Optimal Prediction Model Research Articles

Based on the Improved PSO-TPA-LSTM Model Chaotic Time Series Prediction

In order to enhance the prediction accuracy and computational efficiency of chaotic sequence data, issues such as gradient explosion and the long computation time of traditional methods need to be addressed. In this paper, an improved Particle Swarm Optimization (PSO) algorithm and Long Short-Term Memory (LSTM) neural network are proposed for chaotic prediction. The temporal pattern attention mechanism (TPA) is introduced to extract the weights and key information of each input feature, ensuring the temporal nature of chaotic historical data. Additionally, the PSO algorithm is employed to optimize the hyperparameters (learning rate, number of iterations) of the LSTM network, resulting in an optimal model for chaotic data prediction. Finally, the validation is conducted using chaotic data generated from three different initial values of the Lorenz system. The root mean square error (RMSE) is reduced by 0.421, the mean absolute error (MAE) is reduced by 0.354, and the coefficient of determination (R2) is improved by 0.4. The proposed network demonstrates good adaptability to complex chaotic data, surpassing the accuracy of the LSTM and PSO-LSTM models, thereby achieving higher prediction accuracy.

Development of an interpretable machine learning model for Ki-67 prediction in breast cancer using intratumoral and peritumoral ultrasound radiomics features.

Traditional immunohistochemistry assessment of Ki-67 in breast cancer (BC) via core needle biopsy is invasive, inaccurate, and nonrepeatable. While machine learning (ML) provides a promising alternative, its effectiveness depends on extensive data. Although the current mainstream MRI-centered radiomics offers sufficient data, its unsuitability for repeated examinations, along with limited accessibility and an intratumoral focus, constrain the application of predictive models in evaluating Ki-67 levels. This study aims to explore ultrasound (US) image-based radiomics, incorporating both intra- and peritumoral features, to develop an interpretable ML model for predicting Ki-67 expression in BC patients. A retrospective analysis was conducted on 263 BC patients, divided into training and external validation cohorts. From intratumoral and peritumoral regions of interest (ROIs) in US images, 849 distinctive radiomics features per ROI were derived. These features underwent systematic selection to analyze Ki-67 expression relationships. Four ML models-logistic regression, random forests, support vector machine (SVM), and extreme gradient boosting-were formulated and internally validated to identify the optimal predictive model. External validation was executed to ascertain the robustness of the optimal model, followed by employing Shapley Additive Explanations (SHAP) to reveal the significant features of the model. Among 231 selected BC patients, 67.5% exhibited high Ki-67 expression, with consistency observed across both training and validation cohorts as well as other clinical characteristics. Of the 1698 radiomics features identified, 15 were significantly correlated with Ki-67 expression. The SVM model, utilizing combined ROI, demonstrated the highest accuracy [area under the receiver operating characteristic curve (AUROC): 0.88], making it the most suitable for predicting Ki-67 expression. External validation sustained an AUROC of 0.82, affirming the model's robustness above a 40% threshold. SHAP analysis identified five influential features from intra- and peritumoral ROIs, offering insight into individual prediction. This study emphasized the potential of SVM model using radiomics features from both intra- and peritumoral US images, for predicting elevated Ki-67 levels in BC patients. The model exhibited strong performance in validations, indicating its promise as a noninvasive tool to enable personalized decision-making in BC care.

