Fit R2 Research Articles

Construction and application of optimized model for mine water inflow prediction based on neural network and ARIMA model

Mine water influx is a significant geological hazard during mine development, influenced by various factors such as geological conditions, hydrology, climate, and mining techniques. This phenomenon is characterized by non-linearity and high complexity, leading to frequent water accidents in coal mines. These accidents not only impact coal production quality but also jeopardize the safety of mine staff. In order to better predict the amount of water surging in mines and to provide an important basis for mine water damage prevention work, based on the time series data of mine water influx from January 2020 to February 2023 in Northern Guizhou Province Longfeng Coal Mine, the BP-ARIMA prediction model was established by combining the BP neural network model and ARIMA autoregressive sliding average model, It also predicted the mine influx for a total of 6 months from July 2022 to February 2023, and compared the prediction results with four models, namely, BP neural network model, ARIMA autoregressive sliding average model, traditional method of Large well method, and GM(1,1) grey model, and used the absolute relative error as the calculation of model accuracy. The results show that the established BP-ARIMA(3,1,1) prediction model is much closer to the actual value, with an average absolute relative error of 1.02% and a maximum absolute relative error of 3.036%, and the goodness of fit R² was 0.93, which is much better than the other four single models, and substantially improves the prediction accuracy of mine water influx. Furthermore, utilizing the BP-ARIMA model, future predictions for mine water influx in Longfeng Mine were made, offering a scientific foundation for effective prevention and control measures.

Advanced geospatial analytics for evapotranspiration dynamics: Integration of Sentinel-1A and FAO Penman-Monteith method

Evapotranspiration (ET0) is vital for agriculture and environmental management, facing challenges from climate change. Optical remote sensing overcomes reliance on weather station data. The modeled ET0 using the FAO Penman-Monteith method and Partial Least Squares Regression on Sentinel-1A data with 2016-2017 meteorological archives. Comparative analyses revealed stability in transportation areas within deciduous forests and wetlands, contrasting temporal variations. ET0 was significantly influenced by relative humidity (RH) (70.80% to 89.89%), with temperature (T) playing a crucial role. Urban vegetated areas maintained stable T values (29.37°C), while forests exhibited dynamic T variations (24.24°C to 28.94°C). VH polarization captured diverse climatic influences, resulting in a broader range of dynamic ET0 values (7.38 to 10.76 mm/day) compared to VV polarization (6.74 to 9.34 mm/day). VH sensor performance varied; in October 2016 showed moderate accuracy R2 was 0.50 with slight underestimation Bias -0.08, while exceptional accuracy was seen in December 2017 R2 was 1.00 with positive bias (0.57) and excellent agreement KGE was 0.92. VV sensors in October 2016 had a firm fit R2 was 0.55, with moderate underestimation Bias -0.87, and in December 2017 displayed a good fit the R2 was 0.57, with slight overestimation Bias 0.44, and good agreement KGE 0.44. Integrating machine learning and satellite imagery enhances ET0 accuracy for real-time monitoring in adaptive management, addressing climate change, and showcasing sensor-specific variations. Future research should integrate multi-source synthetic aperture radar satellite data and machine learning for precise ET0 estimation in adaptive environmental management.

The Impact of Fluroxypyr Drift on Soybean Phytotoxicity and the Safety Drift Thresholds

Maize–soybean intercropping can increase soybean yields and stabilize maize yields, and this practice has been widely promoted in China. Fluroxypyr is a recommended herbicide for maize seedlings, and its drift will cause phytotoxicity to neighboring soybean seedlings. A laboratory toxicity test was performed on soybeans by using a mobile bioassay spray tower. It showed that both the carrier volume and the drift deposition rate of fluroxypyr significantly influenced soybean fresh weight. The soybean fresh weight inhibition rate increased with the increase in the drift deposition rate, especially in the range of 1% to 6%, and soybean fresh weight decreased rapidly. The lack of fit R2 was 0.6875, with a 9% maximum deviation between experimental values and simulated values. The drift deposition rate upper threshold for mild phytotoxicity (10% fresh weight inhibition rate, ED10) was determined to be 3.35%, while the threshold for no phytotoxicity (0% fresh weight inhibition rate, ED0) was 1.01%. To ensure soybean safety, isolation devices and anti-drift nozzles were installed on the boom sprayer to maintain drift below ED0 or, at most, ED10. Maize seedling strip weed control field tests showed that the highest drift deposition rate was 0.689% under the carrier volume of 330 L·ha−1. There was no phytotoxicity observed on soybeans after 21 days of application, which was consistent with laboratory research results. In this study, the phytotoxicity risk and safe thresholds for the fluroxypyr drift on soybean seedlings were established, which provide a theoretical basis for the safe production of soybeans.

