Search Results (9,948)

Background: Strychnos madagascariensis Poir (Loganiaceae) is a drought-tolerant indigenous fruit tree of East and southern Africa, valued for its food, medicinal, and socio-economic contributions to rural communities. Despite its importance as a candidate food crop, intraspecific morphological and genetic diversity had not previously been characterized, and no simple sequence repeat (SSR) markers had been developed for this species, leaving breeders and conservation planners without the basic diversity baseline needed to prioritize material for domestication. Methods: This study assessed vegetative and reproductive trait variation, variance components, and broad-sense heritability, and SSR-based genetic diversity among 27 morphologically defined S. madagascariensis morphotypes at Bonamanzi Game Reserve, KwaZulu-Natal, South Africa. Three trees were measured per morphotype (81 trees total), over two growing seasons. Genetic diversity was characterized in one representative tree per morphotype using seventeen newly developed SSR loci, the first such markers reported for this species, and analyzed with population structure (STRUCTURE version 2.3.4), PCA, and Nei’s genetic distance. Results: Twenty-seven morphotypes were identified based on leaf colour, shape, hairiness and size, dominated by grey (41%), elongated (59%), less hairy (48%), and medium-sized (>50–90 mm) leaves. Fruit diameter and mass showed the highest inter-morphotype variation (r = 0.949) and also the highest broad-sense heritability (H² = 55.3% and 47.8%, respectively), indicating strong genetic control of these traits and their suitability as targets for selective breeding. Environmental variance exceeded genotypic variance for most traits. A total of 144 alleles were identified across 17 SSR loci (mean 4.24 alleles/locus; mean PIC = 0.31). Population structure gave a preliminary, tentative signal of two genetic clusters (K = 2) with substantial admixture, which we interpret cautiously, given the limited sampling depth. Conclusions: This is the first study to characterize intraspecific morphological variation in S. madagascariensis and the first to develop SSR markers for the species. The results provide a preliminary, single-site framework for conservation genetics and crop improvement that should be validated with larger, multi-site samples. Grey morphotypes GyEvH1, GyEvH2, GyEvH3, GyRlH1 and GyEH2 combined consistent fruiting performance with favourable fruit-trait values and are proposed as priority candidates for further evaluation in domestication and breeding programmes. Full article

Background/Aims: While pathogenic germline variants play a critical role in pediatric cancer susceptibility, traditional clinical genetics primarily focuses on single-gene interpretations. Transitioning to a systems-level analysis of inherited variation can uncover shared biological vulnerabilities, informing genetic counseling, surveillance, and targeted therapeutics. This study aims to implement an unsupervised machine learning framework to identify and characterize Germline Mutation Signatures (GMS) across diverse pediatric malignancies, elucidating latent genomic patterns that reveal shared oncogenic mechanisms. Methods: We analyzed germline whole-exome and whole-genome sequencing (WES/WGS) data from a retrospective cohort of 420 pediatric cancer patients and matched non-cancer controls. Variants were deeply annotated to capture multi-dimensional features, including predicted pathogenicity, splice-site disruption, regulatory impact, population frequency, and sequence context. To enable robust modeling, we integrated an augmented feature set encompassing evolutionary constraint, loss-of-function intolerance, and compositionally normalized substitution spectra. These high-dimensional annotations were processed using a deep autoencoder for non-linear representation learning, followed by Gaussian Mixture Modeling (GMM) of the latent space. Results: The framework delineated 13 signatures (GMS1–GMS13), yielding an optimal Davies–Bouldin index of 1.051. These signatures map to fundamental biological processes, including DNA repair deficiencies, transcription-coupled damage, replication stress, and aberrant RNA regulation. Crucially, these GMSs transcend traditional tissue-of-origin classifications, manifesting across multiple distinct cancer types. This observation indicates convergent germline etiologies and suggests potential shared susceptibilities to pathway-directed therapies. Conclusions: The discovery of these cross-cancer signatures provides a scalable, biologically interpretable framework for decoding inherited pediatric cancer risk. While the therapeutic mapping networks identified are currently exploratory and serve as a hypothesis-generating foundation, this deep learning-driven paradigm establishes a robust basis for stratified precision medicine. Pending prospective clinical validation, this approach holds significant translational potential to move beyond single-gene paradigms toward unified, systems-level precision oncology strategies. Full article

