检索结果-内蒙古大学图书馆

ensemble learning for landslide displacement prediction: A perspective of Bayesian optimization and comparison of different time series analysis methods

引用

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT 2024年第8期38卷 3031-3058页

作者： Liu, Leilei Yin, Haodong Xiao, Ting Yang, Beibei Lacasse, Suzanne Cent South Univ Sch Geosci & Infophys Key Lab Metallogen Predict Nonferrous Met & Geol E Minist Educ Changsha 410083 Peoples R China Yantai Univ Sch Civil Engn Yantai 264005 Peoples R China Norwegian Geotech Inst N-0806 Oslo Norway

Precise and efficient landslide displacement prediction is crucial for improving the effectiveness of landslide warning systems. Numerous time series decomposition and machine learning (ML) methods have been proposed and applied in landslide displacement prediction. Nevertheless, most ML methods display individual biases when applied to landslide displacement datasets, and the effect of different methods for time series decomposition on prediction results has not been systematically studied. Therefore, this paper adopts four methods commonly used for time series decomposition to decompose the accumulated displacement into a trend term and a periodic term. The double exponential smoothing is utilized to predict the trend displacement. After the grey relation analysis between the periodic displacement and the external cyclical influencing factors, the ensemble algorithm is used to integrate six commonly used ML algorithms for the prediction of periodic displacement, so as to eliminate the bias of individual artificial intelligence method and enhance the accuracy and stability of prediction results. Furthermore, Bayesian optimization is employed to optimize the base-learners, ensuring the integration fairness. The typical step-like landslides (i.e., Bazimen landslide, Caojiatuo landslide) in the Three Gorges area are selected to compare the performance of different methods for time series decomposition and illustrate the effectiveness of the framework of the ensemble algorithm with the evaluation indices of mean absolute error, mean absolute percentage error and root mean square error. The prediction results indicate that the ICEEMDAN method has the best performance in displacement decomposition. In addition, the prediction results of Bayesian optimized ensemble method are more robust than those of individual ML method, facilitating more accurate and stable landslide displacement prediction and more effective reference for landslide early warning.

关键词： Displacement prediction Machine learning ensemble algorithm Bayesian Optimization Time series decomposition

来源：评论

学校读者我要写书评

暂无评论

Tree-based ensemble methods and their applications in analytical chemistry

引用

TRAC-TRENDS IN ANALYTICAL CHEMISTRY 2012年 40卷 158-167页

作者： Cao, Dong-Sheng Xu, Qing-Song Zhang, Liang-Xiao Huang, Jian-Hua Liang, Yi-Zeng Cent South Univ Res Ctr Modernizat Tradit Chinese Med Changsha 410083 Peoples R China Cent South Univ Sch Math & Stat Changsha 410083 Peoples R China Chinese Acad Sci Dalian Inst Chem Phys Key Lab Separat Sci Analyt Chem Dalian 116023 Peoples R China

Large amounts of data from high-throughput analytical instruments have generally become more and more complex, bringing a number of challenges to statistical modeling. To understand complex data further, new statistically-efficient approaches are urgently needed to: (1) select salient features from the data;(2) discard uninformative data;(3) detect outlying samples in data;(4) visualize existing patterns of the data;(5) improve the prediction accuracy of the data;and, finally, (6) feed back to the analyst understandable summaries of information from the data. We review current developments in tree-based ensemble methods to mine effectively the knowledge hidden in chemical and biology data. We report on applications of these algorithms to variable selection, outlier detection, supervised pattern analysis, cluster analysis, and tree-based kernel and ensemble learning. Through this report, we wish to inspire chemists to take greater interest in decision trees and to obtain greater benefits from using the tree-based ensemble techniques. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Chemometrics Classification and regression tree (CART) Cluster analysis Complex data ensemble algorithm Kernel method Outlier detection Pattern analysis Tree-based ensemble Variable selection

来源：评论

学校读者我要写书评

暂无评论

GLE-Net: A Global and Local ensemble Network for Aerial Object Detection

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2022年第1期15卷 1-12页

作者： Liao, Jiajia Liu, Yujun Piao, Yingchao Su, Jinhe Cai, Guorong Wu, Yundong Jimei Univ Comp Engn Coll 185 Yinjiang Rd Xiamen 361021 Peoples R China Chinese Acad Sci Comp Network Informat Ctr Bldg 24 Zhongguancun Nansijie Beijing 100190 Peoples R China

Recent advances in camera-equipped drone applications increased the demand for visual object detection algorithms with deep learning for aerial images. There are several limitations in accuracy for a single deep learning model. Inspired by ensemble learning can significantly improve the generalization ability of the model in the machine learning field, we introduce a novel integration strategy to combine the inference results of two different methods without non-maximum suppression. In this paper, a global and local ensemble network (GLE-Net) was proposed to increase the quality of predictions by considering the global weights for different models and adjusting the local weights for bounding boxes. Specifically, the global module assigns different weights to models. In the local module, we group the bounding boxes that corresponding to the same object as a cluster. Each cluster generates a final predict box and assigns the highest score in the cluster as the score of the final predict box. Experiments on benchmarks VisDrone2019 show promising performance of GLE-Net compared with the baseline network.

