Improve Prediction Accuracy Research Articles

Development of a prediction model based on Hemoglobin, Albumin, Lymphocyte count, and Platelet-score for lymph node metastasis in rectal cancer.

This study aimed to evaluate the ability of the preoperative Hemoglobin, Albumin, Lymphocyte count, and Platelet (HALP) score to predict lymph node metastasis (LNM) in patients with rectal cancer (RC) and improve prediction accuracy by incorporating clinical parameters. Data from 263 patients with RC were analyzed. The receiver operating characteristic (ROC) curve was used to determine the optimal cutoff value (OCV) for the HALP score in predicting LNM. Based on this cutoff value, patients were divided into two groups. A baseline analysis was conducted to identify independent factors linked to LNM. A support vector machine (SVM) prediction model was developed, and its performance was evaluated using ROC, calibration curves, decision curve analysis, and Kolmogorov-Smirnov curve. The OCV for HALP score was 45.979. Patients were then classified into a low HALP group (n = 182) and a high HALP group (n = 81). The analysis found 21 clinical factors significantly associated with LNM. Among them, the key risk factors included high inflammatory status, poor nutritional condition, and a low HALP score. The SVM model incorporated these factors and showed robust predictive performance, with area under the curve values of 0.897, 0.813, and 0.750 for the training, validation, and testing datasets, respectively. The HALP score was significantly associated with LNM in RC patients. A machine learning model integrating the HALP score and inflammatory markers may be an effective tool for predicting LNM in RC.

Psychological and Behavioral Insights From Social Media Users: Natural Language Processing-Based Quantitative Study on Mental Well-Being.

Depression significantly impacts an individual's thoughts, emotions, behaviors, and moods; this prevalent mental health condition affects millions globally. Traditional approaches to detecting and treating depression rely on questionnaires and personal interviews, which can be time consuming and potentially inefficient. As social media has permanently shifted the pattern of our daily communications, social media postings can offer new perspectives in understanding mental illness in individuals because they provide an unbiased exploration of their language use and behavioral patterns. This study aimed to develop and evaluate a methodological language framework that integrates psychological patterns, contextual information, and social interactions using natural language processing and machine learning techniques. The goal was to enhance intelligent decision-making for detecting depression at the user level. We extracted language patterns via natural language processing approaches that facilitate understanding contextual and psychological factors, such as affective patterns and personality traits linked with depression. Then, we extracted social interaction influence features. The resultant social interaction influence that users have within their online social group is derived based on users' emotions, psychological states, and context of communication extracted from status updates and the social network structure. We empirically evaluated the effectiveness of our framework by applying machine learning models to detect depression, reporting accuracy, recall, precision, and F1-score using social media status updates from 1047 users along with their associated depression diagnosis questionnaire scores. These datasets also include user postings, network connections, and personality responses. The proposed framework demonstrates accurate and effective detection of depression, improving performance compared to traditional baselines with an average improvement of 6% in accuracy and 10% in F1-score. It also shows competitive performance relative to state-of-the-art models. The inclusion of social interaction features demonstrates strong performance. By using all influence features (affective influence features, contextual influence features, and personality influence features), the model achieved an accuracy of 77% and a precision of 80%. Using affective features and affective influence features also showed strong performance, achieving 81% precision and an F1-score of 79%. The developed framework offers practical applications, such as accelerating hospital diagnoses, improving prediction accuracy, facilitating timely referrals, and providing actionable insights for early interventions in mental health treatment plans.

User Action Recognition Using a Fabric Pressure Distribution Sensor in an Electric Wheelchair for Soil Cultivation

Advancements in robotics technology and information and communication technology have significantly affected agriculture, especially systems that aid workers. Soil cultivation often requires prolonged bending, which results in physical strain. A commercially available work wheelchair reduces back strain, but lacks power assistance and relies on leg movements. In a previous study, we developed an electric wheelchair with a fabric pressure-distribution sensor on the seat. This sensor, combined with a fuzzy controller, aids movement by measuring the center of pressure fluctuations and reducing leg strain. However, it does not recognize user’s actions, such as standing or sitting, and requires the wheelchair to stop. This study introduced a user-action recognition system using a wheelchair seat pressure sensor. This system accurately recognizes user actions through deep learning time-series data. We evaluated data augmentation and multi-user data to enhance the performance. The results show improved prediction accuracy for action recognition in the test scenarios.

