Search

Background: ICU-acquired weakness (ICU-AW) is a common complication among ICU patients. We used machine learning techniques to construct an ICU-AW inflammatory factor prediction model to predict the risk of disease development and reduce the incidence of ICU-AW. Methods: The least absolute shrinkage and selection operator (LASSO) technique was used to screen key variables related to ICU-AW. Eleven indicators, such as the presence of sepsis, glucocorticoids (GC), neuromuscular blocking agents (NBAs), length of ICU stay, Acute Physiology and Chronic Health Evaluation (APACHE II) II score, and the levels of albumin (ALB), lactate (LAC), glucose (GLU), interleukin-1β (IL-1β), interleukin-6 (IL-6), and interleukin-10 (IL-10), were used as variables to establish the prediction model. We divided the data into a dataset that included inflammatory factors and a dataset that excluded inflammatory factors. Specifically, 70% of the participants in both datasets were used as the training set, and 30% of the participants were used as the test set. Three machine learning methods, logistic regression (LR), random forest (RF), and extreme gradient boosting (XGB), were used in the 70% participant training set to construct six different models, which were validated and evaluated in the remaining 30% of the participants as the test set. The optimal model was visualized for prediction using nomograms. Results: The logistic regression model including the inflammatory factors demonstrated excellent performance on the test set, with an area under the curve (AUC) of 82.1% and the best calibration curve fit, outperforming the other five models. The optimal model is represented visually in the nomograms. Conclusion: This study used easily accessible clinical characteristics and laboratory data that can aid in early clinical recognition of ICU-AW. The inflammatory factors IL-1β, IL-6, and IL-10 have high value for predicting ICU-AW. Trial registration: The trial was registered at the Chinese Clinical Trial Registry with the registration number ChiCTR2300077968. [ABSTRACT FROM AUTHOR]

An open problem in diabetes clinical practice is determining where and how much insulin should be administered to a person with diabetes (PwD) and how many carbohydrates they should eat to maintain blood glucose levels at healthy safe levels. Here, we propose the use of a minimal model describing the glucose dynamics of PwD. Using glucose Pwd's data, we calibrate the minimal model considering the uncertainty due to errors in glucose measurement, finding the model parameter values that best reproduce the current glucose levels. Then, all the possible combinations of insulin administration and carbohydrate intake are analysed with the aim of maintaining the glucose at safe levels during the following hours. The resulting procedure is tested with data from two real persons with scenarios of the most typical situations. We expect to apply this procedure in more complex models to help the physicians to give suitable recommendations to PwD. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Professional Business Review (JPBReview) is the property of Open Access Publications LLC and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As the mining depth increases, the effect of stress on the gas adsorption of coal gradually becomes significant. There are significant differences in the pore volume, specific surface area, and adsorption characteristics of coal before and after stress. In this study, the porosity variation characteristics of coal were studied using axial and confining pressure loading processes, and volumetric stress was introduced to characterize the pore variation law of coal under triaxial stress. By calculating the stress values at different burial depths, gas isothermal adsorption experiments were conducted on coal under different stress effects. The Langmuir equation, D-A equation, and Freundlich empirical formula were used to fit the adsorption experimental results. Combining experiments and models to predict the adsorbed and free gas content under stress, we described the gas adsorption law of coal under different stress effects. [ABSTRACT FROM AUTHOR]

Abstract Due to the use of multi winding high-frequency isolation transformers in the three port isolated bidirectional DC–DC converter to achieve port isolation and power transmission, there is a power coupling problem between each port. This article proposes a Model Prediction Control (MPC) strategy to address this issue. Considering the control objectives for each port of the Triple Active Bridge (TAB) DC–DC converter, a discrete predictive model of the TAB converter is established based on phase-shifting modulation and average model. The MPC problem is solved optimally and a predictive controller is designed with control accuracy to achieve decoupling control effect between each port. And the traditional single voltage closed-loop control, diagonal matrix decoupling control, and model predictive control proposed in this paper are compared through simulation. Finally, a TAB converter experimental platform is built based on the DSP control chip TMS320F28335. The experimental results are verified the effectiveness and superiority of the proposed method, as well as its faster dynamic characteristics and power decoupling ability between each port.

As the mining depth increases, the effect of stress on the gas adsorption of coal gradually becomes significant. There are significant differences in the pore volume, specific surface area, and adsorption characteristics of coal before and after stress. In this study, the porosity variation characteristics of coal were studied using axial and confining pressure loading processes, and volumetric stress was introduced to characterize the pore variation law of coal under triaxial stress. By calculating the stress values at different burial depths, gas isothermal adsorption experiments were conducted on coal under different stress effects. The Langmuir equation, D-A equation, and Freundlich empirical formula were used to fit the adsorption experimental results. Combining experiments and models to predict the adsorbed and free gas content under stress, we described the gas adsorption law of coal under different stress effects.

