Input Variables Of Model Research Articles

Artificial Neural Networks as a Method for Forecasting Migration Balance (A Case Study of the City of Lublin in Poland)

Internal migration regulates both the size and structure of human resources and affects the labor market at different spatial scales. It therefore has not only a demographic dimension, but also a spatial one, which is why it can significantly affect development on both a local and regional scale. The main objective of this study was to examine the usefulness of artificial neural networks (ANN) for predicting the internal migration balance for the city of Lublin in Poland. Another objective was to develop an experimental neural network model for forecasting the internal migration balance for the city of Lublin (for one year ahead) based on selected economic and social factors. The study area included the city of Lublin and 14 municipalities located in the vicinity of the city and functionally connected to it (they form the Lublin Functional Area), i.e., a total of 15 spatial units. Data for the analysis covered the years 2005–2022 and were obtained from the Local Data Bank (BDL) of the Central Statistical Office (GUS). The number of input variables for the ANN model was reduced using principal component analysis (PCA), allowing for the inclusion of the most relevant demographic and economic features. These components can thus be considered reliable predictors of the migration balance for the city of Lublin. This suggests that artificial neural networks may be an effective tool in supporting decision-making processes for forecasting the migration balance of this city.

A comparative study of intelligent prediction models for landslide susceptibility: random forest and support vector machine

Colluvial landslides widely developed in mountainous and hilly areas have the characteristics of mass occurrence and sudden occurrence. How to reveal the spatial distribution rules of potential landslides quickly and accurately is of great significance for landslide warning and prevention in the study area. Landslide susceptibility prediction (LSP) modeling provides an effective way to reveal the spatial distribution of regional landslides, however, it is difficult to accurately divide slope units and select prediction models in the processes of LSP modeling. To solve these problems, this paper takes the widely developed colluvial landslides in Dingnan County, Jiangxi Province, China as the research object. Firstly, the multi-scale segmentation (MSS) algorithm is used to divide Dingnan County into 100,000 slope units, to improve the efficiency and accuracy of slope unit division. Secondly, 18 environmental factors with abundant types and clear meanings, including topography, lithology and hydrological environment factors, were selected as input variables of LSP models. Then, a widely representative Support Vector Machine (SVM) and Random Forest (RF) models were selected to explore the difference characteristics of various machine learning models in predicting landslide susceptibility. Finally, the comprehensive evaluation method is proposed to compare the accuracy of various slope unit-based machine learning methods for LSP. The results show that the MSS algorithm can divide slope units in Dingnan County efficiently and accurately. The RF model (AUC = 0.896) has a higher LSP accuracy than that of the SVM model (AUC = 0.871), and the landslide susceptibility indexes (LSI) predicted by the RF model have a smaller mean value and a larger standard deviation than those of the SVM model. Conclusively, the overall performance of RF model in predicting landslide susceptibility is higher than that of SVM model.

Short-Term Energy Generation Forecasts at a Wind Farm—A Multi-Variant Comparison of the Effectiveness and Performance of Various Gradient-Boosted Decision Tree Models

High-quality short-term forecasts of wind farm generation are crucial for the dynamically developing renewable energy generation sector. This article addresses the selection of appropriate gradient-boosted decision tree models (GBDT) for forecasting wind farm energy generation with a 10-min time horizon. In most forecasting studies, authors utilize a single gradient-boosted decision tree model and compare its performance with other machine learning (ML) techniques and sometimes with a naive baseline model. This paper proposes a comprehensive comparison of all gradient-boosted decision tree models (GBDTs, eXtreme Gradient Boosting (XGBoost), Light Gradient-Boosting Machine (LightGBM), and Categorical Boosting (CatBoost)) used for forecasting. The objective is to evaluate each model in terms of forecasting accuracy for wind farm energy generation (forecasting error) and computational time during model training. Computational time is a critical factor due to the necessity of testing numerous models with varying hyperparameters to identify the optimal settings that minimize forecasting error. Forecast quality using default hyperparameters is used here as a reference. The research also seeks to determine the most effective sets of input variables for the predictive models. The article concludes with findings and recommendations regarding the preferred GBDT models. Among the four tested models, the oldest GBDT model demonstrated a significantly longer training time, which should be considered a major drawback of this implementation of gradient-boosted decision trees. In terms of model quality testing, the lowest nRMSE error was achieved by the oldest model—GBDT in its tuned version (with the best hyperparameter values obtained from exploring 40,000 combinations).

