Search Results (163)

This study evaluates the vulnerability of Siberian larch (Larix sibirica L.) populations to future climate change using a genomic offset (GO) framework that integrates genome-wide SNP data with environmental variables. We analyzed 488 individuals from 37 populations across climatically diverse regions of Russia, genotyped by sequencing at over 20,000 SNP loci using the ddRADseq method. Gene–environment association (GEA) analyses (BayeScEnv, LFMM2, and RDA) identified candidate adaptive loci linked to six key bioclimatic variables. Based on these loci, GO was estimated using three approaches implemented in RONA–RDA, RDA, and Gradient Forest frameworks under multiple climate models (MIROC6, BCC-CSM2-MR, MRI-ESM2-0), scenarios (SSP2-4.5, SSP3-7.0, SSP5-8.5), and time periods (2041–2060, 2061–2080, and 2081–2100). Results revealed consistent spatial patterns of vulnerability, with northern and high-altitude populations, as well as populations from more continental and moisture-limited regions, exhibiting the highest GO and thus the greatest risk of maladaptation. In contrast, several central and southern populations showed relatively low vulnerability. The importance of temperature stability (isothermality) and precipitation of the driest month as key drivers of adaptive variation was highlighted. Despite differences in SNP datasets, population rankings remained highly consistent, supporting the robustness of predictions. Overall, our findings demonstrate substantial heterogeneity in climate vulnerability across the species range and provide a genomic basis for conservation strategies, including assisted gene exchange and climate-adaptive forest management. Full article

Accurate short-term load forecasting is essential for reliable power system operation under increasingly nonlinear, volatile, and multi-scale load patterns. This study proposes a VMD–BayesXGB–BiLSTM hybrid forecasting framework that integrates time-series-cross-validation-based variational mode decomposition (VMD), Bayesian-optimized XGBoost (BayesXGB), and BiLSTM residual correction. First, abnormal values in the raw load and explanatory variables are detected using the $3\sigma$ criterion and corrected by cubic spline interpolation. Then, VMD parameters are selected only within the training sequence, and leakage-free VMD features are generated from historical input windows, avoiding the use of future information. BayesXGB is employed as the primary forecasting model to capture nonlinear relationships between historical load, VMD-derived multi-scale features, and external variables. Finally, a stacked BiLSTM module learns temporal patterns from historical BayesXGB predictions and residuals, and the predicted residual correction is added to the preliminary forecast. Experiments on an Australian electricity load dataset show that the proposed model achieves an RMSE of 122.1003, an MAE of 90.7386, a MAPE of 1.0269%, and an R² of 0.9921, outperforming all compared baseline models while maintaining sub-millisecond inference per sample. Full article

This study investigates data augmentation as a strategy for addressing dataset scarcity in Internet of Medical Things (IoMT) cybersecurity and improving intrusion-detection system performance. Four augmentation methods—Rule-Based, Tabular Variational Autoencoder (TVAE), Conditional Tabular Generative Adversarial Network (CTGAN), and Gaussian Copula—were applied to two publicly available IoMT datasets (ECU-IoHT and WUSTL-EHMS) to generate augmented training data with differing class distributions and feature characteristics. Eleven machine learning algorithms were evaluated using Matthews Correlation Coefficient (MCC), F1-score, accuracy, and error-based metrics. Results showed consistent performance improvements across all evaluated models relative to the baseline datasets. The Rule-Based method produced the strongest overall results, achieving the highest MCC (0.9757), F1-score (99.19%), and accuracy (99.18%) with LightGBM, alongside low false-positive and false-negative rates. Among the generative approaches, TVAE delivered the strongest overall practical performance (F1-score = 96.94%, accuracy = 96.92%), while CTGAN achieved a marginally higher MCC (0.9047) and also produced competitive results with balanced class representation. Gaussian Copula generated the weakest overall outcomes, primarily due to highly skewed class distributions. Traditional models, such as Logistic Regression and Naive Bayes, recorded the largest relative gains, indicating that augmentation can substantially improve simpler classifiers in data-scarce environments. Overall, the findings demonstrate that augmentation quality depends not only on dataset expansion, but also on preserving class balance, feature diversity, and realistic traffic relationships. These results provide practical guidance for strengthening IoMT intrusion-detection systems in healthcare environments. Full article