BACKGROUND AND OBJECTIVES: In recent decades, there has been significant advancement in scholarly research focused on detecting pollutants in marine environments and assessing the potential risks associated with seafood, particularly marine fish. The advancement has been predominantly influenced by the detection of microplastics, which have the ability to permeate food webs via both direct and indirect pathways. Microplastic pollution poses a substantial health risk to organisms at all levels of the food chain, including humans, who are top consumers. Despite the global concern, there is a lack of extensive research on microplastics in fish in Indonesia. The reliance of coastal communities in Indonesia on marine resources raises concerns regarding the potential impact of microplastic contamination. This study sought to assess the extent of microplastic pollutants in commercially caught marine fish from Jakarta Bay, a densely populated and industrialized coastal area accommodating more than 35 million inhabitants.METHODS: The study was conducted at five nearby fresh seafood markets in the northern part of Jakarta, where marine fish specimens were collected between December 2023 and January 2024. In total, 160 samples were gathered, with 20 individuals representing each of the eight diverse marine fish species. The approved protocol for extracting microplastics, which incorporates biological digestion, density separation, and microplastic identification, was strictly followed, although some adaptations were made as the process unfolded. Preventative actions were enacted in order to decrease the risk of microplastic cross-contamination.FINDINGS: It was determined through analysis that 93.75 percent (150 out of 160) of the fish studied contained microplastics, which were detected in samples obtained from both the gut and gill samples. On average, each fish had 3.65 ± 2.34 particles per individual, or approximately 0.12 ± 0.21 particles per gram. Microplastics were found in 81.25 percent of gut samples and 79.38 percent of gill samples. The abundance of microplastics in gut (1.79 ± 1.19 particles per individual) was slightly lower than in gills (1.86 ± 1.30 particles per individual). The variance in microplastic content between the two organs did not reach statistical significance. Fish with carnivorous feeding habits demonstrated a higher average microplastic content when contrasted with those utilizing omnivorous and planktivorous feeding strategies. Fish living in the benthopelagic region tended to have slightly more microplastic particles than those in benthic coastal water and pelagic coastal water. Most of the microplastics detected in commercial marine fish were in the size range of 2000-5000 micrometers, with the majority being in the form of fragments and fibers. The study also pinpointed seven specific polymer classifications, which consist of polyethylene, polypropylene, polystyrene, nylon, polyester, polybutadiene, and polyethylene terephthalate.CONCLUSION: The escalating levels of microplastics in the environment present a substantial threat to food security, marine ecosystems, and human health. It is imperative to develop a standardized risk assessment mechanism utilizing advanced tools and methodologies to quantify the levels of microplastics in the environment and living organisms as the study moves forward. It is imperative that both capture fisheries and aquaculture undergo thorough assessments of risks and hazards. This study underscores the significance of monitoring plastic waste in the Greater Jakarta area and its adjacent coastlines. Further study is essential to evaluate the magnitude of plastic pollution in fish tissues that are consumed by humans, and to assess the potential consequences for food safety.

Abstract This study aimed to preliminarily develop machine learning (ML) models capable of predicting the risk of device-associated infection and 30-day outcomes following invasive device procedures in intensive care unit (ICU) patients. The study utilized data from 8574 ICU patients who underwent invasive procedures, sourced from the Medical Information Mart for Intensive Care (MIMIC)-IV version 2.2 database. Patients were allocated into training and validation datasets in a 7:3 ratio. Seven ML models were employed for predicting device-associated infections, while five models were used for predicting 30-day survival outcomes. Model performance was primarily evaluated using the receiver operating characteristic (ROC) curve for infection prediction and the survival model’s concordance index (C-index). Top-performing models progressively reduced the number of variables based on their importance, thereby optimizing practical utility. The inclusion of all variables demonstrated that extreme gradient boosting (XGBoost) and extra survival trees (EST) models yielded superior discriminatory performance. Notably, when restricted to the top 10 variables, both models maintained performance levels comparable to when all variables were included. In the validation cohort, the XGBoost model, with the top 10 variables, achieved an area under the curve (AUC) of 0.810 (95% CI 0.808–0.812), an area under the precision-recall curve (AUPRC) of 0.226 (95% CI 0.222–0.230), and a Brier score (BS) of 0.053 (95% CI 0.053–0.054). The EST model, with the top 10 variables, reported a C-index of 0.756 (95% CI 0.754–0.757), a time-dependent AUC of 0.759 (95% CI 0.763–0.775), and an integrated Brier score (IBS) of 0.087 (95% CI 0.087–0.087). Both models are accessible via a web application. The internally evaluated XGBoost and EST models demonstrated exceptional predictive accuracy for device-associated infection risks and 30-day survival outcomes post-invasive procedures in ICU patients. Further validation is required to confirm the clinical utility of these two models in future studies.

