Search Results (4,100)

The world has adopted so many IoT devices but it comes with its own share of security vulnerabilities. One such issue is ARP spoofing attack which allows a man-in-the-middle to intercept packets and thereby modify the communication. Also, this allows an intruder to gain access to the user’s entire local area network. The ACI-IoT-2023 dataset captures ARP spoofing attacks, yet its absence of specified extracted features hinders its application in machine learning-aided intrusion detection systems. To combat this, we present a framework for ARP spoofing detection which improves the dataset by extracting ARP-specific features and evaluating their impact under different time-window configurations. Beyond generic feature engineering and model evaluation, we contribute by treating ARP spoofing as a time-window pattern and aligning the window length with observed spoofing persistence from the dataset timesheet—turning window choice into an explainable, repeatable setting for constrained IoT devices; by standardizing deployment-oriented efficiency profiling (inference latency, RAM usage, and model size) reported alongside accuracy, precision, recall and F1-scores to enable edge-feasible model selection; and by providing an ARP-focused, reproducible pipeline that reconstructs L2 labels from public PCAPs and derives missing link-layer indicators, yielding a transparent path from labeling to windowed features to training evaluation. Our research systematically analyzes five models with multiple time-windows, including Decision Tree, Random Forest, XGBoost, CatBoost, and K-Nearest Neighbors. This study shows that XGBoost and CatBoost provide maximum performance at the 1800 s window that corresponds to the longest spoofing duration in the timesheet, achieving accuracy greater than 0.93%, precision above 0.95%, recall near 0.91%, and F1-scores above 0.93%. Although Decision Tree has the least inference latency (∼0.4 ms.), its lower recall risks missed attacks. By contrast, XGBoost and CatBoost sustain strong detection with less than 6$ ms inference and moderate RAM, indicating practicality for IoT deployment. We also observe diminishing returns beyond (∼1800 s) due to temporal over-aggregation. Full article

The fermentation of Lactiplantibacillus plantarum is a complex bioprocess due to the nonlinear and dynamic nature of microbial growth. Traditional monitoring methods often fail to provide early and actionable insights into fermentation outcomes. This study proposes a deep learning-based predictive system using convolutional neural networks (CNNs) to classify fermentation trajectories and anticipate final cell counts based on the first 24 h of process data. A total of 52 fermentation runs were conducted, during which real-time parameters, including pH, temperature, and dissolved oxygen, were continuously recorded and transformed into time-series feature vectors. After rigorous preprocessing and feature selection, the CNN was trained to classify fermentation outcomes into three categories: successful, semi-successful, and failed batches. The model achieved a classification accuracy of 97.87%, outperforming benchmark models such as LSTM and XGBoost. Validation experiments demonstrated the model’s practical utility: early predictions enabled timely manual interventions that effectively prevented batch failures or improved suboptimal fermentations. These findings suggest that deep learning provides a robust and scalable framework for real-time fermentation control, with significant implications for enhancing efficiency and reducing costs in industrial probiotic production. Full article

As global population ageing accelerates and urban governance increasingly prioritizes livability and age-friendly services, the 15-minute living circles concept has emerged as a key strategy to support daily walking exercise, social participation, and healthy ageing. In waterfront cities, blue spaces function as important everyday settings that contribute to environmental quality, recreational opportunities, and ecosystem services for older adults. This study extends the conventional 5D built environment framework by explicitly integrating blue space elements and characterizes older adults’ walking behaviour using four indicators across two dimensions (temporal and preference-based). We applied XGBoost regression and multiscale geographically weighted regression (MGWR) to identify threshold effects and spatial heterogeneity of blue space elements on older adults’ walking, and used K-means clustering to delineate blue space advantage zones within living circles. The results show that blue space accessibility, street scale, and water body density exhibit significant nonlinear relationships with older adults’ walking. Blue space elements shape walking behavior differentially and with pronounced spatial variation: in some living circles they encourage longer, recreational walks, while in others they stimulate high-frequency, short-distance walking. These effects produce destination preferences and time period preferences. The study highlights the pivotal role of blue spaces in age-friendly living circles and, based on spatial synergies among blue space advantage zones and their components, proposes renewal strategies including expanding the functional reach of blue spaces, constructing blue slow-walking corridors, and integrating blue–green symbiotic networks. Full article