A new perspective of wind speed forecasting: Multi-objective and model selection-based ensemble interval-valued wind speed forecasting system

Wind-speed forecasting is pivotal for optimizing resource utilization and promoting sustainable development. Previous studies have predominantly focused on point and interval forecasts derived from single-valued wind speed series, failing to capture the inherent fluctuations and uncertainties in wind speed. This study introduces a novel approach: a multi-objective and model selection-based ensemble interval-valued wind speed forecasting system. The primary objective is to empower decision-makers with enhanced decision support and improved risk management. The proposed system comprises four integral components: an interval-valued wind-speed preprocessing module, a model library module, a model selection module, and a multi-objective ensemble module. First, the preprocessing module decomposes the complex interval-valued wind speed forecasting task into multiple simpler forecasting subtasks. Subsequently, a model library is constructed for different forecasting subtasks. The model selection module utilizes a comprehensive evaluation metric to select the best-suited prediction model for each forecasting subtask. Finally, the multi-objective ensemble module integrates the subtask prediction results to yield the interval-valued wind speed forecasting outcomes. The most significant findings of this study are: (1) When faced with different forecasting subtasks, the choice of the optimal prediction model varies depending on the nature of the task. Therefore, the results of the model selection also differ with changes in the data characteristics. (2) In the ensemble stage, the importance and contribution of different subtasks may differ. The proposed ensemble module considers the interrelations and interactions between subtasks, resulting in varying weights for each subtask. For the two different datasets from the Chengde wind farm, the interval mean absolute percentage error values were 2.0862 % and 3.3632 %, and the interval standard deviation values of the error were 0.1383 and 0.3206, respectively. The experimental results clearly demonstrate the exceptional performance of the proposed system in interval-valued wind speed forecasting, which provides better decision support and risk management for wind speed forecasting.

Integration of Vis–NIR Spectroscopy and Machine Learning Techniques to Predict Eight Soil Parameters in Alpine Regions

Visible and near-infrared spectroscopy (Vis–NIR, 350–1100 nm) has great potential for predicting soil properties. However, current research on the hyperspectral prediction of soil parameters in agricultural areas of alpine regions and the types of parameters included is limited, and optimal spectral treatments and predictive models applicable to different parameters have not been sufficiently investigated. Therefore, we evaluated the accuracy of predicting total nitrogen (TN), phosphorus pentoxide (TP2O5), total potassium oxide (TK2O), alkali-hydrolyzable nitrogen (AHN), effective phosphorus (AP), effective potassium (AK), soil organic matter (SOM), and pH in the Qinghai–Tibet Plateau using the Vis–NIR technique in combination with spectral transformations, correlation analysis, feature selection, and machine learning. The results show that spectral transformations improve the correlation between spectra and parameters but are dependent on the parameter type and the method used. Continuum removal (CR), logarithmic first-order differential (FDL), and inverse first-order differential (FDR) had the most significant effects. The feature bands were extracted using the SPA and modeled using partial least squares (PLSR), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and backpropagation neural networks (BPNNs). The accuracy was evaluated based on R2, RMSE, RPD, and RPIQ. We found that the PLSR model only enables the prediction of SOM and pH with lower accuracy than the remaining models. XGBoost can predict all of the parameters but only for AHN; the prediction performance is better than other methods (R2 = 0.776, RMSE = 0.043 g/kg, and RPIQ = 2.88). The RF, SVM, and BPNN models cannot predict AK, AP, and AHN, respectively. In addition, TP2O5, AP, and pH are best suited for modeling using RF (RPIQ = 2.776, 3.011, and 3.198); TN, AK, and SOM are best suited for modeling using BPNN (RPIQ = 2.851, 2.394, and 3.085); and AHN and TK2O are best suited for XGBoost and SVM, respectively (RPIQ = 2.880 and 3.217). Therefore, this study can provide technical and data support for the accurate and efficient acquisition of soil parameters in alpine agriculture.

