Article
Engineering, Civil
Amirhosein Mosavi, Farzaneh Sajedi Hosseini, Bahram Choubin, Massoud Goodarzi, Adrienn A. Dineva, Elham Rafiei Sardooi
Summary: The study aims to evaluate four ensemble models for groundwater potential prediction, with RF model outperforming the others. Key contributing variables include topographic position index and valley depth. The predicted groundwater potential maps can assist water managers and policymakers in optimal freshwater exploitation.
WATER RESOURCES MANAGEMENT
(2021)
Article
Engineering, Environmental
Guoshao Su, Yuanzhuo Qin, Huajie Xu, Peifeng Li
Summary: A sound-based machine learning method is proposed to recognize tensile and shear cracks in hard rock. The combination of sound signals and deep learning can accurately analyze the failure process of rocks and provide a basis for early warning of rockbursts.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2023)
Article
Engineering, Geological
Long Chen, Shunchuan Wu, Aibing Jin, Chaojun Zhang, Xue Li
Summary: Rockburst prediction is difficult due to the complexity and randomness of rock burst behavior. This study uses the XGBoost algorithm to predict rockburst intensity and proposes a parameter optimization procedure to improve prediction performance. The model performs well in predicting rockburst intensity and identifies important feature parameters. The results show improved performance compared to other supervised learning models.
GEOTECHNICAL AND GEOLOGICAL ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yaqian You, Jianbin Sun, Yu-wang Chen, Caiyun Niu, Jiang Jiang
Summary: The Ensemble-BRB model proposed in this paper aims to address the combinatorial explosion problem in the BRB model by downsizing the belief rule base using the bagging framework. Experimental results validate the effectiveness of this method in classification and prediction tasks, demonstrating its ability to significantly reduce the size of the BRB model while maintaining high modeling accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(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
Automation & Control Systems
Biao Wang, Wenjing Wang, Guanglei Meng, Zhihua Qiao, Yuming Guo, Na Wang, Wei Wang, Zhizhong Mao
Summary: This paper proposes a method to improve the predictive performance of molten steel temperature by outlier detection. The method utilizes dynamic outlier ensemble and clustering analysis to select the best base detectors, thus promoting the performance of predictive models.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Business, Finance
Xiaowei Chen, Cong Zhai
Summary: This study compares the performance of five ensemble learning models based on bagging and boosting in detecting financial fraud in the financial field. The analysis was conducted using data from Chinese A-share listed companies from 2012 to 2022, including the COVID-19 pandemic period. The results show that bagging outperforms boosting in various evaluation indicators, with profitability and asset quality positively affecting financial fraud. This study reveals the mechanism by which ensemble learning affects financial fraud detection and expands related research in the financial field.
ACCOUNTING AND FINANCE
(2023)
Article
Mechanics
Arsalan Mahmoodzadeh, Hamid Reza Nejati, Mokhtar Mohammadi, Amin Salih Mohammed, Hawkar Hashim Ibrahim, Shima Rashidi
Summary: The Rockburst phenomenon in deep underground mines and tunnels can be accurately predicted using the machine learning method of extreme gradient boosting (XGBoost). Fault length and density have the most and least impact on the rockburst phenomenon, respectively.
ENGINEERING FRACTURE MECHANICS
(2022)
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
Manuel Menor-Flores, Miguel A. Vega-Rodriguez
Summary: The number of investigations attempting to align protein-protein interaction (PPI) networks has increased with the growth of studies focused on collecting PPI data. However, there is no standard approach to align PPI networks, and global aligners encounter difficulties in constructing alignments with high biological and structural quality. To address this issue, we propose an innovative ensemble technique that combines the strengths of aligners in the PPI network alignment field while avoiding their weaknesses. Our approach achieves alignments of higher quality and requires minimal time compared to individual aligners.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Ergonomics
Haining Meng, Xinyu Tong, Yi Zheng, Guo Xie, Wenjiang Ji, Xinhong Hei
Summary: This research proposes an ensemble learning strategy for railway accident prediction, including an improved KNN data imputation algorithm and AdaBoost-Bagging method. Experimental results show that this method has smaller prediction error and faster inference time in predicting railway accidents, and can mine important accident features.