Stacked Ensemble with Machine Learning Regressors on Optimal Features (SMOF) of hyperspectral sensor PRISMA for inland water turbidity prediction.

Leveraging hyperspectral data across various domains yields substantial benefits, yet managing many spectral bands and identifying the essential ones poses a formidable challenge. This study identifies the most relevant bands within a hyperspectral data cube for turbidity prediction in inland water. Nine machine learning regressors Cat Boost, Decision Trees, Extra Trees, Gradient Boost, Light Gradient Boost (LightGBM), Recursive Feature Elimination (RFE), Random Forest, Support Vector Regressor (SVR), and Xtreme Gradient Boost (XGBoost) have been used to compute the feature importance of the hyperspectral bands for predicting turbidity. Random Forest has outperformed the other models with a mean absolute percentage error (MAPE) of 1.61%, and the R2 of the linear fit is 0.96. Band 77, with a central wavelength of 1067.61nm, is the most dominating band regarding feature importance. We have also developed a novel framework for turbidity prediction: Stacked Ensemble with Machine Learning Regressors on Optimal Features (SMOF). It employs a stacking ensemble of the nine regressors mentioned above with Random Forest as both base and meta-model, leveraging feature selection outputs. With this framework, the MAPE (%) reached 1.21, while the R2 stood at 0.95. The present study also presents a simple statistical algorithm to detect noisy bands in the Hyperspectral Precursor of the Application Mission (PRISMA) data cube. The approach assesses quadrat-wise intra-band spatial coherence using Renyi's entropy thresholding for noisy band segregation. Radiometric calibration error and absorption due to water vapour are the two primary sources of noise within the data cube. Moreover, this research implements the open-source Water Colour Simulator (WASI) to simulate inland water spectra with varied proportions of turbidity. Overall, the study presents an approach to identify noisy bands and integrates the potential wavelengths for turbidity prediction of inland waters.

Experimental analysis and low-damage machining strategy for composite ultrasonic vibration-assisted grinding of silicon carbide based on DA-MLP-NSGA-II algorithm

At present, because of the lack of ultrasonic composite vibration assisted grinding mechanism, neural network optimization algorithm (NNOA) is used to optimize the processing results. In NNOA, multi-layer perceptron (MLP) neural network model and non-dominated sorting genetic algorithm-II (NSGA-II) are very efficient and accurate methods. In this paper, based on the measurement and analysis of the specific ultrasonic vibration device, the CUVAG experiments on silicon carbide (SiC) ceramic were carried out to investigate the influence of processing parameters on the grinding forces, the ground surface roughness and morphology, and the subsurface damage. Then, the brittle-ductile removal behavior of hard-and-brittle materials could be revealed according to the above analysis. After that, MLP model and NSGA-II were utilized to predict and optimize the processing results in CUVAG. The results show that the grinding forces are basically constant, the surface quality deteriorates, and the subsurface damage increases with increased axial vibration amplitude and workpiece infeed speed, but all fluctuate with enlarged wheel speed, and turns at the inflection point of brittle-ductile transition with increased elliptic vibration amplitude. The fitting goodness R2 of the established MLP neural network prediction model is between 0.94 and 0.975, and the process parameters calculated by the NSGA-II optimization algorithm are verified. With optimized processing parameters, the grinding forces are reduced by about 13 %, the surface roughness is reduced to Ra0.037 μm (by 29 %), and the depth of subsurface damage is reduced by 68 %.