Abstract A model for predicting slope stability is developed using Categorical Boosting (CatBoost), which incorporates 6 slope features to characterize the state of slope stability. The model is trained using a symmetric tree as the base model, utilizing ordered boosting to replace gradient estimation, which enhances prediction accuracy. Comparative models including Support Vector Machine (SVM), Light Gradient Boosting Machine (LGBM), Random Forest (RF), and Logistic Regression (LR) were introduced. Five performance evaluation metrics are utilized to assess the predictive capabilities of the CatBoost model. Based on CatBoost model, the predicted probability of slope instability is calculated, and the early warning model of slope instability is further established. The results suggest that the CatBoost model demonstrates a 6.25% disparity in accuracy between the training and testing sets, achieving a precision of 100% and an Area Under Curve (AUC) value of 0.95. This indicates a high level of predictive accuracy and robust ordering capabilities, effectively mitigating the problem of overfitting. The slope instability warning model offers reasonable classifications for warning levels, providing valuable insights for both research and practical applications in the prediction of slope stability and instability warning.

[Display omitted] • Six machine learning models were used to predict MR and CT. • GPR model demonstrated the best predictive performance. • SHAP and PDP were introduced for model interpretation. • An easy-to-use GUI was developed for the prediction of MR and MC. Preparation of activated carbons is an important way to utilize municipal sludge (MS) resources, while drying is a pretreatment method for making activated carbons from MS. In this study, machine learning techniques were used to develop moisture ratio (MR) and composting temperature (CT) prediction models for the thermally assisted biodrying process of MS. First, six machine learning (ML) models were used to construct the MR and CT prediction models, respectively. Then the hyperparameters of the ML models were optimized using the Bayesian optimization algorithm, and the prediction performances of these models after optimization were compared. Finally, the effect of each input feature on the model was also evaluated using SHapley Additive exPlanations (SHAP) analysis and Partial Dependence Plots (PDPs) analysis. The results showed that Gaussian process regression (GPR) was the best model for predicting MR and CT, with R2 of 0.9967 and 0.9958, respectively, and root mean square errors (RMSE) of 0.0059 and 0.354 ℃. In addition, graphical user interface software was developed to facilitate the use of the GPR model for predicting MR and CT by researchers and engineers. This study contributes to the rapid prediction, improvement, and optimization of MR and CT during thermally assisted biodrying of MS, and also provides valuable guidance for the dynamic regulation of the drying process. [ABSTRACT FROM AUTHOR]

Due to the use of multi winding high-frequency isolation transformers in the three port isolated bidirectional DC–DC converter to achieve port isolation and power transmission, there is a power coupling problem between each port. This article proposes a Model Prediction Control (MPC) strategy to address this issue. Considering the control objectives for each port of the Triple Active Bridge (TAB) DC–DC converter, a discrete predictive model of the TAB converter is established based on phase-shifting modulation and average model. The MPC problem is solved optimally and a predictive controller is designed with control accuracy to achieve decoupling control effect between each port. And the traditional single voltage closed-loop control, diagonal matrix decoupling control, and model predictive control proposed in this paper are compared through simulation. Finally, a TAB converter experimental platform is built based on the DSP control chip TMS320F28335. The experimental results are verified the effectiveness and superiority of the proposed method, as well as its faster dynamic characteristics and power decoupling ability between each port. [ABSTRACT FROM AUTHOR]

This work aims to establish a method for rapidly determining the antioxidant properties of lubricating oil(gear oil) in wind turbine gearboxes using infrared spectroscopy・ Based on the infrared spectral data of wind turbine gear oil, a series of data processing steps including sample set partitioning, data preprocessing, characteristic wavelength extraction and machine learning were sequentially performed ・ Finally, a variety of evaluation indexes were used to comprehensively evaluate the performance of the combined modeL The results indicate that the partial least squares regression model established using spectral data preprocessed with standard normal variate (SNV) transformation performs the best. Among the two feature wavelength extraction methods, principal component analysis (PCA) demonstrates superior dimensionality reduction compared to the successive projections algorithm (SPA)・ Among the three kinds of machine learning, BP neural network has the best prediction effect. The final result indicates that the SNV + PCA 4- BP model has the best prediction eftect, which can better and quickly predict the oxidation resistance of wind turbine gear oil. [ABSTRACT FROM AUTHOR]

Viscosity is a crucial parameter affecting the fluidity of metal melts, which directly influences the founding properties of Al alloys. However, obtaining viscosity measurement data is difficult for metal melts, and the viscosity prediction for ternary and multicomponent alloys would provide the significant data for the selection of process parameters. This study compares the applicability of the Hirai model, SDS model, and R‐K function for viscosity calculations in the sub‐binary systems of Al–Si–Mg–Fe alloys. R‐K function shows the best agreement with experimental data. However, the SDS model shows lower relative error than Hirai model, which would play an important role in those systems lacking experimental data to predict the viscosities. Ultimately, a database capable of predicting viscosity values for the entire composition and temperature range of the Al–Si–Mg–Fe system is established using the CALPHAD method. Viscosity parameters for Al–Si, Al–Mg, Al–Fe, Mg–Si, and Mg–Fe are evaluated and optimized through the R‐K derivation, corroborated with existing experimental data. Using the R‐K function, successful extrapolation and prediction of viscosity for the Al–Si–Mg–Fe ternary and quaternary systems are achieved, with a mean square error between predicted and experimental values of only 0.7%, demonstrating the successful application of the Al–Si–Mg–Fe database for viscosity prediction. [ABSTRACT FROM AUTHOR]

