Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease

• Published in: International journal of psychophysiology Vol. 94; no. 3; pp. 482 - 495
• Main Authors: Yuvaraj, R., Murugappan, M., Ibrahim, Norlinah Mohamed, Sundaraj, Kenneth, Omar, Mohd Iqbal, Mohamad, Khairiyah, Palaniappan, R.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.12.2014; Elsevier
• Subjects: Acoustic Stimulation - methods; Adult; Adult and adolescent clinical studies; Behavioral psychophysiology; Biological and medical sciences; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases; Electroencephalogram; Electroencephalography - classification; Emotion classification; Emotions - physiology; Feature reduction; Female; Fundamental and applied biological sciences. Psychology; Humans; Male; Manifold learning; Medical sciences; Middle Aged; Nervous system (semeiology, syndromes); Nervous system as a whole; Neurology; Organic mental disorders. Neuropsychology; Parkinson Disease - classification; Parkinson Disease - diagnosis; Parkinson Disease - psychology; Parkinson's disease; Photic Stimulation - methods; Psychology. Psychoanalysis. Psychiatry; Psychology. Psychophysiology; Psychopathology. Psychiatry; Parkinson's disease; Manifold learning; Electroencephalogram; Emotion classification; Feature reduction; Affect affectivity; Visualization; Nervous system diseases; Electrophysiology; Parkinson disease; Electroencephalography; Emotion emotionality; Cerebral disorder; Learning; Acquisition process; Central nervous system disease; Classification; Degenerative disease; Extrapyramidal syndrome
• ISSN: 0167-8760; 1872-7697
• DOI: 10.1016/j.ijpsycho.2014.07.014

In addition to classic motor signs and symptoms, individuals with Parkinson's disease (PD) are characterized by emotional deficits. Ongoing brain activity can be recorded by electroencephalograph (EEG) to discover the links between emotional states and brain activity. This study utilized machine-learning algorithms to categorize emotional states in PD patients compared with healthy controls (HC) using EEG. Twenty non-demented PD patients and 20 healthy age-, gender-, and education level-matched controls viewed happiness, sadness, fear, anger, surprise, and disgust emotional stimuli while fourteen-channel EEG was being recorded. Multimodal stimulus (combination of audio and visual) was used to evoke the emotions. To classify the EEG-based emotional states and visualize the changes of emotional states over time, this paper compares four kinds of EEG features for emotional state classification and proposes an approach to track the trajectory of emotion changes with manifold learning. From the experimental results using our EEG data set, we found that (a) bispectrum feature is superior to other three kinds of features, namely power spectrum, wavelet packet and nonlinear dynamical analysis; (b) higher frequency bands (alpha, beta and gamma) play a more important role in emotion activities than lower frequency bands (delta and theta) in both groups and; (c) the trajectory of emotion changes can be visualized by reducing subject-independent features with manifold learning. This provides a promising way of implementing visualization of patient's emotional state in real time and leads to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders. •Emotional state classification in PD patients using machine-learning approach.•Bispectrum feature is superior to other three kinds of features studied.•Higher frequency bands play a more important role in emotional activities.•PD patients give lower accuracy as the EEG is not reflecting the emotion accurately.•The trajectory of emotion changes can be visualized with manifold learning model.