Highly Calibrated Relationship Between Bleomycin Concentrations and Facets of the Active Phase Fibrosis in Classical Mouse Bleomycin Model.

The mouse bleomycin model is useful in pre-clinical IPF research to understand pathophysiological mechanisms and pharmacological interventions. In the present study, we systematically investigated the effects of bleomycin at a 60-fold dose range on experimental features of lung fibrosis in the mouse bleomycin model. We analyzed the effect of intratracheal (i.t.) dosing of 0.05-3 U/kg bleomycin on disease phenotypes, including weight loss, morbidity and mortality, pulmonary inflammation, lung collagen content, various BALF biomarkers, and histology in a 14-day mouse model when the animals are in the active phase of fibrosis. In mice, challenge with 1-2 U/kg bleomycin doses induced significant and saturated responses on fibrotic endpoints, confirmed by collagen content, BALF biomarker levels, and marked weight loss compared to the normal control (NC). We observed 100% mortality in 3 U/kg of bleomycin-treated mice. In contrast, 0.05-0.5 U/kg bleomycin doses induced a dose-dependent fibrotic phenotype. The mice challenged with doses of 0.25-0.5 U/kg bleomycin showed optimum body weight loss, a significant increase in pulmonary inflammation, and the fibrotic phenotype compared to NC. Furthermore, we showed 0.25-0.5 U/kg bleomycin increases expression levels of (pro-) fibrotic cytokines, which are the mediators involved in the activation of myofibroblast during fibrogenesis (TGF-β1, IL-13, IL-6, WISP-1, VEGF), angiogenesis (VEGF), matrix remodeling (TIMP-1), and non-invasive lung function biomarker (CRP) compared to NC. A modified Ashcroft scale quantified that the fibrotic changes in the lungs were significantly higher in the lung of mice dosed at 0.25-0.5 U/kg > 0.1 U/kg bleomycin and non-significant in mice lung dosed at 0.05 U/kg bleomycin compared to NC. We demonstrated that the changes due to 0.25-0.5 U/kg i.t. bleomycin on protein biomarkers are enough to drive robust and detectable fibrotic pathology without mortality. The 0.1 U/kg has a moderate phenotype, and 0.05 U/kg had no detectable phenotype. The Goodness of Fit (r2) and Pearson correlation coefficient (r) analyses revealed a positive linear association between change evaluated in all experimental features of fibrosis and bleomycin concentrations (0.05-0.5 U/kg). Here, we provide an examination of a highly calibrated relationship between 60-fold bleomycin concentrations and a set of in vivo readouts that covers various facets of experimental fibrosis. Our study shows that there is a dose-dependent effect of bleomycin on the features of experimental fibrosis at <1 U/kg, whereas saturated responses are achieved at >1 U/kg. Our careful experimental observations, accuracy, and comprehensive data set provided meaningful insights into the effect of bleomycin dose(s) on the fibrotic phenotype, which is valuable in preclinical drug development and lung fibrosis research. In addition, we have presented a set of reproducible frameworks of endpoints that can be used for reliable assessment of the fibrotic phenotype, and in vivo therapeutic intervention(s) with improved accuracy.

Tree Height–Diameter Model of Natural Coniferous and Broad-Leaved Mixed Forests Based on Random Forest Method and Nonlinear Mixed-Effects Method in Jilin Province, China

Objective: The purpose of this article was to use the Random Forest method and nonlinear mixed-effects method to develop a model for determining tree height–diameter at breast height (DBH) for a natural coniferous and broad-leaved mixed forest in Jilin Province and to compare the advantages and disadvantages of the two methods to provide a basis for forest management practice. Method: Based on the Chinese national forest inventory data, the Random Forest method and nonlinear mixed-effects method were used to develop a tree height–DBH model for a natural coniferous and broad-leaved mixed forest in Jilin Province. Results: The Random Forest method performed well on both the fitting set and validation set, with an R2 of 0.970, MAE of 0.605, and RMSE of 0.796 for the fitting set and R2 of 0.801, MAE of 1.44 m, and RMSE of 1.881 m for the validation set. Compared with the nonlinear mixed-effects method, the Random Forest model improved R2 by 33.83%, while the MAE and RMSE decreased by 67.74% and 66.44%, respectively, in the fitting set; the Random Forest model improved R2 by 9.88%, while the MAE and RMSE decreased by 14.38% and 12.05%, respectively, in the validation set. Conclusions: The tree height–DBH model constructed based on the Random Forest method had higher prediction accuracy for a natural coniferous and broad-leaved mixed forest in Jilin Province and had stronger adaptability for higher-dimensional data, which can be used for tree height prediction in the study area.

