Search Results (387)

Landslides are destructive geological hazards, making accurate landslide susceptibility assessment essential for disaster prevention and mitigation. However, existing studies often lack scientific rigor in negative sample construction and have unclear model applicability. This study focuses on Ya’an City, Sichuan Province, China, and proposes an innovative approach to negative sample construction using Geographically Weighted Regression (GWR), which is then integrated with Tabular Network (TabNet), a deep learning architecture tailored to structured tabular data, to assess landslide susceptibility. The performance of TabNet is compared against Random Forest, Light Gradient Boosting Machine, deep neural networks, and Residual Networks. The experimental results indicate that (1) the GWR-based sampling strategy substantially improves model performance across all tested models; (2) TabNet trained using the GWR-based negative samples achieves superior performance over all other evaluated models, with an average AUC of 0.9828, exhibiting both high accuracy and interpretability; and (3) elevation, land cover, and annual Normalized Difference Vegetation Index are identified as dominant predictors through TabNet’s feature importance analysis. The results demonstrate that combining GWR and TabNet substantially enhances landslide susceptibility modeling by improving both accuracy and interpretability, establishing a more scientifically grounded approach to negative sample construction, and providing an interpretable, high-performing modeling framework for geological hazard risk assessment. Full article

Continuous blood pressure (BP) monitoring provides valuable insight into the body’s dynamic cardiovascular regulation across various physiological states such as physical activity, emotional stress, postural changes, and sleep. Continuous BP monitoring captures different variations in systolic and diastolic pressures, reflecting autonomic nervous system activity, vascular compliance, and circadian rhythms. This enables early identification of abnormal BP trends and allows for timely diagnosis and interventions to reduce the risk of cardiovascular diseases (CVDs) such as hypertension, stroke, heart failure, and chronic kidney disease as well as chronic stress or anxiety disorders. To facilitate continuous BP monitoring, we propose an AI-powered estimation framework. The proposed framework first uses an expert-driven feature engineering approach that systematically extracts physiological features from photoplethysmogram (PPG)-based arterial pulse waveforms (APWs). Extracted features include pulse rate, ascending/descending times, pulse width, slopes, intensity variations, and waveform areas. These features are fused with demographic data (age, gender, height, weight, BMI) to enhance model robustness and accuracy across diverse populations. The framework utilizes a Tab-Transformer to learn rich feature embeddings, which are then processed through an ensemble machine learning framework consisting of CatBoost, XGBoost, and LightGBM. Evaluated on a dataset of 1000 subjects, the model achieves Mean Absolute Errors (MAE) of 3.87 mmHg (SBP) and 2.50 mmHg (DBP), meeting British Hypertension Society (BHS) Grade A and Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed architecture advances non-invasive, AI-driven solutions for dynamic cardiovascular health monitoring. Full article

Image-assisted digital shade guides are increasingly popular for shade matching; however, research on their accuracy remains limited. This study aimed to compare the accuracy and reliability of color coordination in image-assisted digital shade guides constructed using calibrated images of their shade tabs captured by a mirrorless camera (Canon, Tokyo, Japan) (MC-DSG) and a smartphone camera (Samsung, Seoul, Korea) (SC-DSG), using a spectrophotometer as the reference standard. Twenty-nine VITA Linearguide 3D-Master shade tabs were photographed under controlled settings with both cameras equipped with cross-polarizing filters. Images were calibrated using Adobe Photoshop (Adobe Inc., San Jose, CA, USA). The L* (lightness), a* (red-green chromaticity), and b* (yellow-blue chromaticity) values, which represent the color attributes in the CIELAB color space, were computed at the middle third of each shade tab using Adobe Photoshop. Specifically, L* indicates the brightness of a color (ranging from black [0] to white [100]), a* denotes the position between red (+a*) and green (–a*), and b* represents the position between yellow (+b*) and blue (–b*). These values were used to quantify tooth shade and compare them to reference measurements obtained from a spectrophotometer (VITA Easyshade V, VITA Zahnfabrik, Bad Säckingen, Germany). Mean color differences (∆E₀₀) between MC-DSG and SC-DSG, relative to the spectrophotometer, were compared using a independent t-test. The ∆E₀₀ values were also evaluated against perceptibility (PT = 0.8) and acceptability (AT = 1.8) thresholds. Reliability was evaluated using intraclass correlation coefficients (ICC), and group differences were analyzed via one-way ANOVA and Bonferroni post hoc tests (α = 0.05). SC-DSG showed significantly lower ΔE₀₀ deviations than MC-DSG (p < 0.001), falling within acceptable clinical AT. The L* values from MC-DSG were significantly higher than SC-DSG (p = 0.024). All methods showed excellent reliability (ICC > 0.9). The findings support the potential of smartphone image-assisted digital shade guides for accurate and reliable tooth shade assessment. Full article

