检索结果-内蒙古大学图书馆

Data weighing mechanisms for clustering ensembles

COMPUTERS & ELECTRICAL ENGINEERING 2013年第5期39卷 1433-1450页

作者： Parvin, Hamid Minaei-Bidgoli, Behrouz Alinejad-Rokny, Hamid Punch, William F. Iran Univ Sci & Technol Dept Comp Engn Tehran Iran Univ New S Wales Fac Med Ctr Vasc Res Complex Syst Biol Grp Sydney NSW Australia Univ New S Wales Sch Comp Sci & Engn Sydney NSW Australia Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA

Inspired by bagging and boosting algorithms in classification, the non-weighing and weighing-based sampling approaches for clustering are proposed and studied in the paper. The effectiveness of non-weighing-based sampling technique, comparing the efficacy of sampling with and without replacement, in conjunction with several consensus algorithms have been invested in this paper. Experimental results have shown improved stability and accuracy for clustering structures obtained via bootstrapping, subsampling, and boosting techniques. Subsamples of small size can reduce the computational cost and measurement complexity for many unsupervised data mining tasks with distributed sources of data. This empirical research study also compares the performance of boosting and bagging clustering ensembles using different consensus functions on a number of datasets. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： DATA analysis boosting algorithms PERFORMANCE FUNCTIONAL analysis NUMBER theory EMPIRICAL research DATA mining COMPUTER algorithms

来源：评论

学校读者我要写书评

暂无评论

Data-driven machine learning approach for predicting dwell fatigue life in two classes of Titanium alloys

引用

ENGINEERING FRACTURE MECHANICS 2024年 306卷

作者： Rahman, Syed Abdur Chandraker, Abhinav Prakash, Om Chauhan, Ankur Indian Inst Sci IISc Dept Mat Engn Extreme Environm Mat Grp Bengaluru 560012 Karnataka India Boeing Res & Technol India Ctr Bangalore 560016 India

Predicting dwell fatigue life accurately in Titanium (Ti) alloys is vital for designing reliable components such as aero-engine discs and blades. This study proposes a data-driven machine learning (ML) approach for precisely predicting dwell fatigue life in two classes of Ti alloys: near alpha and alpha + beta alloys. To build a robust model, the data-driven approach tackles this multidimensional problem by training a comprehensive dataset of various input features, including alloy composition, monotonic properties, and fatigue testing parameters. Advanced ensemblebased algorithms, Gradient boosting (GBOOST) and Extreme Gradient boosting (XGBOOST) are employed. The split-insensitive best-performing XGBOOST model achieved a high accuracy (R2) score of 89.9 %, indicating impressive prediction capability. The model's robustness is further assessed using an unseen validation dataset to draw qualitative and quantitative conclusions. ML model's validation further involved comparing its predictions with actual experimental trends across relationships, such as dwell life versus dwell time and dwell-debit versus dwell time. Dwell-debit is also predicted as a function of varying stresses normalized to 0.2 % yield strength, highlighting the susceptibility of investigated Ti alloys to dwell fatigue. Additionally, the SHapley Additive exPlanations (SHAP) analysis was conducted to gain deeper insights into various input features affecting dwell fatigue life.

关键词： Titanium alloys Fatigue Dwell fatigue Machine learning boosting algorithms

来源：评论

学校读者我要写书评

暂无评论

Boosted classification trees and class probability/quantile estimation

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2007年第3期8卷 409-439页

作者： Mease, David Wyner, Abraham J. Buja, Andreas San Jose State Univ Dept Mkt & Decis Sci San Jose CA 95192 USA Univ Penn Wharton Sch Dept Stat Philadelphia PA 19104 USA

The standard by which binary classifiers are usually judged, misclassification error, assumes equal costs of misclassifying the two classes or, equivalently, classifying at the 1/2 quantile of the conditional class probability function P [ y = 1 vertical bar x]. Boosted classification trees are known to perform quite well for such problems. In this article we consider the use of standard, off-the-shelf boosting for two more general problems: 1) classification with unequal costs or, equivalently, classification at quantiles other than 1/2, and 2) estimation of the conditional class probability function P [ y = 1 vertical bar x]. We first examine whether the latter problem, estimation of P [ y = 1 vertical bar x], can be solved with Logit-Boost, and with AdaBoost when combined with a natural link function. The answer is negative: both approaches are often ineffective because they overfit P [ y = 1 vertical bar x] even though they perform well as classifiers. A major negative point of the present article is the disconnect between class probability estimation and classification. Next we consider the practice of over/under-sampling of the two classes. We present an algorithm that uses AdaBoost in conjunction with Over/Under-Sampling and Jittering of the data ("JOUS-Boost"). This algorithm is simple, yet successful, and it preserves the advantage of relative protection against overfitting, but for arbitrary misclassification costs and, equivalently, arbitrary quantile boundaries. We then use collections of classifiers obtained from a grid of quantiles to form estimators of class probabilities. The estimates of the class probabilities compare favorably to those obtained by a variety of methods across both simulated and real data sets.