关键词： Convolutional neural networks (CNNs) Aerial images object detection VisDrone2019 dataset Deep learning ensemble algorithm

来源：评论

学校读者我要写书评

暂无评论

AN ARTIFICIAL COMPRESSIBILITY CRANK-NICOLSON LEAP-FROG METHOD FOR THE STOKES-DARCY MODEL AND APPLICATION IN ensemble SIMULATIONS

引用

SIAM JOURNAL ON NUMERICAL ANALYSIS 2021年第1期59卷 401-428页

作者： Jiang, Nan Li, Ying Yang, Huanhuan Univ Florida Dept Math Gainesville FL 32611 USA Shantou Univ Dept Math Shantou 515063 Guangdong Peoples R China

We propose and analyze an efficient, unconditionally stable, second order convergent, artificial compressibility Crank-Nicolson leap-frog (CNLFAC) method for numerically solving the Stokes-Darcy equations. The method decouples the fully coupled Stokes-Darcy system into two smaller subphysics problems, which reduces the size of the linear systems to be solved, at each time step, and allows parallel computing of the two subphysics problems. It also decouples the computation of the velocity and pressure in the free flow region. The pressure only needs to be updated at each time step without solving a Poisson equation, avoiding pressure errors in boundary layers due to imposing artificial boundary conditions. We prove that the method is unconditionally long time stable and second order convergent. We also propose an unconditionally stable ensemble algorithm based on the CNLFAC method. The ensemble algorithm results in a common coefficient matrix for all realizations and consequently allows the use of efficient direct or iterative solvers to reduce the computational cost. Numerical experiments are provided to illustrate the second order convergence and unconditional stability of the CNLFAC method. Moreover, the CNLFAC ensemble algorithm is demonstrated to reduce the computational time of a Crank-Nicolson leap-frog nonensemble algorithm by 95% in our tests.

关键词： artificial compressibility method Crank-Nicolson leap-frog Stokes-Darcy model ensemble algorithm unconditional stability

来源：评论

学校读者我要写书评

暂无评论

3D-AmplifAI: An ensemble Machine Learning Approach to Digital Twin Fault Monitoring for Additive Manufacturing in Smart Factories

引用

IEEE ACCESS 2023年 11卷 64128-64140页

作者： Sampedro, Gabriel Avelino R. Putra, Made Adi Paramartha Abisado, Mideth Univ Philippines Open Univ Fac Informat & Commun Studies Los Banos 4301 Philippines Salle Univ Ctr Computat Imaging & Visual Innovat Manila 1004 Philippines STMIK Primakara Informat Engn Denpasar 80226 Bali Indonesia Natl Univ Coll Comp & Informat Technol Manila 1008 Philippines

In the digital age, the digital twin eliminates physical barriers and risks, facilitating seamless activities in both real and virtual worlds. In the context of additive manufacturing, testing 3D printers can be resource-intensive and prone to printing issues. This research introduces a digital twin-based system that employs the innovative ensemble 3D-AmplifAI algorithm for fault monitoring in 3D printers. The system continuously monitors real-time temperature values and detects faults to prevent potential damage to the printer. Through an ensemble method, the 3D-AmplifAI algorithm combines multiple machine learning models to enhance fault detection in 3D printers. The digital twin environment, developed using Unity, serves as the bridge connecting the physical printer to the virtual world. Comparative evaluations against state-of-the-art algorithms, including Ridge Regression, XGBoost, InceptionTime, Time Series Transformer (TST), Rocket Ridge, Logistic Regression, Rocket XGBoost, ResNet, and Rocket Ridge Regression, demonstrate the superior performance of the 3D-AmplifAI algorithm in terms of accuracy, precision, recall, and F1-score.