Research on prediction of high energy microseismic events in rock burst mines based on BP neural network

In response to the frequent occurrence of high-energy microseismic events in coal mines in China, a back propagation neural network (BPNN) prediction model based on surface subsidence data has been proposed to provide a basis for safely and efficiently predicting coal mine disasters. Theoretical research on the relationship between surface displacement, mining disturbance, and high-energy microseismic event levels has demonstrated a significant correlation among these factors. When there is a sudden increase or decrease in surface displacement or mining disturbance, the advancing working face typically exhibits dynamic characteristics. Therefore, feature parameters relevant to predicting high-energy microseismic event levels were selected as input variables for the BPNN model. Raw data from 88 sets of microseismic events in the 301 working face of the third mining area of a certain coal mine in Inner Mongolia were extracted. First, outlier preprocessing was conducted to obtain a complete dataset, which is then divided into a training set and a testing set. The BPNN model was trained with the training set and subsequently tested to evaluate its predictive performance. Finally, by comparing several model evaluation metrics, it was found that the BPNN model outperforms other common models in predicting high-energy events. The overall prediction accuracy is 86.4%, and the root mean square error (RMSE) is 0.45, indicating that the BPNN-based prediction model for high-energy microseismic events in coal mines is feasible.

An Adaptive Neural Fuzzy Inference System for the Estimation of the Atmospheric Corrosion Rate of Steel

This paper aims to develop a practical Adaptive Neural Fuzzy Inference System (ANFIS) for estimating carbon steel's Atmospheric Corrosion Rate (ACR). The ANFIS model is developed using 125 datasets. The input variables of the ANFIS model include average Temperature (T), average Relative Humidity (RH), total Rainfall (Rf), Time of Wetness (TOW), and average Chloride Ion (Cl-). The output variable of the Machine Learning (ML) model is the ACR value. The results of the proposed model are compared to those of the literature. The comparisons reveal that the ANFIS model established in this study outperforms the existing equations in predicting ACR. Furthermore, a Graphical User Interface (GUI) is developed for practical use in predicting the ACR of carbon steel.

Optimization of Cathode Catalyst Layer Composition of Polymer Electrolyte Fuel Cell for Maximum Cell Performance Using Machine Learning and Genetic Algorithm

The Polymer electrolyte fuel cell (PEFC) is a promising technology for power generation, noted for its potential as a zero-carbon technology at the point of use. However, PEMFC faces challenges that must be addressed to enhance its viability, such as its high cost and inefficient output power density. A key component influencing these factors is the cathode catalyst layer (CCL), which is critical for the mass transport flux and electrochemical reactions within the fuel cell. A strategy to lower costs while maintaining performance involves optimizing the CCL composition, including the ionomer-to-carbon (I/C) ratio, Pt-to-carbon (Pt/C) ratio, CCL thickness, and the type of carbon black used, alongside minimizing the Pt loading. Such optimization involves consideration of multiple factors and, consequently, adjusting the CCL composition might have a high potential to balance cost and performance. In this study, therefore, our goal is to propose an optimized catalyst composition that enables high-cell performance with low Pt loading. In particular, we integrated a surrogate machine learning model with an optimization algorithm to determine the optimization of CCL composition.The composition of each CCL is characterized by several variables, including the Pt/C and I/C, the thickness of the catalyst layer, the ionomer coating condition (uniform and non-uniform coatings), and the type of carbon used, which varied between porous (Ketjen) and non-porous (Vulcan) carbon [1]. These variables and output power density were assigned as input and output variables of the machine learning models, respectively. The dataset for the machine learning model was prepared by conducting cell performances with various CCL compositions by the multi-block method detailed in our previous work [2,3]. A total of 390 simulations were used as the dataset, with 312 data points used for training and 78 data points for testing.An assembled machine-learning algorithm known as Extreme Gradient Boosting (XGB) was employed to develop the surrogate model. To identify the optimal CCL composition that generates the highest output power density at a given Pt loading, the XGB-based surrogate model was integrated with an optimization algorithm based on the genetic algorithm (GA). In particular, the fitness of each individual within the GA population is determined by the XGB-based surrogate model, and the GA iteratively evaluates the fitness using operations such as selection, crossover, and mutation, to converge toward the composition that results in the highest power density.The performance of the XGB-based surrogate model in predicting cell performance is validated by its root mean squared error (RMSE) and square correlation coefficient (R²) on the test set, which are 0.07 and 0.89, respectively. This means the cell performance can be predicted by the surrogate model. In the importance feature analysis, the I/C ratio, carbon type, and thickness were identified as the most important parameters of CCL structures. This suggests that we can reduce the Pt load by optimizing the I/C ratio, CCL thickness, and type of carbon black. From the GA results, an optimal starting Pt loading of 0.25 mg/cm² was refined by adjusting the I/C ratio to 0.95, selecting Vulcan as the carbon type, and setting the CCL thickness to 6.54 µm. Through optimization, the Pt load was successfully reduced to 0.198 mg/cm², while maintaining the same power density as the initial loading of 0.25 mg/cm². This outcome highlights the efficacy of the surrogate model and optimization approach in enhancing the cost-efficiency of PEMFCs without compromising their performance.AcknowledgmentsThis research was supported by the New Energy and Industrial Technology Development Organization (NEDO), Japan (grant number P20003-20001327-0).

