Abstract
In pattern recognition, the selection of appropriate features is paramount to both the performance and the robustness of the system. Over-reliance on machine learning-based feature selection methods can, therefore, be problematic; especially when conducted using small snapshots of data. The results of these methods, if adopted without proper interpretation, can lead to sub-optimal system design or worse, the abandonment of otherwise viable and important features. In this work, a deep exploration of pain-based emotion classification was conducted to better understand differences in the results of the related literature. In total, 155 different time domain and frequency domain features were explored, derived from electromyogram (EMG), skin conductance levels (SCL), and electrocardiogram (ECG) readings taken from the 85 subjects in response to heat-induced pain. To address the inconsistency in the optimal feature sets found in related works, an exhaustive and interpretable feature selection protocol was followed to obtain a generalizable feature set. Associations between features were then visualized using a topologically-informed chart, called Mapper, of this physiological feature space, including synthesis and comparison of results from previous literature. This topological feature chart was able to identify key sources of information that led to the formation of five main functional feature groups: signal amplitude and power, frequency information, nonlinear complexity, unique, and connecting. These functional groupings were used to extract further insight into observable autonomic responses to pain through a complementary statistical interaction analysis. From this chart, it was observed that EMG and SCL derived features could functionally replace those obtained from ECG. These insights motivate future work on novel sensing modalities, feature design, deep learning approaches, and dimensionality reduction techniques.
Highlights
Emotion is the basis of subjective experience that drives human behavior and regulates many physiological states
Over-reliance on automated feature selection methods can be problematic, especially when conducted using small snapshots of data. The results of these methods, if adopted without proper interpretation, can lead to sub-optimal system design, or worse, the abandonment of otherwise viable and important features. To navigate this problem in a tangible way, we focus on a specific case study of emotion recognition; heat pain assessment, for which the selection of features and modalities is a current and acknowledged problem in the scientific literature
Feature Selection Approaches The classification accuracies obtained from the sequential forward selection (SFS) and univariate feature selection (UFS) protocols during the 100 epoch selection served as a robust performance metric for evaluating the modalities and features explored in this study over four classification problems (Tables 2, 3)
Summary
Emotion is the basis of subjective experience that drives human behavior and regulates many physiological states. In the field of affective computing, a desire to reciprocate this interaction has begun through emotion recognition and the development of affect sensitive systems By monitoring these manifestations of emotion, Feature Extraction for Pain Recognition called “affects,” an intelligent surrounding environment can respond to enhance engagement and cohesion with its participants. Deconstruction of emotional states into the concepts of arousal and valence has facilitated the practical application of emotion classification (Russell, 1980; Lang et al, 1998) This two-dimensional scale has provided a framework for quantifying emotional state in many recent affective computing studies (Khalili and Moradi, 2009; Rahnuma et al, 2011 ;Zhang and Zhang, 2017)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