关键词： Additive manufacturing digital twin ensemble algorithm fault monitoring

来源：评论

学校读者我要写书评

暂无评论

ensemble-based overlapping community detection using disjoint community structures

引用

KNOWLEDGE-BASED SYSTEMS 2019年第Jan.1期163卷 241-251页

作者： Chakraborty, Tanmoy Ghosh, Saptarshi Park, Noseong IIIT Delhi Dept CSE New Delhi India IIT Kharagpur Dept CSE Kharagpur W Bengal India George Mason Univ Dept Informat Sci & Technol Fairfax VA 22030 USA

While there has been a plethora of approaches for detecting disjoint communities from real-world complex networks, some methods for detecting overlapping community structures have also been recently proposed. In this work, we argue that, instead of developing separate approaches for detecting overlapping communities, a promising alternative is to infer the overlapping communities from multiple disjoint community structures. We propose an ensemble-based approach, called EnCoD, that leverages the solutions produced by various disjoint community detection algorithms to discover the overlapping community structure. Specifically, EnCoD generates a feature vector for each vertex from the results of the base algorithms and learns which features lead to detect densely connected overlapping regions in an unsupervised way. It keeps on iterating until the likelihood of each vertex belonging to its own community maximizes. Experiments on both synthetic and several real-world networks (with known ground-truth community structures) reveal that EnCoD significantly outperforms nine state-of-the-art overlapping community detection algorithms Finally, we show that EnCoD is generic enough to be applied to networks where the vertices are associated with explicit semantic features. To the best of our knowledge, EnCoD is the second ensemble-based overlapping community detection approach after MEDOC Chakraborty (2016). (C) 2018 Elsevier B.V. All rights reserved.

关键词： ensemble algorithm Overlapping communities Community detection

来源：评论

学校读者我要写书评

暂无评论

Numerical analysis of a second order ensemble method for evolutionary magnetohydrodynamics equations at small magnetic Reynolds number

引用

NUMERICAL METHODS FOR PARTIAL DIFFERENTIAL EQUATIONS 2022年第5期38卷 1407-1436页

作者： Carter, John Jiang, Nan Missouri Univ Sci & Technol Dept Math & Stat Rolla MO 65409 USA Univ Florida Dept Math Gainesville FL 32611 USA

We study a second order ensemble method for fast computation of an ensemble of magnetohydrodynamics flows at small magnetic Reynolds number. Computing an ensemble of flow equations with different input parameters is a common procedure for uncertainty quantification in many engineering applications, for which the computational cost can be prohibitively expensive for nonlinear complex systems. We propose an ensemble algorithm that requires only solving one linear system with multiple right-hands instead of solving multiple different linear systems, which significantly reduces the computational cost and simulation time. Comprehensive stability and error analyses are presented proving conditional stability and second order in time convergent. Numerical tests are provided to illustrate theoretical results and demonstrate the efficiency of the proposed algorithm.

关键词： ensemble algorithm finite element method low magnetic Reynolds number MHD partitioned method uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Unconditionally stable, second order, decoupled ensemble schemes for computing evolutionary Boussinesq equations

引用

APPLIED NUMERICAL MATHEMATICS 2023年第1期192卷 241-260页

作者： Jiang, Nan Yang, Huanhuan Univ Florida Dept Math Gainesville FL 32611 USA Shantou Univ Dept Math Shantou 515063 Guangdong Peoples R China

In this report we present two unconditionally stable, second order, decoupled ensemble schemes for computing evolutionary Boussinesq equations: the stabilized scalar auxiliary variable Crank-Nicolson leap-frog ensemble scheme (Stab-SAV-CNLF-En) and the stabilized scalar auxiliary variable BDF2 ensemble scheme (Stab-SAV-BDF2-En). The two ensemble schemes adopt the recently developed stabilized scalar auxiliary variable (SAV) idea and ensemble timestepping to achieve both high efficiency and unconditional stability. Specifically, the stabilized SAV approach makes it possible to devise unconditionally long time stable schemes for which the nonlinear terms and coupling terms in the Boussinesq equations are made fully explicit, leading to linear systems with constant coefficient matrices to be solved after spatial discretization. The ensemble timestepping further improves the efficiency by making the coefficient matrices of all realizations the same, so that efficient block solvers can be applied to solve the corresponding one linear system with multiple right hand sides and thus greatly reduce the computational cost. We prove the proposed schemes are unconditionally stable and present implementation details. Ample numerical tests are performed to show the efficiency and effectiveness of the combined approach.& COPY;2023 IMACS. Published by Elsevier B.V. All rights reserved.

