Search Results (9,857)

Background: Multi-epitope vaccines have become the preferred strategy for protection against infectious diseases by integrating multiple MHC-restricted T-cell and B-cell epitopes that elicit both humoral and cellular immune responses against pathogens. Computational methods address various aspects independently, yet their orchestration is technically challenging, as most bioinformatics tools are accessible through heterogeneous interfaces and lack interoperability features. The present work proposes a novel framework for rationalized multi-epitope vaccine design that streamlines end-to-end analyses through an integrated web-based environment. Results: VaccineDesigner is a comprehensive web-based framework that streamlines the design of protective epitope-based vaccines by seamlessly integrating computational methods for B-cell, CTL, and HTL epitope prediction. VaccineDesigner incorporates single-epitope prediction and evaluation as well as additional analyses, such as multi-epitope vaccine generation, estimation of population coverage, molecular mimicry, and proteasome cleavage. The functionalities are transparently integrated into a modular architecture, providing a single access point for rationalized, multi-epitope vaccine generation in a time- and cost-effective manner. Conclusions: VaccineDesigner is a web-based tool that identifies and evaluates candidate B-cell, CTL, and HTL epitopes and constructs a library of multi-epitope vaccines that combine strong immunogenic responses, safety, and broad population coverage. The source code is available under the academic license and freely accessible. Full article

Simple Baseline has become a dominant benchmark in human pose estimation (HPE) due to its excellent performance and simple design. However, its “strong encoder + simple decoder” architectural paradigm suffers from two core limitations: (1) its non-branching, linear deconvolutional path prevents it from leveraging the rich, fine-grained features generated by the encoder at multiple scales and (2) the model lacks explicit prior knowledge of both the absolute positions and structural layout of human keypoints. To address these issues, this paper introduces AFJ-PoseNet, a new architecture that deeply enhances the Simple Baseline framework. First, we restructure Simple Baseline’s original linear decoder into a U-Net-like multi-scale fusion path, introducing intermediate features from the encoder via skip connections. For efficient fusion, we design a novel Attention Fusion Module (AFM), which dynamically gates the flow of incoming detailed features through a context-aware spatial attention mechanism. Second, we propose the Joint-Aware Positional Encoding (JAPE) module, which innovatively combines a fixed global coordinate system with learnable, joint-specific spatial priors. This design injects both absolute position awareness and statistical priors of the human body structure. Our ablation studies on the MPII dataset validate the effectiveness of each proposed enhancement, with our full model achieving a mean PCKh of 88.915, a 0.341 percentage point improvement over our re-implemented baseline. On the more challenging COCO val2017 dataset, our ResNet-50-based AFJ-PoseNet achieves an Average Precision (AP) of 72.6%. While this involves a slight trade-off in Average Recall for higher precision, this result represents a significant 2.2 percentage point improvement over our re-implemented baseline (70.4%) and also outperforms other strong, publicly available models like DARK (72.4%) and SimCC (72.1%) under comparable settings, demonstrating the superiority and competitiveness of our proposed enhancements. Full article

Histone post-translational modifications (PTMs) have emerged as promising epigenetic biomarkers with increasing forensic relevance. Unlike conventional genetic markers such as short tandem repeats (STRs), histone modifications can offer additional layers of biological information, capturing individual-specific regulatory states and remaining detectable even in degraded forensic samples. This review highlights recent advances in understanding histone PTMs in forensic contexts, focusing on three key domains: analysis of degraded biological evidence, differentiation of monozygotic (MZ) twins, and postmortem interval (PMI) estimation. We summarize experimental findings from human cadavers, animal models, and typical forensic samples including bone, blood, and muscle, illustrating the stability and diagnostic potential of marks such as H3K4me3, H3K27me3, and γ-H2AX. Emerging technologies including CUT&Tag, MALDI imaging, and nanopore-based sequencing offer novel opportunities to profile histone modifications at high resolution and low input. Despite technical challenges, these findings support the feasibility of histone-based biomarkers as complementary tools for forensic identification and temporal analysis. Future work should prioritize methodological standardization, inter-laboratory validation, and integration into forensic workflows. However, the forensic applicability of these modifications remains largely unvalidated, and further studies are required to assess their reliability in casework contexts. Full article