关键词： boosting algorithms LogitBoost AdaBoost class probability estimation over-sampling under-sampling stratification data jittering

来源：评论

学校读者我要写书评

暂无评论

Comparing Out-of-Sample Performance of Machine Learning Methods to Forecast US GDP Growth

引用

COMPUTATIONAL ECONOMICS 2023年第4期62卷 1567-1609页

作者： Chu, Ba Qureshi, Shafiullah Carleton Univ Dept Econ 1125 Colonel By Dr Ottawa ON Canada NUML Dept Econ Islamabad Pakistan

We run a 'horse race' among popular forecasting methods, including machine learning (ML) and deep learning (DL) methods, that are employed to forecast U.S. GDP growth. Given the unstable nature of GDP growth data, we implement a recursive forecasting strategy to calculate the out-of-sample performance metrics of forecasts for multiple subperiods. We use three sets of predictors: a large set of 224 predictors [of U.S. GDP growth] taken from a large quarterly macroeconomic database (namely, FRED-QD), a small set of nine strong predictors selected from the large set, and another small set including these nine strong predictors together with a high-frequency business condition index. We then obtain the following three main findings: (1) when forecasting with a large number of predictors with mixed predictive power, density-based ML methods (such as bagging, boosting, or neural networks) can somewhat outperform sparsity-based methods (such as Lasso) for short-horizon forecast, but it is not easy to distinguish the performance of these two types of methods for long-horizon forecast;(2) density-based ML methods tend to perform better with a large set of predictors than with a small subset of strong predictors, especially when it comes to shorter horizon forecast;and (3) parsimonious models using a strong high-frequency predictor can outperform other sophisticated ML and DL models using a large number of low-frequency predictors at least for long-horizon forecast, highlighting the important role of predictors in economic forecasting. We also find that ensemble ML methods (which are the special cases of density-based ML methods) can outperform popular DL methods.

关键词： Lasso Ridge regression Random forest boosting algorithms Artificial neural networks Dimensionality reduction methods MIDAS GDP growth

来源：评论

学校读者我要写书评

暂无评论

Colloidal metal oxide nanocrystals as charge transporting layers for solution-processed light-emitting diodes and solar cells

引用

CHEMICAL SOCIETY REVIEWS 2017年第6期46卷 1730-1759页

作者： Liang, Xiaoyong Bai, Sai Wang, Xin Dai, Xingliang Gao, Feng Sun, Baoquan Ning, Zhijun Ye, Zhizhen Jin, Yizheng Zhejiang Univ Sch Mat Sci & Engn State Key Lab Silicon Mat Hangzhou 310027 Zhejiang Peoples R China Linkoping Univ Dept Phys Chem & Biol IFM SE-58183 Linkoping Sweden Soochow Univ Inst Funct Nano & Soft Mat FUNSOM Jiangsu Key Lab Carbon Based Funct Mat & Devices Suzhou 215123 Peoples R China Shanghai Tech Univ Shanghai Peoples R China Zhejiang Univ Dept Chem State Key Lab Silicon Mat Ctr Chem High Performance & Novel Mat Hangzhou 310027 Zhejiang Peoples R China