This study aimed to preliminarily develop machine learning (ML) models capable of predicting the risk of device-associated infection and 30-day outcomes following invasive device procedures in intensive care unit (ICU) patients. The study utilized data from 8574 ICU patients who underwent invasive procedures, sourced from the Medical Information Mart for Intensive Care (MIMIC)-IV version 2.2 database. Patients were allocated into training and validation datasets in a 7:3 ratio. Seven ML models were employed for predicting device-associated infections, while five models were used for predicting 30-day survival outcomes. Model performance was primarily evaluated using the receiver operating characteristic (ROC) curve for infection prediction and the survival model's concordance index (C-index). Top-performing models progressively reduced the number of variables based on their importance, thereby optimizing practical utility. The inclusion of all variables demonstrated that extreme gradient boosting (XGBoost) and extra survival trees (EST) models yielded superior discriminatory performance. Notably, when restricted to the top 10 variables, both models maintained performance levels comparable to when all variables were included. In the validation cohort, the XGBoost model, with the top 10 variables, achieved an area under the curve (AUC) of 0.810 (95% CI 0.808–0.812), an area under the precision-recall curve (AUPRC) of 0.226 (95% CI 0.222–0.230), and a Brier score (BS) of 0.053 (95% CI 0.053–0.054). The EST model, with the top 10 variables, reported a C-index of 0.756 (95% CI 0.754–0.757), a time-dependent AUC of 0.759 (95% CI 0.763–0.775), and an integrated Brier score (IBS) of 0.087 (95% CI 0.087–0.087). Both models are accessible via a web application. The internally evaluated XGBoost and EST models demonstrated exceptional predictive accuracy for device-associated infection risks and 30-day survival outcomes post-invasive procedures in ICU patients. Further validation is required to confirm the clinical utility of these two models in future studies. [ABSTRACT FROM AUTHOR]

Canine atopic dermatitis (CAD) is a common skin disease in dogs. Various pathogenic factors contribute to CAD, with dust mites, environmental pathogens, and other substances being predominant. This research involved comprehensive statistical analysis and prediction of CAD in China, using data from 14 cities. A distributed lag nonlinear model (DLNM) was developed to evaluate the impact of environmental factors on CAD incidence. Additionally, a seasonal auto-regressive moving average (ARIMA) model was used to forecast the monthly number of CAD cases. The findings indicated that CAD mainly occurs during June, July, August, and September in China. There was a positive correlation found between CAD incidence and temperature and humidity, while a negative correlation was observed with CO, PM2.5, and other pollutants. [ABSTRACT FROM AUTHOR]

Machine learning methods have gained much attention in health sciences for predicting various health outcomes but are scarcely used in pharmacoepidemiology. The ability to identify predictors of suboptimal medication use is essential for conducting interventions aimed at improving medication outcomes. It remains uncertain whether machine learning methods could enhance the identification of potentially inappropriate medication use among older adults compared with traditional methods. This study aimed to (1) to compare the performances of machine learning models in predicting use of potentially inappropriate medications and (2) to quantify and compare the relative importance of predictors in a population of community-dwelling older adults (>65 years) in the province of Québec, Canada. We used the Québec Integrated Chronic Disease Surveillance System and selected a cohort of 1 105 295 older adults of whom 533 719 were potentially inappropriate medication users. Potentially inappropriate medications were defined according to the Beers list. We compared performances between 5 popular machine learning models (gradient boosting machines, logistic regression, naive Bayes, neural networks, and random forests) based on receiver operating characteristic curves and other performance criteria, using a set of sociodemographic and medical predictors. No model clearly outperformed the others. All models except neural networks were in agreement regarding the top predictors (sex and anxiety-depressive disorders and schizophrenia) and the bottom predictors (rurality and social and material deprivation indices). Including other types of predictors (eg, unstructured data) may be more useful for increasing performance in prediction of potentially inappropriate medication use. • Potentially inappropriate medications are commonly used in older adults. Being a woman and mental diseases are known to be associated with potentially inappropriate medications use. • When compared with logistic regression, machine learning models did not increase performance for prediction of potentially inappropriate medication. Models ranked predictors similarly, except neural networks. • Our findings reveal that in the specific context of predicting potentially inappropriate medications using medical and administrative databases, classical models yield competitive results. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Contemporary Pediatrics is the property of Xiangya Medical Periodical Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