Enhancing predictive accuracy for urinary tract infections post-pediatric pyeloplasty with explainable AI: an ensemble TabNet approach

Ureteropelvic junction obstruction (UPJO) is a common pediatric condition often treated with pyeloplasty. Despite the surgical intervention, postoperative urinary tract infections (UTIs) occur in over 30% of cases within six months, adversely affecting recovery and increasing both clinical and economic burdens. Current prediction methods for postoperative UTIs rely on empirical judgment and limited clinical parameters, underscoring the need for a robust, multifactorial predictive model. We retrospectively analyzed data from 764 pediatric patients who underwent unilateral pyeloplasty at the Children’s Hospital affiliated with the Capital Institute of Pediatrics between January 2012 and January 2023. A total of 25 clinical features were extracted, including patient demographics, medical history, surgical details, and various postoperative indicators. Feature engineering was initially performed, followed by a comparative analysis of five machine learning algorithms (Logistic Regression, SVM, Random Forest, XGBoost, and LightGBM) and the deep learning TabNet model. This comparison highlighted the respective strengths and limitations of traditional machine learning versus deep learning approaches. Building on these findings, we developed an ensemble learning model, meta-learner, that effectively integrates both methodologies, and utilized SHAP(Shapley Additive Explanation, SHAP) to complete the visualization of the integrated black-box model. Among the 764 pediatric pyeloplasty cases analyzed, 265 (34.7%) developed postoperative UTIs, predominantly within the first three months. Early UTIs significantly increased the likelihood of re-obstruction (P < 0.01), underscoring the critical impact of infection on surgical outcomes. In evaluating the performance of six algorithms, TabNet outperformed traditional models, with the order from lowest to highest as follows: Logistic Regression, SVM, Random Forest, XGBoost, LightGBM, and TabNet. Feature engineering markedly improved the predictive accuracy of traditional models, as evidenced by the enhanced performance of LightGBM (Accuracy: 0.71, AUC: 0.78 post-engineering). The proposed ensemble approach, combining LightGBM and TabNet with a Logistic Regression meta-learner, achieved superior predictive accuracy (Accuracy: 0.80, AUC: 0.80) while reducing dependence on feature engineering. SHAP analysis further revealed eGFR and ALB as significant predictors of UTIs post-pyeloplasty, providing new clinical insights into risk factors. In summary, we have introduced the first ensemble prediction model, incorporating both machine learning and deep learning (meta-learner), to predict urinary tract infections following pediatric pyeloplasty. This ensemble approach mitigates the dependency of machine learning models on feature engineering while addressing the issue of overfitting in deep learning-based models like TabNet, particularly in the context of small medical datasets. By improving prediction accuracy, this model supports proactive interventions, reduces postoperative infections and re-obstruction rates, enhances pyeloplasty outcomes, and alleviates health and economic burdens.Level of evidence IV Case series with no comparison group.

COCONUT PREDICTIVE ANALYSIS USING MACHINE LEARNING

“Coconut Predictive Analysis” focuses on leveraging advanced machine learning techniques to predict the suitability of coconuts for oil production. The project employs transfer learning with the Inception V3 model, a state-of-the-art convolutional neural network (CNN), to analyze complex patterns in coconut-related data, such as images of coconuts. Traditional methods for determining coconut suitability for oil production rely on manual inspection, which can be time-intensive, subjective, and inconsistent. By utilizing transfer learning, this project capitalizes on pre-trained Inception V3 models, which extract meaningful features from large-scale datasets like ImageNet, and fine-tunes them for the specific task of classifying dry coconuts based on their suitability for oil extraction. The fine-tuning process involves freezing initial layers to retain general features while optimizing later layers to improve prediction accuracy for coconut-specific characteristics such as texture, colour, and surface patterns. To ensure accessibility and usability, a Flask web application is developed. This application enables users to upload images of coconuts and receive real-time predictions on their suitability for oil production. The backend integrates the trained model to process inputs, extract features, and generate predictions, making it a scalable and practical solution for agricultural and industrial applications. This project demonstrates the potential of transfer learning in enhancing agricultural and processing efficiency by reducing training time and computational costs while providing accurate and actionable predictions. By combining cutting-edge deep learning with a user-friendly web interface, it bridges the gap between advanced AI models and practical applications, supporting decision-making for farmers, coconut processing units, and industry stakeholders. Key Words: Inception V3, fine-tuning, CNN, Flask, coconut analysis, oil production suitability

