检索结果-内蒙古大学图书馆

PaRSnIP: sequence-based protein solubility prediction using gradient boosting machine

BIOINFORMATICS 2018年第7期34卷 1092-1098页

作者： Rawi, Reda Mall, Raghvendra Kunji, Khalid Shen, Chen-Hsiang Kwong, Peter D. Chuang, Gwo-Yu NIAID Vaccine Res Ctr NIH Bethesda MD 20892 USA Hamad Bin Khalifa Univ Qatar Comp Res Inst Doha 34110 Qatar

Motivation: Protein solubility can be a decisive factor in both research and production efficiency, and in silico sequence-based predictors that can accurately estimate solubility outcomes are highly sought. Results: In this study, we present a novel approach termed PRotein SolubIlity Predictor (PaRSnIP), which uses a gradient boosting machine algorithm as well as an approximation of sequence and structural features of the protein of interest. Based on an independent test set, PaRSnIP outperformed other state-of-the-art sequence-based methods by more than 9% in accuracy and 0.17 in Matthew's correlation coefficient, with an overall accuracy of 74% and Matthew's correlation coefficient of 0.48. Additionally, PaRSnIP provides importance scores for all features used in training. We observed higher fractions of exposed residues to associate positively with protein solubility and tripeptide stretches with multiple histidines to associate negatively with solubility. The improved prediction accuracy of PaRSnIP should enable it to predict protein solubility with greater reliability and to screen for sequence variants with enhanced manufacturability.

关键词： PROTEIN solubility boosting algorithms SEQUENCES (Mathematics) CORRELATORS TRIPEPTIDES ACCURACY

来源：评论

学校读者我要写书评

暂无评论

Regularised gradient boosting for financial time-series modelling

引用

COMPUTATIONAL MANAGEMENT SCIENCE 2017年第3期14卷 367-391页

作者： Agapitos, Alexandros Brabazon, Anthony O'Neill, Michael Univ Coll Dublin Sch Comp Sci Dublin Ireland Univ Coll Dublin Sch Business Dublin Ireland

Gradient boosting (GB) learns an additive expansion of simple basis-models. This is accomplished by iteratively fitting an elementarymodel to the negative gradient of a loss function with respect to the expansion's values at each training data-point evaluated at each iteration. For the case of squared-error loss function, the negative gradient takes the form of an ordinary residual for a given training data-point. Studies have demonstrated that running GB for hundreds of iterations can lead to overfitting, while a number of authors showed that by adding noise to the training data, generalisation is impaired even with relatively few basis-models. Regularisation is realised through the shrinkage of every newly-added basis-model to the expansion. This paper demonstrates that GB with shrinkage-based regularisation is still prone to overfitting in noisy datasets. We use a transformation based on a sigmoidal function for reducing the influence of extreme values in the residuals of a GB iteration without removing them from the training set. This extension is built on top of shrinkage-based regularisation. Simulations using synthetic, noisy data show that the proposed method slows-down overfitting and reduces the generalisation error of regularised GB. The proposed method is then applied to the inherently noisy domain of financial time-series modelling. Results suggest that for the majority of datasets the method generalises better when compared against standard regularised GB, as well as against a range of other time-series modelling methods.

关键词： boosting algorithms Gradient boosting Stagewise additive modelling Regularisation Financial time-series modelling Financial forecasting Feedforward neural networks Noisy data Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Embedding Undersampling Rotation Forest for Imbalanced Problem

引用

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2018年第1期2018卷 1-15页

作者： Guo, Huaping Diao, Xiaoyu Liu, Hongbing Xinyang Normal Univ Sch Comp & Informat Technol Xinyang 464000 Henan Peoples R China

Rotation Forest is an ensemble learning approach achieving better performance comparing to Bagging and boosting through building accurate and diverse classifiers using rotated feature space. However, like other conventional classifiers, Rotation Forest does not work well on the imbalanced data which are characterized as having much less examples of one class (minority class) than the other (majority class), and the cost of misclassifying minority class examples is often much more expensive than the contrary cases. This paper proposes a novel method called Embedding Undersampling Rotation Forest (EURF) to handle this problem (1) sampling subsets from the majority class and learning a projection matrix from each subset and (2) obtaining training sets by projecting re-undersampling subsets of the original data set to new spaces defined by the matrices and constructing an individual classifier from each training set. For the first method, undersampling is to force the rotation matrix to better capture the features of the minority class without harming the diversity between individual classifiers. With respect to the second method, the undersampling technique aims to improve the performance of individual classifiers on the minority class. The experimental results show that EURF achieves significantly better performance comparing to other state-of-the-art methods.