From Clinical to Non-clinical Outcomes in the Treatment of HIV: An Economic and Organizational Impact Assessment.

The aim of this study was to define the economic and organizational impacts related to a broader utilization of bictegravir/emtricitabine/alafenamide (BIC/FTC/TAF) in Italian clinical practice. A budget impact analysis-representing the evolution of the Italian National Healthcare Service (NHS) healthcare expenditure over 3years-was developed, considering the overall Italian population treated for human immunodeficiency virus (HIV). Model input variables were treatment history, therapeutic regimen, development of adverse events, achievement of an undetectable viral load and total direct healthcare costs. Besides the BIA, an organizational impact assessment was conducted to determine the impact on the use of healthcare resources, assessing the release of organizational hospital assets, focusing on the management of drug-related adverse events. Data were collected from scientific evidence, Italian national and regional legislations and healthcare professionals' reports. To verify the robustness of the economic and organizational impact assessment, sensitivity analyses were performed. Results demonstrate economic savings of about 26million euros in total health spending, assuming a higher penetration rate for BIC/FTC/TAF. This change in the current case mix would lead to a reduction in the specific costs related to adverse event management (0.9million euros; -2.09%) and in the medical management of patients (38million euros; -7.79%), with a positive impact on the achievement of virological control. From an organizational perspective, a wider use of BIC/FTC/TAF generates a reduction in the utilization of healthcare resources due to a decrease in adverse events and complications. The model estimated a 19.64% reduction in HIV-related inpatient days, which freed up healthcare professional time. Capable of improving both economic and organizational sustainability for the entire HIV care continuum, BIC/FTC/TAF is an efficient therapeutic strategy for people with HIV.

Predicting resilient modulus for pavement design: a comprehensive review of artificial neural network applications

ABSTRACT The Resilient Modulus (M R) is an essential parameter describing the mechanical behaviour of pavement materials, but the tests to obtain it are time-consuming and costly. Therefore, machine learning, especially Artificial Neural Networks (ANN), has recently been an effective alternative for predicting M R. Although there has been an increase in articles on ANN for predicting M R, no systematic review has yet categorised the publications, algorithm structures, predictive parameters, and model accuracy. This review provides a comprehensive overview of studies using ANN to predict M R for pavement materials. It examines various ANN subtypes and model structures, addressing a gap in understanding these models and identifying prevalent predictive parameters. Twenty-five peer-reviewed articles published in English-language journals were identified using keywords related to neural networks and M R. For fine soils, all models reviewed use moisture content as a predictive parameter. In contrast, granular soils models typically include stress state and physical characteristics of the materials. For recycled or stabilised materials, there is significant variability in model inputs. This review underscores the potential of ANN in enhancing predictive models for M R in pavement engineering, pointing towards future research and application refinement in this area of study.