Occurrence, seasonal variation and gas/particle partitioning of current used pesticides (CUPs) across 60 °C temperature and 30° latitudes in China

Gas and particle phases samples were collected at three sites in China in 2019–2020, with 60 °C temperature span and 30° latitude range. Totally, among 76 target current used pesticides (CUPs) with four types, 51 were quantified in at least one sample. The concentrations of individual CUPs ranged from 8 orders of magnitude, indicating different pollution levels. Herbicides were the dominated CUPs in Northeast China, while higher concentrations of fungicides were found in Southeast China. The highest concentrations of CUPs were observed in Southeast China in spring and winter, while in summer and autumn in Northeast China, caused by local climates and crop cultivation patterns. The gas/particle (G/P) partitioning of CUPs was mainly influenced by their physicochemical properties and ambient temperature. The G/P partitioning study indicated that the L-M-Y model was the optimum prediction model for herbicides, fungicides and pyrethroids. The L-M-Y model and the H-B model presented equal performance for organophosphate insecticides. To our knowledge, the L-M-Y model was firstly applied for the study of the G/P partitioning of CUPs, which provided new insights into the related fields of new emergency contaminates.

Increased rates of indeterminate results in QuantiFERON-TB gold in-tube during the COVID-19 epidemic in Hunan province, China

Increased rates of indeterminate QuantiFERON-TB Gold In-Tube (QFT-GIT) results have been reported since the COVID-19 epidemic in Hunan Province, China. The indeterminate result (ITR) rate of QFT increased from an average of 5.2% to 12.4%, paralleling the first COVID-19 pandemic wave in the region. QFT-GIT results of 243 hospitalized patients with COVID-19 from January 2022 to April 2023 at Xiangya Hospital of Central South University were analyzed. Of the 243 patients, 71 (29.2%) had ITRs due to reduced interferon-gamma production in the positive control. Multiple factors are associated with ITRs, such as disease severity, respiratory failure incidence, immunosuppressant use, and prognosis. Additionally, interferon-gamma (Mitogen-Nil) levels differed significantly depending upon disease severity, prognosis, immunosuppressant use, sepsis symptoms, respiratory failure, or hyperlipidemia. An abnormal increase in the ITR rate in the QFT was observed after the COVID-19 pandemic, and an optimal machine learning predictive model for indeterminate QFT results was established.

Development and validation of a predictive models for predicting the cardiac events within one year for patients underwent percutaneous coronary intervention procedure at IJN

PurposePercutaneous coronary intervention (PCI) is a common treatment modality for coronary artery disease. Accurate prediction of patients at risk for complications and hospital readmission after PCI could improve the overall clinical management. We aimed to develop and validate predictive models to predict any cardiac event within a year post PCI procedure.MethodsThis is a retrospective cohort study utilizing data from the National Cardiovascular Disease (NCVD)-PCI registry. The data collected (N = 28,007) were split into training set (n = 24,409) and testing set (n = 3598). Four predictive models (logistic regression [LR], random forest method, support vector machine [SVM], and artificial neural network) were developed and validated. The outcome on risk prediction were compared.ResultsThe demographic and clinical features of patients in the training and testing cohorts were similar. Patients had mean age ± standard deviation of 58.15 ± 10.13 years at admission with a male majority (82.66%). In over half of the procedures (50.61%), patients had chronic stable angina. Within 1 year of follow up mortality, target vessel revascularization (TVR), and composite event of mortality and TVR were 3.92%, 9.48%, and 12.98% respectively. LR was the best model in predicting mortality event within 1-year post-PCI (AUC: 0.820). SVM had the highest discrimination power for both TVR event (AUC: 0.720) and composite event of mortality and TVR (AUC: 0.720).ConclusionsThis study successfully identified optimal prediction models with the good discriminatory ability for mortality outcome and good discrimination ability for TVR and composite event of mortality and TVR with a simple machine learning framework.

