Article
Environmental Sciences
Nguyen Le Minh, Pham The Truyen, Tran Van Phong, Abolfazl Jaafari, Mahdis Amiri, Nguyen Van Duong, Nguyen Van Bien, Dao Minh Duc, Indra Prakash, Binh Thai Pham
Summary: This study combines ensemble learning techniques and a radial basis function classifier to predict landslide susceptibility. The performance of the models is evaluated based on various metrics, and the Bagging-RBFC model is found to be the most accurate. The study demonstrates the effectiveness of ensemble learning techniques in developing reliable landslide predictive models.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Geography, Physical
Binh Thai Pham, Abolfazl Jaafari, Trung Nguyen-Thoi, Tran Van Phong, Huu Duy Nguyen, Neelima Satyam, Md Masroor, Sufia Rehman, Haroon Sajjad, Mehebub Sahana, Hiep Van Le, Indra Prakash
Summary: This study developed highly accurate ensemble machine learning models for spatial prediction of rainfall-induced landslides in the Uttarkashi district, India. The D-REPT model was identified as the most accurate, providing insights for engineers and modelers to develop more advanced predictive models.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2021)
Article
Computer Science, Artificial Intelligence
Shahrokh Asadi, Seyed Ehsan Roshan
Summary: Bagging is a powerful method in ensemble learning, but faces challenges of generating redundant classifiers and lacking diversity. This paper proposes a new method using multi-objective optimization to address these challenges, which results in accurate and diverse classifiers with fewer redundancies. Experimental results demonstrate the superior performance of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Green & Sustainable Science & Technology
Aihua Wei, Kaining Yu, Fenggang Dai, Fuji Gu, Wanxi Zhang, Yu Liu
Summary: This study compares popular ensemble machine learning-based models and applies them to landslide susceptibility mapping. The results show that several ensemble models can appropriately predict landslide susceptibility maps, with the XGBoost model performing the best.
Article
Ecology
Tran Thi Tuyen, Abolfazl Jaafari, Hoang Phan Hai Yen, Trung Nguyen-Thoi, Tran Van Phong, Huu Duy Nguyen, Hiep Van Le, Tran Thi Mai Phuong, Son Hoang Nguyen, Indra Prakash, Binh Thai Pham
Summary: Ensemble models combining LWL algorithm with CG, Bagging, Decorate, and Dagging techniques were used to predict forest fire susceptibility in Pu Mat National Park, Vietnam, with CG-LWL and Bagging-LWL models showing the highest training performance. These models enhance researchers' understanding of model building processes and can be applied to predict other natural hazards by considering local geo-environmental factors.
ECOLOGICAL INFORMATICS
(2021)
Article
Nuclear Science & Technology
Bu-Seog Ju, Shinyoung Kwag, Sangwoo Lee
Summary: This study aims to develop machine-learning models predicting drifts of the RC shear walls according to the damage limit states and help determine the repairing methods based on damage levels.
NUCLEAR ENGINEERING AND TECHNOLOGY
(2023)
Article
Ecology
Binh Thai Pham, Abolfazl Jaafari, Tran Van Phong, Davood Mafi-Gholami, Mandis Amiri, Nguyen Van Tao, Van-Hao Duong, Indra Prakash
Summary: In this study, a spatially explicit ensemble modeling framework was developed to estimate groundwater potential in Kon Tum Province, Vietnam, using different ensemble learning techniques. The ensemble models outperformed the single NB model in terms of mapping accuracy, with the RFNB model showing the highest accuracy. Feature selection identified key variables for explaining groundwater potential distribution in the region. The proposed methodology and potential maps can assist managers in aligning water use patterns and developing sustainable groundwater management strategies.
ECOLOGICAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Ahmed A. Khalil, Zaiming Liu, Ahmad Salah, Ahmed Fathalla, Ahmed Ali
Summary: Insolvency is a crucial problem for insurance companies, and this study explores the prediction of insurance company insolvency using ensemble learning methods in the Egyptian market. A dataset of 11 Egyptian insurance companies was collected, and different evaluation metrics were used to assess the proposed models.
Article
Thermodynamics
Rahul Gupta, Anil Kumar Yadav, S. K. Jha, Pawan Kumar Pathak
Summary: This article proposes a feature selection method based on VIF-MI and an improved ensemble method for predicting solar irradiance. The results show that the proposed method outperforms other models in estimation performance and error reduction.
INTERNATIONAL JOURNAL OF GREEN ENERGY
(2023)
Article
Geochemistry & Geophysics
Yijia Song, Wei Feng, Gabriel Dauphin, Yijun Long, Yinghui Quan, Mengdao Xing
Summary: In this letter, an ensemble alignment subspace adaptation (EASA) method is proposed for cross-scene classification. It addresses the problem of foreign objects in the same spectrum and different spectra by combining ensemble learning with domain adaptive algorithm. The proposed algorithm reduces uncertainty and randomness of subspace projections, and achieves a significant accuracy improvement compared to traditional machine learning and domain adaptation methods as shown in experimental results on two real datasets.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2023)
Article
Chemistry, Multidisciplinary
Pyae-Pyae Phyo, Chawalit Jeenanunta
Summary: Short-term load forecasting is crucial in the electricity industry, and this study proposes a bagging ensemble model combining linear regression and support vector regression. It outperforms deep learning models in terms of accuracy.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Mechanical
Maolin Shi, Weifei Hu, Muxi Li, Jian Zhang, Xueguan Song, Wei Sun
Summary: This paper proposes two ensemble regression methods based on polynomial regression and decision tree to improve the prediction accuracy and performance robustness of the regression model. Experiments show that the proposed methods outperform other regression methods in most cases.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Green & Sustainable Science & Technology
Snezhana Gocheva-Ilieva, Atanas Ivanov, Maya Stoimenova-Minova
Summary: A novel framework based on machine learning was developed to predict the daily average concentrations of PM10 in Bulgaria. The framework used meteorological parameters as independent variables and built efficient predictive models to improve accuracy.
Article
Green & Sustainable Science & Technology
Li-Ya Wu, Sung-Shun Weng
Summary: Ensemble learning was used to improve risk prediction models for food border inspection in Taiwan. The models enhanced non-conforming product hit rates and overall border control effectiveness. Results indicated that ensemble learning outperformed individual algorithms in predicting food risks, leading to increased inspection accuracy.
Article
Computer Science, Artificial Intelligence
Yulin He, Xuan Ye, Joshua Zhexue Huang, Philippe Fournier-Viger
Summary: This article presents a Bayesian attribute bagging-based extreme learning machine (BAB-ELM) to handle high-dimensional classification and regression problems. BAB-ELM calculates the decision-making degree of a condition attribute based on Bayesian decision theory, and uses bagging attribute groups to train an ensemble learning model of extreme learning machines. The weights for fusing predictions of base ELMs are determined by the information amount ratios of bagging condition attributes. Experimental results show that BAB-ELM achieves higher classification accuracy and lower regression error for high-dimensional problems.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)