|
|
|
| Detrended Fluctuation Analysis Based on the Affective ECG |
| Jing Cheng, Guangyuan Liu |
|
|
|
|
Abstract Electrocardiography (ECG) is one of the most important physiological signals, which has been proven to contain reliable affective information. Four kinds of objective affects including happiness, sadness, angry and fear, are induced by affective fragments from movies, and ECG signals are recorded by Biopac MP 150 synchronously. In an independent experiment the affective videos are played twice, and in the second presentation the press file of affective re-evaluation is obtained, which registers the subjective experience of participants and help us intercept the reliable affective ECG. The detrended fluctuation analysis is used to quantitate the temporal correlations by the scaling exponent in affective ECG. And the result
showed that ECG of happiness, sadness, angry and fear had long-range correlations. Then the scaling exponent is used by the binary classifier of Fisher as an affective feature, and the result showed that the correct recognition rate of happiness, sadness, angry and fear are 89.74%, 90.1%, 70.43%, 84.44% respectively. The whole experiment displays that the nonlinear features have a fine distinction in different emotions.
|
|
|
|
|
|
| Cite this article: |
|
Jing Cheng,Guangyuan Liu. Detrended Fluctuation Analysis Based on the Affective ECG[J]. Journal of Fiber Bioengineering and Informatics, 2014, 7(1): 91-102.
|
|
[1] Zeng Z, Pantic M, Roisman GI, et al. A survey of affect recognition methods: audio, visual and spontaneous expressions. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2009; 3: 39-58.
[2] Picard RW, Vyzas E, Healey J. Toward machine emotional intelligence: Analysis of affective physiological state. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001; 23: 1175-1191.
[3] Kim J, Andre. Emotion recognition based on physiological changes in music listening. IEEE Trans-actions on Pattern Analysis and Machine Intelligence, 2008; 30: 2067-2083.
[4] Sinha R, Lovallo WR, Parsons OA. Cardiovascular Differentiation of Emotions. Psychosomatic Medicine, 1992; 54: 422-435.
[5] AlZoubi O, D'Mello SK, Calvo RA. Detecting Naturalistic Expressions of Nonbasic Affect Using Physiological Signals. IEEE Transactions on affective computing. 2012; 3: 298-310.
[6] Agrafioti F, Hatzinakos D, Anderson AK. ECG Pattern Analysis for Emotion Detection. IEEE Transactions on affective computing. 2012, 3(1): 102-115.
[7] Meng ZL. The psychology of emotion. Bei Jing: Bei Jing University Press, 2005. p.5-6.
[8] Calvo RA, D'Mello S. Affect detection: An interdisciplinary review of models, methods, and their applications. IEEE Transactions on Affective Computing, 2010; 1: 18-37.
[9] Ubeyli ED. Adaptive neuro-fuzzy inference system for classification of ECG signals using Lyapunov exponents. Computer Methods and Programs in Biomedicine, 2005; 93: 313-321.
[10] Acharya RU, Lim CM, Joseph P. Heart rate variability analysis using correlation dimension and detrended fluctuation analysis. ITBM-RBM, 2002; 23: 333-339.
[11] Ning XB, Xu YL, Wang J, Ma XF. Approximate entropy analysis of short-term HFECG based on wave mode. Physica A. 2005; 346(3-4): 475-483.
[12] Peng CK, Buldyrev SV, Havlin S. Mosaic organization of DNA nucleotides. Physical Review E .1994; 49: 1685-1689.
[13] Stam CJ, Montez T, Jones BF, et. al. Disturbed fluctuations of resting state EEG synchronization in Alzheimer's disease. Clinical Neurophysiology. 2005; 116: 708-715.
[14] Ferree TC, Hwa RC. Electrophysiogical measures of acute cerebral ischaemia. Physics in Medicine and Biology. 2005; 50: 3927-3939.
[15] Yue J, Zhao XJ, Shang PJ. Effect of Trendson Detrended Fluctuation Analysis of Precipitation Series. Mathematical Problems in Engineering. 2010; 30: 1015-1030.
[16] Zhang Q, Zhou Y, Singh VP, Chen YD. Comparison of detrending methods for fuctuation analysis in hydrology. Journal of Hydrology. 2011; 400: 121-132.
[17] Cai SM, Zhou PL, Yang HJ, et. al. Diffusion entropy analysis on the scaling behavior of financial markets. Physica A. 2006; 367: 337-344.
[18] Peng CK, Havlin S, Stanley HE, et al. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos. 1995; 5: 82-87.
[19] Lee JM, Kim DJ, Kim I Y, et al. Nonlinear-analysis of human sleep EEG using detrended fluctu-ation analysis. Medical Engineering & Physics. 2004; 26: 773-776.
[20] Parish LM, Worrell GA, Cranstoun SD, et al. Long-range temporal correlations in epileptogenic and non-epileptogenic human hippocampus. Neuroscience. 2004; 125: 1069-1076.
[21] Bhattacharya J, Edwards J and Mamelak AN, et al. Long-range temporal correlations in the spontaneous spiking of neurons in the hippocampa-lamygdala complex of humans. Neuroscience. 2005; 131, 547-550.
[22] Cai SM, Zhou PL, Yang HJ, et al. Diffusion entropy analysis on the stride interval fuctuation of human gait. Physic A. 2007; 375: 687-692.
[23] Nikulin VV, Brismar T. Long-range temporal correlations in electroencephalographic oscillation: relation to topography, frequency band, age and gender. Neuroscience. 2005; 130: 549-558.
[24] Petrantonakis PC, Hadjileontiadis LJ. Emotion Recognition from Brain Signals Using Hybrid Adaptive Filtering and Higher Order Crossings Analysis. IEEE Transactions on affective comput-ing. 2010; 1: 81-97.
[25] Wen WH, Liu GY, Xiong X. Feature Selection Model and Generalization Performance of Two-class Emotion Recognition Systems Based on Physiological Signals. Computer Science. 2011; 38: 220-223. |
|
|
|
2014, Vol. 7 
