Application of LightGBM Algorithm in the Initial Design of a Library in the Cold Area of China Based on Comprehensive Performance

Zhou, Yihuan; Wang, Wanjiang; Wang, Ke; Song, Junkang

doi:10.3390/buildings12091309

Cited by 13 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LightGBM algorithm is capable of aggregating distinct attributes into a consolidated features, which may be utilized to construct histograms that categorize similar attributes [ 100 ]. The objective of the LightGBM algorithm, when applied to a supervised dataset X , is to identify an estimation of the function

that reduces the expected value of a chosen loss function

[ 101 ]:

…”

Section: Materials and Methodsmentioning

confidence: 99%

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

Pratiwi,

Tayara,

Chong

2024

IJMS

View full text Add to dashboard Cite

In this study, we present an innovative approach to improve the prediction of protein–protein interactions (PPIs) through the utilization of an ensemble classifier, specifically focusing on distinguishing between native and non-native interactions. Leveraging the strengths of various base models, including random forest, gradient boosting, extreme gradient boosting, and light gradient boosting, our ensemble classifier integrates these diverse predictions using a logistic regression meta-classifier. Our model was evaluated using a comprehensive dataset generated from molecular dynamics simulations. While the gains in AUC and other metrics might seem modest, they contribute to a model that is more robust, consistent, and adaptable. To assess the effectiveness of various approaches, we compared the performance of logistic regression to four baseline models. Our results indicate that logistic regression consistently underperforms across all evaluated metrics. This suggests that it may not be well-suited to capture the complex relationships within this dataset. Tree-based models, on the other hand, appear to be more effective for problems involving molecular dynamics simulations. Extreme gradient boosting (XGBoost) and light gradient boosting (LightGBM) are optimized for performance and speed, handling datasets effectively and incorporating regularizations to avoid over-fitting. Our findings indicate that the ensemble method enhances the predictive capability of PPIs, offering a promising tool for computational biology and drug discovery by accurately identifying potential interaction sites and facilitating the understanding of complex protein functions within biological systems.

show abstract

that reduces the expected value of a chosen loss function

[ 101 ]:

…”

Section: Materials and Methodsmentioning

confidence: 99%

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

Pratiwi,

Tayara,

Chong

2024

IJMS

View full text Add to dashboard Cite

show abstract

“…Regarding energy conservation, these standards underscore the principle of prioritizing passive energy conservation and advocates for maximizing natural ventilation to enhance the thermal insulation performance of the building envelope structure. Widely acknowledged within the academic community of building energy conservation research in China, this standard serves as a significant academic point of reference for scholars engaged in simulation studies [61], as shown in Table 3.…”

Section: Building Envelope Parameter Se Ingmentioning

confidence: 99%

Research on the Design Strategy of Double–Skin Facade in Cold and Frigid Regions—Using Xinjiang Public Buildings as an Example

Liu,

Wang,

Ding

et al. 2024

Sustainability

View full text Add to dashboard Cite

In the context of global warming, the focus on applying and researching double–skin facade (DSF) systems to reduce energy consumption in buildings has significantly increased. However, researchers have not thoroughly examined the performance and applicability of DSFs in severe cold regions with high winter heating demands. This study aims to evaluate the potential application of DSFs in the harsh cold cities of Northwest China and investigate their role in enhancing energy efficiency in large public buildings. Through energy consumption simulation and a comprehensive evaluation using the TOPSIS entropy weight method, the effects of applying 20 DSF schemes in four cold cities in Xinjiang (Kashgar, Urumqi, Altay, and Turpan) were analyzed. The experimental results indicate that the average EUI energy–saving rates in Kashgar, Urumqi, Altay, and Turpan are 64.75%, 63.19%, 56.70%, and 49.41%, respectively. South–facing orientation is deemed optimal for DSF in Xinjiang cities, with the highest energy–saving rate reaching 15.19%. In Kashgar, the energy–saving benefits of west–facing DSF surpass those of north–facing DSF. Conversely, the order of orientation benefits for other cities is south, north, west, and east. An analysis of heating, cooling, and lighting energy consumption reveals that Box Windows exhibit superior heating energy efficiency, while Corridors are more effective for cooling. This characteristic is also evident in the optimal installation orientation of various types of curtain walls. Given the relatively higher demand for heating compared to cooling in urban areas, Box Windows yields significant benefits when facing south, west, or north; conversely, if there is a high demand for urban cooling, Corridors should be considered in these three directions. Multistorey DSF systems are suitable for east–facing buildings in Xinjiang cities. Selecting suitable DSF schemes based on specific conditions and requirements can reduce building energy consumption. The research findings offer theoretical guidance for designing and implementing DSF in diverse cities in cold regions.

show abstract

“…It has found applications in various domains, including medicine [28], economy [34], and agriculture [35]. LightGBM is a gradient-boosting framework that uses tree-based learning algorithms and relies on a loss function that measures the discrepancy between the predicted and the actual values of the target variable [36,37].…”

Section: Light Gradient-boosting Machine (Lightgbm)mentioning

confidence: 99%

Maximizing Biogas Yield Using an Optimized Stacking Ensemble Machine Learning Approach

Mukasine,

Sibomana,

Jayavel

et al. 2024

Energies

View full text Add to dashboard Cite

Biogas is a renewable energy source that comes from biological waste. In the biogas generation process, various factors such as feedstock composition, digester volume, and environmental conditions are vital in ensuring promising production. Accurate prediction of biogas yield is crucial for improving biogas operation and increasing energy yield. The purpose of this research was to propose a novel approach to improve the accuracy in predicting biogas yield using the stacking ensemble machine learning approach. This approach integrates three machine learning algorithms: light gradient-boosting machine (LightGBM), categorical boosting (CatBoost), and an evolutionary strategy to attain high performance and accuracy. The proposed model was tested on environmental data collected from biogas production facilities. It employs optimum parameter selection and stacking ensembles and showed better accuracy and variability. A comparative analysis of the proposed model with others such as k-nearest neighbor (KNN), random forest (RF), and decision tree (DT) was performed. The study’s findings demonstrated that the proposed model outperformed the existing models, with a root-mean-square error (RMSE) of 0.004 and a mean absolute error (MAE) of 0.0024 for the accuracy metrics. In conclusion, an accurate predictive model cooperating with a fermentation control system can significantly increase biogas yield. The proposed approach stands as a pivotal step toward meeting the escalating global energy demands.

show abstract

Application of LightGBM Algorithm in the Initial Design of a Library in the Cold Area of China Based on Comprehensive Performance

Cited by 13 publications

References 37 publications

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

Research on the Design Strategy of Double–Skin Facade in Cold and Frigid Regions—Using Xinjiang Public Buildings as an Example

Maximizing Biogas Yield Using an Optimized Stacking Ensemble Machine Learning Approach

Contact Info

Product

Resources

About