Article
Green & Sustainable Science & Technology
Zhongyuan Gu, Miaocong Cao, Chunguang Wang, Na Yu, Hongyu Qing
Summary: This study introduces a method for mining subsidence prediction using the genetic algorithm and XGBoost ensemble learning algorithm, and improves the prediction accuracy by optimizing the hyperparameter vector of XGBoost. Compared to other classic ensemble learning models, the GA-XGBoost model has higher prediction accuracy and performance.
Article
Polymer Science
Yuyin Zhang, Ningjie Deng, Shiding Zhang, Pingping Liu, Changjing Chen, Ziheng Cui, Biqiang Chen, Tianwei Tan
Summary: In this study, a genetic algorithm with variable mutation probability was used to screen key molecular descriptors for predicting substitution factor. The improved genetic algorithm significantly enhanced the prediction accuracy. The selected descriptors mainly focused on describing the branching of the molecule, which is consistent with the importance of branching chains in the plasticization process.
Article
Construction & Building Technology
Hainan Yan, Ke Yan, Guohua Ji
Summary: Incorporating intelligent optimization algorithms in the early stages of office building design allows for better adaptation to local climates and improved indoor and outdoor thermal performances. This study utilizes a data-driven workflow based on performance-based generative architectural design to comprehensively assess and rapidly predict the performance of office buildings. By generating 6000 data samples through an iterative process of genetic optimization, this study achieved high precision and recall in categorical prediction using the XGBoost algorithm.
BUILDING AND ENVIRONMENT
(2022)
Article
Engineering, Geological
Chun Xu, Keping Zhou, Xin Xiong, Feng Gao, Yan Lu
Summary: Land subsidence caused by coal mining has led to damage in villages, buildings, and farmland, posing threats to human settlements and ecological environments. This study developed a novel intelligent approach combining sparrow search algorithm, extreme gradient boosting, and technique for order preference to predict mining land subsidence.
Article
Agronomy
Yifang Ren, Fenghua Ling, Yong Wang
Summary: This study used the data from 70 meteorological and soil moisture observation stations in Jiangsu Province, China, to establish a prediction model for 0-10 cm soil relative humidity (RHs10cm) using the extreme gradient boosting (XGBoost) algorithm. The soil moisture observation data were divided into three categories based on soil physical characteristics, and 14 predictors were selected for model construction. The results show that maximum air temperature, cumulative precipitation, and air relative humidity are important factors influencing soil moisture variation, and adding soil factors can improve the accuracy of soil moisture prediction.
Article
Engineering, Environmental
Zuhan Liu, Xuehu Liu, Kexin Zhao
Summary: With the rapid economic development, air pollution, especially haze caused by PM2.5, has become increasingly prominent in China. In order to solve the problems of poor accuracy, large data demand, and slow convergence speed of traditional prediction methods, a PM2.5 prediction model based on stacking integration method is proposed. The experimental results show that this model has higher accuracy and better prediction performance.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2023)
Article
Computer Science, Hardware & Architecture
Yue Li, Jianfang Qi, Haibin Jin, Dong Tian, Weisong Mu, Jianying Feng
Summary: In this study, a new classifier for predicting customer consumption behavior is proposed. The classifier utilizes a feature selection method based on Lasso and PCA to efficiently select relevant features and eliminate correlations between variables. An improved genetic-XGBoost algorithm is also used to optimize the prediction accuracy by adjusting XGBoost parameters and preventing the model from falling into local extremum. Experimental results demonstrate the superiority of the proposed methods over existing ones, providing a decision-making basis for enterprises to formulate better marketing strategies.
Article
Engineering, Chemical
Lu Liu, Jing Liang, Li Ma, Hailin Zhang, Zheng Li, Shan Liang
Summary: This paper proposes a method to automatically perform the feature mining of flow time series by considering the correlation of flow data at both ends of the pipeline, combined with the long short-term memory (LSTM) network. The current and historical data at both pipeline ends are used as input vectors of the LSTM network to predict the terminal output flow at the next moment. The effectiveness and superiority of the proposed method are demonstrated in a real-world NG gathering pipeline.
Article
Chemistry, Multidisciplinary
Gang Zhao, Naiwei Sun, Shen Shen, Xianyun Wu, Li Wang
Summary: This paper presents a GPU-accelerated multiresolution grid algorithm for predicting the echo characteristics of complex underwater targets. The algorithm is more accurate and faster than traditional methods, as demonstrated by experiments.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Wenle Wang, Wentao Xiong, Jing Wang, Lei Tao, Shan Li, Yugen Yi, Xiang Zou, Cui Li
Summary: In this paper, a prediction model based on XGBoost is proposed to predict user purchase behavior. By utilizing multi-feature fusion and analyzing feature importance, the XGBoost model demonstrates superior stability and algorithm efficiency compared to traditional machine learning algorithms.
Article
Computer Science, Information Systems
Mahmoud Y. Shams, Ahmed M. Elshewey, El-Sayed M. El-kenawy, Abdelhameed Ibrahim, Fatma M. Talaat, Zahraa Tarek
Summary: This study utilizes machine learning models to predict water quality index and water quality classification, and improves the accuracy through parameter optimization and tuning. The experimental results show that the GB model performs the best in classification with an accuracy of 99.50%. In regression, the MLP regressor model outperforms other models with a determination coefficient of 99.8%.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Cell Biology
Hao Zhang, Ruisi Xu, Meng Ding, Ying Zhang
Summary: This study identified relationships between proteins and gastric cancer by constructing disease similarity network and protein interaction network, and using computational methods to mine proteomics data knowledge. The high AUC (0.85) and AUPR (0.76) values from the 10-fold cross validation experiments validate the effectiveness of the method.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2021)
Article
Environmental Sciences
Selcuk Demir, Emrehan Kutlug Sahin
Summary: This paper applies three robust machine learning algorithms to predict soil liquefaction and improves the accuracy of the prediction models using feature selection and parameter optimization. The results show that the XGBoost model has the highest accuracy when using the SMOTE algorithm.
ENVIRONMENTAL EARTH SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Zhengxin Joseph Ye, Bjorn W. Schuller
Summary: Post-Earnings-Announcement Drift (PEAD) is a stock market phenomenon where a stock's abnormal return tends to drift in the direction of an earnings surprise post-announcement. This paper explores PEAD dynamics using machine learning, specifically XGBoost, to forecast drift direction effectively and allocate stocks into portfolios with higher returns using a Genetic Algorithm. It also addresses the challenge of trading on PEAD signals in a dynamic market environment.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Chemistry, Multidisciplinary
Juntao Wei, Shuangjin Zheng, Jiafan Han, Kai Bai
Summary: A cementing quality prediction model based on support vector regression (SVR) was established in this study, and the model was optimized using different optimization algorithms to improve prediction accuracy. The results showed that the GA-SVR model optimized using a genetic algorithm achieved the highest accuracy in predicting cementing quality.
APPLIED SCIENCES-BASEL
(2023)