Search Results (1,520)

Unrecognized mechanical faults and emergency sounds in vehicles can compromise safety, particularly for individuals with hearing impairments and in sound-insulated or autonomous driving environments. As intelligent transportation systems (ITSs) evolve, there is a growing need for inclusive, non-intrusive, and real-time diagnostic solutions that enhance situational awareness and accessibility. This study introduces an interpretable, sound-based machine learning framework to detect vehicle faults and emergency sound events using acoustic signals as a scalable diagnostic source. Three purpose-built datasets were developed: one for vehicular fault detection, another for emergency and environmental sounds, and a third integrating both to reflect real-world ITS acoustic scenarios. Audio data were preprocessed through normalization, resampling, and segmentation and transformed into numerical vectors using Mel-Frequency Cepstral Coefficients (MFCCs), Mel spectrograms, and Chroma features. To ensure performance and interpretability, feature selection was conducted using SHAP (explainability), Boruta (relevance), and ANOVA (statistical significance). A two-phase experimental workflow was implemented: Phase 1 evaluated 15 classical models, identifying ensemble classifiers and multi-layer perceptrons (MLPs) as top performers; Phase 2 applied advanced feature selection to refine model accuracy and transparency. Ensemble models such as Extra Trees, LightGBM, and XGBoost achieved over 91% accuracy and AUC scores exceeding 0.99. SHAP provided model transparency without performance loss, while ANOVA achieved high accuracy with fewer features. The proposed framework enhances accessibility by translating auditory alarms into visual/haptic alerts for hearing-impaired drivers and can be integrated into smart city ITS platforms via roadside monitoring systems. Full article

Cable service providers face significant challenges in managing Hybrid Fiber–Coaxial (HFC) networks due to the growing demand for high-speed services. Ensuring high service availability is critical to preventing customer attrition. This study employs machine learning techniques, specifically Decision Tree and Random Forest models, for proactive fault detection in HFC networks using data from the Simple Network Management Protocol (SNMP). Two operational scenarios were considered: a network-wide model and node-specific models. The dataset for fault detection exhibited a severe class imbalance, with outage events being extremely rare. To address this, the Synthetic Minority Oversampling Technique (SMOTE), which generates synthetic samples of the minority class to balance the dataset, was applied. This significantly improved recall and F1-scores—the harmonic mean of precision and recall—while maintaining high precision. The results demonstrate that these machine learning algorithms achieve up to 98% accuracy, and the SMOTE-enhanced models provide more reliable detection of connectivity faults. This approach is highly effective for cable operators in maintaining quality of service, enabling proactive management of problems and enhancement of network performance. Full article

Traditional machine learning approaches for 5G network management relieve data from operational networks, which are often noisy and confounded, making it difficult to identify key influencing factors. This research addresses the critical gap between correlation-based prediction and interpretable, data-driven explanation. To this end, a software-defined standalone 5G architecture was developed using srsRAN and Open5GS to support multi-user scenarios. A multi-user environment was then simulated with GNU Radio, from which the initial dataset was collected. This dataset was further generated using a Conditional Tabular Generative Adversarial Network (CTGAN) to improve diversity and balance. Several machine learning models, including Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and XGBoost, were trained and evaluated for predicting network performance. Among them, XGBoost achieved the best results, with an R² score of 0.998. To interpret the model, we conducted a SHAP (SHapley Additive exPlanations) analysis, which revealed that the download-to-upload bitrate ratio (dl_ul_ratio) and upload bitrate (brate_ul) were the most influential features. By leveraging a controlled experimental 5G environment, this study demonstrates how machine learning can move beyond predictive accuracy to uncover the fundamental principles governing 5G system performance, providing a robust foundation for future network optimization. Full article