Background and Objectives: Postoperative atrial fibrillation (POAF) remains one of the most frequent complications after cardiac surgery, increasing the risk of morbidity, prolonged hospitalization, and adverse long-term outcomes. Although several clinical and echocardiographic factors have been associated with POAF, the integrated contribution of atrial conduction delay, biatrial mechanics, and atrioventricular coupling to arrhythmogenesis remains unclear. Materials and Methods: This retrospective study included 131 adult patients undergoing coronary artery bypass grafting and/or aortic valve replacement. Preoperative echocardiography within one week before surgery provided detailed assessment of atrial phasic function, valvular motion, and total atrial conduction time (TACT). Univariate analysis was followed by multivariable modeling using penalized logistic regression (Elastic Net) to identify the most robust predictors of POAF. Discriminative performance and calibration were evaluated via receiver operating characteristic (ROC) and calibration analysis. An exploratory Extreme Gradient Boosting (XGBoost) model with SHapley Additive exPlanations (SHAP) analysis was used to confirm the stability and directionality of nonlinear feature interactions. Results: POAF occurred in 47 (36%) patients. The Elastic Net model identified prolonged TACT, reduced right atrial active emptying fraction (RAAEF), increased indexed minimal left atrial volume (MIN LA/BSA), and lower tricuspid annular plane systolic excursion (TAPSE) as the most informative predictors. The model demonstrated excellent internal discrimination (AUC = 0.95; 95% CI 0.91–0.99) and satisfactory calibration (Hosmer–Lemeshow p = 0.41). Exploratory XGBoost analysis yielded concordant feature hierarchies, confirming the physiological consistency of the results. Conclusions: POAF arises from an identifiable electromechanical substrate characterized by atrial conduction delay, biatrial mechanical impairment, and reduced atrioventricular coupling. A parsimonious, regularized statistical model accurately delineated this profile, while complementary machine-learning analysis supported its internal validity. These findings underscore the potential of echocardiographic electromechanical parameters for refined preoperative risk stratification, pending prospective multicenter validation. Full article

Background: Parkinson’s disease (PD) is a degenerative neurological disorder that greatly affects motor and speech functions; therefore, early diagnosis is vital for improving patients’ quality of life. This work introduces a unified and explainable AI framework for PD detection that integrates ensemble and deep learning models with transparent interpretability techniques. Methods: Acoustic features were extracted from the Parkinson's Voice Disorder Dataset, and a broad suite of machine learning and deep learning models was evaluated, including traditional classifiers (Logistic Regression, Decision Tree, KNN, Linear Regression, SVM), ensemble methods (Random Forest, Gradient Boosting, XGBoost, LightGBM), and neural architectures (CNN, LSTM, GAN). Results: The ensemble methods—specifically LightGBM (LGBM) and Random Forest (RF)—achieved the best performance, reaching state-of-the-art accuracy (98.01%) and ROC-AUC (0.9914). Deep learning models like CNN and GAN produced competitive results, validating their ability to capture nonlinear and generative voice patterns. XAI analysis revealed that nonlinear acoustic biomarkers such as spread2, PPE, and RPDE are the most influential predictors, consistent with clinical evidence of dysphonia in PD. Conclusions: The proposed framework achieves a strong balance between predictive accuracy and interpretability, representing a clinically relevant, scalable, and non-invasive solution for early Parkinson’s detection. Full article

Purpose: This study aimed to develop a precise predictive model to assess the risk of radiation pneumonitis (RP) and three-year survival in patients with non-small cell lung cancer (NSCLC) following volumetric modulated arc therapy (VMAT). Radiomics features, ensemble stacking, and explainable artificial intelligence (XAI) were integrated to enhance predictive performance and clinical interpretability. Materials and Methods: A retrospective cohort of 221 NSCLC patients treated with VMAT at Kaohsiung Veterans General Hospital between 2013 and 2023 was analyzed, including 168 patients for RP prediction (47 with ≥grade 2 RP) and 118 patients for survival prediction (34 deaths). Clinical variables, dose–volume histogram (DVH) parameters, and radiomic features (original, Laplacian of Gaussian [LoG], and wavelet filtered) were extracted. ANOVA was used for initial feature reduction, followed by LASSO and Boruta-SHAP for feature selection, which formed 10 feature subsets. The data were divided at an 8:2 ratio into training and testing sets, with SMOTE balancing and 10-fold cross-validation for parameter optimization. Six models—logistic regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbors (KNN), XGBoost, and Ensemble Stacking—were evaluated in terms of the AUC, accuracy (ACC), negative predictive value (NPV), precision, and F1 score. SHAP analysis was applied to interpret feature contributions. Results: For RP prediction, the LASSO-selected radiomic subset (FR) combined with Ensemble Stacking achieved optimal performance (AUC 0.91, ACC 0.89), with SHAP identifying V40 Firstorder_Min as the most influential feature. For survival prediction, the FR subset yielded an AUC of 0.97, an ACC of 0.92, and an NPV of 1.00, with V10 Wavelet Firstorder_Min as the top contributor. The multimodal subset (FC+R) also performed strongly, achieving an AUC of 0.91 for RP and 0.96 for survival. Conclusions: This study demonstrated the superior performance of radiomics combined with Ensemble Stacking and XAI for the prediction of RP and survival following VMAT in patients with NSCLC. SHAP-based interpretation enhances transparency and clinical trust, offering a robust foundation for personalized radiotherapy and precision medicine. Full article

