Boosting Algorithms: A Review of Methods, Theory, and Applications

Ferreira, Artur J.; Figueiredo, Mário A. T.

doi:10.1007/978-1-4419-9326-7_2

Cited by 173 publications

(98 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This list of AdaBoost modifications is not exhaustive, but it represents the most common algorithms used to date. For a more in-depth treatment on variants of boosting algorithms, the interested reader is referred to Ferreira and Figueiredo (2012). Long and Servedio (2010) proved that for any booster with a potential convex loss function, and any nonzero random classification noise rate, there is a data set, which can be efficiently learned by the booster if there is no noise, but cannot be learned with accuracy better than 1/2 with random classification noise present.…”

Section: Boosting and Classification Noisementioning

confidence: 99%

Noise peeling methods to improve boosting algorithms

Martinez

Gray

2016

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

Section: Boosting and Classification Noisementioning

confidence: 99%

Noise peeling methods to improve boosting algorithms

Martinez

Gray

2016

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

“…As many distinct boosting methods can be included within the meta-learner library (e.g., XGBoost), combining the power of multi-classifier boosting within a single base learner into the larger CBDA ensemble prediction enhances the method's power by aggregating across multiple base learners. Many studies examine the asymptotic convergence of bagging, boosting and ensemble methods [31][32][33][34]. Similar approaches may be employed to validate CBDA inference in terms of upper error bounds, convergence, and reliability.…”

Section: Cbda Two-phase Bootstrapping Strategymentioning

confidence: 99%

Compressive Big Data Analytics: An Ensemble Meta-Algorithm for High-dimensional Multisource Datasets

Marino

Zhao

Zhou

et al. 2020

Preprint

View full text Add to dashboard Cite

technique on a large-scale clinical study (UK Biobank), which includes imaging, cognitive, 47and clinical assessment data. The UK Biobank archive presents several difficult challenges 48 related to the aggregation, harmonization, modeling, and interrogation of the information. 49These problems are related to the complex longitudinal structure, feature heterogeneity, 50 multicollinearity, incongruency, and missingness, as well as violations of classical parametric 51 assumptions that require novel health analytical approaches. 53Our results showcase the scalability, efficiency and potential of CBDA to compress complex 54 data into structural information leading to derived knowledge and translational action. The 55 results of the real case-study suggest new and exciting avenues of research in the context of 56 identifying, tracking, and treating mental health and aging-related disorders. Following open-57 science principles, we share the entire end-to-end protocol, source-code, and results. This 58 facilitates independent validation, result reproducibility, and team-based collaborative 59 discovery. 60 61 Figure 5: Dissimilarity and variance analysis of the coefficients/weights distributions of the ensemble predictor. Binomial (Panels A-C) and Null (Panels B-D)datasets analysis (each with 10,000 cases and 1,000 features). The x axis displays the top-ranked models (from 50 to 5,000). The y axis shows the mean value of the * Bray-Curtis dissimilarity distance within the SuperLearner coefficients (Panels A-B) and the variance of the SuperLearner coefficients (Panels C and D). *

show abstract

“…In this work, the classification is performed by gentle AdaBoost [66], which is stated to have better performance [67] compared to the original discrete [68] and real AdaBoost [69], due to less severe weighting of wrongly labeled or unrepresentative training samples.…”

Section: Pre-classificationmentioning

confidence: 99%

An Operational System for Estimating Road Traffic Information from Aerial Images

et al. 2014

View full text Add to dashboard Cite

Given that ground stationary infrastructures for traffic monitoring are barely able to handle everyday traffic volumes, there is a risk that they could fail altogether in situations arising from mass events or disasters. In this work, we present an alternative approach for traffic monitoring during disaster and mass events, which is based on an airborne optical sensor system. With this system, optical image sequences are automatically examined on board an aircraft to estimate road traffic information, such as vehicle positions, velocities and driving directions. The traffic information, estimated in real time on board, is immediately downlinked to a ground station. The airborne sensor system consists of a three-head camera system, a real-time-capable GPS/INS unit, five industrial PCs and a downlink unit. The processing chain for automatic extraction of traffic information contains modules for the synchronization of image and navigation data streams, orthorectification and vehicle detection and tracking modules. The vehicle detector is based on a combination of AdaBoost and support vector machine classifiers. Vehicle tracking relies on shape-based matching operators. The processing chain is evaluated on a large number of image sequences recorded during several campaigns, and the data quality is compared to that obtained from induction loops. In summary, we can conclude that the achieved overall quality of the traffic data extracted by the airborne system is in the range of 68% and 81%. Thus, it is comparable to data obtained from stationary ground sensor networks.

show abstract

Boosting Algorithms: A Review of Methods, Theory, and Applications

Cited by 173 publications

References 95 publications

Noise peeling methods to improve boosting algorithms

Noise peeling methods to improve boosting algorithms

Compressive Big Data Analytics: An Ensemble Meta-Algorithm for High-dimensional Multisource Datasets

An Operational System for Estimating Road Traffic Information from Aerial Images

Contact Info

Product

Resources

About