关键词： SHORT rotation forestry BAGGING (Textiles) boosting algorithms MATRICES PERFORMANCE

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

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

Probing for Sparse and Fast Variable Selection with Model-Based boosting

引用

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2017年第1期2017卷 1-8页

作者： Thomas, Janek Hepp, Tobias Mayr, Andreas Bischl, Bernd LMU Munchen Dept Stat Munich Germany FAU Erlangen Nurnberg Dept Med Informat Biometry & Epidemiol Erlangen Germany Univ Hosp Bonn Dept Med Biometry Informat & Epidemiol Bonn Germany

We present a new variable selection method based on model-based gradient boosting and randomly permuted variables. Model-based boosting is a tool to fit a statistical model while performing variable selection at the same time. A drawback of the fitting lies in the need of multiple model fits on slightly altered data (e.g., cross-validation or bootstrap) to find the optimal number of boosting iterations and prevent overfitting. In our proposed approach, we augment the data set with randomly permuted versions of the true variables, so-called shadow variables, and stop the stepwise fitting as soon as such a variable would be added to the model. This allows variable selection in a single fit of the model without requiring further parameter tuning. We show that our probing approach can compete with state-of-the-art selection methods like stability selection in a high-dimensional classification benchmark and apply it on three gene expression data sets.

关键词： HIGH-dimensional model representation STATISTICAL models (Nuclear physics) GENE expression BOOTSTRAPPING (Statistics) boosting algorithms

来源：评论

学校读者我要写书评

暂无评论

Conditional Random Field (CRF)-boosting: Constructing a Robust Online Hybrid boosting Multiple Object Tracker Facilitated by CRF Learning

引用

SENSORS 2017年第3期17卷 617-617页

作者： Yang, Ehwa Gwak, Jeonghwan Jeon, Moongu Gwangju Inst Sci & Technol Sch Elect Engn & Comp Sci Gwangju 61005 South Korea

Due to the reasonably acceptable performance of state-of-the-art object detectors, tracking-by-detection is a standard strategy for visual multi-object tracking (MOT). In particular, online MOT is more demanding due to its diverse applications in time-critical situations. A main issue of realizing online MOT is how to associate noisy object detection results on a new frame with previously being tracked objects. In this work, we propose a multi-object tracker method called CRF-boosting which utilizes a hybrid data association method based on online hybrid boosting facilitated by a conditional random field (CRF) for establishing online MOT. For data association, learned CRF is used to generate reliable low-level tracklets and then these are used as the input of the hybrid boosting. To do so, while existing data association methods based on boosting algorithms have the necessity of training data having ground truth information to improve robustness, CRF-boosting ensures sufficient robustness without such information due to the synergetic cascaded learning procedure. Further, a hierarchical feature association framework is adopted to further improve MOT accuracy. From experimental results on public datasets, we could conclude that the benefit of proposed hybrid approach compared to the other competitive MOT systems is noticeable.

关键词： visual sensors multiple object tracking data association conditional random fields boosting algorithms hybrid approaches

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

boosting Thermoelectric Performance by Controlled Defect Chemistry Engineering in Ta-Substituted Strontium Titanate

引用

CHEMISTRY OF MATERIALS 2015年第14期27卷 4995-5006页

作者： Yaremchenko, Aleksey A. Populoh, Sascha Patricio, Sonia G. Macias, Javier Thiel, Philipp Fagg, Duncan P. Weidenkaff, Anke Frade, Jorge R. Kovalevsky, Andrei V. Univ Aveiro CICECO Aveiro Inst Mat Dept Mat & Ceram Engn P-3810193 Aveiro Portugal Univ Aveiro TEMA NRD Dept Mech Engn AIN P-3810193 Aveiro Portugal Empa Mat Energy Convers CH-8600 Zurich Switzerland Univ Stuttgart Inst Mat Sci Mat Chem DE-70569 Stuttgart Baden Wurttembe Germany