Green roofs are used as nature-based solutions for urban stormwater management and for improving the thermal performance of buildings. Their hydrological performance depends on structural properties and rainfall characteristics, but the relative importance of these factors has not been fully quantified. Therefore, this study aimed to identify the key variables controlling the hydrological effectiveness of a green roof. A conceptual model of a flat roof representing a typical single-family building in south-eastern Poland was developed in the Storm Water Management Model (SWMM), with a modeled roof area of 232 m² and 100% of the roof surface covered by the green roof LID system. A total of 24,576 simulation cases were analyzed, considering different values of soil thickness, berm height, initial saturation, vegetation-related storage, rainfall duration, rainfall probability, and rainfall temporal distribution. The hydrological response was evaluated using peak runoff reduction and cumulative runoff volume ratio determined at selected times after rainfall. Predictive models based on the eXtreme Gradient Boosting (XGBoost) algorithm were developed, and their interpretation was performed using the SHapley Additive exPlanations (SHAP) method. The main novelty of the study is its application-oriented framework combining SWMM simulations, XGBoost modeling, and SHAP explainability to distinguish the factors controlling peak runoff reduction and delayed runoff release from a green roof. The results showed that peak runoff reduction ranged from 10.97% to 100.00%, with a median of 99.91%, indicating a generally high capacity of the analyzed system to attenuate peak flow. In contrast, the cumulative runoff volume ratio increased over time, with median values rising from 0.05% immediately after rainfall to 7.91% after 24 h, confirming the significant retention and detention potential of the green roof. SHAP analysis revealed that peak runoff reduction was governed primarily by berm height, whereas cumulative runoff volume was controlled mainly by initial substrate saturation. The results confirm that different mechanisms control short-term and long-term green roof performance. Full article

Deep learning models for power quality (PQ) disturbance classification remain critically vulnerable to adversarial perturbations, with classification performance degrading severely under white-box attacks. Existing defenses address individual models in isolation and provide no mechanism for operators to assess whether the system is under attack or which classifier remains trustworthy. This paper proposes a two-stage framework that combines adversarial training with large language model (LLM) reasoning to improve both robustness and interpretability. In the first stage, four architecturally diverse classifiers, including a proposed Multi-Scale Temporal Attention Network (MSTAN), are evaluated under four adversarial attacks (FGSM, PGD, C&W, and UAP), and their failure patterns are recorded as structured vulnerability fingerprints. The ensemble is then retrained via adversarial training on mixed clean and perturbed signals. In the second stage, an LLM analyzes the ensemble predictions alongside the fingerprint knowledge base to perform attack detection, fingerprint-guided meta-classification, and operator-facing threat report generation. On a 17-class, 255,000-signal synthetic benchmark, adversarial training recovers FGSM and PGD accuracy from below 25% to the 53–78% range, with MSTAN achieving the highest post-training robustness (78.26% under FGSM, 65.41% under PGD). The LLM reasoning layer provides an additional 3.5–6.2 percentage point improvement over majority voting by selecting the most reliable ensemble member based on the inferred attack condition, and detects adversarial attacks with 87.6% overall accuracy. To our knowledge, this is the first integration of LLM-based ensemble reasoning into the PQ adversarial robustness pipeline and the first application of the C&W optimization attack to power quality signals. Full article