Wireless-Enabled Asynchronous Federated Fourier Neural Network for Turbulence Prediction in Urban Air Mobility (UAM)

To meet the growing mobility needs in intra-city transportation, the concept of urban air mobility (UAM) has been proposed in which vertical takeoff and landing (VTOL) aircraft are used to provide a ride-hailing service. In UAM, aircraft can operate in designated air spaces known as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">corridors</i> , that link the aerodromes, thus avoiding the use of complex routing strategies such as those of modern-day helicopters and alleviating the burden on the ground transportation system. For safety, a UAM aircraft must use air-to-ground communications to report flight plan, off-nominal events, and real-time movement to ground base stations (GBSs). A reliable communication network between GBSs and aircraft enables UAM to adequately utilize the airspace and create a fast, efficient, and safe transportation system. In this paper, to characterize the wireless connectivity performance for UAM, a suitable spatial model is proposed. For the considered setup, assuming that any given aircraft communicates with the closest GBS, the distribution of the distance between an arbitrarily selected GBS and its associated aircraft and the Laplace transform of the interference experienced by the GBS are derived. Using these results, the signal-to-interference ratio (SIR)-based connectivity probability is determined to capture the connectivity performance of the UAM aircraft-to-ground communication network. Then, leveraging these connectivity results, a wireless-enabled asynchronous federated learning (AFL) framework that uses a Fourier neural network is proposed to tackle the challenging problem of turbulence prediction during UAM operations. For this AFL scheme, a staleness-aware global aggregation scheme is introduced to expedite the convergence to the optimal turbulence prediction model used by UAM aircraft. Simulation results validate the theoretical derivations for the UAM wireless connectivity. The results also demonstrate that the proposed AFL framework converges to the optimal turbulence prediction model faster than the synchronous federated learning baselines and a staleness-free AFL approach. Furthermore, the results characterize the performance of wireless connectivity and convergence of the aircraft’s turbulence model under different parameter settings, offering useful UAM design guidelines.

Portable automatic detection system with infrared imaging for measuring steel wires corrosion damage

Accurate, cost-efficient and lightweight quantitative detection of steel wire corrosion in cable is an unsolvable issue that puzzles researchers and bridge owners. This paper proposed a portable automatic detection system for quantitative corrosion detection of replaced steel wires. The developed system consists of three parts (an automatic detection device, high-precision infrared imager, and corrosion evaluation algorithm). The proposed method is derived on the basis of Joule's law and the formula for calculating heat release. Then, the corroded specimens with different corrosion degrees and corresponding mass loss ratio were obtained by pre-corroded test to simulate industrial air corrosion and pickling test. The prior knowledge acquisition test utilizing presented automatic detection equipment was conducted to acquire the surface temperature of steel wires with various corrosion ratios by infrared camera after electric heating. Subsequently, the optimal quantitative corrosion prediction model after electric excitation is selected after infrared image processing, outlier filtering, theoretical method comparison, and model modification. Finally, the damaged steel wires from an in-service cable-stayed bridge are chosen to validate the proposed model's generalization ability and predictive accuracy. Furthermore, based on the discovery of characteristics on surface temperature of corroded steel wires after heating, the automatic detection device can be upgraded to realize the quantitative detection of in-situ corrosion of bridge cable.

Real-time prediction models for remaining cold start time in proton exchange membrane fuel cell based on stack temperature

In order to mitigate the irreversible damage caused by cold start and preserve cell performance, this paper proposes a real-time prediction method based on the remaining cold start time of the proton exchange membrane fuel cell (PEMFC). This method can protect the cell by referencing the current cold start effect. In this work, a real-time prediction model for the remaining cold start time based on the backpropagation (BP) neural network, long short-term memory (LSTM) neural network, and nonlinear regression of logarithmic function is established. Furthermore, a combined prediction model with variable weight is established by integrating these three prediction methods. Results demonstrated that, when considering two distinct cold start experimental conditions as samples, the average prediction accuracy of the three single models across all prediction times is 78.80%, 71.76%, 67.07% and 84.72%, 84.66%, 87.03%, respectively. In comparison to the optimal single prediction model, the combined prediction model exhibits an improvement in prediction accuracy by 9.84% and 2.83% under the two different experimental conditions, respectively. In addition, the maximum average prediction error between predicted values and actual values at each time instant within a range of only 3 s, thereby providing substantial support for accurate cold start performance prediction.