Time Series Prediction of Gas Emission in Coal Mining Face Based on Optimized Variational Mode Decomposition and SSA-LSTM.

The accurate prediction of gas emissions has important guiding significance for the prevention and control of gas disasters in order to further improve the prediction accuracy of gas emissions in the mining face. According to the absolute gas emission monitoring data of the 1417 working face in a coal mine in Shaanxi Province, a GA-VMD-SSA-LSTM gas emission prediction model (GVSL) based on genetic algorithm (GA)-optimized variational mode decomposition (VMD) and sparrow search algorithm (SSA)-optimized long short-term memory (LSTM) is proposed. Firstly, a VMD evaluation standard for evaluating the amount of decomposition loss is proposed. Under this standard, the GA is used to find the optimal parameters of the VMD. Then, the SSA is used to optimize the key parameters of the LSTM to establish a GVSL prediction model. The model predicts each component and finally superimposes the prediction results for each component to obtain the final gas emission result. The results show that the accuracy of the evaluation indexes of the GVSL model and VMD-LSTM model, as well as the SSA-LSTM model and Gaussian process regression (GPR) model, are compared and analyzed horizontally and vertically under three scenarios with prediction sets of 121,94 and 57 groups. The GVSL model has the best prediction effect, and its fitting degree R2 values are 0.95, 0.96, and 0.99, which confirms the effectiveness of the proposed GVSL model for the time series prediction of gas emission in the mining face.

Applicability of two-phase modeling with compression experiments for snow compaction dynamics

Compaction is a rheological process which, in many fields, has been modeled using a 1-D two-phase continuum framework. However, only recently has it been posed as a promising method for modeling the densification of snow into glacial ice, where the conventional model is empirical or semi-empirical. Here, we explore the applicability of a standard one-dimensional two-phase continuum framework for modeling snow compaction through theoretical and laboratory methods by analyzing and simplifying theory, and then experimentally constraining the model coefficient. We find in our theory analysis that the limit of slow compaction is reached such that air evacuation during the compaction process does not impede the deformation of ice grains. Model-data comparisons are performed using data from a series of uniaxial compression experiments of snow samples under a range of compaction rates (1 × 10−6 to 3 × 10−5 m s−1) and densities (250 to 450 kg m−3) at −10° and –20 °C, which show good measures of fit (r2>0.996). By defining a linear effective pressure function, we then constrain the model parameter by tuning against the data. While our model follows proper simplification of theory, the temperature and microstructural dependence are determined exclusively by the model parameter in a rheological formulation with the strain rate, and much scatter still exists. Within the selected range of compaction rates and densities, our results indicate that a 1-D two-phase model with a continuum framework alone does not likely capture important processes involved in the compaction process.

Intelligence analysis of membrane distillation via machine learning models for pharmaceutical separation