Ceramic additive manufacturing offers strong potential for fabricating geometrically complex and application-specific components, yet achieving reliable dimensional fidelity remains challenging because dimensional deviation is governed by highly coupled material, process, thermal, and environmental factors. To address this problem, this study proposes an uncertainty-aware computational framework for dimensional error prediction in ceramic 3D printing under variable material and process conditions. The contribution is positioned as a system-level integration of established learning, uncertainty estimation, calibration, and reliability-interpretation components within a ceramic additive manufacturing dimensional-error prediction workflow, rather than as a fundamental methodological breakthrough. The validation is conducted using the publicly available Ceramic 3D Printing Process Control Dataset, a 1000-sample tabular dataset, and the resulting findings are therefore interpreted as dataset-specific computational evidence rather than direct proof of industrial deployment readiness. The methodology begins with a structured data-driven preprocessing pipeline that transforms the Ceramic 3D Printing Process Control Dataset into a multi-condition feature space through data cleaning, one-hot material encoding, min–max normalization, and engineered descriptors capturing extrusion–speed balance, thermal gradients, cooling intensity, deposition density, and material-conditioned interactions. A multi-branch deep computational architecture is then developed to encode material, process, thermal-environmental, and engineered-feature streams separately, followed by adaptive cross-condition fusion to learn nonlinear dependencies across ceramic printing regimes. To improve reliability beyond deterministic regression, the framework jointly models aleatoric and epistemic uncertainty and incorporates calibration refinement to align predictive confidence with observed error behavior, thereby enabling preliminary reliability-oriented interpretation of stable and high-risk operating conditions. Experimental results demonstrate that the full model achieves the best overall within-dataset performance, with a test MAE of 0.0118, RMSE of 0.0172, $R^2=0.999$, MAPE of 1.74%, calibration error of 0.003, PICP of 0.996, reliability score of 0.992, and a stable prediction rate of 98.7%. Although these values indicate strong predictive behavior under the current structured dataset, the exceptionally high $R^2$ should be interpreted cautiously because external experimental validation, larger measured datasets, and cross-machine ceramic printing trials are still required. These findings show that the proposed framework provides an effective system-level computational strategy for dataset-specific reliability-aware dimensional quality prediction in ceramic additive manufacturing and offers a preliminary data-driven foundation for uncertainty-aware intelligent process optimization. Full article

Low-field benchtop nuclear magnetic resonance (NMR) spectroscopy has emerged as an accessible analytical platform for rapid, routine, and application-oriented analysis. However, its broader analytical adoption remains constrained by intrinsic limitations, including reduced spectral resolution, severe signal overlap, and lower sensitivity compared with conventional high-field instruments. To address these limitations, artificial intelligence (AI), including machine learning and deep learning approaches, has increasingly been explored alongside conventional chemometric strategies to enhance information extraction from low-field spectral data. This review examines recent developments in AI-assisted benchtop NMR across three major application domains: classification and authentication, quantitative analysis, and spectral processing or automated interpretation. Current evidence suggests that classification and authentication currently represent the most mature application area, whereas quantitative analysis shows promising but often condition-dependent performance. In contrast, spectral reconstruction and automated interpretation remain comparatively early-stage and exploratory, despite their potential long-term relevance for addressing intrinsic information limitations. Key challenges, including limited dataset diversity, poor model transferability, validation pitfalls, limited interpretability, and the lack of benchmarking and standardized workflows, are critically discussed. Future progress will likely depend not only on advances in AI algorithms, but also on the development of robust, reproducible, and analytically meaningful workflows. Overall, AI-assisted benchtop NMR is evolving from proof-of-concept applications toward a more structured analytical framework for extracting chemically meaningful information from spectrally constrained low-field data. Full article

Non-attributed graph sequence offers a powerful formalism for modeling the structural dynamics of complex systems—such as social networks, urban infrastructures, and document transmission pathways—where vertex interactions evolve over time without explicit attribute information. Mining association rules from such sequences to uncover recurring topological patterns have attracted growing interest. Yet two fundamental challenges remain: (1) how to effectively encode edge-level temporal dynamics in non-attributed settings, and (2) how to perform efficient and semantically meaningful temporal association rule mining under structural uncertainty. To address these within a systems-oriented framework, we propose two novel algorithms: the weighted temporal association rule mining algorithm and the fuzzy weighted temporal association rule mining algorithm. The first algorithm introduces time-dependent numerical weights to quantify the strength and persistence of vertex connectivity, integrating them into support and confidence measures to capture both the intensity and evolution of interactions. The second algorithm extends this by incorporating fuzzy set theory, modeling ambiguous or context-sensitive relationships (e.g., indistinct links or weakly correlated vertices) and generating fuzzy-weighted rules that enhance interpretability for real-world system analysis. Evaluated through five comprehensive experiments across diverse datasets and scales using standard metrics (support, confidence, rule count, running time), our methods produce more selective rule sets and achieve lower computational times compared to the classical Apriori algorithm. The proposed approaches thus establish a robust, data-driven foundation for analyzing temporal evolution and structural uncertainty in dynamic complex systems—providing a generalizable methodology applicable beyond domain-specific constraints. Full article

