Search Results (108)

Objective: Given the global trend of ecological protection and sustainable development, Global Geoparks have become an essential platform for resource conservation and regional growth. Changzhi City in Shanxi Province, China, is actively applying for Global Geopark status, relying on its rich geoheritage sites, cultural history, and natural landscapes. This paper presents a systematic evaluation of the city’s geodiversity and relic value, analyzes the feasibility of establishing a Global Geopark in Changzhi City, and provides scientific support for Changzhi City’s Global Geopark application. Methods: Geodiversity data were collected by region using a 1:25,000 grid for sampling. Four methods were adopted for evaluation, namely, the Shannon diversity index, Simpson diversity index, entropy weight method (EWM), and Pielou evenness index. Upon comprehensive comparison of the four approaches, the most suitable approach was selected to produce the final results. For the value evaluation of the geoheritage, a combination of the analytic hierarchy process and the entropy weight method was employed. Results: (1) According to the results of all four methods, the geodiversity of Changzhi City is higher in the eastern and western regions and lower in the central area. (2) The geoheritage sites are mainly distributed in the eastern part of the city and have relatively high relic value. (3) Changzhi City contains abundant natural reserves and cultural resources, meeting the fundamental requirements for Global Geopark construction. Specifically, 38 townships across eight counties were identified as potential geopark areas, encompassing 54 geoheritage sites, 76 provincial-level or higher cultural-relic protection sites, and 15 provincial-level or higher natural protected areas, with a total area of 4458.51 km². Conclusions: Our results suggest that the Shannon diversity index is an effective tool for evaluating geodiversity in Changzhi City. Based on the region’s geological and natural conditions, the delineated geopark area is feasible. In summary, our findings provide essential references for the protection and sustainable development of geoheritage sites, geodiversity, and geoparks and offer strong theoretical and data support for Changzhi City’s Global Geopark application. Full article

In struggling against invasive species ravaging riverscape ecosystems, gaps in dispersal pathway knowledge and fragmented approaches across scales have long stalled effective riparian management worldwide. To reduce these limitations and enhance invasion management strategies, selecting appropriate alien species as models for in-depth pathway analysis is essential. Alternanthera philoxeroides (Mart.) Griseb. (alligator weed) emerges as an exemplary model species, boasting an invasion record of around 120 years spanning five continents worldwide, supported by genetic evidence of repeated introductions. In addition, the clonal reproduction of A. philoxeroides supports swift establishment, while its amphibious versatility allows occupation of varied riparian environments, with spread driven by natural water-mediated dispersal (hydrochory) and human-related vectors at multiple scales. Thus, leveraging A. philoxeroides, this review proposes a comprehensive multi-scale framework, which integrates monitoring with remote sensing, environmental DNA, Internet of Things, and crowdsourcing for real-time detection. Also, the framework can further integrate, e.g., MaxEnt (Maximum Entropy Model) for climatic suitability and mechanistic simulations of hydrodynamics and human-mediated dispersal to forecast invasion risks. Furthermore, decision-support systems developed from the framework can optimize controls like herbicides and biocontrol, managing uncertainties adaptively. At the global scale, the dispersal paradigm can employ AI-driven knowledge graphs for genetic attribution, multilayer networks, and causal inference to trace pathways and identify disruptions. Based on the premise that our multi-scale framework can bridge invasion ecology with riverscape management using A. philoxeroides as a model, we contend that the implementation of the proposed framework tackles core challenges, such as sampling biases, shifting environmental dynamics, eco–evolutionary interactions using stratified sampling, and adaptive online algorithms. This methodology is purposed to offer scalable tools for other aquatic invasives, evolving management from reactive measures to proactive, network-based approaches that effectively interrupt dispersal routes. Full article