In this study, we propose a novel approach for human pose estimation (HPE) in occluded scenes by progressively fusing features extracted from RGB-D images, which contain RGB and depth images. Conventional bottom-up human pose estimation models that rely solely on RGB inputs often produce erroneous skeletons when parts of a person’s body are obscured by another individual, because they struggle to accurately infer body connectivity due to the lack of 3D topological information. To address this limitation, we modify the traditional OpenPose that is a bottom-up HPE model to take a depth image as an additional input, thereby providing explicit 3D spatial cues. Each input modality is processed by a dedicated feature extractor. Each input modality is processed by a dedicated feature extractor. In addition to the two existing modules for each stage—joint connectivity and joint confidence map estimations for the color image—we integrate a new module for estimating joint confidence maps for the depth image into the initial few stages. Subsequently, the confidence maps derived from both depth and RGB modalities are fused at each stage and forwarded to the next, ensuring that 3D topological information from the depth image is effectively utilized for both joint localization and body part association. Subsequently, the confidence maps derived from both depth and RGB modalities are fused at each stage and forwarded to the next to ensure that 3D topological information is effectively utilized for estimating both joint localization and their connectivity. The experimental results on the NTU 120+ RGB-D Dataset verify that our proposed approach achieves a 13.3% improvement in average recall compared to the original OpenPose model. The proposed method can enhance the performance of the bottom-up HPE models for the occlusion scenes. Full article

A single-station lightning location has the obvious advantages of low cost and convenience in lightning monitoring and warning. To address the critical challenge of distance estimation accuracy in this technology, we propose a novel physical time-reversal (PTR) method to utilize the full wave information of both the ground wave and the sky wave in the detected signal. First, we improved the numerical model for accurately calculating the lightning sferics signals in the complex propagation environment of the Earth–ionosphere waveguide using the measured International Reference Ionosphere 2020. Subsequently, the sferics signal with multipath effect is transformed by time reversal and back propagated in the numerical model. Furthermore, a broadening factor reflecting the waveform dispersion in the back propagation is defined as the single-station focusing criterion to determine the optimal lightning propagation distance, considering the multipath effect and the focus of the PTR process. The experimental results demonstrate that the average root mean square error (RMSE) and the mean relative error (MRE) of the PTR method for the lightning distance estimation in the numerical simulation within the range of 100–1200 km are 5.517 km and 1.21%, respectively, and the average RMSE and the MRE for the natural lightning strikes to the Canton Tower from the measured data in the range of 181.643–1152.834 km are 9.251 km and 2.07%, respectively. Moreover, the correlation coefficients of the detection results are all as high as 0.999. These results indicate that the PTR method significantly outperforms the traditional ionospheric reflection method, demonstrating that it is able to perform a more accurate single-station lightning distance estimation by utilizing the compensation mechanism of the multipath effect on the sferics. The implementation of the proposed method has significant application value for improving the accuracy of single-station lightning location. Full article

Agroforestry systems (AFSs) enhance long-term carbon sequestration through tree biomass accumulation. As the European Union’s Carbon Farming Certification (CRCF) Regulation now recognizes AFSs in carbon farming (CF) schemes, accurate tree biomass estimation becomes essential for certification. This review examines field-destructive and remote sensing methods for estimating tree aboveground biomass (AGB) in AFSs, with a specific focus on their advantages, limitations, timing, and associated costs. Destructive methods, although accurate and necessary for developing and validating allometric equations, are time-consuming, costly, and labour-intensive. Conversely, satellite- and drone-based remote sensing offer scalable and non-invasive alternatives, increasingly supported by advances in machine learning and high-resolution imagery. Using data from the INNO4CFIs project, which conducted parallel destructive and remote measurements in an AFS in Tuscany (Italy), this study provides a novel quantitative comparison of the resources each method requires. The findings highlight that while destructive measurements remain indispensable for model calibration and new species assessment, their feasibility is limited by practical constraints. Meanwhile, remote sensing approaches, despite some accuracy challenges in heterogeneous AFSs, offer a promising path forward for cost-effective, repeatable biomass monitoring but in turn require reliable field data. The integration of both approaches might represent a valid strategy to optimize precision and resource efficiency in carbon farming applications. Full article