ICEEMDAN-IWOA-BiLSTM Hybrid Algorithm-based Model for Short-term Load Forecasting

Given the uncertain, random, and volatile characteristics of power load, accurate forecasting of power load becomes challenging. To address this issue, this paper proposes an optimized prediction model by using a modified Adaptive White Noise Complete Integrated Empirical Modal Decomposition Algorithm (ICEEMDAN) and the improved Whale Optimization Algorithm (IWOA) for bidirectional short-term and long-term memory networks (BiLSTM). First of all, Australian power load data is preprocessed in this study. Then, the load data is decomposed into a series of sequences by using ICEEMDAN. After that, the improved whale algorithm is employed to analyze the BiLSTM super parameter optimization. Finally, each decomposed component is input into the IWOA-BiLSTM model for load forecasting. The results demonstrate that the proposed algorithm achieves higher accuracy in power load forecasting, compared to individual benchmark models and most portfolio models, indicating its applicability and practical value.

Gut mycobiome as a potential non-invasive tool in early detection of lung adenocarcinoma: a cross-sectional study

BackgroundThe gut mycobiome of patients with lung adenocarcinoma (LUAD) remains unexplored. This study aimed to characterize the gut mycobiome in patients with LUAD and evaluate the potential of gut fungi as non-invasive biomarkers for early diagnosis.MethodsIn total, 299 fecal samples from Beijing, Suzhou, and Hainan were collected prospectively. Using internal transcribed spacer 2 sequencing, we profiled the gut mycobiome. Five supervised machine learning algorithms were trained on fungal signatures to build an optimized prediction model for LUAD in a discovery cohort comprising 105 patients with LUAD and 61 healthy controls (HCs) from Beijing. Validation cohorts from Beijing, Suzhou, and Hainan comprising 44, 17, and 15 patients with LUAD and 26, 19, and 12 HCs, respectively, were used to evaluate efficacy.ResultsFungal biodiversity and richness increased in patients with LUAD. At the phylum level, the abundance of Ascomycota decreased, while that of Basidiomycota increased in patients with LUAD. Candida and Saccharomyces were the dominant genera, with a reduction in Candida and an increase in Saccharomyces, Aspergillus, and Apiotrichum in patients with LUAD. Nineteen operational taxonomic unit markers were selected, and excellent performance in predicting LUAD was achieved (area under the curve (AUC) = 0.9350) using a random forest model with outcomes superior to those of four other algorithms. The AUCs of the Beijing, Suzhou, and Hainan validation cohorts were 0.9538, 0.9628, and 0.8833, respectively.ConclusionsFor the first time, the gut fungal profiles of patients with LUAD were shown to represent potential non-invasive biomarkers for early-stage diagnosis.

Comparison of different prediction models for estimation of walking and running energy expenditure based on a wristwear three-axis accelerometer.

Objective: Objectively and efficiently measuring physical activity is a common issue facing the fields of medicine, public health, education, and sports worldwide. In response to the problem of low accuracy in predicting energy consumption during human motion using accelerometers, a prediction model for asynchronous energy consumption in the human body is established through various algorithms, and the accuracy of the model is evaluated. The optimal energy consumption prediction model is selected to provide theoretical reference for selecting reasonable algorithms to predict energy consumption during human motion. Methods: A total of 100 subjects aged 18-30years participated in the study. Experimental data for all subjects are randomly divided into the modeling group (n = 70) and validation group (n = 30). Each participant wore a triaxial accelerometer, COSMED Quark pulmonary function tester (Quark PFT), and heart rate band at the same time, and completed the tasks of walking (speed range: 2km/h, 3km/h, 4km/h, 5km/h, and 6km/h) and running (speed range: 7km/h, 8km/h, and 9km/h) sequentially. The prediction models were built using accelerometer data as the independent variable and the metabolic equivalents (METs) as the dependent variable. To calculate the prediction accuracy of the models, root mean square error (RMSE) and bias were used, and the consistency of each prediction model was evaluated based on Bland-Altman analysis. Results: The linear equation, logarithmic equation, cubic equation, artificial neural network (ANN) model, and walking-and-running two-stage model were established. According to the validation results, our proposed walking-and-running two-stage model showed the smallest overall EE prediction error (RMSE = 0.76METs, Bias = 0.02METs) and the best performance in Bland-Altman analysis. Additionally, it had the lowest error in predicting EE during walking (RMSE = 0.66METs, Bias = 0.03METs) and running (RMSE = 0.90METs, Bias < 0.01METs) separately, as well as high accuracy in predicting EE at each single speed. Conclusion: The ANN-based walking-and-running two-stage model established by separating walking and running can better estimate the walking and running EE, the improvement of energy consumption prediction accuracy will be conducive to more accurate to monitor the energy consumption of PA.