This study investigates simulation of pharmaceutical separation via membrane distillation process by computational simulation and machine learning modeling strategy. The efficacy of three regression models, i.e., Multi-layer Perceptron (MLP), Gamma Regression, and Support Vector Regression (SVR) in predicting the solute concentration, C(mol/m³), was evaluated. The hyper-parameters were optimized by fine-tuning the models using the Red Deer Algorithm (RDA). Computational analyses were carried out for removal of pharmaceuticals from solution by membrane distillation in continuous mode. Mass transfer and machine learning models were implemented focusing on concentration of solute in the feed section of membrane. Results indicate that the Multi-layer Perceptron model achieved great accuracy with an R2 of 0.9955, an MAE of 0.0084, and an RMSE of 0.0148, effectively capturing complex nonlinear relationships in the data. Gamma Regression also performed acceptably, with fitting R2 of 0.9214, showing its suitability for positively skewed data. The Support Vector Regression model, while capturing the general trend, showed the lowest performance with an R2 of 0.8710. These findings suggest that the Multi-layer Perceptron is the most accurate model for this dataset, followed by Gamma Regression and Support Vector Regression. This underscores the importance of careful model selection and optimization in regression analysis in combination with computational simulation of membrane processes.

Distribution of tetracyclines and sulfonamides resistance genes around a smallholder pig farm: Modeling and attribution

Livestock farm is a major source of antibiotics and antibiotic resistance genes (ARGs) pollution. ARGs can directly enter the environment through runoff and air deposition. The impact extent and the driving factors require further investigation to inform effective policies and actions to mitigate their spread. This study investigated a smallholder pig farm and its surrounding areas to understand the spread of ARGs. Topsoil samples were collected from 56 different sites within one kilometer of the farm, and a comprehensive analysis was conducted to reveal effects of soil properties, antibiotic residues, microbiome, mobilome on the variation of typical ARGs. The results confirmed that the ARGs reduced exponentially with increasing distance from the farm, with a goodness of fit (R2) of 0.7 for total ARGs. For tetracyclines (TC) and sulfonamides (SA) resistance genes, the fitting R2 exceeded 0.9. Model estimates allowed for quantitative comparisons of in-farm increments, out-farm background levels, and spread abilities of ARGs with distinct resistance mechanisms. SA-specific resistance genes (SRGs, 0.097 copies/16S rRNA gene) and TC-specific resistance genes (TRGs, 0.036 copies/16S rRNA gene) showed higher within-farm increases compared to multidrug resistance genes (MDRGs, 0.020 copies/16S rRNA gene). MDRGs, however, had a higher background level and a greater impact distance (0.18 km, 4.4 times the farm radius). Additionally spread abilities of TRGs varied by resistance mechanism, with ribosome protection proteins showing greater spread than TC inactivating enzymes and TC efflux pumps, likely due to different fitness costs. Correlation analysis and structural equation modeling indicated that changes in bacterial community composition and mobilome are primary factors influencing ARGs variation during their spread. Abiotic factors like soil nutrients and antibiotics also selectively enriched ARGs within the farm. These findings provide insights into the ARGs dissemination and could inform strategies to prevent their spread from smallholder livestock farms.

Seismic risk assessment based on residential building stock and field survey results: a case study of 3 cities in Shanxi Province

IntroductionBuildings that collapse or are damaged by earthquakes are responsible for the majority of earthquake-related casualties. High-precision building data are the key to improving the accuracy of risk assessments of earthquake disaster loss. Many countries and regions have also proposed varying regional building exposure models, but most of these models are still based on administrative-level (city or county) statistical data; furthermore, they cannot accurately reflect the differences among buildings in different towns or villages.MethodsAlthough field investigation-based “township to township” methods can obtain more accurate building inventory data, considering costs and timeliness, remote sensing and other diverse data should be combined to acquire building data. Based on the field survey data of three cities in shanxi Province, combined with Global Human Settlement Layer (GHSL) data, this study is conducted on building inventory data. Data regarding the proportion of each building type and corresponding lethality level in each township are obtained based on the classification of building height, and the overall lethality level at the building level and township level is calculated on this basis.ResultsThe fitting results between the calculated results and the field survey results are good, the error is within 0.15, and the fitting R2 values of Xian, Baoji and Ankang are 0.6552, 0.5788 and 0.5937, respectively. Therefore, an earthquake disaster loss risk assessment is conducted based on the building level.DiscussionThe findings indicate that the risk of casualties caused by the same building type can vary by city. Generally, the areas with high disaster loss risk in the three cities are distributed mainly in urban areas; the disaster loss risk in the newly built areas of each city is relatively low. According to the quantitative assessment results for each city, Xi’an has the highest loss risk, while Baoji and Ankang have the same loss risk. Based on the method constructed in this paper, we can realize the quantitative assessment of earthquake disaster loss risk at the building level to better target pre-earthquake emergency preparation and post-earthquake auxiliary decision-making.

