Search Results (1,833)

The hyperspectral image (HSI) is rich in spectral information and has important applications in the field of ground objects classification. However, HSI data have high dimensions and variable spatial–spectral features, which make it difficult for some models to adequately extract the effective features. Recent studies have shown that fusing spatial and spectral features can significantly improve accuracy by exploiting multi-dimensional correlations. Based on this, this article proposes a spectral integration and focused attention network (SIFANet) with a two-branch structure. SIFANet captures the local spatial features and global spectral dependencies through the parallel-designed spatial feature extractor (SFE) and spectral sequence Transformer (SST), respectively. A cross-module attention fusion (CMAF) mechanism dynamically integrates features from both branches before final classification. Experiments on the Salinas dataset and Xiong’an hyperspectral dataset show that the overall accuracy on these two datasets is 99.89% and 99.79%, which is higher than the other models compared. The proposed method also had the lowest standard deviation of category accuracy and optimal computational efficiency metrics, demonstrating robust spatial–spectral feature integration for improved classification. Full article

Non-AIDS-defining cancers (NADCs) have emerged as an increasingly prominent cause of non-AIDS-related morbidity and mortality among people living with HIV (PLWH). However, the scarcity of NADC clinical samples, compounded by privacy and security constraints, continues to present formidable obstacles to advancing pathological and clinical investigations. In this study, we adopted a joint analysis strategy and deeply integrated and analyzed transcriptomic data from 12,486 PLWH and cancer patients to systematically identify potential key regulators for 23 NADCs. This effort culminated in NADCdb—a database specifically engineered for NADC pathological exploration, structured around three mechanistic frameworks rooted in the interplay of immunosuppression, chronic inflammation, carcinogenic viral infections, and HIV-derived oncogenic pathways. The “rNADC” module performed risk assessment by prioritizing genes with aberrant expression trajectories, deploying bidirectional stepwise regression coupled with logistic modeling to stratify the risks for 21 NADCs. The “dNADC” module, synergized patients’ dysregulated genes with their regulatory networks, using Random Forest (RF) and Conditional Inference Trees (CITs) to identify pathogenic drivers of NADCs, with an accuracy exceeding 75% (in the external validation cohort, the prediction accuracy of the HIV-associated clear cell renal cell carcinoma model exceeded 90%). Meanwhile, “iPredict” identified 1905 key immune biomarkers for 16 NADCs based on the distinct immune statuses of patients. Importantly, we conducted multi-dimensional profiling of these key determinants, including in-depth functional annotations, phenotype correlations, protein–protein interaction (PPI) networks, TF-miRNA-target regulatory networks, and drug prediction, to deeply dissect their mechanistic roles in NADC pathogenesis. In summary, NADCdb serves as a novel, centralized resource that integrates data and provides analytical frameworks, offering fresh perspectives and a valuable platform for the scientific exploration of NADCs. Full article

The state of charge (SoC) is one of the critical parameters in battery management systems, as it directly determines the operational safety and reliability of batteries. To accurately predict the SoC of an electric forklift under varying operating conditions, two surrogate models, an improved Transformer and an improved Transformer 2, are developed. The experimental data obtained through real-vehicle tests are multi-dimensional and contain multiple sources of noise, resulting in poor prediction accuracy when only a single preprocessing algorithm is used. Therefore, this paper first discusses the effect of the preprocessing algorithms on SoC estimation. Compared with the original experimental data and the Kalman filter algorithm, the Kalman filter–principal component analysis (PCA) method is more suitable for preprocessing the original electric forklift data. The mean absolute error (MAE) and root mean square error (RMSE) of the improved Transformer model obtained using the Kalman filter – PCA method are reduced by 26.32% and 27.73% respectively, compared to the single Kalman method. Then, this study investigates the impact of data with different dimensions on the prediction performance of the improved Transformer mode. The results show that five-dimensional data can more effectively train the improved Transformer model, since the MAE decreases by 14.63% and 19.54%, and the RMSE decreases by 14.85% and 20.37% compared to three-dimensional and seven-dimensional data. Through the analysis of the improved Transformer model, an improved Transformer 2 model with higher prediction accuracy is obtained. Then, the improved Transformer 2 model is compared with the LSTM and CNN algorithms. The results indicate that the improved Transformer 2 model can predict SoC more stably and accurately than the single LSTM and CNN algorithms. Specifically, compared with the LSTM model, the proposed Transformer 2 model reduces the MAE by 77.16% and the RMSE by 91.75%. In comparison with the CNN model, the MAE is reduced by 71.81% and the RMSE by 80%. Full article

