Search Results (937)

High moisture content (MC) harms wheat storage quality and readily leads to mold growth. Accurate localization of abnormal/high-moisture regions enables early warning, ensuring proper storage and reducing economic losses. The present study introduces the 2D microwave scanning method and investigates a novel localization method for addressing such a challenge. Both static and scanning experiments were performed on a developed mobile and non-destructive microwave detection system to quantify the MC of wheat and then locate abnormal moisture regions. For quantifying the wheat’s MC, a dual-parameter wheat MC prediction model with the random forest (RF) algorithm was constructed, achieving a high accuracy (R² = 0.9846, MSE = 0.2768, MAE = 0.3986). MC scanning experiments were conducted by synchronized moving waveguides; the maximum absolute error of MC prediction was 0.565%, with a maximum relative error of 3.166%. Furthermore, both one- and two-dimensional localizing methods were proposed for localizing abnormal moisture regions. The one-dimensional method evaluated two approaches—attenuation value and absolute attenuation gradient—using computer simulation technology (CST) modeling and scanning experiments. The experimental results confirmed the superior performance of the absolute gradient method, with a center detection error of less than 12 mm in the anomalous wheat moisture region and a minimum width detection error of 1.4 mm. The study performed two-dimensional antenna scanning and effectively imaged the high-MC regions using phase delay analysis. The imaging results coincide with the actual locations of moisture anomaly regions. This study demonstrated a promising solution for accurately localizing the wheat’s abnormal/high-moisture regions with the use of an emerging microwave transmission method. Full article

The BP (Back-Propagation) neural network model (hereafter referred to as the BP model) often gets stuck in local optima when predicting China’s silicon wafer price, which hurts the accuracy of the forecasts. This study addresses the issue by enhancing the BP model. It integrates the principles of genetic algorithm (GA) with particle swarm optimization (PSO) to develop a new model called the GA-PSO-BP. This study also considers the material price from both the supply and demand sides of the photovoltaic industry. These prices are important factors in China’s silicon wafer price prediction. This research indicates that improving the BP model by integrating GA allows for a broader exploration of potential solution spaces. This approach helps to prevent local minima and identify the optimal solution. The BP model converges more quickly by using PSO for weight initialization. Additionally, the method by which particles share information decreases the probability of being confined to local optima. The upgraded GA-PSO-BP model demonstrates improved generalization capabilities and makes more accurate predictions. The MAE (Mean Absolute Error) value of the GA-PSO-BP model is 31.01% lower than those of the standalone BP model and also falls by 19.36% and 16.28% relative to the GA-BP and PSO-BP models, respectively. The smaller the value, the closer the prediction result of the model is to the actual value. This model has proven effective and superior in China’s silicon wafer price prediction. This capability makes it an essential resource for market analysis and decision-making within the silicon wafer industry. Full article

Downhole kick is one of the most severe safety hazards in deep and ultra-deep well drilling operations. Traditional monitoring methods, which rely on surface flow rate and fluid level changes, are limited by their delayed response and insufficient sensitivity, making them inadequate for early warning. This study proposes a real-time monitoring technique for gas content in drilling fluid based on the attenuation principle of Ba-133 γ-rays. By integrating laboratory static/dynamic experiments and Geant4-11.2 Monte Carlo simulations, the influence mechanism of gas–liquid two-phase media on γ-ray transmission characteristics is systematically elucidated. Firstly, through a comparative analysis of radioactive source parameters such as Am-241 and Cs-137, Ba-133 (main peak at 356 keV, half-life of 10.6 years) is identified as the optimal downhole nuclear measurement source based on a comparative analysis of penetration capability, detection efficiency, and regulatory compliance. Compared to alternative sources, Ba-133 provides an optimal energy range for detecting drilling fluid density variations, while also meeting exemption activity limits (1 × 10⁶ Bq) for field deployment. Subsequently, an experimental setup with drilling fluids of varying densities (1.2–1.8 g/cm³) is constructed to quantify the inverse square attenuation relationship between source-to-detector distance and counting rate, and to acquire counting data over the full gas content range (0–100%). The Monte Carlo simulation results exhibit a mean relative error of 5.01% compared to the experimental data, validating the physical correctness of the model. On this basis, a nonlinear inversion model coupling a first-order density term with a cubic gas content term is proposed, achieving a mean absolute percentage error of 2.3% across the full range and R² = 0.999. Geant4-based simulation validation demonstrates that this technique can achieve a measurement accuracy of ±2.5% for gas content within the range of 0–100% (at a 95% confidence interval). The anticipated field accuracy of ±5% is estimated by accounting for additional uncertainties due to temperature effects, vibration, and mud composition variations under downhole conditions, significantly outperforming current surface monitoring methods. This enables the high-frequency, high-precision early detection of kick events during the shut-in period. The present study provides both theoretical and technical support for the engineering application of nuclear measurement techniques in well control safety. Full article