Colloidal metal oxide nanocrystals offer a unique combination of excellent low-temperature solution processability, rich and tuneable optoelectronic properties and intrinsic stability, which makes them an ideal class of materials as charge transporting layers in solution-processed light-emitting diodes and solar cells. Developing new material chemistry and custom-tailoring processing and properties of charge transporting layers based on oxide nanocrystals hold the key to boosting the efficiency and lifetime of all-solution-processed light-emitting diodes and solar cells, and thereby realizing an unprecedented generation of high-performance, low-cost, large-area and flexible optoelectronic devices. This review aims to bridge two research fields, chemistry of colloidal oxide nanocrystals and interfacial engineering of optoelectronic devices, focusing on the relationship between chemistry of colloidal oxide nanocrystals, processing and properties of charge transporting layers and device performance. Synthetic chemistry of colloidal oxide nanocrystals, ligand chemistry that may be applied to colloidal oxide nanocrystals and chemistry associated with post-deposition treatments are discussed to highlight the ability of optimizing processing and optoelectronic properties of charge transporting layers. Selected examples of solution-processed solar cells and light-emitting diodes with oxide-nanocrystal charge transporting layers are examined. The emphasis is placed on the correlation between the properties of oxide-nanocrystal charge transporting layers and device performance. Finally, three major challenges that need to be addressed in the future are outlined. We anticipate that this review will spur new material design and simulate new chemistry for colloidal oxide nanocrystals, leading to charge transporting layers and solution-processed optoelectronic devices beyond the state-of-the-art.

关键词： METALLIC oxides NANOCRYSTALS LIGHT emitting diodes boosting algorithms OPTOELECTRONIC devices

来源：评论

学校读者我要写书评

暂无评论

Validation of a DC-DC Boost Circuit Control Algorithm

引用

SAE INTERNATIONAL JOURNAL OF AEROSPACE 2016年第1期9卷 112-127页

作者： Zumberge, Jon Boyd, Michael Ordonez, Raul AFRL Wright Patterson AFB OH 45433 USA PC Krause & Associates W Lafayette IN USA Univ Dayton Dayton OH 45469 USA

Cost and performance requirements are driving military and commercial systems to become highly integrated, optimized systems which require more sophisticated. highly complex controls. To realize benefits of those complex controls and make confident decisions, the validation of both plant and control models becomes critical. To quickly develop controls for these systems, it is beneficial to develop plant models and determine the uncertainty of those models to predict performance and stability of the control algorithms. A process of model and control algorithm validation for a dc-dc boost converter circuit based on acceptance sampling is presented here. The validation process described in this paper is based on MIL-STD 3022 with emphasis on requirements settings and the testing process. The key contribution of this paper is the process for model and control algorithm validation, specifically a method for decomposing the problem into model and control algorithm validation stages. The other contribution includes projection of model and control uncertainty limits to areas where experimental data has not been taken. These methods will be used to compare delaying of a control action until the beginning of the next control loop versus using the control action immediately but at a non-deterministic time interval (i.e., jitter will be introduced).

关键词： SOFTWARE validation DIRECT current circuits boosting algorithms SYSTEMS engineering ELECTRIC power conversion

来源：评论

学校读者我要写书评

暂无评论

SGB-ELM: An Advanced Stochastic Gradient boosting-Based Ensemble Scheme for Extreme Learning Machine

引用

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2018年第1期2018卷 1-14页

作者： Guo, Hua Wang, Jikui Ao, Wei He, Yulin Lanzhou Univ Finance & Econ Sch Informat Engn Lanzhou 730020 Gansu Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China

A novel ensemble scheme for extreme learning machine (ELM), named Stochastic Gradient boosting-based Extreme Learning Machine (SGB-ELM), is proposed in this paper. Instead of incorporating the stochastic gradient boosting method into ELM ensemble procedure primitively, SGB-ELM constructs a sequence of weak ELMs where each individual ELM is trained additively by optimizing the regularized objective. Specifically, we design an objective function based on the boosting mechanism where a regularization item is introduced simultaneously to alleviate overfitting. Then the derivation formula aimed at solving the output-layer weights of each weak ELM is determined using the second-order optimization. As the derivation formula is hard to be analytically calculated and the regularized objective tends to employ simple functions, we take the output-layer weights learned by the current pseudo residuals as an initial heuristic item and thus obtain the optimal output-layer weights by using the derivation formula to update the heuristic item iteratively. In comparison with several typical ELM ensemble methods, SGB-ELM achieves better generalization performance and predicted robustness, which demonstrates the feasibility and effectiveness of SGB-ELM.