PM_2.5 and O₃ are now the primary air pollutants in Chinese cities and pose serious risks to human health. In particular, the two- and three-dimensional patterns of urban buildings and green spaces play a crucial role in governing the dispersion of air pollutants. Using multi-source geospatial data and 2D/3D morphology metrics, this study employs an Extreme Gradient Boosting (XGBoost) model coupled with Shapley Additive Explanations (SHAP) to analyze the nonlinear effects of 2D/3D landscape and green space patterns on PM_2.5 and O₃ concentrations in the central urban area of Guiyang City. The results indicate the following findings: (1) PM_2.5 exhibits a U-shaped seasonal pattern, being higher in winter and spring and lower in summer and autumn, whereas O₃ displays an inverted U-shaped pattern, being higher in spring and summer and lower in autumn and winter. (2) PM_2.5 concentrations are higher in suburban and industrial zones and lower in central residential areas, while O₃ concentrations increase from the urban core toward the suburbs. (3) MV, BSI, BSA, BEL, BD, FAR, and BV show significant positive correlations with both PM_2.5 and O₃ (p < 0.001), whereas TH shows a significant negative correlation with PM_2.5 (p < 0.001). (4) High-density and complex building-edge patterns intensify both PM_2.5 and O₃ pollution by hindering urban ventilation and enhancing pollutant accumulation, whereas moderate vertical heterogeneity and greater tree height effectively reduce PM_2.5 concentrations but simultaneously increase O₃ concentrations due to enhanced VOC emissions. Urban form and vegetation jointly regulate air quality, highlighting the need for integrated urban planning that balances building structures and green infrastructure. The findings of this study provide practical implications for urban design and policymaking aimed at the coordinated control of PM_2.5 and O₃ pollution through the optimization of urban morphology. Full article

Road agglomerate fog seriously threatens driving safety, making real-time fog state detection crucial for implementing reliable traffic control measures. With advantages in aerial perspective and a broad field of view, UAVs have emerged as a novel solution for road agglomerate fog monitoring. This paper proposes an agglomerate fog detection method based on the fusion of SURF and optical flow characteristics. To synthesize an adequate agglomerate fog sample set, a novel network named FogGAN is presented by injecting physical cues into the generator using a limited number of field-collected fog images. Taking the region of interest (ROI) for agglomerate fog detection in the UAV image as the basic unit, SURF is employed to describe static texture features, while optical flow is employed to capture frame-to-frame motion characteristics, and a multi-feature fusion approach based on Bayesian theory is subsequently introduced. Experimental results demonstrate the effectiveness of FogGAN for its capability to generate a more realistic dataset of agglomerate fog sample images. Furthermore, the proposed SURF and optical flow fusion method performs higher precision, recall, and F1-score for UAV perspective images compared with XGBoost-based and survey-informed fusion methods. Full article

Under the global goals of carbon peaking and carbon neutrality, China’s northern agro-pastoral ecotone—an ecologically fragile transition zone with drastic land use/cover change (LUCC)—is characterized by a lack of in-depth understanding of its “land use conflict–carbon sink response” mechanism, which is essential for regional land optimization and carbon neutrality. This study quantified the spatiotemporal dynamics of carbon storage in the zone from 2000 to 2020 using the InVEST model and identified key driving factors by combining the XGBoost model (R² = 0.73–0.88) with the SHAP framework. The results showed that regional total carbon storage increased by 30.11 × 10⁶ tons (a net growth of 0.57%), mainly driven by forest carbon sinks (+65.74 × 10⁶ tons, accounting for 218.3% of the total increase), while cropland and grassland underwent continuous carbon loss (−53.87 × 10⁶ tons and −35.80 × 10⁶ tons, respectively). Spatially, this presents a pattern of “high-value agglomeration in the central–southern region and low-value fragmentation at urban–rural edges”. The Normalized Difference Vegetation Index (NDVI) was the primary driver (average SHAP value: 426.15–718.91), with its interacting temperature factor evolving from air temperature (2000) to nighttime surface temperature (2020). This study reveals the coupling mechanism of “vegetation restoration–microenvironment regulation–carbon sink gain” driven by the Grain for Green Program, providing empirical support for land use optimization and carbon neutrality in agro-pastoral areas. Full article