ACCIDENT ANALYSIS AND PREVENTION
(2022)
Article
Engineering, Civil
Kouao Laurent Kouadio, Jianxin Liu, Serge Kouamelan Kouamelan, Rong Liu
Summary: In response to water scarcity, international organizations and governments collaborated on drinking water supply projects using geophysical and drilling companies. Financial losses from unsuccessful drillings due to difficulty in locating drilling sites were reduced by using ensemble machine learning (EML) paradigms to predict flow rate (FR) scores before drilling operations. The approach was tested in a water-scarce region and achieved FR prediction scores of 90-96%. EML paradigms can aid in identifying optimal drilling locations and reducing the impact of unsuccessful drillings.
WATER RESOURCES MANAGEMENT
(2023)
Article
Environmental Sciences
Hamid Jafarzadeh, Masoud Mahdianpari, Eric Gill, Fariba Mohammadimanesh, Saeid Homayouni
Summary: The study investigates the capability of different ensemble learning algorithms for satellite image classification, with XGBoost showing superior performance in multispectral, hyperspectral, and Polarimetric Synthetic Aperture Radar (PolSAR) data classification.
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
Construction & Building Technology
Jiaxin Guo, Sining Yun, Yao Meng, Ning He, Dongfu Ye, Zeni Zhao, Lingyun Jia, Liu Yang
Summary: This study proposes four hybrid models (Random-LightGBM, Grid-LightGBM, CMA-ES-LightGBM, and TPE-LightGBM) combined with the LightGBM model for improved prediction accuracy of heating and cooling loads in residential buildings.
BUILDING AND ENVIRONMENT
(2023)
Article
Public, Environmental & Occupational Health
Jian Zhou, Yuxin Chen, Hui Chen, Manoj Khandelwal, Masoud Monjezi, Kang Peng
Summary: Pillar stability is crucial for safe work in mines. Accurate estimation of induced stresses in pillars is important for design and guaranteeing stability. Machine learning algorithms, such as back-propagation neural network (BPNN), have been successfully applied to pillar stability assessment with high accuracy.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Metallurgy & Metallurgical Engineering
Jian Zhou, Peixi Yang, Pingan Peng, Manoj Khandelwal, Yingui Qiu
Summary: Three hybrid support vector machine (SVM) models optimized by particle swarm optimization (PSO), Harris hawk optimization (HHO), and moth flame optimization (MFO) are proposed to predict rockburst hazard level (RHL), achieving better accuracy and performance than the unoptimized SVM model.
MINING METALLURGY & EXPLORATION
(2023)
Article
Chemistry, Physical
Peixi Yang, Chuanqi Li, Yingui Qiu, Shuai Huang, Jian Zhou
Summary: This study utilized three meta-heuristic optimization algorithms to select the optimal hyperparameters of the random forest model for predicting the punching shear strength of FRP-RC beams. The ALO-RF model with a population size of 100 showed the best prediction performance, and adjusting the slab's effective depth effectively controlled the punching shear strength. Furthermore, the hybrid machine learning model optimized by metaheuristic algorithms outperformed traditional models in terms of prediction accuracy and error control.
Article
Chemistry, Physical
Kun Du, Songge Yang, Jian Zhou, Lichang Wang
Summary: It is important to study the evaluation indexes and classification criteria of the bursting liability of hard rocks for the prediction and prevention of rockbursts. In this study, the rockburst tendency was evaluated using the brittleness indicator (B2) and the strength decrease rate (SDR). The measuring methods and classification criteria were analyzed, and four grades of rockburst tendency were defined based on the test results.
Article
Chemistry, Physical
Chuanqi Li, Xiancheng Mei, Daniel Dias, Zhen Cui, Jian Zhou
Summary: This paper proposes a novel hybrid artificial neural network model optimized using a reptile search algorithm with circle mapping to predict the compressive strength of rice husk ash concrete. The proposed model achieved the most satisfactory prediction accuracy regarding R-2 (0.9709), VAF (97.0911%), RMSE (3.4489), and MAE (2.6451), outperforming previously developed models.