Prediction and evaluation of polymer turbulent drag reduction efficiency based on BP neural network

In the process of oil exploitation and transportation, in order to effectively predict and control energy consumption for drag reduction of oil flow, in this paper a BP neural network was proposed based method for predicting and evaluating the turbulent drag reduction efficiency of polymers, which can greatly improve the current situation of relying on empirical formulas and low generality in polymer turbulent drag reduction efficiency prediction. Based on the experimental data sets of four commercial polymer drag-reducing agents FLOXL, М-Flowtreat, Necadd-447, and FLO MXA, obtained at different polymer concentrations, viscosity, density, and Reynolds number, a BP neural network has been established and the optimal number of neurons in the hidden layer was selected using the root mean square error (RMSE) value to obtain the optimal BP neural network prediction model. The BP neural network prediction models for the four polymer drag-reducing agents all have a good fit of 0.98 or above, and the R2 of the trained BP neural network for the Necadd-447 drag-reducing agents is 0.9949, which is the best among the four polymer drag-reducing agents. The BP neural network established in this paper can be applied to the turbulent drag reduction transport of long-distance pipelines for oil products to achieve the prediction of the drag reduction efficiency of polymer additives.

Wife-Mother Role Conflict at the Critical Child-Rearing Stage: A Machine-Learning Approach to Identify What and How Matters in Maternal Depression Symptoms in China.

Maternal depression (MD) was one of the most prevalent psychiatric problems worldwide. However, it easily remains untreated and misses the best time to prevent the emergence or worsening of major depressive symptoms due to under-observed stigma and the lack of effective screening tools. Thus, this study aims to develop and validate a machine learning-based MD symptoms prediction model integrating more observable and objective factors to early detect and monitor MD risk. A cross-sectional study was conducted in 10 community vaccination centers in Wenzhou, China, and a total of 1099 mothers were surveyed by using purposive sampling. A questionnaire containing questions regarding socio-demographic variables, psychophysiological variables, wife role-related variables, and mother role-related variables was used to collect data. A framework of data preprocessing, feature selection, and model evaluation was implemented to develop an optimal risk prediction model. Results demonstrated that the XG-Boost algorithm provided robust performance with the highest AUC and well-balanced sensitivity and specificity (AUC = 0.90, sensitivity = 0.74, specificity = 0.90). Furthermore, the causal mediation analysis indicated that wife-mother role conflict positively predicted MD symptoms, and it also exerted influence on mothers suffering through the mediation of anxiety and insomnia. Findings from the present study may help guide the development of MD screening tools to early detect and provide the modifiable risk factor information for timely tailored prevention.