Research on the prediction of blasting fragmentation in open-pit coal mines based on KPCA-BAS-BP

The blasting block size of open-pit mines is influenced by many factors, and the influencing factors have a very complex nonlinear relationship. Traditional empirical formulas and a single neural network model cannot meet the requirements of modern blasting safety. To improve the prediction accuracy of blasting block size, the measured data of Beskuduk open-pit coal mine is used as training and testing samples. Seven factors including rock tensile strength, rock compressive strength, and blast hole spacing are selected as input variables of the prediction model. The average size of blasting fragmentation X50 is used as the output variable of the prediction model. The kernel principal component analysis (KPCA) is adopted to reduce the dimensionality of the input variables. The beetle antennae search algorithm (BAS) is selected to optimize the parameters of the initial weights and thresholds of the back propagation (BP) neural network. Finally, prediction model of blasting fragmentation in open-pit coal mine based on KPCA-BAS-BP is established. The results show that the average relative error of the model is 1.77%, and the root mean square error is 1.52%. Compared with the unoptimized BP neural network and the BP neural network optimized by the artificial bee colony algorithm (ABC) model, this model has higher prediction accuracy and is more suitable for predicting the blasting block size of open-pit coal mines, it provides a new method for predicting the fragmentation of blasting under the influence of multiple factors, filling the gap in related theoretical research, and has certain practical application value.

Integrating traditional and non-traditional model risk frameworks in credit scoring

Background: An improved understanding of the reasoning behind model decisions can enhance the use of machine learning (ML) models in credit scoring. Although ML models are widely regarded as highly accurate, the use of these models in settings that require explanation of model decisions has been limited because of the lack of transparency. Especially in the banking sector, model risk frameworks frequently require a significant level of model interpretability.Aim: The aim of the article is to evaluate traditional model risk frameworks to determine their appropriateness when validating ML models in credit scoring and enhance the use of ML models in regulated environments by introducing a ML interpretability technique in model validation frameworks.Setting: The research considers model risk frameworks and regulatory guidelines from various international institutions.Method: The research is qualitative in nature and shows how through integrating traditional and non-traditional model risk frameworks, the practitioner can leverage trusted techniques and extend traditional frameworks to address key principles such as transparency.Results: The article proposes a model risk framework that utilises Shapley values to improve the explainability of ML models in credit scoring. Practical validation tests are proposed to enable transparency of model input variables in the validation process of ML models.Conclusion: Our results show that one can formulate a comprehensive validation process by integrating traditional and non-traditional frameworks.Contribution: This study contributes to existing model risk literature by proposing a new model validation framework that utilises Shapley values to explain ML model predictions in credit scoring.

Research on input parameter optimization for NOx deep learning prediction model

Optimizing the input parameters for NOx prediction model is instrumental in enhancing the precision and efficacy of the prediction model. This paper focuses on the input variables of the data-driven diesel engine NOx prediction model. According to the diesel engine NOx generation mechanism, at first relevant variables are selected, then the similarity method and parameter sensitivity method are compared to optimize the input variables. Firstly, this paper conducted a real-road emission test of a heavy-duty diesel vehicle, and proposed a data-driven deep learning model for predicting diesel engine NOx emissions based on the experimental data. The experimental data were processed using an Attention-Mechanism based Convolutional Neural Networks-Long Short-Term Memory (AM-CNN-LSTM) model. Subsequently, input parameters were selected according to the sensitivity weights assigned to each parameter in the preliminary model. This approach refined the modeling data and excluded variables not pertinent to NOx emission prediction. The AM-CNN-LSTM model prediction performance has been improved with 2% increase of model R2 as well as the model training time is reduced by 23%, and the types of parameters required to train the model are reduced by 50%. It accomplished this by effectively reducing data dimensions, discarding non-essential variables for NOx prediction, and diminishing computational complexity. Six input parameters were identified as pivotal in reconstructing the modeling data for accurate NOx prediction: engine speed, torque, EGR valve position, exhaust flow rate, air mass flow rate, and oil temperature. In optimizing the NOx prediction model, it is crucial to determine an optimal number of input parameters. Excessive parameters do not enhance model accuracy, while an insufficient number impairs the model’s ability to precisely emulate the NOx generation process, leading to diminished predictive accuracy.