Proposal for a Sustainable Model for Integrating Robotic Process Automation and Machine Learning in Failure Prediction and Operational Efficiency in Predictive Maintenance

This paper proposes a sustainable model for integrating robotic process automation (RPA) and machine learning (ML) in predictive maintenance to enhance operational efficiency and failure prediction accuracy. The research identified a key gap in the literature, namely the limited integration of RPA, ML, and sustainability in predictive manufacturing, which led to the development of this model. Using the PICO methodology (Population, Intervention, Comparison, Outcome), the study evaluated the implementation of these technologies in Alpha Company, comparing results before and after the model’s adoption. The intervention integrated RPA and ML to improve failure prediction accuracy and optimize maintenance operations. Results showed a 100% increase in mean time between failures (MTBF), a 67% reduction in mean time to repair (MTTR), a 37.5% decrease in maintenance costs, and a 71.4% reduction in unplanned downtime costs. Challenges such as initial implementation costs and the need for continuous training were also noted. Future research could explore integrating big data and AI to further improve prediction accuracy. This model demonstrates that integrating RPA and ML leads to operational improvements, cost reductions, and environmental benefits, contributing to the sustainability of industrial operations.

Modified SWAT Model for Agricultural Watershed in Karst Area of Southwest China

The Soil and Water Assessment Tool (SWAT) model is extensively used globally for hydrological and water quality assessments but encounters challenges in karst regions due to their complex surface and groundwater hydrological environments. This study aims to refine the delineation of hydrological response units within the SWAT model by combining geomorphological classification and to enhance the model with an epikarst zone hydrological process module, exploring the accuracy improvement of SWAT model simulations in karst regions of Southwest China. Compared with the simulation results of the original SWAT model, we simulated runoff and nutrient concentrations in the Mudong watershed from January 2017 to December 2021 using the improved SWAT model. The simulation results indicated that the modified SWAT model responded more rapidly to precipitation events, particularly in bare karst landform, aligning more closely with the actual hydrological processes in Southwest China’s karst regions. In terms of the predictive accuracy for monthly loads of total nitrogen (TN) and total phosphorus (TP), the coefficient of determination (R2) value of the modified model increased by 10.3% and 9.7%, respectively, and the Nash–Sutcliffe efficiency coefficient (NSE) increased by 11.3% and 9.9%, respectively. The modified SWAT model improves prediction accuracy in karst areas and holds significant practical value for guiding non-point source pollution control in agricultural watersheds.

Forecasting Agricultural Trade Based on TCN-LightGBM Models: A Data-Driven Decision

Facing the increasing complexity and dynamic fluctuations of the global agricultural trade market, accurate forecasting plays a key role in supporting agricultural policy formulation, stabilising the market and optimising resource allocation. In order to increase the precision and stability of agricultural trade predictions, this research suggests a hybrid model built on a temporal convolution network (TCN) and a lightweight gradient boosting tree (LightGBM). The TCN module effectively captures the long-term dependence characteristics of time series data through dilated convolution, which improves the model’s ability to identify seasonal and periodic trends. The LightGBM module, on the other hand, makes use of the characteristics of gradient boosting decision trees and excels at efficiently handling nonlinear relationships and avoiding overfitting. Experimental results show that the TCN-LightGBM model outperforms traditional models in terms of mean square error (MSE), mean absolute error (MAE) and prediction accuracy. Specifically, compared with ARIMA, LSTM, TCN alone or LightGBM alone, TCN-LightGBM achieves a prediction accuracy of 91.3% on the test data, with MSE and MAE of 0.021 and 0.115 respectively, significantly improving prediction accuracy and stability. In addition, parameter sensitivity analysis shows that the TCN-LightGBM model maintains a highly consistent prediction trend under different parameter configurations, which verifies the robustness of the model and its practical application value. This study provides a data-driven decision support tool with high accuracy and strong stability, providing a new solution for agricultural trade forecasting and other complex time series prediction tasks.

