A Novel MBAS-RF Approach to Predict Mechanical Properties of Geopolymer-Based Compositions DOI Creative Commons
Shuzhao Chen, Mengmeng Zhou, Xuyang Shi

et al.

Gels, Journal Year: 2023, Volume and Issue: 9(6), P. 434 - 434

Published: May 24, 2023

Using gels to replace a certain amount of cement in concrete is conducive the green industry, while testing compressive strength (CS) geopolymer requires substantial effort and expense. To solve above issue, hybrid machine learning model modified beetle antennae search (MBAS) algorithm random forest (RF) was developed this study CS concrete, which MBAS employed adjust hyperparameters RF model. The performance verified by relationship between 10-fold cross-validation (10-fold CV) root mean square error (RMSE) value, prediction evaluating correlation coefficient (R) RMSE values comparing with other models. results show that can effectively tune model; had high R (training set = 0.9162 test 0.9071) low 7.111 7.4345) at same time, indicated accuracy high; NaOH molarity confirmed as most important parameter regarding importance score 3.7848, grade 4/10 mm least parameter, 0.5667.

Language: Английский

Local Climate Zone Classification Using Daytime Zhuhai-1 Hyperspectral Imagery and Nighttime Light Data DOI Creative Commons
Ying Liang, Wen Song, Shisong Cao

et al.

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(13), P. 3351 - 3351

Published: June 30, 2023

The tremendous advancement of cities has caused changes to the urban subsurface. Urban climate problems have become increasingly prominent, especially with regard intensification heat island (UHI) effect. local zone (LCZ) is a new quantitative method for analyzing that based on kind surface and can effectively deal problem hazy distinction between rural areas in UHI effect research. LCZs are widely used regional modeling, planning, thermal comfort surveys. Existing large-scale LCZ classification methods usually use visual features optical images, such as spectral textural features. There many hyperspectral extraction over large areas. an integrated concept includes geography, society, economy. Consequently, it makes sense consider characteristics human activity images interpret them accurately. ALOS_DEM data depict city’s physical characteristics; however, nighttime lights crucial indicators activity. These three datasets be combination portray environment. Therefore, this study proposes fusing daytime mapping, i.e., Zhuhai-1 their derived feature indices, data, light from Luojia-1. By combining information, proposed approach captures temporal dynamics areas, providing more complete representation characteristics. integration allows refined identification characterization land cover. It comprehensively integrates exploits synergistic information multiple sources, provides higher accuracy resolution mapping. First, we extracted various features, namely spectral, red-edge, Random forest (RF) XGBoost classifiers were used, average impurity reduction was employed assess significance variables. All input variables optimized select best results 5th ring road area Beijing, China, revealed technique achieved mapping good precision, total 87.34%. In addition, examine contrast effects indices accuracy, used. showed accuracies terms improved by 2.33% 2.19% using RF classifier, respectively. radiation brightness value (RBV) (GI = 0.0212) attained classification’s highest variable importance value; DEM also produced high GI (0.0159), indicating night lighting landform strongly influence classification.

Language: Английский

Citations

8
Characterization and prediction of compressive strength in ultralow-temperature frozen soil using nuclear magnetic resonance and WOA-ENN Model DOI
Zhifeng Ren, Enliang Wang, Jiankun Liu

et al.

Transportation Geotechnics, Journal Year: 2023, Volume and Issue: 43, P. 101143 - 101143

Published: Oct. 25, 2023

Language: Английский

Citations

8
Estimating Deformation of Geogrid-Reinforced Soil Structures Using Hybrid LSSVR Analysis DOI

Chen Chien‐Ta,

Tsai Shing‐Wen,

Laing-Hao Hsiao

et al.

International Journal of Geosynthetics and Ground Engineering, Journal Year: 2024, Volume and Issue: 10(1)

Published: Jan. 17, 2024

Language: Английский

Citations

2
Comparison of regression analysis for estimation of initial and total fracture energy of concrete DOI

Jia Peng

Multiscale and Multidisciplinary Modeling Experiments and Design, Journal Year: 2023, Volume and Issue: 7(1), P. 173 - 190

Published: July 17, 2023

Language: Английский

Citations

6
A Novel MBAS-RF Approach to Predict Mechanical Properties of Geopolymer-Based Compositions DOI Creative Commons
Shuzhao Chen, Mengmeng Zhou, Xuyang Shi

et al.

Gels, Journal Year: 2023, Volume and Issue: 9(6), P. 434 - 434

Published: May 24, 2023

Using gels to replace a certain amount of cement in concrete is conducive the green industry, while testing compressive strength (CS) geopolymer requires substantial effort and expense. To solve above issue, hybrid machine learning model modified beetle antennae search (MBAS) algorithm random forest (RF) was developed this study CS concrete, which MBAS employed adjust hyperparameters RF model. The performance verified by relationship between 10-fold cross-validation (10-fold CV) root mean square error (RMSE) value, prediction evaluating correlation coefficient (R) RMSE values comparing with other models. results show that can effectively tune model; had high R (training set = 0.9162 test 0.9071) low 7.111 7.4345) at same time, indicated accuracy high; NaOH molarity confirmed as most important parameter regarding importance score 3.7848, grade 4/10 mm least parameter, 0.5667.

Language: Английский

Citations

5