The carbon emission allowance (CEA) market is a complex socio-technical and environmental-management system in which regulatory design, trading activity, liquidity conditions, and price volatility interact dynamically. Accurate systems-level tail-risk forecasting and early warning remain challenging because carbon-market losses are affected by nonlinear dependence, episodic liquidity stress, and time-varying volatility. This study proposes an Interpretable Quantile Temporal Network (IQTN) as a systems-oriented risk-monitoring framework for China’s national CEA market. By integrating a feature-gating mechanism, a causal temporal convolutional encoder, and a non-crossing quantile output layer, IQTN directly models the conditional tail distribution of future carbon-market losses. The framework produces multi-horizon Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR) forecasts for 1-day, 5-day, and 10-day horizons and converts predicted tail risk into operational early-warning signals. Compared with historical simulation, EWMA, GARCH-type models, machine-learning quantile models, and deep temporal benchmarks, IQTN achieved the lowest 95% VaR pinball loss across all horizons, with values of 0.1765, 0.3958, and 0.5732. VaR backtesting showed empirical exceedance rates of 5.23%, 6.04%, and 6.94%, closest to the nominal 5% level. Interpretability analysis identified rolling volatility, maximum loss, intraday range, trading value, and illiquidity as key risk drivers. The temporal importance results also show that recent observations dominated the risk forecasts, suggesting that the risk state of the CEA market is highly sensitive to short-term market information. This supports the use of a short-horizon temporal network as a systems-oriented tool for carbon-market tail-risk monitoring and early warning. Full article

Predicting the tensile response of multi-material parts produced by material extrusion (MEX) remains difficult because the final behavior depends on both the constituent polymers and the quality and arrangement of dissimilar interfaces. This study introduces a constituent-material-anchored, phase-aware continual-learning framework for full stress–strain curve prediction of PETG/PC-ABS laminate coupons. Experimentally measured PETG and PC-ABS reference curves were combined through a rule-of-mixtures baseline; an XGBoost residual model then learned pointwise corrections using strain, baseline stress, mechanical phase label, and PETG thickness fraction as inputs. Validation used five PETG reference coupons, five PC-ABS reference coupons, five C1 laminate coupons, two C2 out-of-distribution coupons, and three coupons for each model-suggested Rank 1–3 architecture. UTS agreement alone was not sufficient: Rank 2 had a zero-shot UTS error of only $-0.18\%$ but a full-curve RMSE of $20.74\%$. After the first architecture-specific coupon was introduced, RMSE decreased from $12.34\%$ to $2.72\%$ for C1, from $18.60\%$ to $6.38\%$ for C2, from $21.04\%$ to $6.93\%$ for Rank 1, from $20.74\%$ to $7.50\%$ for Rank 2, and from $19.40\%$ to $7.48\%$ for Rank 3. The framework therefore provides a data-efficient, interpretable proof of concept for laminate screening and tensile-curve prediction, while its broader statistical robustness and extension to other loading modes require larger datasets. Full article

Western Guangxi is one of the principal bauxite-producing regions in China; however, its metallogenic model remains unclear. Building on previous studies, this paper systematically examines the ore-forming materials, sedimentary setting, ore genesis, mineral assemblages, diaspore formation, and pisoid (ooid) development of sedimentary bauxite deposits in western Guangxi. Based on this synthesis, a comprehensive metallogenic model is proposed to clarify the formation processes of these deposits. Metallogenic evolution is interpreted to involve five successive stages: weathering, leaching and alteration, deposition, post-depositional modification, and capping–sealing. Ore-forming materials are derived from volcanic ash supplied by the Emeishan Large Igneous Province and the Permian magmatic arc of the Paleo-Tethys. These materials are transported to isolated carbonate platforms and subsequently subjected to intense chemical weathering. During the early stages of ore formation, bauxite undergoes leaching and alteration, and variations in leaching intensity lead to the development of distinct ore types. Future work should focus on the genesis of diaspores, the formation of pisoids (ooids), and ore-forming mechanisms, while also addressing the coupling relationships among deep-time paleoclimate, major geological events, and sedimentary bauxite formation. Such efforts are essential for advancing a comprehensive metallogenic framework for sedimentary bauxites. Full article

