Data Analysis for Emotion Classification Based on Bio-Information in Self-Driving Vehicles

Table 1

Summary of related studies.

Objects (topics)	Signals used	Analysis methodologies	References
Automatic identification of stress causes of employees	GSR	Adaptive windowing	Bakker et al. [16]
Detecting real-world driving stress	HR, EMG, Respiration	Continuous correlations	Healey and Picard [17]
Multi-level assessment model for monitoring elder’s health condition	HR, EEG, ECG	SVM, DT, Expectation maximization	Jung and Yoon [18]
Personal health system for detecting stress	GSR	Latent dirichlet allocation, SVM	Setz et al. [19]
Stress elicitation by examination	HR	Latent dirichlet allocation	Melillo et al. [20]
	Voice, GSR	DT, SVM, K-Means	Kurniawan [21]
Activity-aware mental stress detection (sitting, standing and walking)	HR, GSR, Accelemeter	DT, SVM, Bayes network	Sun et al. [23]
Automatic cry detection in early childhood	Voice	Gentle-boost	Ruvolo and Movellan [24]
Automatic classification of infant crying for early disease detection	Voice	Genetic selection of a fuzzy model	Rosales-Pérez et al. [25]
Automatic detection of the expiratory and inspiratory phases in newborn cry signal	Voice	Hidden markov model	Abou-Abbas et al. [26]