BACKGROUND AND OBJECTIVES: Tourism is a critical component of the economic framework in Thailand and numerous other countries worldwide, acting as a significant revenue generator. In the year 2022, the tourism industry made a significant contribution to Thailand's Gross Domestic Product, representing 22.92 percent of the total. However, the emphasis on urban development and management in order to boost visitor numbers can worsen urban metabolism, leading to an escalation in resource. The urban administration needs to know how much waste must be managed to plan for effective environmental and public health management. The focus of this study is on the construction of an artificial neural network forecasting model that takes into account socioeconomic and demographic variables to anticipate the management of municipal solid waste in a city known for tourism. METHODS: Models were generated by synthesizing and integrating municipal solid waste collection quantities with 17 inputs of socioeconomic, demographic, event occurrences, and tourism-specific metrics variables from 2015-2021 in Chiang Mai municipality. Deep learning techniques were used to create the models. Socioeconomic characteristics were derived using nosecount data at the provincial and municipal levels. Data preprocessing involved the implementation of knowledge discovery in database strategy to ensure the creation of datasets with sufficient numbers and quality for modeling. This issue involved calculating the correlation coefficient between 17 inputs and the quantities of municipal solid waste collected. RapidMiner® computer software was used to construct a model incorporating frameworks using artificial neural network techniques. To ensure robustness and prevent overfitting, the dataset was divided into training and validation sets. The model was trained using backpropagation methods, and the evaluation of the model's performance was based on the correlation between the observed and predicted values of the mean municipal solid waste collection rate. FINDINGS: The waste prediction model achieved optimal performance by incorporating eight input variables across two hidden layers, one consisting of ten nodes and the other of five nodes. Across eight trials, this arrangement produced the lowest correlation coefficient (0.67), mean absolute error (320.779 +/- 22.080), and root mean square error (16.5). On the other hand, the chosen model used 17 input variables split across two hidden layers, each with 8 or 4 nodes. The model yielded a correlation coefficient of 0.69, a mean absolute error of 461.953 +/- 706.680, and a root mean square error of 21.9. The current daily amount of municipal solid waste collected is 340 metric tonnes, while the projection model anticipates an increase to 348 metric tonnes per day by 2023, with a margin of error of 2 percent. The model further predicts a daily garbage collection of 361 metric tons through 2030. CONCLUSION: Future waste management strategies may be planned, and various environmental impacts in tourism cities can be analyzed using the forecasting process and framework for the municipal solid waste collection rate described in this research. These characteristics are harnessed by the model to gain a thorough insight into waste dynamics in metropolitan regions with high tourist activity, ultimately facilitating the adoption of more sustainable urban planning and management approaches. [ABSTRACT FROM AUTHOR]

A new, non‐dimensional ripple reset parameter and a stochastic point process model is used to estimate the likelihood of propagating ocean waves to form ripples on sandy seabeds. The ripple reset parameter is a function only of water depth, significant wave height, and mean grain size. Ripple formation is estimated by the magnitude of an intensity function based on a time series of the ripple reset parameter. The point process model is trained with a time series of observed waves and ripple change, and is then applied to predict the probability that a ripple field with a different geometry will form within a given time interval from another time series of wave data. The model is trained and tested with four field deployments at three field sites to determine its skill in predicting the ripple formation (a) at one field site over one time period after being trained with observations from the same site over a different time period, and (b) at one field site after being trained with observations from another field site. Results show that while the model is sufficient at predicting ripple formation in both scenarios, it is sensitive to the quality and quantity of the training data. Increasing the amount of training data greatly improves model performance. Employing a stochastic model based on a simple ripple reset parameter reduces tunable model parameters and provides a prediction of the probability for ripple formation given only a water depth, grain size, and time series of wave heights. Plain Language Summary: Ripples are small, hill‐like mounds of sand that are formed by water in the ocean moving back and forth by waves. Sand ripples can cause an increase of sand movement on the seafloor, can cause ocean instrumentation to respond unexpectedly, and can bury and expose objects. Understanding when they form is important for scientists to measure and predict ocean dynamics. If the average height of the waves, the water depth, and the sand grain diameter is known, we can predict whether or not the waves will form ripples with mathematical equations. Previously, the equations to predict ripple formation required a lot of difficult to obtain ocean information. We developed an equation and model to quickly and easily predict the likelihood of ripples forming by waves in a specific size sand and water depth. Key Points: A ripple reset parameter based on wave height, water depth, and grain size is presentedA stochastic model based on the ripple reset parameter can predict the probability of ripple formationThe model accurately predicted ripple resets at three different field sites without calibration [ABSTRACT FROM AUTHOR]