Modern energy storage systems for both power and transportation are highly related to lithium-ion batteries (LIBs). However, their safety depends on a potentially hazardous failure mode known as thermal runaway (TR). Predicting and classifying TR causes can widely enhance the safety of power and transportation systems. This paper presents an advanced machine learning method for forecasting and classifying the causes of TR. A generative model for synthetic data generation was used to handle class imbalance in the dataset. Hyperparameter optimization was conducted using Optuna for four classifiers: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), tabular network (TabNet), and Extreme Gradient Boosting (XGBoost). A three-fold cross-validation approach was used to guarantee a robust evaluation. An open-source database of LIB failure events is used for model training and testing. The XGBoost model outperforms the other models across all TR categories by achieving 100% accuracy and a high recall (1.00). Model results were interpreted using SHapley Additive exPlanations analysis to investigate the most significant factors in TR predictors. The findings show that important TR indicators include energy adjusted for heat and weight loss, heater power, average cell temperature upon activation, and heater duration. These findings guide the design of safer battery systems and preventive monitoring systems for real applications. They can help experts develop more efficient battery management systems, thereby improving the performance and longevity of battery-operated devices. By enhancing the predictive knowledge of temperature-driven failure mechanisms in LIBs, the study directly advances thermal analysis and energy storage safety domains. Full article

Air pollution source tracing is vital for effective pollution prevention and control, yet traditional methods often require large amounts of manual data, have limited cross-regional generalizability, and present challenges in capturing complex pollutant interactions. This study introduces AirTrace-SA (Air Pollution Tracing for Source Attribution), a novel hybrid deep learning model designed for the accurate identification and quantification of air pollution sources. AirTrace-SA comprises three main components: a hierarchical feature extractor (HFE) that extracts multi-scale features from chemical components, a source association bridge (SAB) that links chemical features to pollution sources through a multi-step decision mechanism, and a source contribution quantifier (SCQ) based on the TabNet regressor for the precise prediction of source contributions. Evaluated on real air quality datasets from five cities (Lanzhou, Luoyang, Haikou, Urumqi, and Hangzhou), AirTrace-SA achieves an average $R^2$ of 0.88 (ranging from 0.84 to 0.94 across 10-fold cross-validation), an average mean absolute error ($MAE$) of 0.60 (ranging from 0.46 to 0.78 across five cities), and an average root mean square error ($RMSE$) of 1.06 (ranging from 0.51 to 1.62 across ten pollution sources). The model outperforms baseline models such as 1D CNN and LightGBM in terms of stability, accuracy, and cross-city generalization. Feature importance analysis identifies the main contributions of source categories, further improving interpretability. By reducing the reliance on labor-intensive data collection and providing scalable, high-precision source tracing, AirTrace-SA offers a powerful tool for environmental management that supports targeted emission reduction strategies and sustainable development. Full article