Wildfires pose a growing threat to ecosystems, infrastructure, and public safety, particularly in the province of British Columbia (BC), Canada. In recent years, the frequency, severity, and scale of wildfires in BC have increased significantly, largely due to climate change, human activity, and changing land use patterns. This study presents a comprehensive, data-driven approach to wildfire prediction, leveraging advanced machine learning (ML) and deep learning (DL) techniques. A high-resolution dataset was constructed by integrating five years of wildfire incident records from the Canadian Wildland Fire Information System (CWFIS) with ERA5 reanalysis climate data. The final dataset comprises more than 3.6 million spatiotemporal records and 148 environmental, meteorological, and geospatial features. Six feature selection techniques were evaluated, and five predictive models—Random Forest, XGBoost, LightGBM, CatBoost, and an RNN + LSTM—were trained and compared. The CatBoost model achieved the highest predictive performance with an accuracy of 93.4%, F1-score of 92.1%, and ROC-AUC of 0.94, while Random Forest achieved an accuracy of 92.6%. The study identifies key environmental variables, including surface temperature, humidity, wind speed, and soil moisture, as the most influential predictors of wildfire occurrence. These findings highlight the potential of data-driven AI frameworks to support early warning systems and enhance operational wildfire management in British Columbia. Full article

Accurate estimation of carbon sequestration at the single-tree scale is essential for understanding forest carbon dynamics and supporting precision forestry under global carbon-neutral goals. Traditional allometric models often neglect environmental variability, while data-driven machine learning approaches suffer from limited interpretability. To bridge this gap, we developed a hybrid prediction framework that integrates a Structural Causal Model (SCM) with an Enhanced Long Short-Term Memory (LSTM) network. Using 47-year observation data (1975–2022) of Mongolian oak (*Quercus mongolica* Fisch. ex Ledeb.) from the Laoyeling Ecological Station, the SCM was applied to infer causal relationships among growth and environmental factors, while the Enhanced-LSTM combined multiscale convolution and self-attention modules to capture nonlinear temporal dependencies. Results showed that the proposed SCM-Enhanced-LSTM achieved the highest predictive performance (R² = 0.944, RMSE = 0.079 kg, MAE = 0.064 kg), outperforming Bi-LSTM and XGBoost models by over 20% in accuracy and maintaining robustness under noise perturbations. Causal analysis identified soil moisture and stem diameter as the dominant drivers of carbon increment. This study provides a transparent, interpretable, and high-precision framework for single-tree carbon sequestration prediction, offering methodological support for fine-scale forest carbon accounting and sustainable management strategies. Full article

The field of hard milling has recently witnessed growing interest in environmentally sustainable machining practices. Among these, Minimum Quantity Lubrication (MQL) has emerged as an effective strategy, offering not only reduced environmental impact but also economic benefits and enhanced cooling performance compared to conventional flood cooling methods. In hard milling operations, cutting temperature is a critical factor that significantly influences the quality of the finished component. Proper control of this parameter is essential for producing high-precision workpieces, yet measuring cutting temperature is often complex, time-consuming, and costly. These challenges can be effectively addressed by predicting cutting temperature using advanced Machine Learning (ML) models, which offer a faster and more efficient alternative to direct measurement. In this context, the present study investigates and compares the performance of Conventional Minimum Quantity Lubrication (CMQL) and Graphene-Enhanced MQL (GEMQL), with sesame oil serving as the base fluid, in terms of their effect on cutting temperature. The experiments are structured using a Taguchi L36 orthogonal array, with key variables including cutting speed, feed rate, MQL jet pressure, and the type of cooling applied. Additionally, the study explores the predictive capabilities of various advanced ML models, including Decision Tree, XGBoost Regressor, K-Nearest Neighbor, Random Forest Regressor, and CatBoost Regressor, along with a Hybrid Stacking Machine Learning Model (HSMLM) for estimating cutting temperature. The results demonstrate that the GEMQL setup reduced cutting temperature by 36.8% compared to the CMQL environment. Among all the ML models tested, HSMLM exhibited superior predictive performance, achieving the best evaluation metrics with a mean absolute error of 3.15, root mean squared error (RMSE) of 5.3, mean absolute percentage error of 3.9, coefficient of determination (R²) of 0.91, and an overall accuracy of 96%. Full article