Wearable inertial measurement units (IMUs) provide an accessible means of monitoring fatigue-related changes in running biomechanics, yet most existing methods rely on limited feature sets, lack personalization, or fail to generalize across individuals. This study introduces a bioinformatics-inspired stride sequence modeling framework that integrates spectral–entropy features, sample entropy, frequency-domain descriptors, and mixed-effects statistical modeling to detect fatigue using a single lumbar-mounted IMU. Nineteen recreational runners completed non-fatigued and fatigued 400 m runs, from which we extracted stride-level features and evaluated (1) population-level fatigue classification via global leave-one-participant-out (LOPO) models and (2) individualized fatigue detection through supervised participant-specific models and non-fatigued-only anomaly detection. Mixed-effects models revealed robust and multidimensional fatigue effects across key biomechanical features, with large standardized effect sizes (Cohen’s d up to 1.35) and substantial variance uniquely explained by fatigue (partial R² up to 0.31). Global LOPO machine learning models achieved modest accuracy (55%), highlighting strong inter-individual variability. In contrast, personalized supervised Random Forest classifiers achieved near-perfect performance (mean accuracy 97.7%; mean AUC 0.997), and NF-only One-Class SVMs detected fatigue as a deviation from individual baseline patterns (mean AUC 0.967). Entropy and stride-to-stride variability metrics further demonstrated consistent fatigue-linked increases in movement irregularity and reduced neuromuscular control. These findings show that IMU stride sequences contain highly informative, fatigue-sensitive biomechanical signatures, and that combining bioinformatics-inspired sequence analysis with hybrid statistical and personalized AI models enables both robust population-level insights and highly reliable individualized fatigue monitoring. The proposed framework supports future integration into sports analytics platforms, digital coaching systems, and real-time wearable fatigue detection technologies. This highlights the necessity of personalized fatigue-monitoring strategies in wearable systems. Full article

Sestrin2 (SESN2) is a highly conserved stress-inducible protein that serves as a central hub for integrating cellular responses to nutrient availability, oxidative stress, and endoplasmic reticulum (ER) stress. A key function of SESN2 is its role as a direct sensor for the branched-chain amino acid (BCAA) leucine, which modulates the activity of the mechanistic target of rapamycin complex 1 (mTORC1), a master regulator of cell growth and metabolism. While the functional link between leucine and SESN2 is well-established, the precise molecular determinants that confer its high specificity for leucine over other BCAAs, such as isoleucine and valine, remain poorly understood. This study employs an integrated computational approach, spanning atomic interactions to global protein dynamics, combining molecular docking, extensive all-atom molecular dynamics (MD) simulations, and binding free energy calculations, to elucidate the structural and dynamic basis of BCAA-SESN2 recognition. Our thermodynamic analysis reveals a distinct binding affinity hierarchy (Leucine > Isoleucine > Valine), which is primarily driven by superior van der Waals interactions and the shape complementarity of leucine’s isobutyl side chain within the protein’s hydrophobic pocket. Critically, a quantitative analysis of the conformational ensemble reveals that leucine induces a dramatic collapse of the protein’s structural heterogeneity. This “conformational locking” mechanism funnels the flexible, high-entropy unbound protein—which samples 35 distinct conformations—into a sharply restricted ensemble of just 9 stable states. This four-fold reduction in conformational freedom is accompanied by a kinetic trapping effect, which significantly lowers the rate of transitions between states. This process of conformational selection stabilizes a well-defined, signaling-competent structure, providing a comprehensive, atom-to-global-scale model of SESN2’s function. In the context of these findings, this work provides a critical framework for understanding SESN2’s complex role in disease and offers a clear rationale for the design of next-generation allosteric therapeutics. Full article

This paper introduces novel non-parametric entropy-based evidence functions and associated test statistics for assessing the dilation order of probability distributions constructed from cumulative residual entropy and cumulative entropy. The proposed evidence functions are explicitly tuned to questions about distributional variability and stochastic ordering, rather than global model fit, and are developed within a rigorous evidential framework. Their asymptotic distributions are established, providing a solid foundation for large-sample inference. Beyond their theoretical appeal, these procedures act as effective entropy-driven tools for quantifying statistical evidence, offering a compelling non-parametric alternative to traditional approaches, such as Kullback–Leibler discrepancies. Comprehensive Monte Carlo simulations highlight their robustness and consistently high power across a wide range of distributional scenarios, including heavy-tailed models, where conventional methods often perform poorly. A real-data example further illustrates their practical utility, showing how cumulative entropies can provide sharper statistical evidence and clarify stochastic comparisons in applied settings. Altogether, these results advance the theoretical foundation of evidential statistics and open avenues for applying cumulative entropies to broader classes of stochastic inference problems. Full article