This research targets prediction of power consumption change (PCC) in the branch of electrical distribution grid between a sum meter and consumer meter in response to consumer load change. The problem is relevant for power preservation law-based event-driven methods aiming for detection of anomalies like meter errors, electricity thefts, etc. The PCC in the branch is due to the change of technical (wiring) losses as well as change of power consumption of loads connected to the same distribution branch. Using synthesized dataset set a data-driven model is built to predict PCC in the branch. Model performance is assessed using root mean squared error (RMSE), mean absolute, and mean relative error, together with their standard deviations. The preliminary experimental verification using a test bed confirmed the potential of the method. The accuracy of the PCC in the branch prediction is influenced by the systematic error of the meters. Therefore, the error of the consumer meter and the PCC in the branch cannot be evaluated separately. It was observed that the absolute error of the estimate of power measurement gain error was observed to be within ±0.3% and the relative error of PCC in the branch prediction was within ±10%. Full article

This study proposes a novel LK-BP-AFPSO model for the nondestructive evaluation of wood mechanical properties, combining a backpropagation neural network (BP) with adaptive fractional-order particle swarm optimization (AFPSO) and Liang–Kleeman (LK) information flow theory. The model accurately predicts four key mechanical properties—longitudinal tensile strength (SPG), modulus of elasticity (MOE), bending strength (MOR), and longitudinal compressive strength (CSP)—using only nondestructive physical features. Tested across diverse wood types (fast-growing YKS, red-heart CSH/XXH, and iron-heart XXT), the framework demonstrates strong generalizability, achieving an average prediction accuracy (R²) of 0.986 and reducing mean absolute error (MAE) by 23.7% compared to conventional methods. A critical innovation is the integration of LK causal analysis, which quantifies feature–target relationships via information flow metrics, effectively eliminating 29.5% of spurious correlations inherent in traditional feature selection (e.g., PCA). Experimental results confirm the model’s robustness, particularly for heartwood variants, while its adaptive fractional-order optimization accelerates convergence by 2.1× relative to standard PSO. This work provides a reliable, interpretable tool for wood quality assessment, with direct implications for grading systems and processing optimization in the forestry industry. Full article

Background/Objectives: Smartphone addiction (SA) and gaming addiction (GA) have become risk factors for individuals of all ages in recent years. Especially during adolescence, it has become very difficult for parents to control this situation. Physical activity and the effective use of free time are the most important factors in eliminating such addictions. This study aimed to test a new machine learning method by combining routine regression analysis with the gradient-boosting machine (GBM) and random forest (RF) methods to analyze the relationship between SA and GA with leisure time management (LTM) and the enjoyment of physical activity (EPA) among adolescents. Methods: This study presents the results obtained using our developed GBM + RF hybrid model, which incorporates LTM and EPA scores as inputs for predicting SA and GA, following the preprocessing of data collected from 1107 high school students aged 15–19 years. The results were compared with those obtained using routine regression results and the lasso, ElasticNet, RF, GBM, AdaBoost, bagging, support vector regression (SVR), K-nearest neighbors (KNN), multi-layer perceptron (MLP), and light gradient-boosting machine (LightGBM) models. In the GBM + RF model, probability scores obtained from GBM were used as input to RF to produce final predictions. The performance of the models was evaluated using the R², mean absolute error (MAE), and mean squared error (MSE) metrics. Results: Classical regression analyses revealed a significant negative relationship between SA scores and both LTM and EPA scores. Specifically, as LTM and EPA scores increased, SA scores decreased significantly. In contrast, GA scores showed a significant negative relationship only with LTM scores, whereas EPA was not a significant determinant of GA. In contrast to the relatively low explanatory power of classical regression models, ML algorithms have demonstrated significantly higher prediction accuracy. The best performance for SA prediction was achieved using the Hybrid GBM + RF model (MAE = 0.095, MSE = 0.010, R² = 0.9299), whereas the SVR model showed the weakest performance (MAE = 0.310, MSE = 0.096, R² = 0.8615). Similarly, the Hybrid GBM + RF model also showed the highest performance for GA prediction (MAE = 0.090, MSE = 0.014, R² = 0.9699). Conclusions: These findings demonstrate that classical regression analyses have limited explanatory power in capturing complex relationships between variables, whereas ML algorithms, particularly our GBM + RF hybrid model, offer more robust and accurate modeling capabilities for multifactorial cognitive and performance-related predictions. Full article