Background: Artificial intelligence (AI) is transforming medical practice, enhancing diagnostic accuracy, personalisation, and clinical efficiency. However, this transition raises complex ethical challenges related to transparency, accountability, fairness, and human oversight. This study examines how the literature conceptualises and distributes ethical responsibility in AI-assisted healthcare. Methods: This semi-systematic, theory-informed thematic review was conducted in accordance with the PRISMA 2020 guidelines. Publications from 2020 to 2025 were retrieved from PubMed, ScienceDirect, IEEE Xplore databases, and MDPI journals. A semi-quantitative keyword-based scoring model was applied to titles and abstracts to determine their relevance. High-relevance studies (n = 187) were analysed using an eight-category ethical framework: transparency and explainability, regulatory challenges, accountability, justice and equity, patient autonomy, beneficence–non-maleficence, data privacy, and the impact on the medical profession. Results: The analysis revealed a fragmented ethical landscape in which technological innovation frequently outperforms regulatory harmonisation and shared accountability structures. Transparency and explainability were the dominant concerns (34.8%). Significant gaps in organisational responsibility, equitable data practices, patient autonomy, and professional redefinition were reported. A multilevel ethical responsibility model was developed, integrating micro (clinical), meso (institutional), and macro (regulatory) dimensions, articulated through both ex ante and ex post perspectives. Conclusions: AI requires governance frameworks that integrate ethical principles, regulatory alignment, and epistemic justice in medicine. This review proposes a multidimensional model that bridges normative ethics and operational governance. Future research should explore empirical, longitudinal, and interdisciplinary approaches to assess the real impact of AI on clinical practice, equity, and trust. Full article

With the widespread adoption of renewable energy, distribution grids face increasing challenges in efficiency, safety, and economic performance due to stochastic generation and fluctuating load demand. Traditional operational models often exhibit limited adaptability, weak coordination, and insufficient holistic optimization, particularly in early-/mid-stage distribution planning where feeder-level network information may be incomplete. Accordingly, this study adopts a planning-oriented formulation and proposes a distributed energy storage system (DESS) planning strategy to enhance distribution network resilience under high uncertainty. First, representative wind and photovoltaic (PV) scenarios are generated using an improved Gaussian Mixture Model (GMM) to characterize source-side uncertainty. Based on a grid-based network partition, a priority index model is developed to quantify regional storage demand using quality- and efficiency-oriented indicators, enabling the screening and ranking of candidate DESS locations. A mixed-integer linear multi-objective optimization model is then formulated to coordinate lifecycle economics, operational benefits, and technical constraints, and a sequential connection strategy is employed to align storage deployment with load-balancing requirements. Furthermore, a node–block–grid multi-dimensional evaluation framework is introduced to assess resilience enhancement from node-, block-, and grid-level perspectives. A case study on a Zhejiang Province distribution grid—selected for its diversified load characteristics and the availability of detailed historical wind/PV and load-category data—validates the proposed method. The planning and optimization process is implemented in Python and solved using the Gurobi optimizer. Results demonstrate that, with only a 4% increase in investment cost, the proposed strategy improves critical-node stability by 27%, enhances block-level matching by 88%, increases quality-demand satisfaction by 68%, and improves grid-wide coordination uniformity by 324%. The proposed framework provides a practical and systematic approach to strengthening resilient operation in distribution networks. Full article

This paper introduces an iceberg-based digital risk twin (DRT) framework for the health monitoring of complex engineering systems. The proposed model transforms multidimensional sensor and contextual data into a structured, interpretable three-dimensional geometry that captures both observable and latent risk components. Each monitored parameter is represented as a vertical geometric sheet whose height encodes a normalized risk level, producing an evolving iceberg structure in which the visible and submerged regions distinguish emergent anomalies from latent degradation. A formal mathematical formulation is developed, defining the mappings from the risk vector to geometric height functions, spatial layout, and surface composition. The resulting parametric representation provides both analytical tractability and intuitive visualization. A case study involving an aircraft fuel system demonstrates the capacity of the DRT to reveal dominant risk drivers, parameter asymmetries, and temporal trends not easily observable in traditional time-series analysis. The model is shown to integrate naturally into AI-enabled health management pipelines, providing an interpretable intermediary layer between raw data streams and advanced diagnostic or predictive algorithms. Owing to its modular structure and domain-agnostic formulation, the DRT approach is applicable beyond aviation, including power grids, rail systems, and industrial equipment monitoring. The results indicate that the iceberg representation offers a promising foundation for enhancing explainability, situational awareness, and decision support in the monitoring of complex engineering systems. Full article