The geographical origin of aniseed (Pimpinella anisum L.) represents a key quality determinant, as it directly influences the chemical composition and commercial value of its essential oil. Agronomic traits of aniseed (plant height, umbel diameter, number of umbels per plant), productivity-related traits (number of seeds, thousand-seed weight, yield per plant, plant biomass, harvest index, yield per hectare, essential oil content and yield), and physiological traits (germination energy and total germination) exhibit variations depending on geographical origin. The study proposes an integrated framework for accurate classification by combining agronomic, productivity, and physiological data with GC-MS profiles and advanced machine learning (ML) techniques. A total of 144 samples were analyzed, based on a factorial design including three locations, six fertilizer treatments, two years, and four replications. trans-Anethole was the dominant compound in all samples (89.508–101.441%). Several classification models, including artificial neural networks, random forests, MARSplines, boosted trees, interactive trees, naïve Bayes, and support vector machines, were evaluated to discriminate samples by geographical origin using agro-meteorological and GC-MS data. The results indicate that AI and ML approaches effectively captured complex non-linear relationships. Overall, the multi-model framework highlights the strong potential of machine learning for agro-food authentication, supporting improved traceability, site-specific decision-making, and quality control. Full article

Chicken (Gallus gallus domesticus) domestication, likely associated with dry-rice farming in central Thailand, has led to substantial loss of ancestral immune-related genetic diversity in commercial chicken lineages. This study addresses allelic loss by providing the first comprehensive analysis of the highly polymorphic BG1 gene, an MHC-linked marker across the wild–domestic interface in Thailand and Vietnam, using high-depth Illumina amplicon sequencing. Genomic DNA from 47 Thai and Vietnamese chicken populations was extracted using a salting-out protocol following ethical sampling. Allelic variation was examined by targeting the BG1 intron 15–exon 16 region using triplicate PCR and Salus Pro NGS sequencing. Evolutionary dynamics and selection pressures were analyzed using AmpliSAS, MrBayes, and Datamonkey, while AlphaFold 3 was used to predict and validate 3D protein structures. We identified 98 novel alleles and 172 polymorphic sites within the BG1 intron 15–exon 16 region encoding an Ig-like domain. Extensive allele sharing between indigenous chickens and red junglefowl indicated strong balancing selection and trans-species polymorphism. Selection analyses showed that purifying selection conserved structural integrity at codons 9, 13, and 18, while variation at other sites enhanced immune recognition. AlphaFold 3 modeling confirmed conservation of the β-sandwich fold across variants, maintaining stability of the Immunoreceptor Tyrosine-based Inhibition Motif (ITIM). Thus, despite the regional gene flow, geographic isolation has shaped distinct signatures, as evidenced by the presence of 38 unique Thai and 9 unique Vietnamese alleles in addition to breed-specific private markers in the Betong (BG1*TH88), Decoy (BG1*TH91), and Tre (BG1*VN54) populations. A notable adaptive outlier under positive selection (ω = 1.357) was detected in the Dong Tao population, suggesting a recent selective sweep. These findings support the mission of the Siam Chicken Bioresource Project (SCBP) to utilize indigenous breeds as genetic reservoirs and provide a molecular basis for restoring resilience traits in domestic poultry to enhance global food security. Full article

Active sonar tracking of multiple underwater targets is frequently challenged by intense reverberation, which leads to sonar returns that are both non-stationary and non-Gaussian. In such scenarios, the generalized labeled multi-Bernoulli (GLMB) filter, which relies on a Gaussian assumption, often experiences a rise in an Optimal Subpattern Assignment (OSPA) distance, along with recurrent label switching. To mitigate this problem, a robust delta-generalized labeled multi-Bernoulli technique (ST-δ-GLMB) is introduced; it characterizes noise using a Student’s t-distribution and employs variational Bayes to estimate the corresponding parameters. More precisely, the Student’s t-distribution is utilized to represent measurement non-stationarity, and an online variational Bayesian estimation of the noise parameters is conducted within a multi-target framework based on the Student’s t-model. Moreover, without altering the GLMB data-association and label-management machinery, we derive closed-form updates and propagation for the Student’s t-parameters, thereby keeping the recursive computational burden and practical implementability under control. Finally, Monte Carlo simulations and lake-trial data demonstrate that, under non-stationary and heavy-clutter conditions, ST-δ-GLMB maintains stable track continuity and accurate target-number (cardinality) estimates in the presence of non-stationary measurements. Full article