Accurate fire source location in an aircraft cargo compartment cannot be determined by common design practices. This study proposes an advanced fire location inversion framework based on a Convolutional Long-Short-Term Memory (ConvLSTM) network. A self-designed interpolation preprocessing module is introduced to realize the integration of spatial and temporal sensor data. The model was trained and validated using a comprehensive database generated from large-scale fire dynamics simulations. Hyperparameter optimization, including a learning rate of 0.001 and a 5 × 5 convolution kernel size, can effectively avoid the systematic errors introduced by interpolation preprocessing, further enhancing model robustness. Validation in simplified scenarios demonstrated a mean squared error of 0.0042 m and a mean positional deviation of 0.095 m for the fire source location. Moreover, the present study assessed the model’s timeliness and reliability in full-scale cabin complex scenarios. The model maintained high performance across varying heights within cargo compartments, achieving a correlation coefficient of 0.99 and a mean absolute relative error of 1.9%. Noteworthily, reasonable location accuracy can be achieved with a minimum of three detectors, even in obstructed environments. These findings offer a robust tool for enhancing fire safety systems in aviation and other similar complex scenarios. Full article

The acquisition of plant phenotypic traits is essential for selecting superior varieties, improving crop yield, and supporting precision agriculture and agricultural decision-making. Therefore, it plays a significant role in modern agriculture and plant science research. Traditional manual measurements of phenotypic traits are labor-intensive and inefficient. In contrast, combining 3D reconstruction technologies with autonomous vehicles enables more intuitive and efficient trait acquisition. This study proposes a 3D semantic reconstruction system based on an improved ORB-SLAM3 framework, which is mounted on an unmanned vehicle to acquire phenotypic traits in tomato cultivation scenarios. The vehicle is also equipped with the A * algorithm for autonomous navigation. To enhance the semantic representation of the point cloud map, we integrate the BiSeNetV2 network into the ORB-SLAM3 system as a semantic segmentation module. Furthermore, a two-stage filtering strategy is employed to remove outliers and improve the map accuracy, and OctoMap is adopted to store the point cloud data, significantly reducing the memory consumption. A spherical fitting method is applied to estimate the number of tomato fruits. The experimental results demonstrate that BiSeNetV2 achieves a mean intersection over union (mIoU) of 95.37% and a frame rate of 61.98 FPS on the tomato dataset, enabling real-time segmentation. The use of OctoMap reduces the memory consumption by an average of 96.70%. The relative errors when predicting the plant height, canopy width, and volume are 3.86%, 14.34%, and 27.14%, respectively, while the errors concerning the fruit count and fruit volume are 14.36% and 14.25%. Localization experiments on a field dataset show that the proposed system achieves a mean absolute trajectory error (mATE) of 0.16 m and a root mean square error (RMSE) of 0.21 m, indicating high localization accuracy. Therefore, the proposed system can accurately acquire the phenotypic traits of tomato plants, providing data support for precision agriculture and agricultural decision-making. Full article

Concrete in cold areas is often subjected to a freeze–thaw cycle period, and a harsh environment will seriously damage the structure of concrete and shorten its life. The frost resistance of concrete is primarily evaluated by relative dynamic elastic modulus and mass loss rate. To predict the frost resistance of concrete more accurately, based on the four ensemble learning models of random forest (RF), adaptive boosting (AdaBoost), categorical boosting (CatBoost), and extreme gradient boosting (XGBoost), this paper optimises the ensemble learning models by using a dynamic multi-stage optimisation algorithm (DMSOA). These models are trained using 7090 datasets, which use nine features as input variables; relative dynamic elastic modulus (RDEM) and mass loss rate (MLR) as prediction indices; and six indices of the coefficient of determination (R²), mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (CC), and standard deviation ratio (SDR) are selected to evaluate the models. The results show that the DMSOA-CatBoost model exhibits the best prediction performance. The R² of RDEM and MLR are 0.864 and 0.885, respectively, which are 6.40% and 11.15% higher than those of the original CatBoost model. Moreover, the model performs better in error control, with significantly lower MSE, RMSE, and MAE and stronger generalization ability. Additionally, compared with the two mainstream optimisation algorithms (SCA and AOA), DMSOA-CatBoost also has obvious advantages in prediction accuracy and stability. Related work in this paper has a certain significance for improving the durability and quality of concrete, which is conducive to predicting the performance of concrete in cold conditions faster and more accurately to optimise the concrete mix ratio whilst saving on engineering cost. Full article