Nitrous oxide (${\mathrm{N}}_2\mathrm{O}$) emissions from agriculture are rising due to increased fertilizer use and intensive farming, posing a major challenge for climate mitigation. This study introduces a novel reinforcement learning (RL) framework to optimize farm management strategies that balance crop productivity with environmental impact, particularly ${\mathrm{N}}_2\mathrm{O}$ emissions. By modeling agricultural decision-making as a partially observable Markov decision process (POMDP), the framework accounts for uncertainties in environmental conditions and observational data. The approach integrates deep Q-learning with recurrent neural networks (RNNs) to train adaptive agents within a simulated farming environment. A Probabilistic Deep Learning (PDL) model was developed to estimate ${\mathrm{N}}_2\mathrm{O}$ emissions, achieving a high Prediction Interval Coverage Probability (PICP) of 0.937 within a 95% confidence interval on the available dataset. While the PDL model’s generalizability is currently constrained by the limited observational data, the RL framework itself is designed for broad applicability, capable of extending to diverse agricultural practices and environmental conditions. Results demonstrate that RL agents reduce ${\mathrm{N}}_2\mathrm{O}$ emissions without compromising yields, even under climatic variability. The framework’s flexibility allows for future integration of expanded datasets or alternative emission models, ensuring scalability as more field data becomes available. This work highlights the potential of artificial intelligence to advance climate-smart agriculture by simultaneously addressing productivity and sustainability goals in dynamic real-world settings. Full article

Precipitable water vapor (PWV) is a critical component of the Earth’s atmosphere, playing a pivotal role in weather systems, climate dynamics, and hydrological cycles. Accurate estimation of PWV is essential for numerical weather prediction, climate modeling, and atmospheric correction in remote sensing. Ground-based observation stations can only provide PWV measurements at discrete points, whereas spaceborne infrared remote sensing enables spatially continuous coverage, but its retrieval algorithm is restricted to clear-sky conditions. This study proposes an innovative approach that uses ensemble learning models to integrate infrared and microwave satellite data and other geographic features to achieve all-weather PWV retrieval. The proposed product shows strong consistency with IGRA radiosonde data, with correlation coefficients (R) of 0.96 for the ascending orbit and 0.95 for the descending orbit, and corresponding RMSE values of 5.65 and 5.68, respectively. Spatiotemporal analysis revealed that the retrieved PWV product exhibits a clear latitudinal gradient and seasonal variability, consistent with physical expectations. Unlike MODIS PWV products, which suffer from cloud-induced data gaps, the proposed method provides seamless spatial coverage, particularly in regions with frequent cloud cover, such as southern China. Temporal consistency was further validated across four east Asian climate zones, with correlation coefficients exceeding 0.88 and low error metrics. This algorithm establishes a novel all-weather approach for atmospheric water vapor retrieval that does not rely on ground-based PWV measurements for model training, thereby offering a new solution for estimating water vapor in regions lacking ground observation stations. Full article

With the rapid adoption of automated driving systems, ensuring safe and efficient driver takeover has become a crucial challenge for road safety. This study introduces a novel psychological framework for understanding and predicting takeover behavior in conditionally automated vehicles, leveraging an extended Theory of Planned Behavior (TPB) model enriched by real-world driver experience. Drawing on survey data from 385 automated driving system users recruited in Shaoguan City, China, through face-to-face questionnaire administration covering various ADS types (ACC, lane-keeping, automatic parking), we demonstrate that driver attitudes, perceived behavioral control, and subjective norms are significant determinants of takeover intention, collectively explaining nearly half of its variance (R² = 48.7%). Importantly, our analysis uncovers that both intention and perceived behavioral control have robust, direct effects on actual takeover behavior. Crucially, this work is among the first to reveal that individual user characteristics—such as driving experience and ADS (automated driving system) usage frequency—substantially moderate these psychological pathways: experienced or frequent users rely more on perceived control and attitude, while less experienced drivers are more susceptible to social influences. By advancing a multi-dimensional psychological model that integrates personal, social, and experiential moderators, our findings deliver actionable insights for the design of adaptive human–machine interfaces, tailored driver training, and targeted safety interventions in the context of automated driving. Using structural equation modeling with maximum likelihood estimation (χ²/df = 2.25, CFI = 0.941, RMSEA = 0.057), this psychological approach complements traditional engineering models by revealing that takeover behavior variance is explained at 58.3%. Full article

