Feature Extraction and Selection for Pain Recognition Using Peripheral Physiological Signals

• Published in: Frontiers in neuroscience Vol. 13; p. 437
• Main Authors: Campbell, Evan, Phinyomark, Angkoon, Scheme, Erik
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 07.05.2019; Frontiers Media S.A
• Subjects: affective computing; Automation; Classification; Conductance; Cybernetics; Dementia; EKG; Electrocardiography; Electromyography; EMG; emotion recognition; Emotions; Engineering; Experiments; feature extraction; feature selection; International conferences; Learning algorithms; Medical research; multimodal analysis; Neuroscience; Neurosciences; Pain; Pain perception; Pattern recognition; Physiology; Privacy; Respiration; Signal processing; Canada; physiological signals; affective computing; feature extraction; multimodal analysis; emotion recognition; EMG; feature selection; heat pain

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...