Microscale Temperature-Humidity Index (THI) Distribution Estimated at the City Scale: A Case Study in Maebashi City, Gunma Prefecture, Japan

Global warming and climate change are significantly impacting local climates, causing more intense heat during the summer season, which poses risks to individuals with pre-existing health conditions and negatively affects overall human health. While various studies have examined the Surface Urban Heat Island (SUHI) phenomenon, these studies often focus on small to large geographic regions using low-to-moderate-resolution data, highlighting general thermal trends across large administrative areas. However, there is a growing need for methods that can detect microscale thermal patterns in environments familiar to urban residents, such as streets and alleys. The temperature-humidity index (THI), which incorporates both temperature and humidity data, serves as a critical measure of human-perceived heat. However, few studies have explored microscale THI variations within urban settings and identified potential THI hotspots at a local level where SUHI effects are pronounced. This research aims to address this gap by estimating THI at a finer resolution scale using data from multiple sensor platforms. We developed a model with the random forest algorithm to assess THI trends at a resolution of 0.5 m, utilizing various variables from different sources, including Landsat 8 land surface temperature (LST), unmanned aerial system (UAS)-derived LST, Sentinel-2 NDVI and NDMI, a wind exposure index, solar radiation modeled from aircraft and UAS-derived Digital Surface Models, and vehicle density and building floor area from social big data. Two models were constructed with different variables: Modelnatural, which includes variables related to only natural factors, and Modelmix, which includes all variables, including anthropogenic factors. The two models were compared to reveal how each source contributes to the model development and SUHI effects. The results show significant improvements, as Modelnatural had a fitting R2 = 0.5846, a root mean square error (RMSE) = 0.5936 and a mean absolute error (MAE) = 0.4294. Moreover, when anthropogenic factors were introduced, Modelmix performed even better, with R2 = 0.9638, RMSE = 0.1751, and MAE = 0.1065 (n = 923). This study contributes to the future of microscale SUHI analysis and offers important insights into urban planning and smart city development.

Prediction of quasi-static mechanical properties of flexible porous metal rubber structures in ultra-wide temperature range

Metal rubber, which has the advantages of low density, strong environmental adaptability, and excellent design flexibility, is widely applied in manufacturing industries such as the aerospace, shipping, and automotive industries. Based on the research object of flexible porous metal rubber (FPMR) structures made of high-temperature elastic alloys, this study established a constitutive model for the quasi-static mechanical properties of FPMR structure under ultra-wide temperature range conditions. Firstly, the forming mechanism and the influencing factors of the static stiffness properties of the FPMR micro-structure were analyzed. Then, the theoretical model of the FPMR micro-element spring was established by applying the cylindrical spiral compression spring stiffness theory, and the theoretical model was corrected based on the large deformation theory and numerical analysis methods. A comparative analysis was carried out through the corrected theoretical model and the test results of different test samples. And the results show that the corrected theoretical model can comprehensively reflect the nonlinear quasi-static stiffness characteristics of the FPMR structure in an ultra-wide temperature range. More importantly, by comparison with the prediction models proposed by other scholars, it is proved that the model proposed in this paper has higher prediction accuracy and the goodness of fit R2 is closer to 1, which provides a theoretical basis for the application of metal rubber in flexible support structures under ultra-high temperature environments.

High sensitivity optical fiber accelerometer based on symmetric hinge structure with dual mass blocks

Abstract An optical fiber Bragg grating accelerometer with symmetric multi-stage flexible hinge and double mass block structure is designed. According to the working principle of the two-degree-of-freedom vibration system, there are vibration nodes in the double mass block during the vibration process, and the vibration nodes can reduce the amplitude of the system and protect the optical fiber; and the multi-stage flexible hinge can reduce the structural rigidity and improve the sensitivity of the accelerometer. The experimental results show that the vibration signal is in the range of 5-90Hz, the acceleration is in the range of 0.1-1G, the sensitivity of the accelerometer is 878.4pm/G, and the linear fit R2=0.991. At the same time, the mechanical structure of the accelerometer is an integrated processing, with high mechanical strength, which can ensure the stability of the work of the accelerometer, and the structure is simple, and easy to package. Changing the length and thickness of the hinge can further expand the measurement range and application scenarios of the accelerometer.