Probabilistic roadmap (PRM) methods are widely used for robot navigation in both 2D and 3D environments; however, a major drawback is that the raw paths tend to be jagged. Executing a trajectory along such paths can lead to significant overshoots and tight turns, making it difficult to achieve a near-optimal solution under motion constraints. This paper presents an enhanced PRM-based path planning approach designed to improve path quality and computational efficiency. The method integrates advanced sampling strategies, adaptive neighbor selection with spatial data structures, and multi-stage path post-processing. In particular, shortcut smoothing and polynomial fitting are used to generate smoother trajectories suitable for motion-constrained robots. The proposed hybrid sampling scheme biases sample generation toward critical regions—near obstacles, in narrow passages, and between the start and goal—to improve graph connectivity in challenging areas. An adaptive k-d tree-based connection strategy then efficiently builds a roadmap using variable connection radii guided by PRM* theory. Once a path is found using an any-angle graph search, post-processing is applied to refine it. Unnecessary waypoints are removed via line-of-sight shortcuts, and the final trajectory is smoothed using a fitted polynomial curve. The resulting paths are shorter and exhibit gentler turns, making them more feasible for execution. In simulated complex scenarios, including narrow corridors and cluttered environments, the advanced PRM achieved a 100% success rate where standard PRM frequently failed. It also reduced calculation time to 30% and peak turning angle by up to 50% compared to conventional methods. The approach supports dynamic re-planning: when the environment changes, the roadmap is efficiently updated rather than rebuilt from scratch. Furthermore, the use of an adaptive k-d tree structure and incremental roadmap updates leads to an order-of-magnitude speedup in the connection phase. These improvements significantly increase the planner’s path quality, runtime performance, and reliability. Quantitative results are provided to substantiate the performance gains of the proposed method. Full article

The accurate positioning and state estimation of surface vessels are prerequisites to autonomous navigation. Recently, the rapid development of 3D LiDARs has promoted the autonomy of both land and aerial vehicles, which has attracted the interest of researchers in the maritime community. However, in traditional maritime surface multi-scenario applications, LiDAR scan matching has low point cloud scanning and matching efficiency and insufficient positional accuracy when dealing with large-scale point clouds, so it has difficulty meeting the real-time demand of low-computing-power platforms. In this paper, we use ICP-SVD for point cloud alignment in the Stanford dataset and outdoor dock scenarios and propose an optimization scheme (iVox + ICP-SVD) that incorporates the voxel structure iVox. Experiments show that the average search time of iVox is 72.23% and 96.8% higher than that of ikd-tree and kd-tree, respectively. Executed on an NVIDIA Jetson Nano (four ARM Cortex-A57 cores @ 1.43 GHz) the algorithm processes 18 k downsampled points in 56 ms on average and 65 ms in the worst case—i.e., ≤15 Hz—so every scan is completed before the next 10–20 Hz LiDAR sweep arrives. During a 73 min continuous harbor trial the CPU temperature stabilized at 68 °C without thermal throttling, confirming that the reported latency is a sustainable, field-proven upper bound rather than a laboratory best case. This dramatically improves the retrieval efficiency while effectively maintaining the matching accuracy. As a result, the overall alignment process is significantly accelerated, providing an efficient and reliable solution for real-time point cloud processing. Full article

Binary code similarity detection (BCSD) plays an important role in software security. Recent deep learning-based methods have made great progress. Existing methods based on a single feature, such as semantics or graph structure, struggle to handle changes caused by the architecture or compilation environment. Methods fusing semantics and graph structure suffer from insufficient learning of the function, resulting in low accuracy and robustness. To address this issue, we proposed Fus, a method that integrates semantic information from the pseudo-C code and structural features from the Abstract Syntax Tree (AST). The pseudo-C code and AST are robust against compilation and architectural changes and can represent the function well. Our approach consists of three steps. First, we preprocess the assembly code to obtain the pseudo-C code and AST for each function. Second, we employ a Siamese network with CodeBERT models to extract semantic embeddings from the pseudo-C code and Tree-Structured Long Short-Term Memory (Tree LSTM) to encode the AST. Finally, function similarity is computed by summing the respective semantic and structural similarities. The evaluation results show that our method outperforms the state-of-the-art methods in most scenarios. Especially in large-scale scenarios, its performance is remarkable. In the vulnerability search task, Fus achieves the highest recall. It demonstrates the accuracy and robustness of our method. Full article