Urban electricity power consumption (EPC) prediction plays a crucial role in urban management and sustainable development. Nighttime light (NTL) remote sensing imagery has demonstrated significant potential in estimating urban EPC due to its strong correlation with human activities and energy use. However, most existing models focus on annual-scale estimations, limiting their ability to capture month-scale EPC. To address this limitation, a novel monthly EPC prediction model that incorporates monthly average temperature, and the interaction between NTL data and temperature was proposed in this study. The proposed method was applied to cities within the Yangtze River Delta (YRD) urban agglomeration, and was validated using datasets constructed from NPP/VIIRS and SDGSAT-1 satellite imageries, respectively. For the NPP/VIIRS dataset, the proposed method achieved a Mean Absolute Relative Error (MARE) of 7.96% during the training phase (2017–2022) and of 10.38% during the prediction phase (2023), outperforming the comparative methods. Monthly EPC spatial distribution maps from VPP/VIIRS data were generated, which not only reflect the spatial patterns of EPC but also clearly illustrate the temporal evolution of EPC at the spatial level. Annual EPC estimates also showed superior accuracy compared to three comparative methods, achieving a MARE of 7.13%. For the SDGSAT-1 dataset, leave-one-out cross-validation confirmed the robustness of the model, and high-resolution (40 m) monthly EPC maps were generated, enabling the identification of power consumption zones and their spatial characteristics. The proposed method provides a timely and accurate means for capturing monthly EPC dynamics, effectively supporting the dynamic monitoring of urban EPC at the monthly scale in the YRD urban agglomeration. Full article

Solar power generation is rapidly emerging within renewable energy due to its cost-effectiveness and ease of deployment. However, improper inspection and maintenance lead to significant damage from unnoticed solar hotspots. Even with inspections, factors like shadows, dust, and shading cause localized heat, mimicking hotspot behavior. This study emphasizes interpretability and efficiency, identifying key predictive features through feature-level and What-if Analysis. It evaluates model training and inference times to assess effectiveness in resource-limited environments, aiming to balance accuracy, generalization, and efficiency. Using Unmanned Aerial Vehicle (UAV)-acquired thermal images from five datasets, the study compares five Machine Learning (ML) models and five Deep Learning (DL) models. Explainable AI (XAI) techniques guide the analysis, with a particular focus on MPEG (Moving Picture Experts Group)-7 features for hotspot discrimination, supported by statistical validation. Medium Gaussian SVM achieved the best trade-off, with 99.3% accuracy and 18 s inference time. Feature analysis revealed blue chrominance as a strong early indicator of hotspot detection. Statistical validation across datasets confirmed the discriminative strength of MPEG-7 features. This study revisits the assumption that DL models are inherently superior, presenting an interpretable alternative for hotspot detection; highlighting the potential impact of domain mismatch. Model-level insight shows that both absolute and relative temperature variations are important in solar panel inspections. The relative decrease in “blueness” provides a crucial early indication of faults, especially in low-contrast thermal images where distinguishing normal warm areas from actual hotspot is difficult. Feature-level insight highlights how subtle changes in color composition, particularly reductions in blue components, serve as early indicators of developing anomalies. Full article

Significant regional environmental differences result in varied patterns of pavement temperature changes. To enhance the cross-regional adaptability of temperature prediction models, transfer learning (TL) was introduced into the random forest (RF) model to improve its generalization capability. Firstly, meteorological data on air temperature, solar radiation, relative humidity, and wind speed were collected from different regions. Pavement temperatures at various depths were also monitored over a long period. Secondly, prediction models were constructed using the RF method. The prediction performance of the models was evaluated. Thirdly, the RF model was optimized using TL with a feature enhancement strategy. Finally, the optimized model was validated using data from other regions not included in the initial training set. The results indicated that although the RF model achieved good prediction accuracy within individual regions, its performance declined when applied across different regions. After optimization through TL with feature enhancement, the model’s prediction accuracy in target regions was significantly improved. Specifically, the mean squared error was reduced from 44.91 to 14.88, the mean absolute error from 4.91 to 2.78, and the coefficient of determination increased from 0.75 to 0.92. Further validation revealed that the determination coefficient exceeded 0.94 and the mean absolute error remained below 2.3 °C at all depths. In summary, the transfer learning approach based on the random forest model demonstrates strong adaptability to different regions. It effectively addresses the issue of reduced prediction accuracy caused by regional differences and provides a reliable method for accurate pavement temperature prediction across multiple regions. Full article