With the continuous expansion of high-density urban forms, residents’ opportunities for daily contact with natural environments have been increasingly reduced, making the equity of urban green space allocation a critical challenge for sustainable urban development. Existing studies have largely focused on green space quantity or accessibility at single time points, lacking systematic investigations into the spatiotemporal evolution of green space exposure (GSE) and its equity from the perspective of residents’ actual environmental experiences. GSE refers to the integrated level of residents’ contact with urban green spaces during daily activities across multiple dimensions, including visual exposure, physical accessibility, and spatial distribution, emphasizing the relationship between green space provision and lived environmental experience. Based on this framework, this study takes the central urban area of Hangzhou as the study area and integrates multi-temporal remote sensing imagery with large-scale street view data. A deep learning–based approach is developed to identify green space exposure, combined with spatial statistical methods and equity measurement models to systematically analyze the spatiotemporal patterns and evolution of GSE and its equity from 2013 to 2023. The results show that (1) GSE in Hangzhou increased significantly over the study period, with accessibility exhibiting the most pronounced improvement. However, these improvements were mainly concentrated in peripheral areas, while changes in the urban core remained relatively limited, revealing clear spatial heterogeneity. (2) Although overall GSE equity showed a gradual improvement, pronounced mismatches between low exposure and high demand persisted in densely populated areas, particularly in older urban districts and parts of newly developed residential areas. (3) The spatial patterns and evolutionary trajectories of equity varied significantly across different GSE dimensions. Composite inequity characterized by “low visibility–low accessibility” formed stable clusters within the urban core. This study further explores the mechanisms underlying green space exposure inequity from the perspectives of urban renewal patterns, land-use intensity, and population concentration. By constructing a multi-dimensional and temporally explicit analytical framework for assessing GSE equity, this research provides empirical evidence and decision-making references for refined green space management and inclusive, sustainable urban planning in high-density cities. Full article

Coalbed methane, an abundant clean energy resource in China, is gaining significant attention. Electric submersible progressive cavity pumps, ideal for downhole extraction with high solids content, are vital in coalbed methane operations. Current fault diagnosis research for these pumps mainly relies on machine learning algorithms to identify fault features, but complex working conditions and imbalanced sample distributions challenge these models’ ability to perceive multi-scale and multi-dimensional features. To enhance the model’s perception of deep abnormal data in complex multi-case industrial datasets, this study proposes a deep learning model based on a multi-scale extraction and residual module convolutional neural network. Innovatively, a cross-attention module using global autocorrelation and local cross-correlation is introduced to constrain the multi-scale feature extraction process, making the model better suited to specific and differentiated data environments. Post feature extraction, the model employs Borderline-SMOTE to augment minority class samples and uses Tomek Links for noise removal. These enhancements improve the comprehensive perception of fault types with significant differences in period, amplitude, and dimension, as well as the learning capability for rare faults. Based on field-collected fault data and using enhanced and cleaned features for classifier training, tests on a real industrial dataset show the proposed model achieves an F1 Measure of 90.7%—an improvement of 13.38% over the unimproved model and 9.15–31.64% over other common fault diagnosis models. Experimental results confirm the method’s effectiveness in adapting to extremely imbalanced sample distributions and complex, variable field data characteristics. Full article