Strawberry post-harvest losses are estimated at 50%, due to improper handling and harvest timing, necessitating the use of non-invasive methods. This study develops a non-invasive in situ bioelectrical spectroscopy for strawberry peduncles. Based on traditional assessments and invasive metrics, 100 physiologically ripe (PR) and 100 commercially mature (CM) strawberries were distinguished. Spectra from their peduncles were measured from 1 kHz to 1 MHz, collecting four parameters (magnitude (Z(f)), phase angle (θ(f)), resistance (R(f)), and reactance (X(f))), resulting in 80,000 raw data points. Through systematic spectral preprocessing, Bode and Cole–Cole plots revealed a distinction between PR and CM strawberries. Frequency selection identified seven key frequencies (1, 5, 50, 75, 100, 250, 500 kHz) for deriving 37 engineered features from spectral, extrema, and derivative parameters. Feature selection reduced these to 6 parameters: phase angle at 50 kHz (θ (50 kHz)); relaxation time (τ); impedance ratio (|Z_1k/Z_250k|); dispersion coefficient (α); membrane capacitance (Cm); and intracellular resistivity (ρi). Four algorithms (TabPFN, CatBoost, GPC, EBM) were evaluated with Monte Carlo cross-validation with five iterations, ensuring robust evaluation. CatBoost achieved the highest accuracy at 93.3% ± 2.4%. Invasive reference metrics showed strong correlations with bioelectrical parameters (r = 0.74 for firmness, r = −0.71 for soluble solids). These results demonstrate a solution for precise harvest classification, reducing post-harvest losses without compromising marketability. Full article

Although the Power Internet of Things (PIoT) significantly improves operational efficiency by enabling real-time monitoring, intelligent control, and predictive maintenance across the grid, its inherently open and deeply interconnected cyber-physical architecture concurrently introduces increasingly complex and severe security threats. Existing IoT security solutions are not fully adapted to the specific requirements of power systems, such as safety-critical reliability, protocol heterogeneity, physical/electrical context awareness, and the incorporation of domain-specific operational knowledge unique to the power sector. These limitations often lead to high false positives (flagging normal operations as malicious) and false negatives (failing to detect actual intrusions), ultimately compromising system stability and security response. To address these challenges, we propose a domain knowledge-driven threat source detection and localization method for the PIoT. The proposed method combines multi-source features—including electrical-layer measurements, network-layer metrics, and behavioral-layer logs—into a unified representation through a multi-level PIoT feature engineering framework. Building on advances in multimodal data integration and feature fusion, our framework employs a hybrid neural architecture combining the TabTransformer to model structured physical and network-layer features with BiLSTM to capture temporal dependencies in behavioral log sequences. This design enables comprehensive threat detection while supporting interpretable and fine-grained source localization. Experiments on a real-world Power Internet of Things (PIoT) dataset demonstrate that the proposed method achieves high detection accuracy and enables the actionable attribution of attack stages aligned with the MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) framework. The proposed approach offers a scalable and domain-adaptable foundation for security analytics in cyber-physical power systems. Full article

Objective: The risk of Abdominal Aortic Aneurysm (AAA) rupture is associated with the aneurysm size and growth rate. This study aims to provide a global description of growth rates per intervals of AAA diameter size for individuals in the Spanish population, to understand possible comorbidities associated with growth rate variability, and to assess practitioners on safe follow-up visits for AAA patients. Methods: We present the Triple-A Barcelona Study (TABS), a new hospital-based longitudinal study recruiting consecutive individuals with AAAs in Barcelona. So far, 469 individuals with measurements of the abdominal aortic diameter, along with anthropometric, clinical information, and blood samples for most follow-up visits, have been recruited. Statistical modeling was performed to identify the most relevant predictors of the diameter size and expansion in individuals with AAAs using linear mixed-effect models. Results: The average growth rate per interval was 0.78 (2.34) mm/year for aneurysms with an initial diameter between 30 and 40 mm, 1.22 (3.34) mm/year for aneurysms with an initial diameter between 40 and 50 mm, and 4.12 (5.09) mm/year for aneurysms with an initial diameter equal to or greater than 50 mm. The main factors determining the growth rate beyond the aortic diameter are sex and related comorbidities (COPD and DM). The estimated time to reach the surgical threshold for individuals with small aneurysms exceeded 10 years, on average. Conclusions: Overall, this study serves as a promising step towards the development of better prediction tools to assess clinical decisions in AAA patients in the Spanish population and to guide future screening policies. Full article

