Classification of Interbeat Interval Time-Series Using Attention Entropy

• Published in: IEEE transactions on affective computing Vol. 14; no. 1; pp. 321 - 330
• Main Authors: Yang, Jiawei, Choudhary, Gulraiz I., Rahardja, Susanto, Franti, Pasi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Attention entropy; Classification; Complexity; Complexity theory; Data points; Delays; Diseases; Entropy; Frequency analysis; Frequency distribution; Heart rate variability; HRV; interbeat interval; Parameter sensitivity; peak points; RR interval; State-of-the-art reviews; synthetic signals; the complexity-loss; Time series; Time-frequency analysis
• ISSN: 1949-3045; 1949-3045
• DOI: 10.1109/TAFFC.2020.3031004

Classification of interbeat interval time-series which fluctuates in an irregular and complex manner is very challenging. Typically, entropy methods are employed to quantify the complexity of the time-series for classifying. Traditional entropy methods focus on the frequency distribution of all the observations in a time-series. This requires a relatively long time-series with at least a couple of thousands of data points, which limits their usages in practical applications. The methods are also sensitive to the parameter settings. In this paper, we propose a conceptually new approach called attention entropy , which pays attention only to the key observations. Instead of counting the frequency of all observations, it analyzes the frequency distribution of the intervals between the key observations in a time-series. Attention entropy does not need any parameter to tune, it is robust to the time-series length, and requires only linear time to compute. Experiments show that it outperforms fourteen state-of-the-art entropy methods evaluated by real-world datasets. It achieves average classification accuracy of AUC = 0.71 while the second-best method, multiscale entropy, achieves AUC = 0.62 when classifying four groups of people with a time-series length of 100.