Accurate quantification of forest aboveground biomass (AGB) is essential for monitoring terrestrial carbon stocks. While total AGB estimation is widely practiced, resolving component biomass such as canopy, branches, leaves, and trunks enhances the precision of carbon sink assessments and provides critical structural parameters for ecosystem modeling. Most studies rely on a single SAR sensor or a limited range of SAR features, which restricts their ability to represent vegetation structural complexity and reduces biomass estimation accuracy. Here, we propose a phased fusion strategy that integrates backscatter intensity, interferometric coherence, texture measures, and polarimetric decomposition parameters derived from dual-frequency ALOS-2, GF-3, and Sentinel-1A SAR data. These complementary multi-dimensional SAR features are incorporated into a Random Forest model optimized using an Adaptive Genetic Algorithm (RF-AGA) to estimate forest total and component estimation. The results show that the progressive incorporation of coherence and texture features markedly improved model performance, increasing the accuracy of total AGB to R² = 0.88 and canopy biomass to R² = 0.78 under leave-one-out cross-validation. Feature contribution analysis indicates strong complementarity among SAR parameters. Polarimetric decomposition yielded the largest overall contribution, while L-band volume scattering was the primary driver of trunk and canopy estimation. Coherence-enhanced trunk prediction increased R² by 13 percent, and texture improved canopy representation by capturing structural heterogeneity and reducing saturation effects. This study confirms that integrating coherence and texture information within the RF-AGA framework enhances AGB estimation, and that the differential contributions of multi-dimensional SAR parameters across total and component biomass estimation originate from their distinct structural characteristics. The proposed framework provides a robust foundation for regional carbon monitoring and highlights the value of integrating complementary SAR features with ensemble learning to achieve high-precision forest carbon assessment. Full article

Intimate relationship stability is fundamental to human wellbeing, yet its quantitative assessment faces dual challenges: the inherent subjectivity of psychological constructs and the complexity of social ecosystems. Symmetry, as a fundamental structural feature of social interaction, plays a pivotal role in shaping relational dynamics. To address these limitations, this study proposes an innovative computational framework that integrates Fuzzy Set Theory with Social Network Analysis (SNA). The framework consists of two complementary components: (1) a psychologically grounded fuzzy assessment model that employs differentiated membership functions to transform discrete subjective ratings into continuous and interpretable relationship quality indices and (2) an enhanced Fuzzy C-Means (FCM) threat detection model that utilizes Weighted Mahalanobis Distance to accurately identify and cluster potential interference sources within social networks. Empirical validation using a simulated dataset—comprising typical characteristic samples from 10 couples—demonstrates that the proposed framework not only generates interpretable relationship diagnostics by correcting biases associated with traditional averaging methods, but also achieves high precision in threat identification. The results indicate that stable relationships exhibit greater symmetry in partner interactions, whereas threatened nodes display structural and behavioural asymmetry. This study establishes a rigorous mathematical paradigm—“Subjective Fuzzification → Multidimensional Feature Engineering → Intelligent Clustering”—for relationship science, thereby advancing the field from descriptive analysis toward data-driven, quantitative evaluation and laying a foundation for systematic assessment of relational health. Full article

Accurate measurement of semantic similarity between geographic terms is a fundamental challenge in geographic information science, directly influencing tasks such as knowledge retrieval, ontology-based reasoning, and semantic search in geographic information systems (GIS). Traditional ontology-based approaches primarily rely on a narrow set of features (e.g., semantic distance or depth), which inadequately capture the multidimensional and context-dependent nature of geographic semantics. To address this limitation, this study proposes an ontology-driven semantic similarity model that integrates a backpropagation (BP) neural network with multiple ontological features—hierarchical depth, node distance, concept density, and relational overlap. The BP network serves as a nonlinear optimization mechanism that adaptively learns the contributions of each feature through cross-validation, balancing interpretability and precision. Experimental evaluations on the Geo-Terminology Relatedness Dataset (GTRD) demonstrate that the proposed model outperforms traditional baselines, including the Thesaurus–Lexical Relatedness Measure (TLRM), Word2Vec, and SBERT (Sentence-BERT), with Spearman correlation improvements of 4.2%, 74.8% and 80.1%, respectively. Additionally, comparisons with Linear Regression and Random Forest models, as well as bootstrap analysis and error analysis, confirm the robustness and generalization of the BP-based approach. These results confirm that coupling structured ontological knowledge with data-driven learning enhances robustness and generalization in semantic similarity computation, providing a unified framework for geographic knowledge reasoning, terminology harmonization, and ontology-based information retrieval. Full article