The integration of energy-active elements into the building envelope in the form of large-area heating/cooling, active thermal protection (ATP), thermal barriers (TB), and TABS represents a technical solution that is consistent with the principles of energy sustainability, resilience, and adaptability to climate change and ensures affordable and clean energy for all while protecting the climate in the context of the UN Sustainable Development Goals. The aim and innovation of our research is to develop energy multifunctional facades (EMFs) that are capable of performing a dual role, which includes the primary known energy functions of end elements and the additional innovative ability to serve as a source of heat/cooling/electricity. This new function of EMFs will facilitate heat dissipation from overheated facade surfaces, preheating of hot water, and electricity generation for the operation of building energy systems through integrated photovoltaic components. The theoretical assumptions and hypotheses presented in our previous research work must be verified by experimental measurements with predictions of the optimal operation of building energy systems. Most existing studies on thermal barriers are based on calculations. However, there are few empirical measurements that quantify the benefits of ATP in real operation and specify the conditions under which different types of ATP are feasible. In this article, we present the development, design, and implementation of an experimental prototype of a prefabricated building module with integrated energy-active elements. The aim is to fill the knowledge gaps by providing a comprehensive framework that includes the development, research, design, and implementation of combined energy systems for buildings. The design of energy systems will be developed in BIM. An important result of this research is the development of a technological process for the implementation of a contact insulation system with integrated ATP in modular and panel buildings with a lightweight envelope. Full article

The lack of interpretability in AI-based intrusion detection systems poses a critical barrier to their adoption in forensic cybersecurity, which demands high levels of reliability and verifiable evidence. To address this challenge, the integration of explainable artificial intelligence (XAI) into forensic cybersecurity offers a powerful approach to enhancing transparency, trust, and legal defensibility in network intrusion detection. This study presents a comparative analysis of SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) applied to Extreme Gradient Boosting (XGBoost) and Attentive Interpretable Tabular Learning (TabNet), using the UNSW-NB15 dataset. XGBoost achieved 97.8% validation accuracy and outperformed TabNet in explanation stability and global coherence. In addition to classification performance, we evaluate the fidelity, consistency, and forensic relevance of the explanations. The results confirm the complementary strengths of SHAP and LIME, supporting their combined use in building transparent, auditable, and trustworthy AI systems in digital forensic applications. Full article

This study proposes a predictive framework that integrates machine learning techniques with Transactional Net Promoter Score (tNPS) data to enhance sustainable Human Resource management. A synthetically generated dataset, simulating real-world employee feedback across divisions and departments, was used to classify employee performance and engagement levels. Six machine learning models such as XGBoost, TabNet, Random Forest, Support Vector Machines, K-Nearest Neighbors, and Neural Architecture Search were applied to predict high-performing and at-risk employees. XGBoost achieved the highest accuracy and robustness across key performance metrics, including precision, recall, and F1-score. The findings demonstrate the potential of combining real-time sentiment data with predictive analytics to support proactive HR strategies. By enabling early intervention, data-driven workforce planning, and continuous performance monitoring, the proposed framework contributes to long-term employee satisfaction, talent retention, and organizational resilience, aligning with sustainable development goals in human capital management. Full article

Rapid and efficient evaluation of cultivated land quality in black soil regions at the farm scale using remote sensing techniques is crucial for resource protection. However, current studies face challenges in developing convenient and reliable models that directly leverage raw spectral reflectance. Therefore, this study develops and validates a deep learning framework specifically for this task. The framework first selects remote sensing images from typical periods using a Random Forest model in Google Earth Engine (GEE). Subsequently, the raw spectral reflectance data from these images, without any transformation into vegetation indices, are directly input into an optimized BO-Stacking-TabNet model. This model is enhanced through a two-step Stacking ensemble process and a Bayesian optimization algorithm. A case study at Shuanghe Farm in Northeast China shows that (1) compared to the BO-Stacking-TabNet model using vegetation indices as input, the BO-Stacking-TabNet model based on spectral reflectance as the input indicator achieved an improvement of 10.62% in Accuracy, 1.55% in Precision, 11.05% in Recall, and 10.18% in F1-score. (2) Compared to the original TabNet model, the BO-Stacking-TabNet model optimized by the two-step Stacking process and Bayesian optimization algorithm improved Accuracy by 2.13%, Precision by 12.59%, Recall by 1.83%, and F1-score by 2.19%. These results demonstrate the reliability of the new farm-scale black soil region cultivated land evaluation method we proposed. The method provides significant references for future research on cultivated land quality assessment at the farm scale in terms of remote sensing image data processing and model construction. Full article