Objective To analyze the epidemiological distribution characteristics of chickenpox in Urumqi City from 2015 to 2023, to construct a prediction model by combining Baidu search keywords, and to explore the complementary application of Baidu index in chickenpox prevention and monitoring. Methods Descriptive epidemiological methods were used to analyze the characteristics of varicella case triple distribution in Urumqi City from 2015 to 2023. Chickenpox keywords were identified and a comprehensive Baidu search index was constructed. The models ARIMA and ARIMAX were constructed, the prediction effectiveness of the two models was evaluated by mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). Results The average annual reported incidence rate of varicella in Urumqi was 80.85/100 000, with a higher incidence in men than in women (χ² = 1.136, P = 0.287), there were statistically significant differences in incidence rates by age group (χ² = 7 582.372, P < 0.001), seven districts and one county had different average annual incidence rates (χ² = 21.496, P < 0.001), with the highest in the Toutunhe district (100.54/100 000). ARIMAX(1,1,0)(1,0,0)52 was selected as the best prediction model (prediction set MAE 12.04%, RMSE 13.80%, MASE 1.18%) with a good fitting effect. Conclusion The ARIMAX prediction model established based on the search term Baidu index has a certain degree of predictability and sensitivity, and can predict the epidemic trend of chickenpox in Urumqi in time, which can be used as a technical support and further expansion of the traditional monitoring and early warning system. [ABSTRACT FROM AUTHOR]

Copyright of Cotton Textile Technology is the property of Cotton Textile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To control the diesel engine urea SCR system with high accuracy, firstly, the partial differential equations of the SCR system are simplified through variable substitution and the method of characteristic lines to eliminate the partial derivative terms of the hyperbolic partial differential equations in the flow direction. The backward difference method is used to solve the problem, and the adaptive time step is adjusted to improve computational efficiency. Secondly, the Levenberg-Marquardt algorithm is applied to identify the model parameters per second based on the 1800-s test bench data. By combining the experimental data with the parameter identification results, this paper calculated the downstream NOx concentration with 99.5 % accuracy. Finally, the 1800s transient test data was applied to a commonly used single-state SCR control model, and cell numbers 1–4 of the cases were numerically simulated. It was found that the reduced-order model had a computation time of 1 s but was less accurate. When the test data was applied to the model presented in this study, the calculation time was 27s, and the model's calculation results show that the average error of the downstream NOx concentration is 16.95 ppm, which is 14.3 ppm lower than that of the two-cell one-state model.

Aiming at the situation of random changes in tactics and uncertain information in the confrontation pattern between missile and target in the air combat environment. By analyzing the motion relationship of a single missile attack to determine the target, the principles of dynamic game and differential game are introduced into the relative motion relationship between missile and target. In the dynamic game process of attack and defense confrontation, the terminal guidance problem of a single missile attacking and intercepting the target is modeled as a "one to one missile target" game model. The missile guidance law based on game theory under mixed strategy and the global strategic situation of bilateral optimization of the opponent at a certain moment are proposed. The method of model rolling prediction combined with differential game theory is introduced to simulate the confrontation between missile and target in uncertain attack and defense environments. The simulation results show that using this method can reduce the miss distance of missile to target and improve the hit accuracy of missile. The model provides a basis for missile attack and defense operations.

Abstract The enhancement of flexibility, energy efficiency, and environmental friendliness constitutes a widely acknowledged trend in the development of urban infrastructure. The proliferation of various types of transportation vehicles exacerbates the complexity of traffic regulation. Intelligent transportation systems, leveraging real-time traffic status prediction technologies, such as velocity estimation, emerge as viable solutions for the efficacious management and control of urban road networks. The objective of this project is to address the complex task of increasing accuracy in predicting traffic conditions on a big scale using deep learning techniques. To accomplish the objective of the study, the historical traffic data of Paris and Istanbul within a certain timeframe were used, considering the impact of variables such as speed, traffic volume, and direction. Specifically, traffic movie clips based on 2 years of real-world data for the two cities were utilized. The movies were generated with HERE data derived from over 100 billion GPS (Global Positioning System) probe points collected from a substantial fleet of automobiles. The model presented by us, unlike the majority of previous ones, takes into account the cumulative impact of speed, flow, and direction. The developed model showed better results compared to the well-known models, in particular, in comparison with the SR-ResNet model. The pixel-wise MAE (mean absolute error) values for Paris and Istanbul were 4.299 and 3.884 respectively, compared to 4.551 and 3.993 for SR-ResNET. Thus, the created model demonstrated the possibilities for further enhancing the accuracy and efficacy of intelligent transportation systems, particularly in large urban centres, thereby facilitating heightened safety, energy efficiency, and convenience for road users. The obtained results will be useful for local policymakers responsible for infrastructure development planning, as well as for specialists and researchers in the field. Future research should investigate how to incorporate more sources of information, in particular previous information from physical traffic flow models, information about weather conditions, etc. into the deep learning framework, as well as further increasing of the throughput capacity and reducing processing time.

