An improved symbolic aggregate approximation approach using rotation forest achieved 60.02% accuracy in classifying various emotional states from electrodermal activity signals.
An improved symbolic aggregate approximation approach combined with machine learning can effectively classify emotional states from electrodermal activity signals.
Analysis of fluctuations in electrodermal activity (EDA) signals is widely preferred for emotion recognition. In this work, an attempt has been made to determine the patterns of fluctuations in EDA signals for various emotional states using improved symbolic aggregate approximation. For this, the EDA is obtained from a publicly available online database. The EDA is decomposed into phasic components and divided into equal segments. Each segment is transformed into a piecewise aggregate approximation (PAA). These approximations are discretized using 11 time-domain features to obtain symbolic sequences. Shannon entropy is extracted from each PAA-based symbolic sequence using varied symbol size Formula: see text and window length Formula: see text. Three machine-learning algorithms, namely Naive Bayes, support vector machine and rotation forest, are used for the classification. The results show that the proposed approach is able to determine the patterns of fluctuations for various emotional states in EDA signals. PAA features, namely maximum amplitude and chaos, significantly identify the subtle fluctuations in EDA and transforms them in symbolic sequences. The optimal values of Formula: see text and Formula: see text yield the highest performance. The rotation forest is accurate (F-Formula: see text and 60.02% for arousal and valence dimensions) in classifying various emotional states. The proposed approach can capture the patterns of fluctuations for varied-length signals. Particularly, the support vector machine yields the highest performance for a lower length of signals. Thus, it appears that the proposed method might be utilized to analyze various emotional states in both normal and clinical settings.
Veeranki et al. (Wed,) conducted a other in Emotional states. Improved symbolic aggregate approximation and machine learning was evaluated on Classification of emotional states (arousal and valence dimensions). An improved symbolic aggregate approximation approach using rotation forest achieved 60.02% accuracy in classifying various emotional states from electrodermal activity signals.