Predicting and extracting thermal behavior rules of hydronic thermal barrier with interpretable ensemble learning in the heating season

Hydronic thermal barrier (HTB) creates dynamic thermal resistance in buildings, enabling buildings to adapt to outdoor weather fluctuations and regulate indoor environments. However, the lack of a comprehensive model to predict thermal behavior and explain the underlying rules is a significant limitation to its real-life situations. Additionally, the high computational cost of traditional numerical modelling also poses a challenge. To address these issues, this study proposed a framework for predicting HTB thermal behavior and extracting rules. A benchmark model was first introduced that incorporates coupled physical fields and accounts for multi-source uncertainties, reducing rule failures resulting from system changes. A data-driven prediction model was then developed, using machine learning and the finite element method, to clarify thermal behavior during the heating season in cold and severely cold regions of China. To enhance model generalization and applicability, three typical feature selection methods were employed. A comprehensive trial involving five ensemble learning models was conducted. Recursive Feature Elimination (RFE) selected the most representative features for prediction models. For heat storage efficiency, RFE combined with Light Gradient Boosting Machine achieved the best prediction performance with an R2 of 0.877, while the optimal prediction model for exergy efficiency was developed by combining RFE with Categorical Boosting with an R2 of 0.782. Finally, the profound HTB thermal behavior rules were extracted by the Shapley Additive exPlanation framework from both global and individual perspectives. Taken together, these findings can serve as a reference for the practical design and operation management of HTB.

Construction of a prediction model for predicting rebleeding in patients with obscure gastrointestinal bleeding after capsule endoscopy

Objective: To explore the risk factors of rebleeding in patients with obscure gastrointestinal bleeding (OGIB) after capsule endoscopy (CE), and construct a model to predict rebleeding. Methods: The data of patients with OGIB who underwent CE in Zhongda Hospital Affiliated to Southeast University from July 2018 to September 2021 were retrospectively analyzed. Follow-up data were obtained via electronic medical records or telephone interviews. Univariate and multivariate Cox regression models were performed to figure out the risk factors of rebleeding in OGIB patients. Then the optimal prediction model was determined and presented as a nomogram. The model was evaluated by C statistic, calibration curve and decision curve analysis. Results: One hundred and thirty patients with OGIB were included, including 64 females and 66 males, aged (55.8±17.2) years (18-87 years), and 39 (30.0%) cases developed rebleeding during follow-up. Univariate and multivariate Cox regression model analysis showed the duration of more than 2 weeks OGIB (HR=3.70, 95%CI: 1.85-7.42, P<0.001), a history of previous gastrointestinal bleeding (HR=5.25, 95%CI: 2.00-13.81, P<0.001), positive CE findings (HR=3.72, 95%CI: 1.66-8.33, P=0.001), and the lowest hemoglobin level before CE<80 g/L (HR=2.00, 95%CI: 1.02-3.84, P=0.044) were risk factors for rebleeding, while specific treatment (HR=0.25, 95%CI: 0.11-0.54, P<0.001) was a protective factor. The corresponding scores of the above five predictive factors were: OGIB duration>2 weeks: 79 points; Previous history of gastrointestinal bleeding: 100 points; The result of CE was positive: 79 points; Specific treatment:-85 points; Minimum hemoglobin before CE<80 g/L: 41 points. The prediction model constructed from the above five variables had good discriminative capability (concordance index=0.798, 95%CI: 0.732-0.865). The calibration curves showed high consistency between nomogram-predicted probabilities and actual observations. The decision curves showed that when the threshold probability was above 0.04, the use of the nomogram to predict rebleeding provided a greater net benefit than the assumption of "all patients rebleeding or no patients rebleeding". Conclusion: The prediction model established in this study has a good ability to predic rebleeding in patients with OGIB after CE examination.

Study of flexural strength of concrete containing mineral admixtures based on machine learning

In this paper, the prediction of flexural strength was investigated using machine learning methods for concrete containing supplementary cementitious materials such as silica fume. First, based on a database of suitable characteristic parameters, the flexural strength prediction was carried out using linear (LR) model, random forest (RF) model, and extreme gradient boosting (XGB) model. Subsequently, the influence of each input parameter on the flexural strength was analyzed using the SHAP model based on the optimal prediction model. The results showed that LR, RF, and XGB enhanced the accuracy of forecasting sequentially. Among the characteristic parameters, the most significant effect on the flexural strength of concrete is the water-binder ratio, and the water-binder ratio shows a negative correlation with flexural strength. The effect of maintenance age on flexural strength is second only to the water-binder ratio, and it shows a positive trend. When the amount of fly ash is less than 40% and the amount of slag or silica fume is less than 30%, the correlation between the amount of supplementary cementitious materials and flexural strength fluctuates and a positive peak in flexural strength is observed. However, at a dosage greater than the above, the supplementary cementitious materials all reduce flexural strength. The interaction interval and the degree of interaction between the supplementary cementitious materials and the cement content also differ in predicting flexural strength.