Abstract This study aimed to develop a machine learning (ML)-based tool for early and accurate prediction of in-hospital mortality risk in patients with spontaneous intracerebral hemorrhage (sICH) in the intensive care unit (ICU). We did a retrospective study in our study and identified cases of sICH from the MIMIC IV (n = 1486) and Zhejiang Hospital databases (n = 110). The model was constructed using features selected through LASSO regression. Among five well-known models, the selection of the best model was based on the area under the curve (AUC) in the validation cohort. We further analyzed calibration and decision curves to assess prediction results and visualized the impact of each variable on the model through SHapley Additive exPlanations. To facilitate accessibility, we also created a visual online calculation page for the model. The XGBoost exhibited high accuracy in both internal validation (AUC = 0.907) and external validation (AUC = 0.787) sets. Calibration curve and decision curve analyses showed that the model had no significant bias as well as being useful for supporting clinical decisions. XGBoost is an effective algorithm for predicting in-hospital mortality in patients with sICH, indicating its potential significance in the development of early warning systems.

Interlaminar property is an important indicator to evaluate the overall quality of composite components. In the process of automated fiber placement (AFP) in situ consolidation, the interlaminar properties of the composite are affected by the processes such as temperature history, polymer degradation and crystallization, interlaminar bonding, and void dynamics. Interlaminar bonding is the primary process of forming the overall structure between layers of the component. In this study, the interlaminar bonding process of CF/PPS composites and the interlaminar properties of the laminates fabricated by AFP in situ consolidation were investigated. The influence of the processing parameters on intimate contact, polymer healing, and interlaminar bonding was analyzed through theoretical models. Taking the interlaminar shear strength of the laminates as an index, the model results were verified by experiments. The time required for diffusion of polymer molecular chain was much shorter than that of intimate contact. For the CF/PPS system used, the intimate contact process was found to be the control factor of interlaminar bonding. Furthermore, the results of the degree of intimate contact indicated that the ideal rectangular surface model was more consistent with the experimental values. [ABSTRACT FROM AUTHOR]

The absorption heat exchanger with a large temperature difference has a higher heat transfer superiority than the other heat exchangers (including plate heat exchanger), which is more suitable for long-distance heating. To improve its system performance, parameter collaborative optimization (including building accurate predictive models) has become an effective method because it does not require too much investment. In this study, a heat exchange station was chosen as a case study, and a model of a long short-term memory (LSTM) neural network was used to predict the temperatures of primary return water and secondary return water. Accordingly, the reliability of the fitting result based on the model was confirmed through a contrastive analysis with the prediction results of a support vector machine (SVM) model, a random forest (RF) model, and an extreme gradient boosting (XGBoost) model. In addition, the algorithm of particle swarm optimization was used to optimize the flow rate of primary supply water. The results showed that the temperature of primary-side return water decreased from 29.6 °C to 28.2 °C, the temperature of secondary-side return water decreased from 39.8 °C to 38.6 °C, and the flow rate of primary-side supply water decreased from 39 t/h to 35.2 t/h after the optimization of the flow rate of primary supply water. The sensibility assessment emerged that the secondary-side flow rate to the secondary-side supply water temperature was about 7 times more sensitive than the primary-side supply water temperature, and concretely, the lower the temperature, the higher the sensibility. In summary, the accuracy of the proposed prediction model was validated and the optimization direction was pointed out, which can be used to provide guidance for designing and planning absorption heat exchange stations with large temperature differences. [ABSTRACT FROM AUTHOR]

The paper investigates the effect of high temperature exposure on the performance of concrete confined through textile/fabric‐reinforced composites. Small‐scale cylindrical specimens (150 × 300 mm) were confined using two types of carbon fibers (dry and epoxy‐resin coated). For the sake of comparison, two confining layers were applied to all specimens. After curing, cylinders were exposed to four ranges of increasing temperatures—being 20°C (ambient), 80°C, 100°C, and 250°C and, after cooling down, were tested under compressive cyclic loading. The experimental results show that thermal stress significantly influences the confinement effectiveness of textile‐reinforced composites. Exposure to high temperatures reduces the ultimate confined strength and significantly influences the overall axial stress–strain behavior. [ABSTRACT FROM AUTHOR]

Many commonly used mathematical models in the field of mathematical biology involve challenges of parameter non-identifiability. Practical non-identifiability, where the quality and quantity of data does not provide sufficiently precise parameter estimates is often encountered, even with relatively simple models. In particular, the situation where some parameters are identifiable and others are not is often encountered. In this work we apply a recent likelihood-based workflow, called Profile-Wise Analysis (PWA), to non-identifiable models for the first time. The PWA workflow addresses identifiability, parameter estimation, and prediction in a unified framework that is simple to implement and interpret. Previous implementations of the workflow have dealt with idealised identifiable problems only. In this study we illustrate how the PWA workflow can be applied to both structurally non-identifiable and practically non-identifiable models in the context of simple population growth models. Dealing with simple mathematical models allows us to present the PWA workflow in a didactic, self-contained document that can be studied together with relatively straightforward Julia code provided on . Working with simple mathematical models allows the PWA workflow prediction intervals to be compared with gold standard full likelihood prediction intervals. Together, our examples illustrate how the PWA workflow provides us with a systematic way of dealing with non-identifiability, especially compared to other approaches, such as seeking ad hoc parameter combinations, or simply setting parameter values to some arbitrary default value. Importantly, we show that the PWA workflow provides insight into the commonly-encountered situation where some parameters are identifiable and others are not, allowing us to explore how uncertainty in some parameters, and combinations of parameters, regardless of their identifiability status, influences model predictions in a way that is insightful and interpretable. [ABSTRACT FROM AUTHOR]