Nitrogen fertilization is decisive for maize productivity, fertilizer use efficiency, and sustainability, which calls for fast and nondestructive nutritional diagnosis. This study evaluated the classification of maize plant nutritional status from red, green, and blue (RGB) leaf images using texture attributes. A greenhouse experiment was conducted under a completely randomized factorial design with four nitrogen doses, one maize hybrid Pioneer 30F35, and four replicates, at two sampling times corresponding to distinct phenological stages, totaling thirty-two experimental units. Images were processed with the gray-level cooccurrence matrix computed at three distances 1, 3, and 5 pixels and four orientations 0°, 45°, 90°, and 135°, yielding eight texture descriptors that served as inputs to five supervised classifiers: an artificial neural network, a support vector machine, k nearest neighbors, a decision tree, and Naive Bayes. The results indicated that texture descriptors discriminated nitrogen doses with good performance and moderate computational cost, and that homogeneity, dissimilarity, and contrast were the most informative attributes. The artificial neural network showed the most stable performance at both stages, followed by the support vector machine and k nearest neighbors, whereas the decision tree and Naive Bayes were less suitable. Confusion matrices and receiver operating characteristic curves indicated greater separability for omission and excess classes, with D1 standing out, and the patterns were consistent with the chemical analysis. Future work should include field validation, multiple seasons and genotypes, integration with spectral indices and multisensor data, application of model explainability techniques, and assessment of latency and scalability in operational scenarios. Full article

Amid accelerating global nitrogen deposition, China has emerged as the world’s third-largest hotspot after Western Europe and North America. Disentangling how elevated N inputs interact with intensifying precipitation and silvicultural practices is therefore essential for forecasting forest responses to ongoing climate change. Taking advantage of the “canopy-simulated nitrogen deposition” platform in Jigongshan National Nature Reserve, we compared tree-level census data from 2012 and 2022 to quantify decadal shifts in neighborhood competition under seven nitrogen addition and rainfall enhancement regimes. After using ordered-sample clustering to identify eight competitors as the optimal neighborhood size, we applied the Hegyi family of competitive indices (CI, CI1, CI2, mCI, mCI1 and mCI2) to analyze competitive responses at three hierarchical levels: the entire stand, all surviving trees and three dominant species (Quercus acutissima, Quercus variabilis, and Liquidambar formosana). The results indicate: (1) Nitrogen addition and rainfall enhancement did not alter the dominant tree species of the stand, which remained primarily Q. acutissima, Q. variabilis, and L. formosana. (2) The competition indices based on all trees showed an upward trend, whereas those calculated for surviving trees and for dominant species declined markedly (surviving trees p < 0.1, L. formosana CI1 p < 0.05). (3) Although nitrogen addition treatments did not alter overall stand competition intensity, it relieved competitive pressure on surviving trees by suppressing interspecific interactions (CI2 and mCI2); intraspecific competition also weakened, but at a slower rate. (4) Interspecific competition intensity for surviving L. formosana decreased significantly, whereas competition indices for Q. acutissima and Q. variabilis remained statistically unchanged. (5) Nitrogen addition methods (canopy vs. understory) had no significant effect on competition indices, while nitrogen addition intensity exhibited a dose-dependent effect: high nitrogen addition significantly reduced interspecific competition intensity more than low nitrogen addition (p < 0.05). In summary, nitrogen deposition primarily regulates interspecific competition through concentration rather than pathway, providing scientific basis for adaptive management of broad-leaved mixed forests in transitional zones under sustained nitrogen deposition scenarios. Full article

This study focuses on determining stress distribution in elastic continuous beam foundations subjected to large eccentricities primarily induced by the overturning moments generated when horizontal forces, like those from earthquakes and wind, act on the superstructure. Traditional linear static solutions provide an incorrect stress distribution when a foundation loses partial contact with the ground, as they erroneously calculate tensile stress in the uplifted regions. This research aims to formulate a mathematical model that accurately calculates the corrected stress distribution. An optimization problem is defined to minimize the discrepancy between the external effects (loads and moments) from the superstructure and the internal resistance effects from the redistributed base stress under the condition of partial foundation uplift. To solve this, meta-heuristic optimization methods, including Artificial Bee Colony (ABC), Tree Seed Algorithm (TSA), and Biogeography-Based Optimization (BBO), are employed to derive accurate mathematical formulas. The performance of these methods is evaluated under varying soil conditions and loading scenarios. The Tree Seed Method has consistently delivered the most accurate results, with near-zero optimization errors. The findings provide the applicability of algorithmic methods and their potential for improving stress distribution modeling in elastic foundations. Full article