Sitting posture recognition, defined as automatically localizing and categorizing seated human postures, has become essential for large-scale ergonomics assessment and longitudinal health-risk monitoring in classrooms and offices. However, in real-world multi-person scenes, pervasive occlusions and overlaps induce keypoint misalignment, causing global-attention backbones to fail to localize critical local structures. Moreover, annotation scarcity makes small-sample training commonplace, leaving models insufficiently robust to misalignment perturbations and thereby limiting cross-domain generalization. To address these challenges, we propose LAViTSPose, a lightweight cascaded framework for sitting posture recognition. Concretely, a YOLOR-based detector trained with a Range-aware IoU (RaIoU) loss yields tight person crops under partial visibility; ESBody suppresses cross-person leakage and estimates occlusion/head-orientation cues; a compact ViT head (MLiT) with Spatial Displacement Contact (SDC) and a learnable temperature (LT) mechanism performs skeleton-only classification with a local structural-consistency regularizer. From an information-theoretic perspective, our design enhances discriminative feature compactness and reduces structural entropy under occlusion and annotation scarcity. We conducted a systematic evaluation on the USSP dataset, and the results show that LAViTSPose outperforms existing methods on both sitting posture classification and face-orientation recognition while meeting real-time inference requirements. Full article

At present, with the increasing global awareness of sustainable development and environmental protection, significant attention has been directed toward the ecological living environment in rural areas. Selecting appropriate rural waste treatment methods is crucial for promoting the sustainable development of the rural ecological environment. Existing research reveals that, in certain regions—ecological conservation zones—there is a lack of targeted evaluation systems for rural waste treatment methods. Moreover, how regional characteristics can be integrated with quantitative assessment outcomes to inform specific treatment solutions remains relatively less explored. This study took Beigou Village in Huairou District, Beizhuang Town in Miyun District, Wangping Town in Mentougou District, and Dakezhuang Township in Yanqing District—all located within Beijing’s ecological conservation areas—as research subjects. It develops a suitability evaluation framework for rural waste treatment, encompassing five dimensions: economic investment, technological factors, environmental pollution, social benefits, and carbon emissions. This study combined the Analytic Hierarchy Process (AHP) and the entropy weight method to determine indicator weights. The fuzzy comprehensive evaluation method was then employed to calculate comprehensive scores and conduct a graded assessment. The evaluation results effectively differentiated the sample grades (e.g., Beigou Village received a comprehensive score of 2.373, rated as “Good”). Based on the evaluation results and field investigations, tailored solutions—including physical, thermal, recycling, and integrated treatment approaches—were proposed for each village and town. This study investigated the precise “evaluation–solution” matching for rural waste treatment in ecological conservation areas, demonstrating distinct novelty compared to previous research. It provides direct guidance for waste management in the four villages and towns within Beijing’s ecological conservation areas, thereby enhancing the efficiency of resource utilization in rural regions. Full article

Accurate and robust bearing fault diagnosis is crucial for the reliability of rotating machinery. To improve the precision of bearing fault classification, this study introduces a novel methodology that integrates the Adaptive t-distribution Slime Mold Algorithm (AtSMA) with the Least Squares Support Vector Machine (LSSVM). During the signal processing phase, Local Mean Decomposition (LMD) is employed to extract intrinsic mode functions from bearing vibration signals, which are subsequently reconstructed using the Pearson correlation coefficient method. Key features, such as sample entropy, permutation entropy, and energy entropy, are calculated to create a comprehensive feature vector for fault diagnosis. To enhance the convergence stability and global exploration capabilities of the Slime Mold Algorithm (SMA), an adaptive t-distribution mutation mechanism is incorporated to increase population diversity. Additionally, an improved step size strategy is implemented to prevent premature convergence and to expedite optimization speed. AtSMA is utilized to optimize the kernel parameters and penalty factor of LSSVM, thereby enhancing fault classification accuracy. Experimental evaluations conducted on two benchmark bearing datasets reveal that the proposed method achieves an average diagnostic accuracy of 96% on the Case Western Reserve University (CWRU) dataset and 93.25% on the Xi’an Jiaotong University dataset, surpassing conventional optimization algorithms and diagnostic techniques. These findings substantiate the superior diagnostic precision and robustness of the proposed approach under various fault scenarios and dynamic operating conditions. Full article

