NSTL国家科技图书文献中心

1. Elevator fault classification based on multi-grained cascade forest with variable importance measure NSTL国家科技图书文献中心

Ji, Yijin | Sun, Haoxiang ... - 《International Journal of Automation and Control》 - 2025,19(3) - 331～349 - 共19页

摘要： running efficiency than not using variable importance | platform and the basic parameters of elevators. Variable | importance is then evaluated using random forest with mean | . Using the variables with high importance* as input* | Current deep learning based elevator fault

关键词： elevator fault | fault classification | variable importance | importance measure | random forest | mean decrease accuracy | multi-grained cascade forest

2. Assessing variable importance in survival analysis using machine learning NSTL国家科技图书文献中心

Wolock, C. J. | Gilbert, P. B.... - 《Biometrika》 - 2025,112(2) - 共22页

摘要： variable importance measures for prediction in the | interest to quantify the relative importance* of a subset* | censoring, and existing methods for assessing variable | importance are typically not intended to be used in this | Given a collection of features available

关键词： Censoring | Debiased machine learning | Feature importance | Time-to-event outcome

3. Comparison and prediction of shallow groundwater nitrate in Shaying River basin based on urban distribution using multiple machine learning approaches NSTL国家科技图书文献中心

Zipeng Huang | Baonan He ... - 《Water Environment Research》 - 2025,97(2) - e70033.1～e70033.15 - 共15页

摘要： activities (feature importance* of Cl~- = 78.64* | ~- (feature importance* = 52.06% and 18.41%), indicative of a* | Groundwater, a pivotal water resource in | numerous regions worldwide, confronts formidable | challenges posed by severe nitrate pollution. Traditional

关键词： groundwater nitrate | machine learning | Shaying River Basin | variable importance | XGB

4. An index of effective number of variables for uncertainty and reliability analysis in model selection problems NSTL国家科技图书文献中心

Martino, Luca | Morgado, Eduardo ... - 《Signal Processing》 - 2025,227 - 共9页

摘要： number of features in a variable* selection application* | An index of an effective number of variables | (ENV) is introduced for model selection in nested | models. This is the case, for instance, when we have to | decide the order of a polynomial function or the number

关键词： Model selection | Elbow detection | Information criterion | Effective Sample Size (ESS) | Gini index | Uncertainty analysis | Variable importance

5. Data-driven modeling of the quantitative structure-activity relationship between aggregate contact parameters and dynamic modulus in asphalt mixtures NSTL国家科技图书文献中心

Lin Kong | Xiuquan Lin ... - 《Construction and Building Materials》 - 2025,470(Apr.4) - 140698.1～140698.18 - 共18页

摘要： crossvalidation, and the importance* of model input parameters to* | importance of the number of contact points (6.81 %) and the | This study aims to establish a preliminary | mapping relationship between aggregate contact | characteristics and dynamic modulus. In building the holographic

关键词： Holistic Genomics | Variable importance | Dynamic modulus prediction | Internal structure index | Asphalt Mixtures

6. Quantifying Sahel Runoff Sensitivity to Climate Variability, Soil Moisture and Vegetation Changes Using Analytical Methods NSTL国家科技图书文献中心

Elias,Nkiaka | Robert G.,Bryant ... - 《Earth systems and enviroment》 - 2025,9(1) - 491～504 - 共14页

摘要：Abstract Whilst substantial efforts have been | deployed to understand the “Sahel hydrological paradox | ”, most of the studies focused on small experimental | watersheds around the central and western Sahel. To our | knowledge, there is no study on this issue covering all

关键词： Analytical methods | Budyko framework | Elasticity concept | Geospatial data | Sahel hydrological paradox | Variable Importance in Projection

7. Integrating machine learning models for optimizing ecosystem health assessments through prediction of nitrate–N concentrations in the lower stretch of Ganga River, India NSTL国家科技图书文献中心

Basanta Kumar,Das | Sanatan,Paul ... - 《Environmental Science and Pollution Research》 - 2025,32(8) - 4670～4689 - 共20页

摘要： highlight the importance* of advanced machine learning* | Abstract Nitrate, a highly reactive form of | inorganic nitrogen, is commonly found in aquatic | environments. Understanding the dynamics of nitrate–N | concentration in rivers and its interactions with other water

关键词： Nitrate–N | Ganga River | GAMs | RF | XGboost | RMSE | MAE | NSE | Variable importance

8. Blasting-Induced Ground Vibration Modeling in Tunnel Excavation: A Comparative Study of ANN, Hybrid ANNs, and Empirical Models NSTL国家科技图书文献中心

Nafiu Olanrewaju,Ogu... | Chanhwi,Shin ... - 《Rock Mechanics and Rock Engineering》 - 2025,58(3) - 2711～2737 - 共27页

摘要：Abstract Blasting is the most widely adopted | tunneling method worldwide because it is economical | , inexpensive, and adaptable to all geological terrains | compared with mechanical excavation methods. However, the | use of explosives and explosive materials for rock

关键词： Artificial neural networks | Tunnel excavation | Blasting-induced ground vibration | Metaheuristic optimization | Variable importance analysis

9. Interpretable machine learning for time-to-event prediction in medicine and healthcare NSTL国家科技图书文献中心

Baniecki H. | Sobieski B.... - 《Artificial intelligence in medicine》 - 2025,159(Jan.) - 1.1～1.11 - 共11页

摘要：-dependent feature effects and global feature importance | performance to include the importance* of multi-omics feature* | © 2024 Elsevier B.V.Time-to-event prediction | , e.g. cancer survival analysis or hospital length of | stay, is a highly prominent machine learning task in

关键词： Explainable AI | Interpretability | Radiomics | Survival analysis | Time-dependent explanation | Variable importance

10. Comparative transcriptomic analysis and volatile compound characterization of Aspergillus tubingensis and Penicillium oxalicum during their infestation of Japonica rice NSTL国家科技图书文献中心

Jian Guo | Mingming Qiu ... - 《Food Microbiology》 - 2025,125(Jan.) - 104626.1～104626.11 - 共11页

摘要：Volatile organic compounds (VOCs), a byproduct | of mold metabolism, have garnered increasing | interest because the VOCs can be used to detect food | early contamination. So far, the use of VOCs as | indicators of rice mildew, specifically caused by

关键词： Variable importance in the projection | Alkanes volatile substances | Alcohols volatile substances | Paddy storage | Fatty acid degradation | Pathogen detection

摘要： running efficiency than not using variable importance | platform and the basic parameters of elevators. Variable | importance is then evaluated using random forest with mean | . Using the variables with high importance as input | Current deep learning based elevator fault