Inspired by recent research results that have demonstrated appealing thermoelectric performance of A-site cation-deficient titanates, this work focuses on detailed analysis of the changes in performance promoted by altering the defect chemistry mechanisms. The series of cation-stoichiometric SrTi1-xTaxO3 +/-delta and A-site deficient Sr1-x/2Ti1-xTaxO3-delta compositions (0.05 <= x <= 0.30) with cubic perovskite-like structure were selected to demonstrate the defect chemistry engineering approaches, which result in promising electric and thermal properties. High power factors were observed in compositions where appropriate concentration of the charge carriers and their mobility were attained by the presence of strontium- and oxygen vacancies and suppressed formation of the oxygen-rich layers. Noticeable deviations from stoichiometric oxygen content were found to decrease the lattice thermal conductivity, suggesting good phonon scattering ability for oxygen vacancies, vacant A-sites, and oxygen-excessive defects, while the effect from donor substitution on the thermal transport was less pronounced. The obtained guidelines for the defect chemistry engineering in donor-substituted strontium titanates open new possibilities for boosting the thermoelectric performance, especially if followed by complementary microstructural design to further promote electrical and thermal transport.

关键词： THERMOELECTRICITY boosting algorithms CRYSTAL defects TANTALUM STRONTIUM titanate THERMOELECTRIC effects

来源：评论

学校读者我要写书评

暂无评论

2015 Marshall Urist Young Investigator Award: Prognostication in Patients With Long Bone Metastases: Does a boosting Algorithm Improve Survival Estimates?

引用

CLINICAL ORTHOPAEDICS AND RELATED RESEARCH 2015年第10期473卷 3112-3121页

作者： Janssen, Stein J. van der Heijden, Andrea S. van Dijke, Maarten Ready, John E. Raskin, Kevin A. Ferrone, Marco L. Hornicek, Francis J. Schwab, Joseph H. Harvard Univ Massachusetts Gen Hosp Sch Med Dept Orthopaed SurgOrthopaed Oncol Serv Boston MA USA Harvard Univ Brigham & Womens Hosp Sch Med Dept Orthopaed SurgOrthopaed Oncol Serv Boston MA 02115 USA Massachusetts Gen Hosp Boston MA 02114 USA

Survival estimation guides surgical decision-making in metastatic bone disease. Traditionally, classic scoring systems, such as the Bauer score, provide survival estimates based on a summary score of prognostic factors. Identification of new factors might improve the accuracy of these models. Additionally, the use of different algorithms-nomograms or boosting algorithms-could further improve accuracy of prognostication relative to classic scoring systems. A nomogram is an extension of a classic scoring system and generates a more-individualized survival probability based on a patient's set of characteristics using a figure. boosting is a method that automatically trains to classify outcomes by applying classifiers (variables) in a sequential way and subsequently combines them. A boosting algorithm provides survival probabilities based on every possible combination of variables. We wished to (1) assess factors independently associated with decreased survival in patients with metastatic long bone fractures and (2) compare the accuracy of a classic scoring system, nomogram, and boosting algorithms in predicting 30-, 90-, and 365-day survival. We included all 927 patients in our retrospective study who underwent surgery for a metastatic long bone fracture at two institutions between January 1999 and December 2013. We included only the first procedure if patients underwent multiple surgical procedures or had more than one fracture. Median followup was 8 months (interquartile range, 3-25 months);369 of 412 (90%) patients who where alive at 1 year were still in followup. Multivariable Cox regression analysis was used to identify clinical and laboratory factors independently associated with decreased survival. We created a classic scoring system, nomogram, and boosting algorithms based on identified variables. Accuracy of the algorithms was assessed using area under the curve analysis through fivefold cross validation. The following factors were associated with a decreased

关键词： BONE metastasis RESEARCH MEDICAL decision making SURVIVAL analysis (Biometry) boosting algorithms BODY mass index NOMOGRAPHY (Mathematics) FOLLOW-up studies (Medicine)

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：