Micro-expressions are extremely subtle and short-lived facial muscle movements that often reveal an individual’s genuine emotions. However, micro-expression recognition (MER) remains highly challenging due to its short duration, low motion intensity, and the imbalanced distribution of training samples. To address these issues, this paper proposes a Global–Local Feature Fusion Network (GLFNet) to effectively extract discriminative features for MER. Specifically, GLFNet consists of three core modules: the Global Attention (LA) module, which captures subtle variations across the entire facial region; the Local Block (GB) module, which partitions the feature map into four non-overlapping regions to emphasize salient local movements while suppressing irrelevant information; and the Adaptive Feature Fusion (AFF) module, which employs an attention mechanism to dynamically adjust channel-wise weights for efficient global–local feature integration. In addition, a class-balanced loss function is introduced to replace the conventional cross-entropy loss, mitigating the common issue of class imbalance in micro-expression datasets. Extensive experiments are conducted on three benchmark databases, SMIC, CASME II, and SAMM, under two evaluation protocols. The experimental results demonstrate that under the Composite Database Evaluation protocol, GLFNet consistently outperforms existing state-of-the-art methods in overall performance. Specifically, the unweighted F1-scores on the Combined, SAMM, CASME II, and SMIC datasets are improved by 2.49%, 2.02%, 0.49%, and 4.67%, respectively, compared to the current best methods. These results strongly validate the effectiveness and superiority of the proposed global–local feature fusion strategy in micro-expression recognition tasks. Full article

Constructing the regional digital innovation ecosystem is not merely a strategic response to the global digital transformation but also an essential driver for fostering high-quality regional development. From the perspective of symbiosis and in combination with the theory of dissipative structure, and the evaluation index system of “digital innovation investment – digital innovation environment ” framework is constructed. Then, the evolution of the regional digital innovation ecosystem, characterized by dissipative processes, is analyzed using the “global entropy–catastrophe progression” evaluation model. Through empirical analysis of the dissipative evolution of digital innovation ecosystems across 30 Chinese provinces between 2013 and 2023, this study revealed that: (1) In the sample areas, the digital innovation ecosystem’s dynamic evolution meets the conditions required for forming a dissipative structure. (2) The level of digital innovation dissipation in the sample areas has generally shown an upward trend year by year. Still, no dissipation structure was formed during the research period. (3) There is an evolutionary trajectory from the third quadrant to the second quadrant and finally to the first quadrant is often shown by the two-dimensional framework of a “digital innovation investment-digital innovation environment” in the sample areas. Both the digital innovation environment and investment evaluation values exhibit an increased tendency. The results play a key role in strengthening China’s digital innovation ecosystem and promoting long-term social development. Full article