Article
Computer Science, Interdisciplinary Applications
Jian Zhou, Zhenyu Wang, Chuanqi Li, Wei Wei, Shiming Wang, Danial Jahed Armaghani, Kang Peng
Summary: Rock mass fractures have a significant impact on the shear behavior of natural rocks, and understanding the shear parameters of these fractures is important for maintaining the stability of underground structures. A novel approach combining the random forest (RF) model and two optimization algorithms (the Sine Cosine Algorithm (SCA) and the whale optimization algorithm (WOA)) was proposed to predict the shear strength, peak shear displacement, and dilation angles of rock fractures. The prediction performance indicated that the SCA-RF and WOA-RF models achieved high accuracy in predicting the shear strength and dilation angles of rock fractures.
JOURNAL OF COMPUTATIONAL SCIENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Jian Zhou, Yulin Zhang, Chuanqi Li, Weixun Yong, Yingui Qiu, Kun Du, Shiming Wang
Summary: This research introduces a groundbreaking intelligent model called the GWO-RF model for predicting water inflow during tunnel construction. By combining the capabilities of Grey Wolf Optimization (GWO) with the Random Forest (RF) algorithm, this model aims to enhance the accuracy and effectiveness of water inflow prediction, ultimately improving safety measures in tunnel construction projects. The GWO-RF model outperforms other ensemble models in terms of predictive accuracy, making it invaluable for tunneling projects.
EARTH SCIENCE INFORMATICS
(2023)
Article
Mining & Mineral Processing
Chuanqi Li, Jian Zhou, Kun Du, Daniel Dias
Summary: This paper aims to develop hybrid support vector machine (SVM) models improved by three metaheuristic algorithms known as grey wolf optimizer (GWO), whale optimization algorithm (WOA) and sparrow search algorithm (SSA) for predicting the hard rock pillar stability. The results confirmed that the SSA-SVM model is the best prediction model with the highest values of all global indices and local indices. However, the performance of the SSA-SVM model for predicting the unstable pillar is not as good as those for stable and failed pillars.
INTERNATIONAL JOURNAL OF MINING SCIENCE AND TECHNOLOGY
(2023)
Article
Geosciences, Multidisciplinary
Chuanqi Li, Jian Zhou, Daniel Dias, Kun Du, Manoj Khandelwal
Summary: In this study, 386 rock samples were used to predict the uniaxial compressive strength (UCS) using various empirical equations and artificial intelligence methods. The evaluation results showed that the artificial intelligence models outperformed the empirical approaches, especially the LSO-RF model. The porosity (Pn) was identified as the most important input variable for predicting UCS.
Article
Engineering, Geological
Yingui Qiu, Jian Zhou
Summary: Rockburst poses significant risks to mine workers and infrastructure. This study developed a novel hybrid model, SCSO-XGBoost, for predicting the scale of short-term rockburst damage. The model achieved high accuracy and outperformed other models, demonstrating its effectiveness in rockburst damage prediction.
ROCK MECHANICS AND ROCK ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Mingchun Lin, Guanqi Wang, Jian Zhou, Wei Zhou, Ni An, Gang Ma
Summary: This study analyzes the deformation characteristics of crushable particle materials through a series of cyclic loading tests conducted by numerical simulation. The investigation of hysteretic behavior from a particle scale reveals that an increase in particles with contacts less than two may cause residual strain, and particle breakage facilitates particle rearrangement and volume contraction. The accumulation of plastic strain and the resilient modulus are found to be influenced by confining pressures, stress levels, cyclic loading amplitudes, and the number of cycles. A function for plastic strain accumulation and an evolution function for resilient modulus are proposed.
JOURNAL OF ZHEJIANG UNIVERSITY-SCIENCE A
(2023)
Article
Engineering, Civil
Jian Zhou, Shuai Huang, Ming Tao, Manoj Khandelwal, Yong Dai, Mingsheng Zhao
Summary: This study proposes a new prediction method based on machine learning to scientifically adjust the critical span graph. The prediction performance of the proposed PSO-GBDT model is the most reliable among the other eight models, with a classification accuracy of 0.93. It has great potential to provide a more scientific and accurate choice for the stability prediction of underground excavations.