This paper introduces a rigorous class of two-dimensional Markov-switching autoregressive moving-average (2D MS-ARMA) models for spatial lattice data exhibiting regime-dependent dynamics. The switching mechanism is governed by a latent causal Markov random field that drives spatial transitions between regime-specific autoregressive and moving-average structures. We provide sufficient conditions for the existence of a strictly stationary solution through the top Lyapunov exponent associated with a sequence of random matrices obtained from a state-space representation constructed along the lexicographic order. For the first-order bidirectional specification, we derive explicit spectral conditions linking stationarity to the regime-dependent spectral radii. Sufficient conditions ensuring the existence of finite second-order moments are also provided. Parameter estimation is carried out using a variational expectation–maximization (VEM) algorithm based on a mean-field approximation of the posterior distribution of the hidden regimes. The E-step yields closed-form coordinate ascent updates, while the M-step relies on gradient-based numerical optimization with derivatives computed via recursive differentiation. Under increasing-domain asymptotics, we discuss the consistency and asymptotic behavior of the variational estimator. The proposed framework fills a methodological gap between classical one-dimensional Markov-switching ARMA models and spatial autoregressive structures by extending regime-switching theory to multi-indexed processes with rigorous probabilistic foundations. It provides a comprehensive basis for statistical inference, model diagnostics, and prediction in spatially heterogeneous environments. Full article

Background/Objectives: Glioblastoma is the most common and aggressive primary malignant brain tumor in adults, characterized by infiltrative growth and poor prognosis. Achieving maximal resection without inducing neurological deficits remains a challenge in glioblastoma surgery. While 5-aminolevulinic acid-based fluorescence-guided surgery supports intraoperative tumor visualization, its reliability is limited by patient variability and weak fluorescence signals. This study proposes a machine learning framework to enhance fluorescence-guided surgery sensitivity by analyzing surgical microscope images at the pixel level. Methods: Fluorescence-mode neurosurgical microscope images of synthetic samples with known Protoporphyrin IX (PPIX) concentrations were used to train three classifiers (Support Vector Machine, Naïve Bayes, Neural Network) for pixel-wise fluorescence detection. In parallel, three contrastive-learning-based Variational Autoencoders (VAE, $\beta$ = 1, 2, 3) were evaluated for detecting weak fluorescence beyond visual perception. Additionally, a regression model was trained to relate pixel features to PPIX concentration. The best-performing VAE ($\beta$ = 1) was subsequently trained on real intraoperative data, and its detection sensitivity was compared to annotations from four experienced surgeons. Results: The proposed model achieved the highest detection rates on synthetic test data when calibrated for 99% specificity. Applied to real intraoperative images, the model revealed fluorescent areas substantially larger than those marked by experienced surgeons. In non-5-ALA control cases, minimal false positives were observed, indicating a specificity exceeding 99.9%. The regression model reliably quantified PPIX concentration in synthetic samples ($R^2=0.92$). Conclusions: By enabling more sensitive and objective fluorescence detection, this approach offers a valuable tool for improving surgical decision-making and facilitating safer, more extensive tumor resections. Full article