Cotton is a globally strategic crop that plays a crucial role in sustaining national economies and livelihoods. To address the challenges of accurate cotton field extraction in the complex planting environments of Xinjiang’s Alaer reclamation area, a cotton field identification model was developed that integrates multi-source satellite remote sensing data with machine learning methods. Using imagery from Sentinel-2, GF-1, and Landsat 8, we performed feature fusion using principal component, Gram–Schmidt (GS), and neural network techniques. Analyses of spectral, vegetation, and texture features revealed that the GS-fused blue bands of Sentinel-2 and Landsat 8 exhibited optimal performance, with a mean value of 16,725, a standard deviation of 2290, and an information entropy of 8.55. These metrics improved by 10,529, 168, and 0.28, respectively, compared with the original Landsat 8 data. In comparative classification experiments, the endmember-based random forest classifier (RFC) achieved the best traditional classification performance, with a kappa value of 0.963 and an overall accuracy (OA) of 97.22% based on 250 samples, resulting in a cotton-field extraction error of 38.58 km². By enhancing the deep learning model, we proposed a U-Net architecture that incorporated a Convolutional Block Attention Module and Atrous Spatial Pyramid Pooling. Using the GS-fused blue band data, the model achieved significantly improved accuracy, with a kappa coefficient of 0.988 and an OA of 98.56%. This advancement reduced the area estimation error to 25.42 km², representing a 34.1% decrease compared with that of the RFC. Based on the optimal model, we constructed a digital map of continuous cotton cropping from 2021 to 2023, which revealed a consistent decline in cotton acreage within the reclaimed areas. This finding underscores the effectiveness of crop rotation policies in mitigating the adverse effects of large-scale monoculture practices. This study confirms that the synergistic integration of multi-source satellite feature fusion and deep learning significantly improves crop identification accuracy, providing reliable technical support for agricultural policy formulation and sustainable farmland management. Full article

Deep learning models have obvious advantages in detecting oil spills, but the training of deep learning models heavily depends on a large number of samples of high quality. However, due to the accidental nature, unpredictability, and urgency of oil spill incidents, it is difficult to obtain a large number of labeled samples in real oil spill monitoring scenarios. Surprisingly, few-shot learning can achieve excellent classification performance with only a small number of labeled samples. In this context, a new cross-domain few-shot SAR oil spill detection network is proposed in this paper. Significantly, the network is embedded with a hybrid attention feature extraction block, which consists of a coordinate attention module to perceive the channel information and spatial location information, as well as a global self-attention transformer module capturing the global dependencies and a multi-scale self-attention module depicting the local detailed features, thereby achieving deep mining and accurate characterization of image features. In addition, to address the problem that it is difficult to distinguish between the suspected oil film in seawater and real oil film using few-shot due to the small difference in features, this paper proposes a double loss function category determination block, which consists of two parts: a well-designed category-perception loss function and a traditional cross-entropy loss function. The category-perception loss function optimizes the spatial distribution of sample features by shortening the distance between similar samples while expanding the distance between different samples. By combining the category-perception loss function with the cross-entropy loss function, the network’s performance in discriminating between real and suspected oil films is thus maximized. The experimental results effectively demonstrate that this study provides an effective solution for high-precision oil spill detection under few-shot conditions, which is conducive to the rapid identification of oil spill accidents. Full article

Groundwater nitrate (NO₃⁻) contamination has emerged as a critical global environmental issue, posing serious human health risks. This study systematically investigated the hydrochemical processes, sources of NO₃⁻ pollution, the impact of land use on NO₃⁻ pollution, and drinking water safety in an urban area of southwestern China. Thirty-one groundwater samples were collected and analyzed for major hydrochemical parameters and dual isotopic composition of NO₃⁻ (δ¹⁵N-NO₃⁻ and δ¹⁸O-NO₃⁻). The groundwater samples were characterized by neutral to slightly alkaline nature, and were dominated by the Ca-HCO₃ type. Hydrochemical analysis revealed that water–rock interactions, including carbonate dissolution, silicate weathering, and cation exchange, were the primary natural processes controlling hydrochemistry. Additionally, anthropogenic influences have significantly altered NO₃⁻ concentration. A total of 19.35% of the samples exceeded the Chinese guideline limit of 20 mg/L for NO₃⁻. Isotopic evidence suggested that primary sources of NO₃⁻ in groundwater include NH₄⁺-based fertilizer, soil organic nitrogen, sewage, and manure. Spatial distribution maps indicated that the spatial distribution of NO₃⁻ concentration correlated strongly with land use types. Elevated NO₃⁻ levels were observed in areas dominated by agriculture and artificial surfaces, while lower concentrations were associated with grass-covered ridge areas. The unabsorbed NH₄⁺ from nitrogen fertilizer entered groundwater along with precipitation and irrigation water infiltration. The direct discharge of domestic sewage and improper disposal of livestock manure contributed substantially to NO₃⁻ pollution. The nitrogen fixation capacity of the grassland ecosystem led to a relatively low NO₃⁻ concentration in the ridge region. Despite elevated NO₃⁻ and F⁻ concentrations, the entropy weighted water quality index (EWQI) indicated that all groundwater samples were suitable for drinking. This study provides valuable insights into NO₃⁻ source identification and hydrochemical processes across varying land-use types. Full article

