Bagging Based Feature Selection for Dimensional Affect Recognition in the continuous Emotion Space
Chen Aihua, Yuan Shuai, Jiang Dongmei
Available Online November 2013.
- https://doi.org/10.2991/icmt-13.2013.172How to use a DOI?
- Affect dimensions · Feature selection · Bagging · Correlation based feature selection
- This paper exploits the Bagging based feature selection method on the baseline audio features provided by AVEC2012 challenge competition. The selected features are input to SVR and RVM regression models, respectively, to estimate the affect dimensions arousal, valence, expectation, and power embedded in the audio speech. Experiments have been carried out on the word based and frame based baseline features, respectively, and the Pearson correlations between the estimated affect dimensions and their ground-truth labels are compared to those from the traditional correlation based feature selection (CFS) method with BestFirst or sequential floating forward selection (SFFS) algorithm. Experimental results show that both on word based and frame based baseline feature selection obtains the best accuracy in estimating the affect dimensions, while keeping the lowest number of features.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Chen Aihua AU - Yuan Shuai AU - Jiang Dongmei PY - 2013/11 DA - 2013/11 TI - Bagging Based Feature Selection for Dimensional Affect Recognition in the continuous Emotion Space PB - Atlantis Press SP - 1397 EP - 1404 SN - 1951-6851 UR - https://doi.org/10.2991/icmt-13.2013.172 DO - https://doi.org/10.2991/icmt-13.2013.172 ID - Aihua2013/11 ER -