Self-optimization wavelet-learning method for predicting nonlinear thermal conductivity of highly heterogeneous materials with randomly hierarchical configurations

In the present work, we propose a self-optimization wavelet-learning method (SO-W-LM) with high accuracy and efficiency to compute the equivalent nonlinear thermal conductivity of highly heterogeneous materials with randomly hierarchical configurations. The randomly structural heterogeneity, temperature-dependent nonlinearity and material property uncertainty of heterogeneous materials are considered within the proposed self-optimization wavelet-learning framework. Firstly, meso- and micro-structural modeling of random heterogeneous materials are achieved by the proposed computer representation method, whose simulated hierarchical configurations have relatively high volume ratio of material inclusions. Moreover, temperature-dependent nonlinearity and material property uncertainties of random heterogeneous materials are modeled by a polynomial nonlinear model and Weibull probabilistic model, which can closely resemble actual material properties of heterogeneous materials. Secondly, an innovative stochastic three-scale homogenized method (STSHM) is developed to compute the macroscopic nonlinear thermal conductivity of random heterogeneous materials. Background meshing and filling techniques are devised to extract geometry and material features of random heterogeneous materials for establishing material databases. Thirdly, high-dimensional and highly nonlinear material features of material databases are preprocessed and reduced by wavelet decomposition technique. The neural networks are further employed to excavate the predictive models from dimension-reduced low-dimensional data. At the same time, advanced intelligent optimization algorithms are utilized to self-search the optimal network structure and learning rate for obtaining the optimal predictive models. Finally, the computational accuracy and efficiency of the presented approach are validated via various numerical experiments on realistic random composites.

Assessing the suitability and dynamics of three medicinal Sambucus species in China under current and future climate scenarios.

Climate change exerts profound influences on the ecological environments on a global scale, leading to habitat destruction and altering distribution patterns for numerous plant species. Traditional Chinese medicinal plants, such as those belonging to the Sambucus genus, have been extensively utilized for several centuries to treat fractures, rheumatism, and inflammation. However, our understanding of their geographic distribution and climatic adaptation within China still needs to be improved. In this study, we screened the optimal predictive model (random forest model) to predict the potential suitable distribution of three Sambucus species (Sambucus adnata, Sambucus javanica, and Sambucus williamsii) across China under both current and future climate scenarios. Moreover, we identified key climate factors that influence their potential distributions. Our findings revealed that S. adnata and S. javanica are predominantly shaped by temperature seasonality and mean diurnal range, respectively, whereas S. williamsii is significantly affected by the precipitation of the wettest month. Currently, S. williamsii is primarily distributed in north and central south China (covering 9.57 × 105 km2), S. javanica is prevalent in the south and east regions (covering 6.41×105 km2), and S. adnata predominantly thrives in the southwest China (covering 1.99×105 km2). Under future climate change scenarios, it is anticipated that S. adnata may migrate to higher latitudes while S. javanica may shift to lower latitudes. However, potentially suitable areas for S. williamsii may contract under certain scenarios for the years 2050 and 2090, with an expansion trend under the SSP585 scenario for the year 2090. Our study emphasizes the importance of climatic variables in influencing the potential geographic distribution of Sambucus species. These findings provide valuable theoretical insights for the preservation, cultivation, and utilization of Sambucus medicinal plant resources in the context of ongoing climate change.