Understanding genetic diversity and population structure in wild Citrus relatives is crucial for conservation and crop improvement. Here, we examined genetic variation in Atalantia buxifolia from the island of Taiwan and Atalantia ceylanica from Sri Lanka using 21 transferable microsatellite (SSR) markers originally developed for Citrus. A total of 132 individuals from 13 populations were genotyped. Both species exhibited moderate levels of polymorphism, with A. buxifolia showing slightly higher allelic richness and heterozygosity than A. ceylanica. Analysis of molecular variance indicated that most genetic variation occurred within individuals (68% in A. buxifolia and 82% in A. ceylanica), while moderate population differentiation was detected (F_ST = 0.356 and 0.204, respectively). STRUCTURE, DAPC, PCoA, and F_ST analyses revealed distinct regional clustering in A. buxifolia, particularly in the Shoushan population, whereas populations of A. ceylanica were weakly structured. Monmonier’s analysis identified genetic barriers only in A. buxifolia, and BayesAss indicated high self-recruitment and localized gene flow in both species. Overall, these results suggest high within-population genetic diversity but limited connectivity among populations, shaped by geographic isolation and habitat fragmentation. Our findings provide a baseline for conservation planning in Atalantia populations and highlight the importance of maintaining habitat connectivity to preserve genetic resilience. Full article

Rapid advancements in the field of deep learning have had a profound impact on a wide range of scientific studies. This paper incorporates the power of deep neural networks to learn complex relationships in longitudinal data. The novel generative approach, Variational Deep Alliance (VaDA), is established, where an “alliance” is formed across repeated measurements via the strength of Variational Auto-Encoder. VaDA models the generating process of longitudinal data with a unified and well-structured latent space, allowing outcomes prediction, subjects clustering and representation learning simultaneously. The integrated model can be inferred efficiently within a stochastic Auto-Encoding Variational Bayes framework, which is scalable to large datasets and can accommodate variables of mixed type. Quantitative comparisons to those baseline methods are considered. VaDA shows high robustness and generalization capability across various synthetic scenarios. Moreover, a longitudinal study based on the well-known CelebFaces Attributes dataset is carried out, where we show its usefulness in detecting meaningful latent clusters and generating high-quality face images. Full article

Background/Objectives: Detecting copy number variations (CNVs) from next-generation sequencing (NGS) is challenging, particularly in targeted sequencing panels, especially for cell-free DNA (cfDNA), where the signal is weak and noise is high. Methods: We present BayesCNV, a Bayesian hierarchical model for gene-level copy ratio estimation from targeted amplicon read depths compared to a CNV-neutral reference sample. The model provides posterior uncertainty for each gene and supports interpretable calling based on effect size and posterior confidence. The model also provides a principled quality-control strategy based on the marginal log likelihood of each sample, with low values indicating low confidence in the calls. BayesCNV uses thermodynamic integration, a technique to reliably estimate this quantity. We benchmark our method against two publicly available CNV callers using Seracare^® reference samples with known CNVs on the OncoReveal^® Core Lbx panel. Results: Our method achieves a sensitivity of 0.87 and specificity of 0.996, dramatically outperforming two competitor methods, IonCopy and DeviCNV. In a separate FFPE dataset using the OncoReveal^® Essential Lbx panel, we show that the marginal log likelihood cleanly separates, degraded from high-quality samples, even when conventional sequencing QC metrics do not. Conclusions: BayesCNV provides accurate and interpretable gene-level CNV estimates and uncertainty quantification, along with an evidence-based quality control metric that improves robustness in targeted cfDNA workflows. Full article

Background/objectives: Metabolic abnormalities, independent of excess weight, may contribute to cancer risk even among individuals of normal weight, though their role remains unclear. This study sought to ascertain if metabolically unhealthy normal-weight (MUNW) individuals, generally characterized by a normal body mass index alongside the presence of metabolic abnormalities, have higher cancer risk than metabolically healthy peers, to analyze variations in risk across obesity-related cancer types, and to examine which single specific metabolic components can predict cancer independently in normal-weight individuals. Methods: Two authors systematically searched the PubMed, EMBASE, and Web of Science databases for longitudinal studies, published from inception to July 2025, that included normal-weight adults, classified participants by metabolic health status, and reported incident cancer outcomes in metabolically unhealthy versus healthy normal-weight groups. Hazard ratio (HR) estimates were extracted from each study and were pooled using random-effects inverse-variance model with empirical Bayes variance estimator. Results: Thirty-five studies involving 18,210,858 participants (56.0% females, mean age = 53.8 years) were included. A total of 280,828 new cancer cases were diagnosed during follow-up (mean = 10.6 years). In comparison with metabolically healthy normal-weight individuals, MUNW individuals had a 20% higher risk of cancer (HR = 1.20, 95% confidence interval [CI]: 1.13–1.28). Increased risks were observed for gastric cancer (HR = 1.40, 95% CI: 1.04–1.87), pancreatic cancer (HR = 1.37, 95% CI: 1.21–1.54), and colorectal cancer (HR = 1.34, 95% CI: 1.14–1.57), which were the cancer types showing statistically significant associations in subgroup analyses. Normal-weight participants presenting specific metabolic factors like central adiposity or glucose metabolism abnormalities had a 20% (HR = 1.20, 95% CI: 1.13–1.37) and 23% (HR = 1.23, 95% CI: 1.06–1.41) increased cancer risk, respectively. Conclusions: MUNW individuals are at higher risk of cancer, with specific metabolic abnormalities, particularly central adiposity and impaired glucose regulation, emerging as the factors most strongly associated with increased risk in normal-weight individuals. Routine metabolic screening and detailed phenotyping are crucial to identify these risks. Full article