Prediction of FeO content in sintered ore based on ICEEMDAN and CNN-BiLSTM-AM

FeO content of sintered ore is an important reference index for measuring the performance of sintered ore. It significantly impacts the ironmaking process, iron quality, and energy consumption. Aiming at the current problem of delayed and poor accuracy of sintered ore FeO content detection results, this article proposes a hybrid network model that incorporates improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and attention mechanism (AM) for FeO content prediction. First, the FeO content time series were decomposed using ICEEMDAN to obtain sub-layers with different frequencies. Then, the features with higher correlation with FeO content were selected by feature selection as model inputs, followed by predicting the decomposition sequences of FeO content using CNN-BiLSTM-AM for the feature-selected variables, respectively. Finally, all predicted sublayer predictions were reconstructed into the final prediction by summation. The proposed model effectively captures the essence of the sequence through the ICEEMDAN algorithm, extracts deep features from FeO content data using CNN, captures contextual information through BiLSTM, and enhances feature extraction capability with AM. The experimental results show that the collaboration of CNN, BiLSTM, and AM effectively enhances the modelling capability of the model and significantly improves the prediction accuracy. Additionally, the ICEEMDAN decomposition algorithm is employed to enhance the prediction performance further, offering advantages over other decomposition techniques. The MAE, MAPE, RMSE, RRMSE, and R² of the new ICEEMDAN-CNN-BiLSTM-AM (ICBA) model are 0.0751, 0.846%, 0.0937, 1.0500%, and 0.9646, respectively, demonstrating a significant improvement in prediction accuracy and outperforming the relevant comparison models.

Synthesizing Local Capacities, Multi-Source Remote Sensing and Meta-Learning to Optimize Forest Carbon Assessment in Data-Poor Regions

As the climate emergency escalates, the role of forests in carbon sequestration is paramount. This paper proposes a framework that integrates local capacities, multi-source remote sensing data, and meta-learning to enhance forest carbon assessment methodologies in data-scarce regions. By integrating multi-source optical and radar remote sensing data alongside community forest inventories, we applied a meta-modelling approach using stacked generalization ensemble to estimate forest above-ground carbon (AGC). We also conducted a Kruskal–Wallis test to determine significant differences in AGC among different tree species. The Kruskal–Wallis test (p = 1.37 × 10−13) and Dunn post-hoc analysis revealed significant differences in carbon stock potential among tree species, with Afzelia quanzensis (x~ = 12 kg/ha, P-holm-adj. = 0.05) and the locally known species M’buta (x~ = 6 kg/ha, P-holm-adj. = 5.45 × 10−9) exhibiting a significantly higher median AGC. Our results further showed that combining optical and radar remote sensing data substantially improved prediction accuracy compared to single-source remote sensing data. To improve forest carbon assessment, we employed stacked generalization, combining multiple machine learning algorithms to leverage their complementary strengths and address individual limitations. This ensemble approach yielded more robust estimates than conventional methods. Notably, a stacking ensemble of support vector machines and random forest achieved the highest accuracy (R2 = 0.84, RMSE = 1.36), followed by an ensemble of all base learners (R2 = 0.83, RMSE = 1.39). Additionally, our results demonstrate that factors such as the diversity of base learners and the sensitivity of meta-leaners to optimization can influence stacking performance.

Combined Prediction of PM10 Concentration at Smart Construction Sites Based on Quadratic Mode Decomposition and Deep Learning

The accurate prediction of PM10 concentrations at smart construction sites is crucial for improving urban air quality, protecting public health, and advancing sustainable development in the construction industry. PM10 concentrations at construction sites are influenced by the interaction of construction intensity and environmental meteorological factors, resulting in nonlinear and volatile data. To improve prediction accuracy, this paper presents a two-stage mode decomposition method that integrates Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Variational Mode Decomposition (VMD). This method is combined with a Bidirectional Long Short-Term Memory (BiLSTM) neural network, optimized using the Sparrow Search Algorithm (SSA), to establish a hybrid model for forecasting PM10 concentrations at construction sites. Initially, CEEMDAN decomposes the original sequence into several Intrinsic Mode Functions (IMFs). The sample entropy of each component is then calculated, and K-means clustering is used to group them. VMD is applied to further decompose the high-frequency components obtained after clustering. SSA is then employed to optimize the parameters of the BiLSTM network, which models all the components with the optimized predictive model. The predicted values of all components are aggregated to generate the final forecast. Real-time monitoring data from Construction Site A in Nanjing are used for case study validation. The empirical results demonstrate that the proposed hybrid prediction model outperforms comparison models on all evaluation metrics, offering a scientific foundation for sustainable and automated dust reduction decision-making at smart construction sites, thereby facilitating the shift toward greener, smarter, and more digitized construction practices.