Efficient management of soil–water resources is critical for global food security under intensifying climatic and demographic pressures. This review provides a comprehensive synthesis of artificial intelligence (AI) and distributed deep learning methodologies applied to soil–water interactions in precision agriculture. The physical and hydraulic foundations of soil–water systems—including water retention, unsaturated flow governed by the Richards equation, and soil degradation processes—are examined and situated within a unified framework of AI-based modeling and decision support. Classical machine learning (ML) algorithms (Random Forests, Support Vector Machines, gradient boosting) and deep learning architectures (convolutional neural networks, long short-term memory networks, transformers) are evaluated with respect to their capacity to predict soil moisture dynamics, estimate hydraulic properties, support smart irrigation scheduling, and generate digital soil maps at field-to-regional scales. Distributed training paradigms, federated learning for privacy-preserving multi-farm analytics, and edge AI deployment on low-power IoT hardware are assessed as enabling infrastructures for scalable agricultural intelligence. This review further addresses explainability, uncertainty quantification, and ethical dimensions inherent to AI-driven agricultural systems. Key challenges—including training data scarcity in data-poor regions, model interpretability, integration with physics-based hydrological models, and real-time deployment constraints—are critically discussed. Prospective research directions encompass physics-informed neural networks, foundation models for earth observation, autonomous digital twins of soil–water systems, and federated learning architectures aligned with data sovereignty frameworks. The synthesis underscores AI’s transformative potential for sustainable agricultural water management while delineating the technical and sociotechnical barriers that must be resolved to realize this potential at a global scale. Full article

Outlier detection in time series is traditionally formulated as the identification of rare or extreme observations with respect to global statistical properties. While effective for stationary processes, this perspective becomes insufficient in complex and non-stationary systems, where atypical behavior may manifest as disruptions of stable relationships rather than numerical extremeness. This paper proposes a rule-based framework for detecting structural outliers in non-stationary time series. Regular system behavior is represented by an interpretable set of deterministic IF–THEN rules describing stable relational patterns between features. Each rule defines a logical context and an admissible range of a diagnostic quantity, estimated nonparametrically from historical observations satisfying the rule condition. For a given observation, the set of active rules is identified and a structural inconsistency score is computed as the fraction of violated rule consequences. Additionally, observations lacking support from high-frequency contexts are treated as candidates for structural atypicality. The method is deterministic and avoids the need for explicit probabilistic modeling or iterative parameter learning, which simplifies interpretation and implementation. The framework is illustrated on daily EUR/USD data (2010–2022) using technical indicators (EMA, RSI) and absolute log-returns as the diagnostic measure. Results provide evidence that structurally atypical events can be identified even when global statistical thresholds remain unviolated, suggesting the practical relevance of relational analysis for non-stationary time series monitoring contexts. Full article

Chronic wounds represent a substantial and growing clinical burden, yet durable healing remains difficult to achieve in a large proportion of patients. The skin microbiome plays a central role in this challenge: in healthy tissue, resident microorganisms support barrier integrity and calibrate immune responses, whereas in chronic wounds, community disruption—often combined with persistent biofilm formation—drives non-resolving inflammation, impairs re-epithelialisation, and increases antimicrobial tolerance. As antibiotic resistance escalates, these features strengthen the rationale for microbiome-directed strategies that target wound ecology while reducing reliance on conventional antimicrobials. Current evidence is still dominated by mechanistic and preclinical studies, with only early clinical signals for selected approaches; therefore, next-generation probiotics, including Lactiplantibacillus/Lactobacillus spp., as well as defined prebiotic and postbiotic formulations, should be interpreted as promising adjuncts rather than clinically established therapies. Causal mechanisms, optimal formulations, reproducibility, and patient-level determinants of response remain insufficiently defined, representing a critical knowledge gap that limits translation. Here, we synthesise current evidence linking microbial ecology to key wound-healing pathways and propose a precision framework that integrates metagenomics, transcriptomics, metabolomics, and spatial profiling to map host–microbe interactions, identify predictive biomarkers, and guide stratified therapy. We further highlight combinatorial approaches pairing ecological engineering with biofilm-disruptive materials and immune-modulatory molecules. Realising the potential of these interventions will require mechanism-resolved clinical trials, standardised outcome frameworks, and patient stratification tools—advances that could improve chronic wound management while reducing selective pressure for antimicrobial resistance. Full article