Introduction: Federated Learning (FL) is a distributed machine learning paradigm where a global model is collaboratively trained across multiple decentralized clients without exchanging raw data. This is especially important in sensor networks and edge intelligence, where data privacy, bandwidth constraints, and data locality are paramount. Traditional FL methods like FedAvg struggle with highly heterogeneous (non-IID) client data, which is common in these settings. Background: Traditional FL aggregation methods, such as FedAvg, weigh client updates primarily by dataset size, potentially overlooking the informativeness or diversity of each client’s contribution. These limitations are especially pronounced in sensor networks and IoT environments, where clients may hold sparse, unbalanced, or single-modality data. Methods: We propose FedEmerge, an entropy-guided aggregation approach that adjusts each client’s impact on the global model based on the information entropy of its local data distribution. This formulation introduces a principled way to quantify and reward data diversity, enabling an emergent collective learning dynamic in which globally informative updates drive convergence. Unlike existing methods that weigh updates by sample count or heuristics, FedEmerge prioritizes clients with more representative, high-entropy data. The FedEmerge algorithm is presented with full mathematical detail, and we prove its convergence under the Polyak–Łojasiewicz (PL) condition. Results: Theoretical analysis shows that FedEmerge achieves linear convergence to the optimal model under standard assumptions (smoothness and PL condition), similar to centralized gradient descent. Empirically, FedEmerge improves global model accuracy and convergence speed on highly skewed non-IID benchmarks, and it reduces performance disparities among clients compared to FedAvg. Evaluations on CIFAR-10 (non-IID), Federated EMNIST, and Shakespeare datasets confirm its effectiveness in practical edge-learning settings. Conclusions: This entropy-guided federated strategy demonstrates that weighting client updates by data diversity enhances learning outcomes in heterogeneous networks. The approach preserves privacy like standard FL and adds minimal computation overhead, making it a practical solution for real-world federated systems. Full article

In recent years, the continuous development of deep learning has significantly advanced its application in the field of remote sensing. However, the semantic segmentation of high-resolution remote sensing images remains challenging due to the presence of multi-scale objects and intricate spatial details, often leading to the loss of critical information during segmentation. To address this issue and enable fast and accurate segmentation of remote sensing images, we made improvements based on SegNet and named the enhanced model CSNet. CSNet is built upon the SegNet architecture and incorporates a coordinate attention (CA) mechanism, which enables the network to focus on salient features and capture global spatial information, thereby improving segmentation accuracy and facilitating the recovery of spatial structures. Furthermore, skip connections are introduced between the encoder and decoder to directly transfer low-level features to the decoder. This promotes the fusion of semantic information at different levels, enhances the recovery of fine-grained details, and optimizes the gradient flow during training, effectively mitigating the vanishing gradient problem and improving training efficiency. Additionally, a hybrid loss function combining weighted cross-entropy and Dice loss is employed. To address the issue of class imbalance, several categories within the dataset are merged, and samples with an excessively high proportion of background pixels are removed. These strategies significantly enhance the segmentation performance, particularly for small-sample classes. Experimental results from the Five-Billion-Pixels dataset demonstrate that, while introducing only a modest increase in parameters compared to SegNet, CSNet achieves superior segmentation performance in terms of overall classification accuracy, boundary delineation, and detail preservation, outperforming established methods such as U-Net, FCN, DeepLabv3+, SegNet, ViT, HRNe and BiFormert. Full article