The tomato leaf miner, Tuta absoluta (Lepidoptera: Gelechiidae), is a destructive pest of Solanaceae crops worldwide. Its olfactory system plays an important role in locating mating partners and recognizing host plants. Understanding its olfactory recognition mechanism, particularly the function of odorant-binding proteins (OBPs), may reveal potential targets for pest management. In this study, we characterized two antenna-specific OBPs, TabsOBP45 and TabsOBP46, which were identified from the T. absoluta genome. Sequence analysis revealed that both TabsOBPs belong to the classic OBP subfamily, which is characterized by the presence of six conserved cysteine residues and an N-terminal signal peptide. Both TabsOBPs showed predominant antennal expression in quantitative real-time PCR (qRT-PCR) assays, suggesting their key roles in olfactory perception. Fluorescence competitive binding assays with a total of 63 tested volatiles revealed that 13 compounds exhibited strong binding affinities (Ki < 22 µM) to TabsOBP45, with the highest binding affinity to β-ionone, β-caryophyllene, terpinolene, and cinnamaldehyde. Nine compounds showed strong binding affinities to TabsOBP46, with the strongest binding to 4-anisaldehyde, 4-methoxybenzaldehyde, cinnamaldehyde, and β-ionone. Molecular docking analysis revealed the key residues involved in β-ionone binding: TabsOBP45 interacted with ILE8, ALA9, PHE12, TRP37, ILE92, PHE94, THR115, and PHE118, while TabsOBP46 interacted with ILE8, PHE12, PHE36, TRP37, ILE92, LEU94, PHE118, and VAL134. These results provide new insights into the olfactory mechanism of T. absoluta and potential molecular targets for the development of olfactory-based pest control strategies. Full article

Soybean frogeye leaf spot (FLS), a serious soybean disease, causes severe yield losses in the largest production regions of China. However, both conventional field monitoring and machine learning algorithms remain challenged in achieving rapid and accurate detection. In this study, an HSDT-TabNet model was proposed for the grading of soybean FLS under field conditions by analyzing unmanned aerial vehicle (UAV)-based hyperspectral data. This model employs a dual-path parallel feature extraction strategy: the TabNet path performs sparse feature selection to capture fine-grained local discriminative information, while the hierarchical soft decision tree (HSDT) path models global nonlinear relationships across hyperspectral bands. The features from both paths are then dynamically fused via a multi-head attention mechanism to integrate complementary information. Furthermore, the overall generalization ability of the model is improved through hyperparameter optimization based on the tree-structured Parzen estimator (TPE). Experimental results show that HSDT-TabNet achieved a macro-accuracy of 96.37% under five-fold cross-validation. It outperformed the TabTransformer and SVM baselines by 2.08% and 2.23%, respectively. For high-severity cases (Level 4–5), the classification accuracy exceeded 97%. This study provides an effective method for precise field-scale crop disease monitoring. Full article

In this study, landslide risk assessment was conducted in the Renhe District, Panzhihua City, China. Firstly, based on 190 landslide points and 10 influencing factors, the landslide hazard was assessed using three models: random forest (RF), eXtreme Gradient Boosting (XGBoost), and Tabular Prior-data Fitted Network (TabPFN). The results indicate that the RF and XGBoost models exhibit comparable performance, both demonstrating strong generalization and accuracy, with the RF model achieving superior generalization, as evidenced by an area-under-the-curve (AUC) value of 0.9471. While the AUC value of TabPFN is 0.9243, indicating higher accuracy, it also poses a risk of overfitting and is therefore more suitable for applications involving small sample sizes and the need for rapid responses. The vulnerability assessment utilized the Analytic Hierarchy Process (AHP) to determine the weights of four disaster-bearing bodies, with sensitivity analysis revealing that road type was the most sensitive vulnerability factor. Finally, the landslide risk-assessment map of the Renhe District was produced by integrating the landslide hazard assessment map with the vulnerability assessment map. The findings indicate that the high-risk zones comprised 2.08% of the research region, which includes three principal train stations and necessitates enhanced protective measures. The medium-risk zones comprise 34.23% of the total area and are scattered throughout the region. It is important to enhance local capabilities for landslide monitoring and early warning systems. Relevant conclusions can provide a significant reference for landslide disaster prevention and mitigation work in the Renhe District and help ensure the safe operation of public transport infrastructure, such as railway stations and airports in the district. Full article