Combined Prediction of Dust Concentration in Opencast Mine Based on RF-GA-LSSVM

Accurate prediction of dust concentration is essential for effectively preventing and controlling mine dust. The environment of opencast mines is intricate, with numerous factors influencing dust concentration, making accurate predictions challenging. To enhance the prediction accuracy of dust concentration in these mines, a combined prediction algorithm utilizing RF-GA-LSSVM is developed. Initially, the random forest (RF) algorithm is employed to identify key features from the meteorological and dust concentration data collected on site, ultimately selecting five indicators—temperature, humidity, stripping amount, wind direction, and wind speed—as the input variables for the prediction model. Next, the data are split into a training set and a test set at a 7:3 ratio, and the genetic algorithm (GA) is applied to optimize the least squares support vector machine (LSSVM) model for predicting dust concentration in opencast mines. Additionally, model evaluation metrics and testing methods are established. Compared with LSSVM, PSO-LSSVM, ISSA-LSSVM, GWO-LSSVM, and other prediction models, the GA-LSSVM model demonstrates a final fitting degree of 0.872 for PM2.5 concentration data and 0.913 for PM10 concentration data. The GA-LSSVM model clearly demonstrates a strong predictive performance with low error and high fitting. The research results can serve as a foundation for developing dust control measures in opencast mines.

Optimization of Ansys CFX Input Parameters for Numerical Modeling of Pump Performance in Turbine Operation

The paper deals with the issue of determining the optimal setting of input variables in Ansys CFX for modeling pump flow in turbine operation (PAT). The pump model was created in Autodesk Inventor. The mesh for numerical simulations was created using Ansys Fluent Meshing, considering the mesh quality parameters’ skewness and aspect ratio. The Ansys CFX computational model was experimentally verified on an actual pump by measuring the performance parameters on a test circuit and using the PIV (particle image velocimetry) method. The research indicated that the most suitable setting for the model input variables was the inlet pressure and PAT flow rate combination. Another option was to adjust the pressure at the pump inlet and outlet. However, the calculation time in this case was up to 30% longer. The comparison of the model results with the experiment showed that the deviations in the numerical model performance values did not exceed 10% of the values measured on the test circuit. Only the calculated torque was 1.2 ± 0.13 Nm higher on average than the torque measured on the test circuit. This difference is most likely due to the simplification of the geometry of the computational mesh in order to reduce the computation time.

Establishing the program to predict Shirt Sizes with Fuzzy Logic

This paper presents a program for prediction shirt size with a fuzzy logic technique. The Mamdani model is applied to a MISO fuzzy system with two inputs and one output. Neck girth and sleeve length are chosen as the primary dimensions, serving as input variables for this simulation model. In this study, fuzzy logic is used to select the size of the Min-Max rule. The IF-THEN structure is applied to execute commands effectively within this model. The outcome is an appropriate size. The program’s fuzzy rule matrix consists of 45 rows and 5 columns. Each row is a fuzzy rule. The first column represents the 9 sizes of necklaces. The second column represents the 5 groups of sleeve lengths. The third column represents the 9 predicted sizes in the output. The third column represents the 9 predicted output sizes. The fourth column is the weight coefficient. The last column represents the logical connection type. The fuzzy logic approaches significantly reduces the time required. This approach provides an alternative method for prediction sizes that more accurately align with individual body measurements, offering a personalized fit.

Improved maize leaf area index inversion combining plant height corrected resampling size and random forest model using UAV images at fine scale

ContextAccurate monitoring of leaf area index (LAI) is conducive to timely and targeted management measures. Unmanned aerial vehicle (UAV) remote sensing provides an important way for non-destructive monitoring of crop leaf area index. ObjectiveIn this study, visible light (RGB) and multispectral remote sensing data from the UAV and ground-measured LAI data from the Plant Canopy Analyzer LAI-2200 C were used to conduct inversion of maize LAI on a fine scale. MethodsTo address the problem of spatial scale mismatch between the spatial resolution of UAV images and the ground-measured LAI, the scale difference between UAV image data and ground-measured data was reduced by removing the outermost ring data measured by the LAI-2200 C instrument, calculating the spatial resolution of the UAV images after resampling based on the height of the plant, and the resampling method based on the circle. Finally, through the above method to resample the UAV images, we extract the vegetation index and canopy height features as the input variables of the random forest model to build the maize LAI inversion model in vegetative stages and reproductive stages respectively, which is referred to as the Vis_H+RF method. Results and conclusionsThe Vis_H+RF method of Tongliao experimental station has an R2 of 0.96 in the vegetative stages and a R2 of 0.61 in the reproductive stages, both of which perform well and have certain migration capabilities. SignificanceThe LAI inversion model constructed based on the method in this study is basically consistent with the actual situation and can provide data support for maize growth monitoring.

