection. To address these issues, we propose DSEE-YOLO (Dynamic Ship Edge-Enhanced YOLO), an efficient lightweight infrared ship detection algorithm. It integrates three innovative modules with pruning and self-distillation: the C3k2_MultiScaleEdgeFusion module replaces the original bottleneck with a MultiEdgeFusion structure to boost edge feature expression; the lightweight DS_ADown module uses DSConv (depthwise separable convolution) to reduce parameters while preserving feature capability; and the DyTaskHead dynamically aligns classification and localization features through task decomposition. Redundant structures are pruned via LAMP (Layer-Adaptive Sparsity for the Magnitude-Based Pruning), and performance is optimized via BCKD (Bridging Cross-Task Protocol Inconsistency for Knowledge Distillation) self-distillation, yielding a lightweight, efficient model. Experimental results show the DSEE-YOLO outperforms YOLOv11n when applied to our self-constructed IRShip dataset by reducing parameters by 42.3% and model size from 10.1 MB to 3.5 MB while increasing mAP@0.50 by 2.8%, mAP@0.50:0.95 by 3.8%, precision by 2.3%, and recall by 3.0%. These results validate its high-precision detection capability and lightweight advantages in complex infrared scenarios, offering an efficient solution for real-time maritime infrared ship monitoring. Full article

This study comprehensively evaluates the impact of remote work intensity on employee well-being, productivity, and sustainable practices within the IT sector, utilizing a cross-sectional online survey of 1003 employees. Findings reveal that remote work consistently boosts self-rated health, enhances perceived productivity, and promotes the adoption of sustainable workplace practices, with these benefits largely consistent across gender and most age groups. However, its effect on perceived stress is complex and significantly age-dependent, showing increased stress for younger employees (under 25) while mid-career professionals (26–35) experience stress reduction. Perceived stress did not emerge as a statistically significant mediator in the remote work-productivity relationship, suggesting that positive effects on productivity are primarily driven by direct mechanisms such as increased autonomy and flexibility. This research contributes to the Job Demands-Resources and Self-Determination Theory by illuminating how digital work demands and psychological needs are experienced heterogeneously across demographics in the remote context. Practical implications emphasize the need for differentiated stress management strategies tailored to younger employees, as well as a broader promotion of remote work, to enhance sustainable behavior within organizations. Methodologically, the study highlights the value of utilizing large, non-probability datasets, along with carefully constructed proxy scales, and proposes the future integration of AI-powered analytics for deeper insights. Full article

Pharmacy and nursing professions collaborate closely in healthcare settings. Effective interprofessional practice is now widely recognised as essential for achieving optimal patient care outcomes. Little has been published on nursing-pharmacy Interprofessional learning (IPL) in a simulated environment in Australian contexts. This study aimed to evaluate whether an IPL activity improved participants’ communication confidence, role understanding, clinical knowledge, and preparedness for hospital placement, while also assessing student satisfaction and identifying areas for improvement. A pedagogically structured teaching and learning model was developed, involving a high-fidelity on-campus simulated hospital ward, supplemented with a virtual online environment to immerse nursing and pharmacy students in a realistic clinical environment to achieve deep learning in preparation for safe practice. An online anonymous survey was conducted to evaluate participants’ experience and preparedness following the simulation. 280 students participated and 52 completed the evaluation. Most students reported that the experience boosted their confidence in communicating with other healthcare professionals (82%), increased clinical/therapeutic knowledge (86%), gave them a better understanding of the roles of nurses/pharmacists within the hospital setting (88%) and left them feeling better prepared for hospital placement (85%). Student free-text responses from the evaluation survey further supported the expansion of the IPL sessions in the future. IPL involving nursing and pharmacy students in a simulated hospital builds confidence in communicating and increases self-reported preparedness for placement. Full article

Low-voltage series arc faults pose a significant threat to power system safety due to their random, nonlinear, and non-stationary characteristics. Traditional detection methods often suffer from low sensitivity and poor robustness under complex load conditions. To address these challenges, this paper proposes a novel detection framework based on Random Forest (RF) feature selection, Adaptive Boosting (Adaboost) classification, and SHapley Additive exPlanations (SHAP) interpretability. First, RF is employed to rank and select the most discriminative features from arc fault current signals. Then, the selected features are input into an Adaboost classifier to enhance the detection accuracy and generalization capability. Finally, SHAP values are introduced to quantify the contribution of each feature, improving the transparency and interpretability of the model. Experimental results on a self-built arc fault dataset demonstrate that the proposed method achieves an accuracy of 97.1%, outperforming five widely used traditional classifiers. The integration of SHAP further reveals the physical relevance of key features, providing valuable insights for practical applications. This study confirms that the proposed RF-Adaboost-SHAP framework offers both high accuracy and interpretability, making it suitable for real-time arc fault detection in complex load scenarios. Full article

Polyaspartic ester polyurea (PEP) elastomers are highly promising for self-healable protective coatings in industrial applications, yet their broader adoption is limited by insufficient mechanical and corrosion resistance. Herein, we develop a multifunctional PEP nanocomposite by incorporating Jeffamine D2000-functionalized graphene nanoplatelets (F-GNPs), prepared through a one-step mechanochemical process. This strategy promotes strong interfacial bonding and uniform dispersion, yielding synergistic property enhancements. At an optimal loading of 0.3 wt%, the PEP/F-GNP nanocomposite exhibited a substantial performance enhancement, with its tensile and tear strengths augmented by 263.0% and 64.2%, respectively. Moreover, the resulting coating delivered an 84.0% boost in impact resistance on aluminum alloy, along with enhanced substrate adhesion. Electrochemical and salt spray tests further confirmed its exceptional anti-corrosion performance. While the reinforcement strategy presented a classic trade-off with self-healing, it is critical to note that the nanocomposite preserved a high healing efficiency of 83.3% after impact damage. Overall, this scalable interfacial engineering strategy simultaneously enhances the material’s mechanical robustness and protective performance, while striking a favorable balance with its intrinsic self-healing capability, paving the way for next-generation coatings. Full article