关键词： Boussinesq equations ensemble algorithm SAV Uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification

引用

APPLIED ENERGY 2019年 236卷 55-69页

作者： Wang, Wei Hong, Tianzhen Li, Nan Wang, Ryan Qi Chen, Jiayu Southeast Univ Sch Architecture Nanjing 210018 Jiangsu Peoples R China Lawrence Berkeley Natl Lab Bldg Technol & Urban Syst Div Cyclotron Roach Berkeley CA 94720 USA Tsinghua Univ Dept Construct Management Beijing 100084 Peoples R China Northeastern Univ Dept Civil & Environm Engn 433 SN360 Huntington Ave Boston MA 02115 USA City Univ Hong Kong Dept Architecture & Civil Engn Kowloon Y6621AC1Tat Chee Ave Hong Kong Peoples R China

With the rapid advances in sensing and digital technologies, cyber-physical systems are regarded as the most viable platforms for improving building design and management. Researchers investigated the possibility of integrating energy management systems with cyber-physical systems to form energy-cyber-physical systems in order to promote building energy management. However, minimizing energy consumption while fulfilling building functions for energy-cyber-physical systems is challenging due to the dynamics of building occupants. As occupant behavior is a major source of uncertainty for energy management, ignoring it often results in both energy waste caused by overheating and overcooling as well as discomfort due to insufficient thermal and ventilation services. To mitigate such uncertainties, this study proposes an occupancy-linked energy-cyber-physical system that incorporates WiFi probe-based occupancy detection. The proposed framework utilizes ensemble classification algorithms to extract three forms of occupancy information. It creates a data interface to link energy management systems and cyber-physical systems and allows for automated occupancy detection and interpretation by assembling multiple weak classifiers for WiFi signals. A validation experiment in a large office room was conducted to examine the performance of the proposed occupancy-linked energy-cyber-physical systems. The experiment and simulation results suggest that, with a proper classifier and occupancy data type, the proposed model can potentially save about 26.4% of energy consumption in cooling and ventilation demands.

关键词： Energy-cyber-physical systems Building occupancy Wi-Fi probe technology ensemble algorithm

来源：评论

学校读者我要写书评

暂无评论

A comparative study of empirical and ensemble machine learning algorithms in predicting air over-pressure in open-pit coal mine

引用

ACTA GEOPHYSICA 2020年第2期68卷 325-336页

作者： Hoang Nguyen Xuan-Nam Bui Quang-Hieu Tran Pham Van Hoa Dinh-An Nguyen Le Thi Thu Hoa Qui-Thao Le Ngoc-Hoan Do Tran Dinh Bao Hoang-Bac Bui Moayedi, Hossein Hanoi Univ Min & Geol Dept Surface Min 18 Vien StDuc Thang Ward Hanoi Vietnam Hanoi Univ Min & Geol Ctr Min Electromech Res 18 Vien StDuc Thang Ward Hanoi Vietnam St Petersburg Min Univ Fac Min St Petersburg Russia Hanoi Univ Min & Geol Fac Geosci & Geoengn 18 Vien StDuc Thang Ward Hanoi Vietnam Hanoi Univ Min & Geol Ctr Excellence Anal & Expt 18 Vien StDuc Thang Ward Hanoi Vietnam Ton Duc Thang Univ Dept Management Sci & Technol Dev Ho Chi Minh City Vietnam Ton Duc Thang Univ Fac Civil Engn Ho Chi Minh City Vietnam

This study aims to take into account the feasibility of three ensemble machine learning algorithms for predicting blast-induced air over-pressure (AOp) in open-pit mine, including gradient boosting machine (GBM), random forest (RF), and Cubist. An empirical technique was also applied to predict AOp and compared with those of the ensemble models. To employ this study, 146 events of blast were investigated with 80% of the total database (approximately 118 blasting events) being used for developing the models, whereas the rest (20% 28 blasts) were used to validate the models' accuracy. RMSE, MAE, and R-2 were used as performance indices for evaluating the reliability of the models. The findings revealed that the ensemble models yielded more precise accuracy than those of the empirical model. Of the ensemble models, the Cubist model provided better performance than those of RF and GBM models with RMSE, MAE, and R-2 of 2.483, 0.976, and 0.956, respectively, whereas the RF and GBM models provided poorer accuracy with an RMSE of 2.579, 2.721;R-2 of 0.953, 0.950, and MAE of 1.103, 1.498, respectively. In contrast, the empirical model was interpreted as the poorest model with an RMSE of 4.448, R-2 of 0.872, and MAE of 3.719. In addition, other findings indicated that explosive charge capacity, spacing, stemming, monitoring distance, and air humidity were the most important inputs for the AOp predictive models using artificial intelligence.

关键词： Air over-pressure Open-pit mine ensemble algorithm Random forest Gradient boosting machine Cubist

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：