ANN-Based Filtering of Drone LiDAR in Coastal Salt Marshes Using Spatial–Spectral Features

Salt marshes provide diverse habitats for a wide range of creatures and play a key defensive and buffering role in resisting extreme marine hazards for coastal communities. Accurately obtaining the terrains of salt marshes is crucial for the comprehensive management and conservation of coastal resources and ecology. However, dense vegetation coverage, periodic tide inundation, and pervasive ditch distribution create challenges for measuring or estimating salt marsh terrains. These environmental factors make most existing techniques and methods ineffective in terms of data acquisition resolution, accuracy, and efficiency. Drone multi-line light detection and ranging (LiDAR) has offered a fire-new perspective in the 3D point cloud data acquisition and potentially exhibited great superiority in accurately deriving salt marsh terrains. The prerequisite for terrain characterization from drone multi-line LiDAR data is point cloud filtering, which means that ground points must be discriminated from the non-ground points. Existing filtering methods typically rely on either LiDAR geometric or intensity features. These methods may not perform well in salt marshes with dense, diverse, and complex vegetation. This study proposes a new filtering method for drone multi-line LiDAR point clouds in salt marshes based on the artificial neural network (ANN) machine learning model. First, a series of spatial–spectral features at the individual (e.g., elevation, distance, and intensity) and neighborhood (e.g., eigenvalues, linearity, and sphericity) scales are derived from the original data. Then, the derived spatial–spectral features are selected to remove the related and redundant ones for optimizing the performance of the ANN model. Finally, the reserved features are integrated as input variables in the ANN model to characterize their nonlinear relationships with the point categories (ground or non-ground) at different perspectives. A case study of two typical salt marshes at the mouth of the Yangtze River, using a drone 6-line LiDAR, demonstrates the effectiveness and generalization of the proposed filtering method. The average G-mean and AUC achieved were 0.9441 and 0.9450, respectively, outperforming traditional geometric information-based methods and other advanced machine learning methods, as well as the deep learning model (RandLA-Net). Additionally, the integration of spatial–spectral features at individual–neighborhood scales results in better filtering outcomes than using either single-type or single-scale features. The proposed method offers an innovative strategy for drone LiDAR point cloud filtering and salt marsh terrain derivation under the novel solution of deeply integrating geometric and radiometric data.

Development of a System for Predicting Hospitalization Time for Patients With Traumatic Brain Injury Based on Machine Learning Algorithms: User-Centered Design Case Study.

Currently, the treatment and care of patients with traumatic brain injury (TBI) are intractable health problems worldwide and greatly increase the medical burden in society. However, machine learning-based algorithms and the use of a large amount of data accumulated in the clinic in the past can predict the hospitalization time of patients with brain injury in advance, so as to design a reasonable arrangement of resources and effectively reduce the medical burden of society. Especially in China, where medical resources are so tight, this method has important application value. We aimed to develop a system based on a machine learning model for predicting the length of hospitalization of patients with TBI, which is available to patients, nurses, and physicians. We collected information on 1128 patients who received treatment at the Neurosurgery Center of the Second Affiliated Hospital of Anhui Medical University from May 2017 to May 2022, and we trained and tested the machine learning model using 5 cross-validations to avoid overfitting; 28 types of independent variables were used as input variables in the machine learning model, and the length of hospitalization was used as the output variables. Once the models were trained, we obtained the error and goodness of fit (R2) of each machine learning model from the 5 rounds of cross-validation and compared them to select the best predictive model to be encapsulated in the developed system. In addition, we externally tested the models using clinical data related to patients treated at the First Affiliated Hospital of Anhui Medical University from June 2021 to February 2022. Six machine learning models were built, including support vector regression machine, convolutional neural network, back propagation neural network, random forest, logistic regression, and multilayer perceptron. Among them, the support vector regression has the smallest error of 10.22% on the test set, the highest goodness of fit of 90.4%, and all performances are the best among the 6 models. In addition, we used external datasets to verify the experimental results of these 6 models in order to avoid experimental chance, and the support vector regression machine eventually performed the best in the external datasets. Therefore, we chose to encapsulate the support vector regression machine into our system for predicting the length of stay of patients with traumatic brain trauma. Finally, we made the developed system available to patients, nurses, and physicians, and the satisfaction questionnaire showed that patients, nurses, and physicians agreed that the system was effective in providing clinical decisions to help patients, nurses, and physicians. This study shows that the support vector regression machine model developed using machine learning methods can accurately predict the length of hospitalization of patients with TBI, and the developed prediction system has strong clinical use.