Fatigue cracking prediction of RIOHTrack full-scale test track based on variable-order fractional Burgers model

We propose a modified thermal cracking (MTC) model in this paper, which utilizes the evolution of crack propagation to predict the number and density of cracks that will form on the RIOHTrack full-scale test track. We incorporate the variable-order fractional Burgers model as an important component of the thermal cracking (TC) model, for calculating the creep compliance. Furthermore, we apply the Levenberg–Marquardt (LM) algorithm as a data-driven approach, for parameter fitting. The MTC model is constructed technically through creep compliance approximation compute and parameter fitting as follows. First, we employ the variable-order fractional Burgers model to calculate the asymptotic creep compliance of each pavement segment within the RIOHTrack full-scale test track. More precisely, we derive the explicit asymptotic expansion of creep compliance based on the variable-order fractional Burgers model. Such an asymptotic expansion represented by the Gamma function is a simplified representation of the creep compliance, and it ensures that the fitting accuracy R2 is greater than 0.87. Parameter fitting of the creep compliance is based on the RIOHTrack full-scale pavement test data, using the LM algorithm. Then, the creep compliance in the original TC model is mathematically upgraded to the above variable-order fractional approximation form, and parameters in the MTC model are numerically estimated using the LM algorithm based on prior knowledge from the RIOHTrack test data. Our prediction analyses based on the RIOHTrack data demonstrate the superior performance of the proposed MTC model.

Feasibility of aligning creatine kinase MB activity and mass data in multicentre trials using generalized additive modelling.

Elevated serum creatine kinase isoenzyme MB (CK-MB) levels indicate myocardial ischaemia and periprocedural myocardial injury during treatment of heart diseases. We established a method to predict CK-MB mass from activity data based on a prospective pilot study in order to simplify multicentre trials. 38 elective cardiac surgery patients without acute myocardial ischaemia and terminal renal failure were recruited. CK-MB mass and activity were determined in venous blood samples drawn preoperatively, postoperatively, 6 h post-op, and 12 h post-op. Linear regression and generalized additive models (GAMs) were applied to describe the relationship of mass and activity. Influences of demographic and perioperative factors on the fit of GAMs was evaluated. The agreement of predicted and measured CK-MB masses was assessed by Bland-Altman analyses. Linear regression provided an acceptable overall fit (r2 = 0.834) but showed deviances at low CK-MB levels. GAMs did not benefit from the inclusion of age, body mass index and surgical times. The minimal adequate model predicted CK-MB masses from activities, sex and sampling time with an r2 of 0.981. Bland-Altman analyses confirmed narrow limits of agreement (spread: 8.87 µg/l) and the absence of fixed (P = 0.41) and proportional (P = 0.21) biases. GAM-based modelling of CK-MB data in a representative patient cohort allowed to predict CK-MB masses from activities, sex and sampling time. This approach simplifies the integration of study centres with incompatible CK-MB data into multicentre trials in order to facilitate inclusion of CK-MB levels in statistical models.

