TY - GEN
T1 - Feature selection for stress level classification into a physiologycal signals set
AU - Jimenez-Limas, Marco A.
AU - Ramirez-Fuentes, Carlos A.
AU - Tovar-Corona, Blanca
AU - Garay-Jimenez, Laura I.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/13
Y1 - 2018/11/13
N2 - This paper describes the methodology and results obtained when classifying two states of stress, low and high using a data base from Physionet that contains the recordings of physiological signals under several stress conditions. The signals were first denoised and then, features were extracted for segments of 5 minutes. Four out of 6 signals were chosen: Heart rate variability, respiration, galvanic skin response from the hand, and galvanic skin response from the foot. Two non-lineal features were extracted: Approximate entropy and correlation dimension, both with m=2 and m=3. Besides, three linear features were extracted: Energy, mean and standard deviation. Five machine learning classifiers were compared: K-nearest neighbours, Support vector machines with a linear kernel, support vector machines with a Gaussian kernel, Naïve Bayes classifier, Random forest classifier and logistic regression. It was found that approximate entropy and correlation dimension with m=3 provide the greater differences between the two stress states. It was also found that choosing only three physiological signals and correlation dimension with m=3 the logistic regression classifier achieved and accuracy of 81.38%, the best performance compared to other combinations of signals and classifiers. The three physiological signals that provided the best features were heart rate variability, respiration and galvanic skin response on the foot.
AB - This paper describes the methodology and results obtained when classifying two states of stress, low and high using a data base from Physionet that contains the recordings of physiological signals under several stress conditions. The signals were first denoised and then, features were extracted for segments of 5 minutes. Four out of 6 signals were chosen: Heart rate variability, respiration, galvanic skin response from the hand, and galvanic skin response from the foot. Two non-lineal features were extracted: Approximate entropy and correlation dimension, both with m=2 and m=3. Besides, three linear features were extracted: Energy, mean and standard deviation. Five machine learning classifiers were compared: K-nearest neighbours, Support vector machines with a linear kernel, support vector machines with a Gaussian kernel, Naïve Bayes classifier, Random forest classifier and logistic regression. It was found that approximate entropy and correlation dimension with m=3 provide the greater differences between the two stress states. It was also found that choosing only three physiological signals and correlation dimension with m=3 the logistic regression classifier achieved and accuracy of 81.38%, the best performance compared to other combinations of signals and classifiers. The three physiological signals that provided the best features were heart rate variability, respiration and galvanic skin response on the foot.
KW - Galvanic skin conductance
KW - Heart rate variability
KW - Machine learning
KW - Non linear features
KW - Respiration
KW - Statistical classifiers
UR - http://www.scopus.com/inward/record.url?scp=85058459905&partnerID=8YFLogxK
U2 - 10.1109/ICEEE.2018.8533968
DO - 10.1109/ICEEE.2018.8533968
M3 - Contribución a la conferencia
AN - SCOPUS:85058459905
T3 - 2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2018
BT - 2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2018
Y2 - 5 September 2018 through 7 September 2018
ER -