Multi-dimensional failure risk load prediction of electric motor based on physical model and data-driven approach

Dynamic prediction of failure risk loads is a critical prerequisite for system damage monitoring and service life evaluation. As the failure mechanism of electric vehicle drive motors under multi-source load excitations is complex, and the risk load poses challenges in rapid acquisition, a physics-based and data-driven method for multi-dimensional failure risk load prediction of motors is proposed. Based on actual operational data collected from users, we analyze the failure risk loads of various components of a motor. A physical simulation model of the motor is established to extract multi-dimensional failure risk load time history, and the effectiveness of the simulation model is verified using data from bench tests. Moreover, using the physical model simulation data as a foundation, a two-stage data-driven model is constructed. In the first stage, the genetic algorithm optimized back propagation neural network (GA-BPNN) model is implemented for multi-dimensional loss prediction of the motor, and serves as the primary input for the second stage model, which integrates prediction accuracy and training efficiency. In the second stage, by comprehensively considering the spatial and temporal correlation features with the input layer reconstructed using correlation matrix weights, an improved convolutional neural network with bidirectional long short-term memory (CNN-BiLSTM) model is employed to predict multi-scale loads. Compared with traditional models, the proposed method exhibits significantly improved prediction accuracy, with R2 greater than 0.95. Furthermore, the damage error between the predicted load and the expected load is within 10%, which provides technical support for reliability evaluation and life prediction of electric motor.

Simulation of Flow Around a Finite Rectangular Prism: Influence of Mesh, Model, and Subgrid Length Scale.

This study investigates the flow field around a finite rectangular prism using both experimental and computational methods, with a particular focus on the influence of the turbulence approach adopted, the mesh resolution employed, and different subgrid length scales. Ten turbulence modelling and simulation approaches, including both 'scale-modelling' Reynolds-Averaged Navier-Stokes (RANS) models and 'scale-resolving' Delayed Detached Eddy Simulation (DDES), were tested across six different mesh resolutions. A case with sharp corners allows the location of the flow separation to be fixed, which facilitates a focus on the separated flow region and, in this instance, the three-dimensional interaction of three such regions. The case, therefore, readily enables an assessment of the 'grey-area' issue, whereby some DDES methods demonstrate delayed activation of the scale-resolving model, impacting the size of flow recirculation. Experimental measurements were shown to agree well with reference data for the same geometry, after which particle image velocimetry (PIV) data were gathered to extend the reference dataset. Numerical predictions from the RANS models were generally quite reasonable but did not show improvement with further refinement, as one would expect, whereas DDES clearly demonstrated continuous improvement in predictive accuracy with progressive mesh refinement. The shear-layer-adapted (SLA) subgrid length scale (ΔSLA) displayed consistently superior performance compared to the more widely used length scale based on local cell volume, particularly for moderate mesh resolutions commonly employed in industrial settings with limited resources. In general, front-body separation and reattachment exhibited greater sensitivity to mesh refinement than wake resolution. Finally, in order to correlate the observed DDES mesh requirements with the observations from the converged RANS solutions, an approximation for the Taylor microscale was explored as a potential tool for mesh sizing.

STOCK PRICE PREDICTION AND SIMULATION USING GEOMETRIC BROWNIAN MOTION-KALMAN FILTER: A COMPARISON BETWEEN KALMAN FILTER ALGORITHMS

Stocks have high-profit potential but also have high risk. Many people have ways to forecast stock prices. The Geometric Brownian Motion (GBM) method forecasts stock prices. The data used in this study are closing stock price data from July 1, 2021 to August 31, 2021 taken from Yahoo! Finance. The stocks used in this research are Bank Rakyat Indonesia (BBRI), Indofood Sukses Makmur (INDF), and Telkom Indonesia (TLKM). A strategy is carried out to improve prediction accuracy by utilising the Kalman Filter (KF). This research will compare the mean absolute percentage error (MAPE) value between GBM-KF, which was manually computed and computed using the Python library. As an example of this research, for BBRI stock, the high GBM MAPE value of 9.02% can be reduced to 3.52% with manually computed GBM-KF and 3.68% with Python library computed GBM-KF. Similarly, INDF and TLKM stocks are showing a significant reduction in MAPE values to deficient levels in some cases. The GBM-KF method employing manual computing may enhance the overall precision of stock price forecasting. Future research may enhance this study by using the GBM-KF model on alternative financial instruments, integrating supplementary market data, or evaluating its efficacy under extreme market conditions.