Heat stress is a critical constraint to poultry production in tropical regions, where the temperature–humidity index (THI) frequently exceeds thermoneutral thresholds. Despite growing interest in climate-resilient livestock, limited research has explored the genetic sensitivity of local chicken breeds to increasing THI levels. This study aimed to evaluate the genetic effects of increasing THI on growth performance traits in two tropical chicken breeds. The data included body weight (BW), average daily gain (ADG), and absolute growth rate (AGR) from 4,745 black-boned and 3,001 Thai native synthetic chickens across five generations. Growth data were collected from hatching to 12 weeks of age, whereas temperature and humidity were continuously recorded to calculate daily THI values. A reaction norm model was used to estimate genetic parameters and rate of decline of BW, ADG, and AGR traits under varying THI thresholds (THI70 to THI80). Results indicated that the onset of heat stress occurred at THI72 for black-boned chickens and at THI76 for Thai native synthetic chickens. Heritability estimates for BW, ADG, and AGR decreased as the THI increased in both chicken breeds. However, the Thai native synthetic chickens consistently exhibited higher genetic potential across all THI levels (average heritability: BW = 0.28, ADG = 0.25, AGR = 0.36) compared to the black-boned chickens (average heritability: BW = 0.21, ADG = 0.15, AGR = 0.23). Under mild heat stress (THI72), black-boned chickens showed sharp declines in all traits (average reduction in BW = −10.9 g, ADG = −0.87 g/day, AGR = −3.20 g/week), whereas Thai native synthetic chickens maintained stable performance. At THI76, both breeds experienced significant reductions, particularly in males. Estimated breeding values (EBVs) for AGR decreased linearly with THI, though Thai native synthetic chickens showed greater individual variability, with some birds maintaining stable or positive EBVs up to THI80—suggesting the presence of heat-resilient genotypes. In conclusion, Thai native synthetic chickens demonstrated superior thermotolerance and genetic robustness under increasing THI conditions. The identification of breed-specific THI thresholds and resilient individuals provides novel insights for climate-smart poultry breeding. These findings offer valuable tools for genetic selection, environmental management, and long-term adaptation strategies in response to global climate change. Full article

This study pioneers the integration of Sentinel-2 satellite imagery with Kolmogorov–Arnold networks (KAN) for the evaluation of chlorophyll-a (Chl-a) concentrations in inland lakes. Using Baiyangdian Lake in Hebei Province, China, as a case study, a specialized KAN architecture was designed to extract spectral features from Sentinel-2 data, and a robust algorithm was developed for Chl-a estimation. The results demonstrate that the KAN model outperformed traditional feature-engineering-based machine learning (ML) methods and standard multilayer perceptron (MLP) deep learning approaches, achieving an R² of 0.8451, with MAE and RMSE as low as 1.1920 μg/L and 1.6705 μg/L, respectively. Furthermore, attribution analysis was conducted to quantify the importance of individual features, highlighting the pivotal role of bands B3 and B5 in Chl-a retrieval. Furthermore, spatio-temporal distributions of Chl-a concentrations in Baiyangdian Lake from 2020 to 2024 were generated leveraging the KAN model, further elucidating the underlying causes of water quality changes and examining the driving factors. Compared to previous studies, the proposed approach leverages the high spatial resolution of Sentinel-2 imagery and the accuracy and interpretability of the KAN model, offering a novel framework for monitoring water quality parameters in inland lakes. These findings may guide similar research endeavors and provide valuable decision-making support for environmental agencies. Full article

In today’s fast-paced and evolving job market, salary continues to play a critical role in career decision-making. The ability to accurately classify job titles and predict corresponding salary ranges is increasingly vital for organizations seeking to attract and retain top talent. This paper proposes a novel approach, the Hybrid Bayesian Model (HBM), which combines Bayesian classification with advanced regression techniques to jointly address job title identification and salary prediction. HBM is designed to capture the inherent complexity and variability of real-world job market data. The model was evaluated against established machine learning (ML) algorithms, including Random Forests (RF), Support Vector Machines (SVM), Decision Trees (DT), and multinomial naïve Bayes classifiers. Experimental results show that HBM outperforms these benchmarks, achieving 99.80% accuracy, 99.85% precision, 100% recall, and an F1 score of 98.8%. These findings highlight the potential of hybrid ML frameworks to improve labor market analytics and support data-driven decision-making in global recruitment strategies. Consequently, the suggested HBM algorithm provides high accuracy and handles the dual tasks of job title classification and salary estimation in a symmetric way. It does this by learning from class structures and mirrored decision limits in feature space. Full article