In the field of energy transformation, the application of batteries is widening. To address the challenge of health state estimation of energy storage batteries with multiple operating conditions, this study analyzes the aging cycle operation data of lithium-ion batteries and develops a scheme to extract a number of raw features and their corresponding health status labels. Multidimensional candidate feature sets that capture aging information under different conditions are constructed. Subsequently, a three-stage feature selection strategy, including Pearson and Spearman correlation analysis, hierarchical redundancy elimination, and minimum redundancy maximum relevance, was applied to screen the candidate feature set of each condition, resulting in customized feature sets with condition adaptability. By analyzing the occurrence frequency and mean absolute correlation coefficient of each feature within the custom feature set, a comprehensive feature set with multi-condition adaptability was screened and determined. On this basis, by integrating temporal sequence information and operating condition information, a dual-path fusion estimation model with attention mechanism and condition modulation was established. The validation results of the lithium-ion battery multi-condition cycling aging dataset demonstrate that the model achieves accurate health state estimation, with mean absolute error and root mean square error of 0.8281% and 0.9835%, respectively. Finally, comparisons with other methods were conducted in terms of feature selection strategies and model estimation performance. The results demonstrate that the proposed approach achieves superior estimation accuracy and enhanced interpretability. Full article

Adlay (Coix lacryma-jobi L.) stands out as a vital health-promoting cereal due to its dual nutritional and medicinal properties; however, it remains significantly underdeveloped compared to major crops. The lack of mechanistic understanding of its caryopsis development and trait formation severely constrains targeted genetic improvement. While transformative technologies, specifically micro-computed tomography (micro-CT) imaging combined with AI-assisted analysis (e.g., Segment Anything Model (SAM)) and multi-omics approaches, have been successfully applied to unravel the structural and physiological complexities of model cereals, their systematic adoption in adlay research remains fragmented. Going beyond a traditional synthesis of these methodologies, this article proposes a novel, multidimensional framework specifically designed for adlay. This forward-looking strategy integrates high-resolution 3D phenotyping with spatial multi-omics data to bridge the gap between macroscopic caryopsis architecture and microscopic metabolic accumulation. By offering a precise digital solution to elucidate adlay’s unique developmental mechanisms, the proposed framework aims to accelerate precision breeding and advance the scientific modernization of this promising underutilized crop. Full article

Fault diagnosis is a core technology ensuring the safe and efficient operation of industrial systems. A paradigm shift has been observed wherein traditional signal analysis has been replaced by intelligent, algorithm-driven approaches. In recent years, large language models, digital twins, and knowledge graphs have been introduced. A new stage of intelligent integration has been reached that is characterized by data-driven methods, knowledge guidance, and physical–virtual fusion. In the present paper, the evolutionary context of fault diagnosis technologies was systematically reviewed, with a focus on the theoretical methods and application practices of traditional machine learning, digital twins, knowledge graphs, and large language models. First, the research background, core objectives, and development history of fault diagnosis were described. Second, the principles, industrial applications, and limitations of supervised and unsupervised learning were analyzed. Third, innovative uses were examined involving physical–virtual mapping in digital twins, knowledge modeling in knowledge graphs, and feature learning in large language models. Subsequently, a multi-dimensional comparison framework was constructed to analyze the performance indicators, applicable scenarios, and collaborative potential of different technologies. Finally, the key challenges faced in the current fault diagnosis field were summarized. These included data quality, model generalization, and knowledge reuse. Future directions driven by the fusion of large language models, digital twins, and knowledge graphs were also outlined. A comprehensive technical map was established for fault diagnosis researchers, as well as an up-to-date reference. Theoretical innovation and engineering deployment of intelligent fault diagnosis are intended to be supported. Full article

Multi-dimensional inequality among rural residents has become a major obstacle hindering the achievement of global poverty alleviation goals. This study utilized household sample data from the China Family Panel Studies (CFPS) over four periods from 2014 to 2020 and applied them to a high-dimensional fixed effects model to estimate the impact of digital literacy on multi-dimensional inequality among rural residents. The results show that digital literacy can effectively alleviate the multi-dimensional inequality of rural residents. From the perspective of a mediating effect, digital literacy alleviates the multi-dimensional inequality of rural residents by improving the level of social capital and promoting social harmony. Moreover, the alleviation of multi-dimensional inequality among rural residents by digital literacy varies among different groups. The impact of digital literacy on the multi-dimensional inequality of agricultural workers and rural residents in western regions is relatively greater than that of non-agricultural workers and rural residents in other regions. Information processing literacy in digital literacy has the most significant impact on the multi-dimensional inequality of rural residents. This paper enriches the mechanism paths of digital literacy in alleviating the multi-dimensional inequality among rural residents in terms of both material and spiritual aspects, and provides a certain reference value for achieving the all-round development of rural residents and contributing to rural production practices. Full article