Machine Learning Systems for Multimodal Affect Recognition

Description

Markus Kächele offers a detailed view on the different steps in the affective computing pipeline, ranging from corpus design and recording over annotation and feature extraction to post-processing, classification of individual modalities and fusion in the context of ensemble classifiers. He focuses on multimodal recognition of discrete and continuous emotional and medical states. As such, specifically the peculiarities that arise during annotation and processing of continuous signals are highlighted. Furthermore, methods are presented that allow personalization of datasets and adaptation of classifiers to new situations and persons. Front Matter ....Pages i-xix Introduction (Markus Kächele)....Pages 1-6 Classification and regression approaches (Markus Kächele)....Pages 7-30 Applications and Affective corpora (Markus Kächele)....Pages 31-45 Modalities and Feature extraction (Markus Kächele)....Pages 47-62 Machine learning for the estimation of affective dimensions (Markus Kächele)....Pages 63-106 Adaptation and personalization of classifiers (Markus Kächele)....Pages 107-114 Experimental validation of pain intensity estimation (Markus Kächele)....Pages 115-130 Experimental validation of Methodological advancements (Markus Kächele)....Pages 131-135 Discussion (Markus Kächele)....Pages 137-140 Conclusion (Markus Kächele)....Pages 141-143 Back Matter ....Pages 145-187