A Mathematical Model of Diel Activity and Long Time Survival in Phototrophic Mixed-Species Subaerial Biofilms

Subaerial biofilms (SAB) are intricate microbial communities living on terrestrial surfaces, of interest in a variety of contexts including cultural heritage preservation, microbial ecology, biogeochemical cycling, and biotechnology. Here we propose a mathematical model aimed at better understanding the interplay between cyanobacteria and heterotrophic bacteria, common microbial SAB constituents, and their mutual dependence on local environmental conditions. SABs are modeled as thin mixed biofilm-liquid water layers sitting on stone. A system of ordinary differential equations regulates the dynamics of key SAB components: cyanobacteria, heterotrophs, polysaccharides and decayed biomass, as well as cellular levels of organic carbon, nitrogen and energy. These components are interconnected through a network of energetically dominant metabolic pathways, modeled with limitation terms reflecting the impact of biotic and abiotic factors. Daily cylces of temperature, humidity, and light intensity are considered as input model variables that regulate microbial activity by influencing water availability and metabolic kinetics. Relevant physico-chemical processes, including pH regulation, further contribute to a description of the SAB ecology. Numerical simulations explore the dynamics of SABs in a real-world context, revealing distinct daily activity periods shaped by water activity and light availability, as well as longer time scale survivability conditions. Results also suggest that heterotrophs could play a substantial role in decomposing non-volatile carbon compounds and regulating pH, thus influencing the overall composition and stability of the biofilm.

Short-Term Forecasts of Energy Generation in a Solar Power Plant Using Various Machine Learning Models, along with Ensemble and Hybrid Methods

High-quality short-term forecasts of electrical energy generation in solar power plants are crucial in the dynamically developing sector of renewable power generation. This article addresses the issue of selecting appropriate (preferred) methods for forecasting energy generation from a solar power plant within a 15 min time horizon. The effectiveness of various machine learning methods was verified. Additionally, the effectiveness of proprietary ensemble and hybrid methods was proposed and examined. The research also aimed to determine the appropriate sets of input variables for the predictive models. To enhance the performance of the predictive models, proprietary additional input variables (feature engineering) were constructed. The significance of individual input variables was examined depending on the predictive model used. This article concludes with findings and recommendations regarding the preferred predictive methods.

Estimation of winter wheat LAI based on color indices and texture features of RGB images taken by UAV.

Leaf area index (LAI) is an important indicator for assessing plant growth and development, and is also closely related to photosynthesis in plants. The realization of rapid accurate estimation of crop LAI plays an important role in guiding farmland production. In study, the UAV-RGB technology was used to estimate LAI based on 65 winter wheat varieties at different fertility periods, the wheat varieties including farm varieties, main cultivars, new lines, core germplasm and foreign varieties. Color indices (CIs) and texture features were extracted from RGB images to determine their quantitative link to LAI. The results revealed that among the extracted image features, LAI exhibited a significant positive correlation with CIs (r = 0.801), whereas there was a significant negative correlation with texture features (r = -0.783). Furthermore, the visible atmospheric resistance index, the green-red vegetation index, the modified green-red vegetation index in the CIs, and the mean in the texture features demonstrated a strong correlation with the LAI with r > 0.8. With reference to the model input variables, the backpropagation neural network (BPNN) model of LAI based on the CIs and texture features (R2 = 0.730, RMSE = 0.691, RPD = 1.927) outperformed other models constructed by individual variables. This study offers a theoretical basis and technical reference for precise monitor on winter wheat LAI based on consumer-level UAVs. The BPNN model, incorporating CIs and texture features, proved to be superior in estimating LAI, and offered a reliable method for monitoring the growth of winter wheat. © 2024 Society of Chemical Industry.