This paper proposes a low-complexity signal detection method for orthogonal time frequency space (OTFS) communication systems, based on a separable convolutional neural network (SeCNN), termed SeCNN-OTFS. A novel SeparableBlock architecture is introduced, which integrates residual connections and a channel attention mechanism to enhance feature discrimination and training stability under high Doppler conditions. By decomposing standard convolutions into depthwise and pointwise operations, the model achieves a substantial reduction in computational complexity. To validate its effectiveness, simulations are conducted under a standard OTFS configuration with 64-QAM modulation, comparing the proposed SeCNN-OTFS with conventional CNN-based models and classical linear estimators, such as least squares (LS) and minimum mean square error (MMSE). The results show that SeCNN-OTFS consistently outperforms LS and MMSE, and when the signal-to-noise ratio (SNR) exceeds 12.5 dB, its bit error rate (BER) performance becomes nearly identical to that of 2D-CNN. Notably, SeCNN-OTFS requires only 19% of the parameters compared to 2D-CNN, making it highly suitable for resource-constrained environments such as satellite and IoT communication systems. For scenarios where higher accuracy is required and computational resources are sufficient, the CNN-OTFS model—with conventional convolutional layers replacing the separable convolutional layers—can be adopted as a more precise alternative. Full article

Extreme precipitation events severely impact agriculture, reducing yields and land use efficiency. The spatiotemporal distribution of Total Column Water Vapor (TCWV), the primary gaseous form of water, directly influences sustainable agricultural management. This study, through multi-source data fusion, employs methods including the Mann–Kendall test, sliding change-point detection, wavelet transform, pixel-scale trend estimation, and linear regression to analyze the spatiotemporal dynamics of global TCWV from 1959 to 2023 and its impacts on agricultural systems, surpassing the limitations of single-method approaches. Results reveal a global TCWV increase of 0.0168 kg/m²/year from 1959–2023, with a pivotal shift in 2002 amplifying changes, notably in tropical regions (e.g., Amazon, Congo Basins, Southeast Asia) where cumulative increases exceeded 2 kg/m² since 2000, while mid-to-high latitudes remained stable and polar regions showed minimal content. These dynamics escalate weather risks, impacting sustainable agricultural management with irrigation and crop adaptation. To enhance prediction accuracy, we propose a novel hybrid model combining wavelet transform with LSTM, TCN, and GRU deep learning models, substantially improving multidimensional feature extraction and nonstationary trend capture. Comparative analysis shows that WT-TCN performs the best (MAE = 0.170, R² = 0.953), demonstrating its potential for addressing climate change uncertainties. These findings provide valuable applications for precision agriculture, sustainable water resource management, and disaster early warning. Full article

Sensor selection in IoT-based smart healthcare systems is a complex fuzzy decision-making problem due to the presence of numerous uncertain and interdependent evaluation criteria. Traditional fuzzy multi-criteria decision-making (MCDM) approaches often assume independence among criteria and rely on aggregation operators that impose sharp transitions between preference levels. These assumptions can lead to decision outcomes with insufficient differentiation, limited discriminatory capacity, and potential issues in consistency and sensitivity. To overcome these limitations, this study proposes a novel fuzzy decision-making framework by integrating Quasi-D-Overlap functions into the fuzzy MARCOS (Measurement of Alternatives and Ranking According to Compromise Solution) method. Quasi-D-Overlap functions represent a generalized extension of classical overlap operators, capable of capturing partial overlaps and interdependencies among criteria while preserving essential mathematical properties such as associativity and boundedness. This integration enables a more intuitive, flexible, and semantically rich modeling of real-world fuzzy decision problems. In the context of real-time health monitoring, a case study is conducted using a hybrid edge–cloud architecture, involving sensor tasks such as heartrate monitoring and glucose level estimation. The results demonstrate that the proposed method provides greater stability, enhanced discrimination, and improved responsiveness to weight variations compared to traditional fuzzy MCDM techniques. Furthermore, it effectively supports decision-makers in identifying optimal sensor alternatives by balancing critical factors such as accuracy, energy consumption, latency, and error tolerance. Overall, the study fills a significant methodological gap in fuzzy MCDM literature and introduces a robust fuzzy aggregation strategy that facilitates interpretable, consistent, and reliable decision making in dynamic and uncertain healthcare environments. Full article