Soybean (Glycine max (L.) Merr.), as a crucial source of oil and protein globally, is widely cultivated in many countries. Low-temperature stress has become one of the major environmental factors affecting soybean production, especially in colder regions, making the improvement of cold tolerance traits in soybean a key breeding objective. This study integrates Genome-Wide Association Studies (GWAS) and Marker-Assisted Selection (MAS) to enhance the predictive performance of soybean cold tolerance traits. First, three GWAS methods—Fast3VmrMLM, fastGWA, and FarmCPU—were used to analyze soybean cold tolerance traits, and significant SNP markers were identified. Principal Component Analysis (PCA) was employed to reveal genetic differences among various soybean germplasm. Then, based on the identified SNP markers, multiple Genomic Selection (GS) models, such as GBLUP, BayesA, BayesB, BayesC, BL, and BRR, were used for prediction to evaluate the contribution of genetic effects to phenotypic variation. The results showed that the markers selected through GWAS significantly improved the prediction accuracy of genomic selection, especially with the Fast3VmrMLM and FarmCPU methods in larger datasets. Finally, Gene Ontology (GO) analysis was performed to further identify candidate genes associated with cold tolerance traits and their biological functions, providing theoretical support for molecular breeding of cold-tolerant soybean varieties. Full article

This study proposes Bayesian estimation of multivariate regular vine (R-vine) copula models with generalized autoregressive conditional heteroskedasticity (GARCH) margins modeled by Gaussian-mixture distributions. The Bayesian estimation approach includes Markov chain Monte Carlo and variational Bayes with data augmentation. Although R-vines typically involve computationally intensive procedures limiting their practical use, we address this challenge through parallel computing techniques. To demonstrate our approach, we employ thirteen bivariate copula families within an R-vine pair-copula construction, applied to a large number of marginal distributions. The margins are modeled as exponential-type GARCH processes with intertemporal capital asset pricing specifications, using a mixture of Gaussian and generalized Pareto distributions. Results from an empirical study involving 100 financial returns confirm the effectiveness of our approach. Full article

We compare three modern Bayesian approaches, Hamiltonian Monte Carlo (HMC), Variational Bayes (VB), and Integrated Nested Laplace Approximation (INLA), for two classic spatial econometric specifications: the spatial lag model and spatial error model. Our Monte Carlo experiments span a range of sample sizes and spatial neighborhood structures to assess accuracy and computational efficiency. Overall, posterior means exhibit minimal bias for most parameters, with precision improving as sample size grows. VB and INLA deliver substantial computational gains over HMC, with VB typically fastest at small and moderate samples and INLA showing excellent scalability at larger samples. However, INLA can be sensitive to dense spatial weight matrices, showing elevated bias and error dispersion for variance and some regression parameters. Two empirical illustrations underscore these findings: a municipal expenditure reaction function for Île-de-France and a hedonic price for housing in Ames, Iowa. Our results yield actionable guidance. HMC remains a gold standard for accuracy when computation permits; VB is a strong, scalable default; and INLA is attractive for large samples provided the weight matrix is not overly dense. These insights help practitioners select Bayesian tools aligned with data size, spatial neighborhood structure, and time constraints. Full article