Structural adaptations of wood to environmental conditions play a crucial role in shaping its mechanical and hydraulic properties, which are vital for the performance and survival of fir and beech. In this study, we investigated how site-specific climatic conditions influence tree-ring widths and wood-anatomical traits of fir and beech in the Carpathians. Increment cores were collected from three forest stands across the Carpathians, each characterized by distinct climate regimes. We developed chronologies for mean tree-ring width (MRW), mean lumen area of vessels/tracheids (MLA), cell density (CD), relative conductive tissue area (RCTA), and, for fir, mean tangential cell wall thickness (CWTTAN), covering the period from 1980 to 2016. By comparing MRW and wood-anatomical traits with climatic variables—daily minimum and maximum temperatures and daily precipitation sums from E-OBS climate data—we identified clear differences among the three sites. The relationships between tree-ring widths and wood-anatomical traits varied between fir and beech, reflecting species-specific responses to local climate conditions. Notably, beech appeared more sensitive to warm summer temperatures, while fir was comparatively less affected. Evaluating the variability in radial growth and wood anatomy is essential for understanding the plasticity of fir and beech under diverse environmental conditions, and represents a first step toward predicting their responses to future climate scenarios. Full article

Mechanical vibrations induced by electromagnetic forces during transformer operation can lead to winding deformation or failure, an issue responsible for over 12% of all transformer faults. While previous studies have predominantly relied on accelerometers for vibration monitoring, this study explores the use of an optical sensor for real-time vibration measurement in a dry-type transformer. Experiments were conducted using a custom-designed single-phase transformer model specifically developed for laboratory testing. This experimental setup offers a unique advantage: it allows for the interchangeable simulation of healthy and deformed winding sections without causing permanent damage, enabling controlled and repeatable testing scenarios. The transformer’s secondary winding was short-circuited, and three levels of current (low, intermediate, and high) were applied to simulate varying stress conditions. Vibration displacement data were collected under load to assess mechanical responses. The primary goal was to classify this vibration data to localize potential winding deformation faults. Five supervised learning algorithms were evaluated: Random Forest, Support Vector Machine, K-Nearest Neighbors, Logistic Regression, and Decision Tree classifiers. Hyperparameter tuning was applied, and a comparative analysis among the top four models yielded average prediction accuracies of approximately 60%. These results, achieved under controlled laboratory conditions, highlight the promise of this approach for further development and future real-world applications. Overall, the combination of optical sensing and machine learning classification offers a promising pathway for proactive monitoring and localization of winding deformations, supporting early fault detection and enhanced reliability in power transformers. Full article

The acquisition of plant ecological indicators, such as leaf area index and leaf area density values, typically relies on labor-intensive field sampling and measurements, which are often time-consuming and hinder large-scale application. As different plant ecological indicators are closely related to plants’ geometric characteristics, the development of dynamic correlation and prediction methods for relevant indicators has become an important research topic. However, existing 3D plant models are mainly used for visualization purposes, which cannot accurately reflect the plant’s growth process or geometric characteristics. This study presents a workflow for parametric 3D plant modeling and ecological indicator analysis, integrating dynamic plant modeling, indicator calculation, and microclimate simulation. With the established plant model, a method for calculating and analyzing ecological indicators, including the leaf area index, leaf area density, aboveground biomass, and aboveground carbon storage, was then proposed. A method for exporting the model-generated data into ENVI-met v.5.0 to simulate the microclimate environment was also established. Then, by taking Daijia Lake Park as an example, this study utilized site planting construction drawings and field survey data to perform parametric modeling of 21,685 on-site trees from 65 species at three different growth stages using Blender v.4.0 and The Grove plugin v.10. The generated plant model’s accuracy was then verified using the 3D IoU ratio between the models and on-site scanned point cloud data. Plant ecological indicators at various stages were then extracted and exported to ENVI-met for microclimate analysis. The workflow integrates the simulation of plant growth dynamics and their interactions with environmental factors. It can also be used for scenario-based predictions in planting design and serves as a basis for urban green space monitoring and management. Full article