Machine learning (ML) extends rapidly in many research areas including design of novel processing routines, imaging, and material science. Particularly, ML enables design of new materials with complex structures and shorten the development cycle through model prediction from existing database. Calcium carbonate (CaCO 3) particles are regarded as promising candidates for drug delivery, biomedical, food, and industrial filler applications due to their good physicochemical properties and biocompatibility. However, a prerequisite for these applications is the production of particles with desired morphology, size, and phase compositions. Here, it is shown that the crystal growth and phase transition induced the transformation of spherical particles into spindle-like, square and needle-like morphologies with increasing temperature, and the increase of concentration increased this transition temperature. Furthermore, it is found that the concentration of the reacting salt solutions shifted the phase transition temperatures to higher values. Subsequently, ML is applied to precisely investigate and predict the polymorph formation of CaCO 3 particles based on the experimental data obtained under 85 conditions, which would enable us to track crystallization trends, aiding in the identification of optimal conditions for generating monophase samples, and provide a feasible scheme for learning similar materials. [ABSTRACT FROM AUTHOR]

Copyright of Electric Machines & Control / Dianji Yu Kongzhi Xuebao is the property of Electric Machines & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The enhancement of flexibility, energy efficiency, and environmental friendliness constitutes a widely acknowledged trend in the development of urban infrastructure. The proliferation of various types of transportation vehicles exacerbates the complexity of traffic regulation. Intelligent transportation systems, leveraging real-time traffic status prediction technologies, such as velocity estimation, emerge as viable solutions for the efficacious management and control of urban road networks. The objective of this project is to address the complex task of increasing accuracy in predicting traffic conditions on a big scale using deep learning techniques. To accomplish the objective of the study, the historical traffic data of Paris and Istanbul within a certain timeframe were used, considering the impact of variables such as speed, traffic volume, and direction. Specifically, traffic movie clips based on 2 years of real-world data for the two cities were utilized. The movies were generated with HERE data derived from over 100 billion GPS (Global Positioning System) probe points collected from a substantial fleet of automobiles. The model presented by us, unlike the majority of previous ones, takes into account the cumulative impact of speed, flow, and direction. The developed model showed better results compared to the well-known models, in particular, in comparison with the SR-ResNet model. The pixel-wise MAE (mean absolute error) values for Paris and Istanbul were 4.299 and 3.884 respectively, compared to 4.551 and 3.993 for SR-ResNET. Thus, the created model demonstrated the possibilities for further enhancing the accuracy and efficacy of intelligent transportation systems, particularly in large urban centres, thereby facilitating heightened safety, energy efficiency, and convenience for road users. The obtained results will be useful for local policymakers responsible for infrastructure development planning, as well as for specialists and researchers in the field. Future research should investigate how to incorporate more sources of information, in particular previous information from physical traffic flow models, information about weather conditions, etc. into the deep learning framework, as well as further increasing of the throughput capacity and reducing processing time. [ABSTRACT FROM AUTHOR]

In order to explore the influence of vegetation root content on the water holding and permeability characteristics of expansive soil, samples with different root content were prepared by mixing bermudagrass roots with expansive soil from Nanning expansive soil area, and indoor pressure plate test and variable head permeability test were conducted, the Van Genuchten-Mualem model was used to predict the unsaturated permeability coefficient of expansive soil with different root contents. The results show that the water holding capacity of expansive soil decreases after the addition of roots, and the addition of roots increases the proportion of large and medium pores in the expansive soil. The higher the root content, the greater the proportion of large pore volume to total pore volume, and the greater the decrease in water holding capacity compared to pure soil. In saturated state, the permeability coefficient of expansive soil increases with the increase of root content. In unsaturated state, the permeability of expansive soil at low suction stage (0 ~ 25 kPa) increases with the increase of root content. As the matrix suction increases to high suction stage (200 ~ 1 000 kPa), the effect of root dominant flow decreases, and the permeability of expansive soil with roots gradually tends to be lower than that of pure soil. The mesoscopic results indicate that the incorporation of root system causes through cracks in the expansive soil, which is a key factor affecting the water holding and permeability of the expansive soil. This study further reveals the mechanism and regularity of the infiltration enhancement effect of vegetation roots on expansive soil, providing a reference for comprehensive evaluation of the effect of vegetation protection on expansive soil slopes. [ABSTRACT FROM AUTHOR]