A Weighted Bayesian Kernel Machine Regression Approach for Predicting the Growth of Indoor-Cultured Abalone

The cultivation of abalone, a species with high economic value, faces significant challenges due to its slow growth rate and sensitivity to environmental conditions, resulting in prolonged cultivation periods and increased mortality risks. To address these challenges, we propose a novel probabilistic machine learning approach based on a Bayesian framework to predict abalone growth by modeling key environmental factors, including water temperature, pH, salinity, nutrient supply, and dissolved oxygen levels. The proposed method employs a weighted Bayesian kernel machine regression model, integrating Gaussian processes with a spike-and-slab prior to identify influential variables. This approach accommodates heteroscedasticity, capturing varying levels of variance across observations, and models complex, non-linear relationships between environmental factors and abalone growth. Our analysis reveals that time, dissolved oxygen, salinity, and nutrient supply are the most critical factors influencing growth, while water temperature and pH play relatively minor roles under controlled indoor farming conditions. Interaction analysis highlights the non-linear dependencies among factors, such as the combined effects of salinity and nutrient supply. The proposed model not only improves prediction accuracy compared to baseline methods, but also provides actionable insights into the environmental dynamics that optimize abalone growth. These findings underscore the potential of advanced machine learning techniques in enhancing aquaculture practices and offer a robust framework for managing complex, multi-variable systems in sustainable farming.

Dynamic Spatial–Temporal Graph Neural Network for Cooling Capacity Prediction in HVDC Systems

Predicting the cooling capacity of converter valves is crucial for maintaining the stability and efficiency of high-voltage direct current (HVDC) systems. This task involves handling complex, multi-dimensional time-series data with strong inter-variable dependencies and temporal dynamics. Traditional machine learning methods, while effective in static scenarios, struggle to capture these dependencies, and existing deep learning models often lack the ability to jointly model spatial and temporal relationships. To address these challenges, we propose a novel framework that integrates Graph Neural Networks (GNNs) with temporal dynamics. The GNN component captures spatial dependencies by representing the data as a graph, where nodes correspond to system variables, and edges encode their relationships. Temporal dependencies are modeled using temporal convolutional layers and recurrent neural networks (RNNs), enabling the framework to learn both short-term variations and long-term trends. Additionally, a graph attention mechanism dynamically adjusts the importance of variable relationships, improving prediction accuracy and interoperability. The proposed method demonstrates superior performance over traditional machine learning and deep learning baselines on real-world cooling system data. These results validate the effectiveness of the framework for industrial applications such as cooling system monitoring and predictive maintenance.

Enhanced accuracy in solar irradiance forecasting through machine learning stack-based ensemble approach

ABSTRACT Accurate solar irradiance (SI) prediction is vital for optimizing solar photovoltaic systems. This study addresses shortcomings in existing forecasting methods by exploring advanced machine-learning techniques using meteorological satellite data. We develop three novel models for SI forecasting: Stack-based Ensemble Fusion with Meta-Neural Network (SEFMNN), Extreme Gradient Boosting-Squared Error (XGB-SE), and Extreme Learning Machine (ELM). These models predict All-sky and Clear-sky shortwave solar irradiance across three Chinese provinces (Guangdong, Shandong, and Zhejiang) and one Saudi Arabian province (Najran). The SEFMNN model combines Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM) to improve prediction accuracy. The XGB-SE model employs a specialized loss function to manage extreme values in historical data. These models are designed to mitigate overfitting and data inconsistency while balancing computational efficiency and predictive accuracy. Comparative analysis reveals that SEFMNN and XGB-SE outperform the ELM model, with SEFMNN achieving an R2 of 0.9979, MAE of 0.0231, and MSE of 0.0020 in Najran. This demonstrates that SEFMNN significantly enhances solar irradiance forecasting, aiding efficient solar photovoltaic system planning and operation.