Precise detection of canopy parameters is vital as it offers essential information for pest management in orchards. Among these parameters, leaf area density stands out as a key indicator of orchard canopies. A detection algorithm for leaf area density was proposed, and a leaf area density detection system for orchard canopies was designed based on the algorithm. By processing the point cloud data acquired by using LiDAR together with the algorithm, the total leaf area of the fitted leaves was calculated. Through an orthogonal regression experiment conducted on a laboratory-simulated canopy, this research established a mathematical calculation model ($R^2$ = 0.96) for determining the leaf area density of an orchard canopy. The leaf area density of an orchard canopy can be calculated using the total leaf area of the fitted leaves and an established mathematical model. To assess the accuracy of the detection system, both laboratory-simulated canopy experiments and real orchard canopy experiments were conducted. The results revealed that the absolute value of the mean relative error in the laboratory-simulated canopy experiments was 11.58%, and the absolute value of the mean relative error in the orchard canopy experiments was 16.75%. The research results have confirmed the feasibility of the LiDAR point cloud data processing algorithm. Furthermore, this algorithm can provide theoretical support for the subsequent development of intelligent plant protection equipment in orchards. Full article

Atmospheric methane (CH₄) concentrations have increased to 2.5 times their pre-industrial levels, with a marked acceleration in recent decades. CH₄ is responsible for approximately 30% of the global temperature rise since the Industrial Revolution. This growing concentration contributes to environmental degradation, including ocean acidification, accelerated climate change, and a rise in natural disasters. The column-averaged dry-air mole fraction of methane (XCH₄) is a crucial indicator for assessing atmospheric CH₄ levels. In this study, the Sentinel-5P TROPOMI instrument was employed to monitor, map, and estimate CH₄ concentrations on both regional and global scales. However, TROPOMI data exhibits limitations such as spatial gaps and relatively coarse resolution, particularly at regional scales or over small areas. To mitigate these limitations, a novel Convolutional Neural Network Autoencoder (CNN-AE) model was developed. Validation was performed using the Total Carbon Column Observing Network (TCCON), providing a benchmark for evaluating the accuracy of various interpolation and prediction models. The CNN-AE model demonstrated the highest accuracy in regional-scale analysis, achieving a Mean Absolute Error (MAE) of 28.48 ppb and a Root Mean Square Error (RMSE) of 30.07 ppb. This was followed by the Random Forest (RF) regressor (MAE: 29.07 ppb; RMSE: 36.89 ppb), GridData Nearest Neighbor Interpolator (NNI) (MAE: 30.06 ppb; RMSE: 32.14 ppb), and the Radial Basis Function (RBF) Interpolator (MAE: 80.23 ppb; RMSE: 90.54 ppb). On a global scale, the CNN-AE again outperformed other methods, yielding the lowest MAE and RMSE (19.78 and 24.7 ppb, respectively), followed by RF (21.46 and 27.23 ppb), GridData NNI (25.3 and 32.62 ppb), and RBF (43.08 and 54.93 ppb). Full article

Environmental monitoring systems often operate continuously, measuring various parameters, including carbon dioxide levels (CO₂), relative humidity (RH), temperature (T), and other factors that affect environmental conditions. Such systems are often referred to as smart systems because they can autonomously monitor and respond to environmental conditions and can be integrated both indoors and outdoors to detect, for example, structural anomalies. However, these systems typically have high energy consumption, data overload, and large equipment sizes, which makes them difficult to install in constrained spaces. Therefore, three challenges remain unresolved: efficient energy use, accurate data measurement, and compact installation. To address these limitations, this study proposes a two-to-one threshold sampling approach, where the CO₂ measurement is activated when the specified T and $RH$ change thresholds are exceeded. This event-driven method avoids redundant data collection, minimizes power consumption, and is suitable for resource-constrained embedded systems. The proposed approach was implemented on a low-power, small-form and self-made multivariate sensor based on the PIC16LF19156 microcontroller. In contrast, a commercial monitoring system and sensor modules based on the Arduino Uno were used for comparison. As a result, by activating only key points in the T and $RH$ signals, the number of CO₂ measurements was significantly reduced without loss of essential signal characteristics. Signal reconstruction from the reduced points demonstrated high accuracy, with a mean absolute error (MAE) of 0.0089 and root mean squared error (RMSE) of 0.0117. Despite reducing the number of CO₂ measurements by approximately 41.9%, the essential characteristics of the signal were saved, highlighting the efficiency of the proposed approach. Despite its effectiveness in controlled conditions (in buildings, indoors), environmental factors such as the presence of people, ventilation systems, and room layout can significantly alter the dynamics of CO₂ concentrations, which may limit the implementation of this approach. Future studies will focus on the study of adaptive threshold mechanisms and context-dependent models that can adjust to changing conditions. This approach will expand the scope of application of the proposed two-to-one sampling technique in various practical situations. Full article