This study presents the design and implementation of a crop environmental monitoring system powered by a plant–soil bioelectrochemical energy source. The system integrates a Cu–Zn electrode power unit, a boost converter, a supercapacitor-based energy management module, and a wireless sensing node for real-time monitoring of environmental parameters. Unlike conventional plant microbial fuel cells (PMFCs), the output current originates partly from the galvanic effect of Cu–Zn electrodes and is further regulated by rhizosphere conditions and microbial activity. Under the optimal external load (900 Ω), the system achieved a maximum output power of 0.477 mW, corresponding to a power density of 0.304 mW·cm⁻². Stability tests showed that with the boost converter and supercapacitor, the system maintained a stable operating voltage sufficient to power the sensing node. Soil moisture strongly influenced performance, with higher water content increasing power by about 35%. Theoretical calculations indicated that Zn corrosion alone would limit the anode lifetime to ~66 days; however, stable output during the experimental period suggests contributions from plant–microbe interactions. Overall, this work demonstrates a feasible self-powered crop monitoring system and provides new evidence for the potential of plant–soil bioelectrochemical power sources in low-power applications. Full article

The health of electricity meters directly affects measurement accuracy and the interests of users. Traditional evaluation methods for electricity meters are limited by static error detection and manual calibration, and are unable to capture dynamic operating conditions or the complex influence of the power environment. To address this issue, this paper proposes an enhanced Cox proportional hazard (CoxPH) model based on Transformer for evaluating the health of electricity meters through a data-driven approach. This model integrates the data collected by the terminal (such as three-phase voltage, current, power, etc.) and operation and maintenance records. After data preprocessing, key covariates were extracted, including the average values of three-phase voltage and current fluctuations, current polarity reversal, and measurement error. The Transformer-based Cox proportional hazard (Trans CoxPH) model overcomes the linear assumption of the traditional CoxPH model by utilizing the self-attention and multi-head attention mechanisms of Transformer, and is able to capture the nonlinear relationships and time dependencies in time-series power data. Experimental results show that the performance of the Trans CoxPH model is superior to the traditional CoxPH model, temporal convolutional network-based Cox proportional hazard (TCN-CoxPH) model, extreme gradient boosting-based Cox proportional hazard (XGBoost CoxPH) model, and DeepSurvival long short-term memory (DeepSurvival LSTM) model. On the validation set, its concordance index (C-index) reaches 0.7827 with a Brier score of only 0.0501, significantly improving prediction accuracy and generalization ability. This model can effectively identify complex patterns and provides a reliable tool for the intelligent operation and maintenance of a power metering system. Full article

In the contexts of rapid urbanization and the Healthy China Strategy, understanding how the built environment affects residents’ health has become a pressing issue for the development of new rural communities. This study aims to investigate the associations between facility accessibility and residents’ health, and to provide evidence for health-oriented rural planning. Taking Pujiang County in Chengdu as the case study, we measured the accessibility of nine categories of facilities using GIS-based network analysis and evaluated residents’ health through the Self-Rated Health Measurement Scale (SRHMS). Gradient Boosting Decision Trees (GBDT) combined with SHAP interpretation were employed to examine and explain the influence of accessibility factors on health outcomes. The results indicate that the accessibility of road entrances, public toilets, garbage transfer points, schools, and community service centers is negatively associated with residents’ health, with variations across physical, mental, and social health dimensions. Moreover, social health is insufficiently explained by physical accessibility alone, implying the additional importance of social and cultural conditions. These findings offer practical guidance for optimizing facility layout and spatial design in new rural communities and provide an empirical basis for promoting health-oriented rural planning in China and similar contexts. Full article

Rolling bearing failures cause significant production downtime and economic losses. Traditional diagnostic methods suffer from low efficiency, suboptimal accuracy, and susceptibility to human subjectivity. To address these limitations, this paper proposes a novel bearing fault diagnosis (BFD) approach leveraging a Gated Recurrent Unit (GRU) network. Key contributions include: (1) Employing Bayesian optimization to automate the search for the optimal GRU architecture (layers, hidden units) and hyperparameters (learning rate, batch size, epochs), significantly enhancing diagnostic performance (achieving 97.9% accuracy). (2) Integrating a self-attention mechanism to further improve the GRU’s feature extraction capability from vibration signals, boosting accuracy to 99.6%. (3) Demonstrating the robustness of the optimized GRU with self-attention across varying motor speeds (1772 rpm, 1750 rpm, 1730 rpm), consistently maintaining diagnostic accuracy above 97%. Comparative studies with Bayesian-optimized Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) models confirm the superior accuracy (97.9% vs. 95.1% and 90.0%) and faster inference speed (0.27 s) of the proposed GRU-based method. The results validate that the combination of Bayesian optimization, GRU, and self-attention provides an efficient, accurate, and robust intelligent solution for automated BFD. Full article