In this report, the AdaBoost algorithm is applied to multi-class 3D gesture recognition problem. The performance of AdaBoost is compared across different base classifiers and between different data sets. One method of improving AdaBoost by regularizing the distribution weights is also presented and discussed.

In order to solve the overfitting of sample weights and the low detection rate in training process of the traditional AdaBoost algorithm, an improved AdaBoost algorithm based on Haar-like features and LBP features is proposed. This method improves weight updating rule and weights normalization rule of the traditional AdaBoost algorithm. Then combining this method with the AdaBoost algorithm bas...

AdaBoost is an excellent committee-based tool for classification. However, its effectiveness and efficiency in multiclass categorization face the challenges from methods based on support vector machine SVM , neural networks NN , naı̈ve Bayes, and k-nearest neighbor kNN . This paper uses a novel multi-class AdaBoost algorithm to avoid reducing the multi-class classification problem to multiple tw...

Asymmetric classification problems are characterized by class imbalance or unequal costs for different types of misclassifications. One of the main cited weaknesses of AdaBoost is its perceived inability to handle asymmetric problems. As a result, a multitude of asymmetric versions of AdaBoost have been proposed, mainly as heuristic modifications to the original algorithm. In this paper we chal...

AdaBoost is an iterative algorithm to constructclassifier ensembles. It quickly achieves high accuracy by focusingon objects that are difficult to classify. Because of this, AdaBoosttends to overfit when subjected to noisy datasets. We observethat this can be partially prevented with the use of validationsets, taken from the same noisy training set. But using less thanth...

We investigate further improvement of boosting in the case that the target concept belongs to the class of r-of-k threshold Boolean functions, which answers “+1” if at least r of k relevant variables are positive, and answers “−1” otherwise. Given m examples of a r-of-k function and literals as base hypotheses, popular boosting algorithms (e.g., AdaBoost [FS97]) construct a consistent final hyp...

We explore the relation between the Adaboost weight update procedure and Kelly’s theory of betting. Specifically, we show that an intuitive optimal betting strategy can easily be interpreted as the solution of the dual of the classical formulation of the Adaboost minimisation problem. This sheds new light over a substantial simplification of Adaboost that had so far only been considered a mere ...