关键词： MACHINE learning STOCHASTIC models boosting algorithms STATISTICAL ensembles MATHEMATICAL optimization

来源：评论

学校读者我要写书评

暂无评论

Short-term wind power forecasting using integrated boosting approach

引用

FRONTIERS IN ENERGY RESEARCH 2024年 12卷

作者： Ahmed, Ubaid Muhammad, Rasheed Abbas, Syed Sami Aziz, Imran Mahmood, Anzar Mirpur Univ Sci & Technol Dept Elect Engn Mirpur Pakistan Uppsala Univ Dept Phys & Astron Uppsala Sweden

Rapidly increasing global energy demand and environmental concerns have shifted the attention of policymakers toward the large-scale integration of renewable energy resources (RERs). Wind energy is a type of RERs with vast energy potential and no environmental pollution is associated with it. The sustainable development goals: affordable and clean energy, climate action, and industry, innovation and infrastructure, can be achieved by integrating wind energy into the existing power systems. However, the integration of wind energy will bring instability challenges due to its intermittent nature. Mitigating these challenges necessitates the implementation of effective wind power forecasting models. Therefore, we have proposed a novel integrated approach, Boost-LR, for hour-ahead wind power forecasting. The Boost-LR is a multilevel technique consisting of non-parametric models, extreme gradient boosting (XgBoost), categorical boosting (CatBoost), and random forest (RF), and parametric approach, linear regression (LR). The first layer of the Boost-LR uses the boosting algorithms that process the data according to their tree development architectures and pass their intermediary forecast to LR which is deployed in layer two and processes the intermediary forecasts of layer one models to provide the final predicted wind power. To demonstrate the generalizability and robustness of the proposed study, the performance of Boost-LR is compared with the individual models of CatBoost, XgBoost, RF, deep learning networks: long short-term memory (LSTM) and gated recurrent unit (GRU), Transformer and Informer models using root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and normalized root mean square error (NRMSE). Findings demonstrate the effectiveness of the Boost-LR as its forecasting performance is superior to the compared models. The improvement in MAE of Boost-LR is recorded as to be 31.42%, 32.14%, and 27.55% for the datasets of Bruska, Jelina

关键词： wind power forecasting hybrid model boosting algorithms deep learning network LSTM

来源：评论

学校读者我要写书评

暂无评论

An Update on Statistical boosting in Biomedicine

引用

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2017年第1期2017卷 1-12页

作者： Mayr, Andreas Hofner, Benjamin Waldmann, Elisabeth Hepp, Tobias Meyer, Sebastian Gefeller, Olaf Friedrich Alexander Univ Erlangen Nurnberg FAU Inst Med Informat Biometrie & Epidemiol Erlangen Germany Ludwig Maximilians Univ Munchen Inst Stat Munich Germany Paul Ehrlich Inst Langen Germany

Statistical boosting algorithms have triggered a lot of research during the last decade. They combine a powerful machine learning approach with classical statistical modelling, offering various practical advantages like automated variable selection and implicit regularization of effect estimates. They are extremely flexible, as the underlying base-learners (regression functions defining the type of effect for the explanatory variables) can be combined with any kind of loss function (target function to be optimized, defining the type of regression setting). In this review article, we highlight the most recent methodological developments on statistical boosting regarding variable selection, functional regression, and advanced time-to-event modelling. Additionally, we provide a short overview on relevant applications of statistical boosting in biomedicine.

关键词： boosting algorithms MACHINE learning STATISTICAL models LOSS functions (Statistics) REGRESSION analysis MEDICINE

来源：评论

学校读者我要写书评

暂无评论

Recognition of human activities for wellness management using a smartphone and a smartwatch: A boosting approach

引用

DECISION SUPPORT SYSTEMS 2021年 140卷 113426-113426页

作者： Tarafdar, Pratik Bose, Indranil OP Jindal Global Univ Jindal Global Business Sch Informat Syst & Analyt Sonipat 131001 Haryana India Indian Inst Management Calcutta Diamond Harbour Rd Kolkata 700104 India

Mobile health applications are considered to be powerful tools for activity-based wellness management. With the availability of multimodal sensors in smart devices used in our daily lives, it is possible to track human activity and deliver context-aware wellness services. The embedded sensors in naturally used devices such as smartphones, smartwatches, and wearables contain rich information that can be integrated for human activity recognition. Our research demonstrates how powerful boosting algorithms can extract knowledge for human activity classification in a real-life setting. Our results show that boosting classifiers outperform traditional machine learning classifiers in the detection of basic human activities such as walking, standing, sitting, exercise, and sleeping. Further, we perform feature engineering to compare the potential of a smartphone and a smartwatch in activity detection. Our feature engineering strategy provides directions about the selection of sensor features for improvement in classification of basic human activities. The theoretical and practical implications of this research for activity-based wellness management are also discussed.

关键词： Activity-based wellness management boosting algorithms Human activity recognition Machine learning Mobile health Multimodal sensors

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：