Prediction of Deformation in Expansive Soil Landslides Utilizing AMPSO-SVR

A non-periodic “step-like” variation in displacement is exhibited owing to the repeated instability of expansive soil landslides. The dynamic prediction of deformation for expansive soil landslides has become a challenge in actual engineering for disaster prevention and mitigation. Therefore, a support vector regression prediction (AMPSO-SVR) model based on adaptive mutation particle swarm optimization is proposed, which is suitable for small samples of data. The shallow displacement is decomposed into a trend component and fluctuating component by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and the trend displacement is predicted by cubic polynomial fitting. In this paper, the multiple disaster-inducing factors of expansive landslides and the time hysteresis effect between displacement and its influencing factors are fully considered, and the crucial influencing factors which eliminate the time lag effect and state factors are input into the model to predict the fluctuation displacement. Monitoring data in the Ningming area of China are employed for the model validation. The predicted results are compared with those of the traditional model. The model performance is evaluated through indicators such as the goodness of fit R2 and root mean square error RMSE. The results show that the prediction RMSE of the new model for three monitoring stations can reach 2.6 mm, 6.6 mm, and 2.5 mm, respectively. Compared with the common Grid search support vector regression (GS-SVR), the Particle Swarm Optimization Support Vector Regression (PSO-SVR) and Back Propagation Neural Network (BPNN) models have average improvements of 58.4%, 38.1%, and 25.2% respectively. The goodness of fit R2 is superior to 0.99 in the new method. The proposed model can effectively be deployed for the displacement prediction of non-periodic stepped expansive soil landslides driven by multiple influencing factors, providing a reference idea for the deformation prediction of expansive soil landslides.

A bioinspired triboelectric wireless anemometer with low cut-in wind speed for meteorological UAVs

Currently, unmanned aerial vehicles (UAVs) play a pivotal role in meteorological wind speed measurements. Nevertheless, existing anemometers exhibit notable issues, including excessive weight, high cost and high cut-in wind speed. This investigation introduces a biomimetic owl wing airfoil wind speed sensor utilizing the principles of the triboelectric nanogenerator (BOW-TENG) designed for UAV applications. Inspired by owl wings, an airfoil configuration with superior aerodynamic characteristics is ascertained, subsequently fabricating it into an impeller, and a wind speed sensor with low weight, low cost and low cut-in wind speed is developed. Experimental results affirm the BOW-TENG’s precision in depicting wind speed across the range of 1.6–10.7 m/s, featuring a sensitivity of 21.893 Hz/(m·s−1), a goodness of fit R2 of 0.9995, and a remarkable resolution of 0.057 m/s. The sensor weighs only 30 g. Furthermore, a cost-effective triboelectric signal processing system is devised for integrating the BOW-TENG into the UAV, as well as the optimal positioning for BOW-TENG on the UAV is identified through simulations. The relative wind direction can be calculated from signals of the BOW-TENGs on the four arms of the UAV. Ultimately, application experiments demonstrate the feasibility of employing BOW-TENG for wireless wind speed transmission from UAVs. This work incorporates bionics and proposes a practical application of triboelectric sensors for UAVs, as well as a solution for developing wind speed sensors in the field of meteorological UAV detection.

Extraction of Moso Bamboo Parameters Based on the Combination of ALS and TLS Point Cloud Data.

Extracting moso bamboo parameters from single-source point cloud data has limitations. In this article, a new approach for extracting moso bamboo parameters using airborne laser scanning (ALS) and terrestrial laser scanning (TLS) point cloud data is proposed. Using the field-surveyed coordinates of plot corner points and the Iterative Closest Point (ICP) algorithm, the ALS and TLS point clouds were aligned. Considering the difference in point distribution of ALS, TLS, and the merged point cloud, individual bamboo plants were segmented from the ALS point cloud using the point cloud segmentation (PCS) algorithm, and individual bamboo plants were segmented from the TLS and the merged point cloud using the comparative shortest-path (CSP) method. The cylinder fitting method was used to estimate the diameter at breast height (DBH) of the segmented bamboo plants. The accuracy was calculated by comparing the bamboo parameter values extracted by the above methods with reference data in three sample plots. The comparison results showed that by using the merged data, the detection rate of moso bamboo plants could reach up to 97.30%; the R2 of the estimated bamboo height was increased to above 0.96, and the root mean square error (RMSE) decreased from 1.14 m at most to a range of 0.35-0.48 m, while the R2 of the DBH fit was increased to a range of 0.97-0.99, and the RMSE decreased from 0.004 m at most to a range of 0.001-0.003 m. The accuracy of moso bamboo parameter extraction was significantly improved by using the merged point cloud data.