Prediction of microbial crude protein flow from the rumen of dairy cattle by means of dietary characteristics – a meta-analysis

ABSTRACT Protein supply to ruminants relies mainly on the flow of microbial crude protein (MCP) from the rumen, which is commonly assumed to primarily depend on energy supply. This study evaluated this assumption with recent data and tested if ruminally fermented organic matter (FOM) was a better predictor of MCP flow than total-tract digestible organic matter (DOM) and if more variables could improve the prediction of MCP flow. A previously published data set was extended by additional studies resulting in a data set of 139 studies including 407 treatment means, typical to Central European rations. Either DOM or FOM had to be reported and estimates of MCP were all based on gastrointestinal measurements. Dietary treatments were restricted to a maximum concentrate proportion of 0.6 and a CP concentration from 10% to 20% of dietary dry matter (DM). Treatments with more than 1% of animal by-products were excluded. Mixed models with “study” as random effect were used to test the ratios between MCP and DOM or FOM. Dietary characteristics including DM intake, OM digestibility (OMD), OM fermentability (OMF), and ruminal N balance and dietary concentrations of CP, rumen-degraded CP (RDP), rumen-undegraded CP (RUP), neutral detergent fibre, starch, and ether extract were evaluated as additional variables to improve prediction accuracy. Regression of MCP flow against DOM (n = 324) or FOM (n = 349) revealed estimates of 139 g ± 36 g and 164 g ± 40 g of MCP for each kg of DOM or FOM, respectively. The best-fitting mixed model estimating MCP/DOM [g/kg] was 312–2.75 · OMD − 0.229 · RUP + 0.290 · RDP whereas MCP/FOM [g/kg] may be calculated as 294–2.80 · OMF + 0.401 · RDP, with OMD and OMF in [%] and RDP and RUP in [g/kg DM]. Microbial CP flow [g/d] was most accurately described as 1896 + 110 · DOM − 23.7 · OMD − 0.164 · RUP + 0.153 · RDP, with DOM in [kg], OMD in [%] and RDP and RUP in [g/d]. Predictions based on DOM were at least as precise as FOM-based predictions and comparison with published models revealed that the presented models were of similar accuracy as the ones from literature.

Machine learning-driven power prediction in continuous extrusion of pure titanium for enhanced structural resilience under extreme loading

The increasing demand for advanced materials capable of withstanding extreme loading conditions, such as those encountered during impact or blast events, underscores the need for innovative approaches in material processing. This study focuses on leveraging machine learning (ML) to enhance predictive accuracy in the continuous extrusion of CP-Titanium Grade 2, a material vital for structural resilience in critical applications. Specifically, an Artificial Neural Network (ANN) model optimized using Stochastic Gradient Descent (SGD) was introduced to forecast power requirements with high precision. The analysis utilized a published dataset that comprises theoretical, numerical, and experimental power calculations as a robust foundation for validation and comparison. A visualization highlighted the influence of process parameters, such as feedstock temperature and extrusion wheel velocity, on structural performance to align with the thematic focus of resilient material design. The ANN-SGD model achieved an RMSE of 0.9954 and a CVRMSE of 11.53% which demonstrated significant improvements in prediction accuracy compared to traditional approaches. By achieving superior alignment with experimental results, the model validated its efficacy as a reliable and efficient tool for understanding and optimizing complex manufacturing processes. This research emphasizes the potential of ML to revolutionize material processing for extreme conditions and contribute to the broader goals of structural resilience and sustainable manufacturing.

MIESTC: A Multivariable Spatio-Temporal Model for Accurate Short-Term Wind Speed Forecasting

Wind speed forecasting is an essential part of weather prediction, with significant value in economics, business, and management. Utilizing multiple meteorological variables can improve prediction accuracy, but existing methods face challenges such as mixing and noise due to variable differences, as well as difficulty in capturing complex spatio-temporal dependencies. To address these issues, this study introduces a novel short-term wind speed forecasting model named as MIESTC. The proposed model employs an independent encoder to extract features from each meteorological variable, mitigating the issues of noise that are caused by variable mixing. Then, a multivariate spatio-temporal correlation module is used to capture the global spatio-temporal dependencies between variables and model their interactions. Experimental results on the ERA5-LAND dataset show that, compared to the ConvLSTM, UNET, and SimVP models, the MIESTC model reduces RMSE by 14.60%, 8.64%, and 10.41%, respectively, for a 1 h prediction duration. For a 6 h prediction duration, the corresponding reductions are 13.91%, 8.20%, and 6.95%, validating its superior performance in short-term wind speed forecasting. Furthermore, an analysis of variable impacts reveals that U10, V10, and T2M play dominant roles in wind speed prediction, while TP exhibits a relatively lower impact, aligning with the results of the correlation analysis. These findings underscore the potential of MIESTC as an effective and reliable tool for short-term wind speed prediction.