Software quality assessment in agile projects remains fragmented. Technical, process-related, and team-related indicators are often evaluated through separate models, tools, and reports. This fragmentation limits cross-project comparability and weakens evidence-based decisions for software quality improvement. To address this problem, this study proposes the Overall Software Quality Index (OSQI), a multidimensional decision-support framework for software quality assessment in agile projects. OSQI integrates code quality, process quality, and team quality into a single project-level assessment model. The framework was initially grounded in ISO/IEC 25010:2011 and is discussed in relation to the ISO/IEC 25010:2023 revision, particularly its explicit inclusion of Safety as a product quality characteristic. Since the industrial datasets used in this study were not collected from safety-critical systems, Safety was not modeled as a separate OSQI dimension in the current version; instead, it is addressed as a scope limitation and future extension. The measurement structure was defined using the Goal–Question–Metric (GQM) approach. An initial set of 49 candidate metrics was reduced to 15 core indicators. This reduction was performed using dimension-specific strategies: Random Forest-based feature importance for code quality, Delphi and Analytic Hierarchy Process (AHP) for process quality, and thematic consolidation for team quality. The selected indicators were normalized and integrated through entropy-based weighting. This process generates an interpretable composite quality score. The main contribution of OSQI is not the isolated use of these methods, but their integration into a reproducible and tool-supported framework. The framework converts heterogeneous software engineering signals into a unified decision-support index. OSQI was evaluated using industrial agile project data. The data included static code analysis outputs, issue-tracking records, team assessment results, and product outcome indicators. In an exploratory validation across five industrial projects, OSQI showed a strong positive association with Net Promoter Score ($r=0.97, p=0.0076$) and a strong negative association with churn rate ($r=-0.97, p=0.0061$). A supporting software tool was also developed to automate data integration, score calculation, visualization, and project-level comparison. The findings suggest that OSQI can support quality monitoring, project benchmarking, and evidence-based improvement decisions in agile software engineering contexts. Full article

Global agriculture faces a dual imperative: increase food production to meet rising demand while simultaneously reducing environmental impacts and resource inefficiencies. Addressing this challenge requires repositioning ruminant nutrition as the intelligent nexus linking crop and livestock production within Integrated Crop–Livestock Systems (ICLS). In this role, nutrition becomes central to restoring ecological, nutritional, and economic synergies that have been fragmented by decades of agricultural specialization. While ICLS provides the ecological foundation, Precision Livestock Farming delivers the technological and analytical infrastructure necessary to operationalize integration at the individual-animal level. Real-time sensing, Internet of Things platforms, and Artificial Intelligence (AI) enable dynamic monitoring of animal physiology, behavior, and environmental interactions across scales. A key advancement in this evolution is the development of Hybrid Intelligent Mechanistic Models (HIMM), which integrate biologically grounded mechanistic models with data-driven AI approaches. By combining interpretability with adaptive learning, HIMM enhances predictive accuracy, extrapolative capacity, and decision transparency, enabling the creation of digital twins that simulate biological responses before management interventions are implemented. Such architectures extend precision nutrition beyond feed efficiency and methane mitigation to include nutrient density and product quality, thereby linking different ecosystem processes directly to human dietary needs. Integrating nutrition with advanced modeling and monitoring tools can help livestock systems move beyond static “net-zero” benchmarks toward sustainable strategies that are responsive to local production contexts. In this reframed paradigm, nutrition is not merely a production input but the central analytical framework that computationally links biological mechanisms, environmental stewardship, technological innovation, and human health within sustainable ruminant systems. Full article