Robust Asymmetric Adaboost

摘要: In real world pattern recognition problems, such as computer-assisted medical diagnosis, events of a given phenomena are usually found in minority, making it necessary to build algorithms that emphasize the effect one classes at training time. this paper we propose variation well-known Adaboost algorithm is able improve its performance by using an asymmetric and robust cost function. We assess proposed method on two datasets synthetic with different levels imbalance compare our results against three state-of-the-art ensemble learning approaches, achieving better comparable results.