The rapid expansion of the Industrial Internet of Things (IIoT) within smart grid infrastructures has increased the risk of sophisticated cyberattacks, where severe class imbalance and stringent real-time requirements continue to hinder the effectiveness of conventional intrusion detection systems (IDSs). Existing approaches often achieve high accuracy on specific datasets but lack generalizability, interpretability, and stability when deployed across heterogeneous IIoT environments. This paper introduces AegisGuard, a hybrid intrusion detection framework that integrates an adaptive four-stage sampling process with a calibrated ensemble learning strategy. The sampling module dynamically combines SMOTE, SMOTE-ENN, ADASYN, and controlled under sampling to mitigate the extreme imbalance between benign and malicious traffic. A quantum-inspired feature selection mechanism then fuses statistical, informational, and model-based significance measures through a trust-aware weighting scheme to retain only the most discriminative attributes. The optimized ensemble, comprising Random Forest, Extra Trees, LightGBM, XGBoost, and CatBoost, undergoes Optuna-based hyperparameter tuning and post-training probability calibration to minimize false alarms while preserving accuracy. Experimental evaluation on four benchmark datasets demonstrates the robustness and scalability of AegisGuard. On the CIC-IoT 2023 dataset, it achieves 99.6% accuracy and a false alarm rate of 0.31%, while maintaining comparable performance on TON-IoT (98.3%), UNSW-NB15 (98.4%), and Bot-IoT (99.4%). The proposed framework reduces feature dimensionality by 54% and memory usage by 65%, enabling near real-time inference (0.42 s per sample) suitable for operational IIoT environments. Full article

To meet the increasing demands for data, elastic optical networks (EONs) require highly efficient resource management. While classical Routing and Spectrum Assignment (RSA) algorithms establish a path and allocate spectrum, advanced versions such as Routing, Modulation-format-selection, and Spectrum Assignment (RMSA) also optimize modulation format selection. However, these approaches often lack adaptability to diverse network aspects. The hybrid routing and spectrum assignment (HRSA) algorithm offers a more flexible and robust approach by providing multiple choices between route (resource savings) and spectrum prioritization (fragmentation mitigation and network load balancing) for each network node pair. Despite its potential, the adaptive nature of HRSA introduces complexity, and the influence of topological features on its decisions remains not fully understood. This knowledge gap hinders the ability to optimize network design and resource allocation fully. This paper examines how topological features influence HRSA’s adaptive decisions regarding routing and spectrum assignment prioritization for source-destination node pairs in EONs. By employing machine learning approaches—Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—we model and identify the key topological features that influence HRSA’s decision-making. Then, we compare the models generated by each approach and extract insights using an a posteriori analysis technique to evaluate feature importance. Our results show the algorithm’s behavior is highly predictable (over 91% accuracy), with decisions driven primarily by the network’s structure and node metrics. This work advances the understanding of how topological features influence the RSA problem. Full article

Early and reliable detection of skin cancer is critical for improving patient outcomes and minimizing diagnostic uncertainty in dermatological practice. This study proposes an interpretable hybrid framework that integrates ConvMixer-based deep feature extraction with gradient boosting classifiers to perform multi-class skin lesion classification on the publicly available PAD-UFES-20 dataset. The dataset contains 2298 dermoscopic and clinical images with associated patient metadata (age, gender, and anatomical site), enabling a joint evaluation of demographic and anatomical factors influencing model performance. After data augmentation, normalization, and class balancing using Borderline-SMOTE, Image embeddings extracted via ConvMixer were integrated with patient metadata and subsequently classified using CatBoost, XGBoost, and LightGBM. Among these, CatBoost achieved the highest macro-AUC of 0.94 and macro-F1 of 0.88, with a melanoma sensitivity of 0.91, while maintaining good calibration (Brier score = 0.06). Grad-CAM and SHAP analyses confirmed that the model’s attention and feature importance correspond to clinically relevant lesion regions and attributes. The results highlight that age and body-region imbalances in the PAD-UFES-20 dataset modestly influence predictive behavior, emphasizing the importance of balanced sampling and stratified validation. Overall, the proposed ConvMixer–CatBoost framework provides a compact, explainable, and generalizable solution for AI-assisted skin cancer classification. Full article