Articulated tracked robots (ATRs) equipped with dual active flippers are widely used due to their ability to climb over complex obstacles like animals with legs. This paper presents a novel planning framework designed to empower ATRs with the capability of autonomously generating global paths that integrate obstacle-crossing maneuvers in complex terrains. This advancement effectively mitigates the issue of excessive dependence on remote human control, thereby enhancing the operational efficiency and adaptability of ATRs in challenging environments. The framework consists of three core components. First, a lightweight DeepLab V3+ architecture augmented with an edge-aware module is used for real-time semantic segmentation of elevation maps. Second, a simplified model of the robot-terrain contact is constructed to rapidly calculate the robot’s pose at map sampling points through contact point traversal. Finally, based on rapidly-exploring random trees, the cost of flipper motion smoothness is incorporated into the search process, achieving collaborative planning of passable paths and flipper maneuvers in obstacle-crossing scenarios. The framework was tested on our Crawler robot, which can quickly and accurately identify flat areas, obstacle-crossing areas, and impassable areas, avoiding redundant planning in non-obstacle areas. Compared to manually operated remote control, the planned path demonstrated shorter travel time, better stability, and lower flipper energy expenditure. This framework offers substantial practical value for autonomous navigation in demanding environments. Full article

Fodder maize constitutes a key economic crop in Thailand, particularly in the northeastern region, where it significantly contributes to livestock feed production and local economic development. Nevertheless, the planning and management of cultivation areas remain a major challenge, especially in urban and peri-urban agricultural zones, due to the limited availability of spatial data and suitable analytical frameworks. These difficulties are exacerbated in urban settings, where the complexity of land use patterns and high spectral similarity among land cover types hinder accurate classification. The Google Earth Engine (GEE) platform provides an efficient and scalable solution for geospatial data processing, enabling rapid land use classification and spatiotemporal analysis. This study aims to enhance the classification accuracy of fodder maize cultivation areas in Mueang District, Nakhon Ratchasima Province, Thailand—an area characterized by a heterogeneous mix of urban development and agricultural land use. The research integrates GEE with four machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), Naïve Bayes (NB), and Classification and Regression Trees (CART). Eleven datasets were developed using Sentinel-2 imagery and a combination of biophysical variables, including elevation, slope, Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), and Modified Normalized Difference Water Index (MNDWI), to classify land use into six categories: fodder maize cultivation, urban and built-up areas, forest, water bodies, paddy fields, and other field crops. Among the 44 classification scenarios evaluated, the highest performance was achieved using Dataset 11—which integrated all spectral and biophysical variables—with the SVM classifier. This model attained an overall accuracy of 97.41% and a Kappa coefficient of 96.97%. Specifically, fodder maize was classified with 100% accuracy in both Producer’s and User’s metrics, as well as a Conditional Kappa of 100%. These findings demonstrate the effectiveness of integrating GEE with machine learning techniques for precise agricultural land classification. This approach also facilitates timely monitoring of land use changes and supports sustainable land management through informed planning, optimized resource allocation, and mitigation of land degradation in urban and peri-urban agricultural landscapes. Full article

Urban vegetation plays a key role in mitigating thermal stress in cities, particularly in Mediterranean climates increasingly affected by urban heat. This study evaluates the impact of vegetation on outdoor thermal comfort in Piazzetta San Michele Arcangelo, a square in Lecce (Southern Italy), using the ENVI-met microclimate model. Two scenarios were simulated: the current configuration and a hypothetical one without trees. Results show that vegetation reduces air temperature during the hottest hours (up to −0.52 °C on average) and improves thermal comfort, as indicated by the Universal Thermal Climate Index (UTCI), with reductions in “very strong heat stress” up to 43% at peak times. At night, tree canopies limit radiative cooling, leading to slight temperature increases. The findings confirm the crucial role of urban greening in enhancing outdoor thermal comfort and provide quantitative support for sustainable urban planning strategies in Mediterranean contexts. Full article