Missing data analysis in emotion recognition

Abstract

Missing data is a widespread fundamental problem that cannot be ignored. It distorts the data, sometimes even to the point where it is impossible to analyze data at all. In emotion recognition, it was discovered that one of the best approaches to identify human emotions is by analyzing EEG (electroencephalography) results combined with peripheral signals. In this thesis EEG data is used to test which missing data techniques are more efficient and reliable in emotion recognition. During the research, the software was created, which implicates all the methods that are tested. In the end, author concludes which techniques should be used in emotion recognition and when.