Classification of falling asleep states using HRV analysis

• Autorzy: Piotrowski Z. , Szypulska M.

Identyfikatory

DOI

10.1016/j.bbe.2017.02.003

• Języki publikacji: EN

Abstrakty

EN

The article presents the results of studies on drowsiness and drowsiness detection performed using heart rate variability analysis (HRV). The results of those studies indicate that the most significant parameters, from the standpoint of classification of drowsiness are the following parameters of the HRV analysis: the low and high frequency band the ratio of the tachogram power in the LF and HF bands, and the total power distribution. The best detection results were obtained for the following methods, in the following order: the nearest neighborhood with metrics: standardized Euclides and Mahalanobis, the square discriminant analysis, and the Bayesian classifier. In order to classify drowsiness periods, a neural network was also used; it consisted of four inputs, six neurons in the hidden layer, and three outputs, one of which was assigned to one of the accepted classes. In order to obtain the most effective learning, a linear feed forward network was designed using back propagation of errors and the RPROP algorithm. In the case of this type of networks, the achieved accuracy of the individual classes was on the level of 98.7%.

Słowa kluczowe

EN

HRV analysis; falling asleep; discriminant analysis; k nearest neighbors; artificial neural network

PL

analiza HRV; zasypianie; analiza dyskryminacyjna; metoda k najbliższych sąsiadów; sztuczna sieć neuronowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2017
• Tom: Vol. 37, no. 2
• Strony: 290--301
• Opis fizyczny: Bibliogr. 39 poz., rys., tab., wykr.

Twórcy

autor

Piotrowski Z.

• Military University of Technology, Faculty of Electronics, Kaliskiego 2, Warsaw, Poland

autor

Szypulska M.

• Military University of Technology, Faculty of Electronics, Kaliskiego 2, Warsaw, Poland

Bibliografia

• [1] Ann Williamsona, Lombardib David A, Simon Folkardc, Jane Stutts, Courtneyb Theodore K, Connor Jennie L. The link between fatigue and safety. Accid Anal Prevent 2011;43:498–515.
• [2] Di Milia Lee, Smolensky Michael H, Giovanni Costa, Howarth Heidi D, Ohayon Maurice M, Pierre Philip. Demographic factors, fatigue, and driving accidents: An examination of the published literature. Accid Anal Prevent 2011;43:516–32.
• [3] Ogilvie Robert D. The process of falling asleep. Sleep Med Rev 2001;5(3):247–70.
• [4] José Vicente, Pablo Laguna, Ariadna Bartra, Raquel Bailón. Detection of driver's drowsiness by means of HRV analysis. Comput Cardiol 2011;38:89–92.
• [5] Hong Xiao Meng Yan, Jinzhong Song, Yuzhou Yang, Xianglin Yang. Sleep stages classification based on heart rate variability and random forest. Biomed Signal Process Control 2013;8:624–33.
• [6] Alan Jovic, Nikola Bogunovic. Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features. Artif Intell Med 2011;51:175–86.
• [7] Borejda Xhyheri, Olivia Manfrini, Massimiliano Mazzolini, Carmine Pizzi, Raffaele Bugiardini. Heart rate variability today. Progr Cardiovasc Dis 2012;55:321–31.
• [8] Shanshan Yu, Bei Wang, Yujue Wang, Xingyu Wan.Feature Extraction of Vigilance Level Based on Heart Rate Variability of Electrocardiogram; 2011.
• [9] Indra Hermawan, Sakti Alvissalim M, Iqbal Tawakal M, Wisnu Jatmiko. An Integrated Sleep Stage Classification Device Based on Electrocardiograph Signal. ICACSIS; 2012.
• [10] Werteni Hayet, Yacoub Slim.Sleep-Wake Stages Classification Based on Heart Rate Variability; 2012.
• [11] Rogado E, García JL, Barea R, Bergasa LM, López E. Driver Fatigue Detection System; 2009.
• [12] Patel M, Lal SKL, Kavanagh D, Rossiter P. Applying neural network analysis on heart rate variability data to assess driver fatigue; 2011, Australia.
• [13] Murata A, Hiramatsu Y. Evaluation of drowsiness by HRV measure. Proposal of prediction method of low arousal state; 2009, Japan.
• [14] Murata A, Matsuda Y, Moriwaka M, Hayami T. An Attempt to Predict Drowsiness by Bayesian Estimation; 2011.
• [15] Begum S, Ahmed MU, Filla R. Mental State Monitoring System for the Professional Drivers Based on Heart Rate Variability Analysis and Case-based Reasoning; 2012, Sweden.
• [16] Lewicke AT, Sazonovl ES, Corwin MJ, Schuckers SAC. Reliable determination of Sleep versus Wake from heart variability using neural networks; 2005.
• [17] Vicente J, Laguna P, Bartra A, Bailón R. Detection of Driver's Drowsiness by Means of HRV Analysis; 2011, Spain.
• [18] Charbonnier S, Zoubek L, Lesecq S, Chapotot F. Self-evaluated automatic classifier as a decision-support tool for sleep/wake staging; 2011.
• [19] Jovic A, Bogunovic N. Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features; 2011.
• [20] Hayet W, Slim Y. Sleep-Wake Stages Classification Based on Heart Rate Variability; 2012.
• [21] Sainudiin R, Lee D. Computational Statistical Experiments in Matlab; 2011, Christchurch.
• [22] Martinez WL, Martinez AR. Exploratory Data Analysis with MATLAB. CRC Press; 2011.
• [23] Steyvers M. Computional Statistics with Matlab; 2011.
• [24] Patel M, Lal SKL, Kavanagh D, Rossiter P. Applying neural network analysis on heart rate variability data to assess driver fatigue. Expert Syst Appl 2011;38:7235–42.
• [25] Shinar Z, Akselrod S, Dagan Y, Bahara A. Autonomic changes during wake – sleep transition: A heart rate variability based approach; 2006.
• [26] Diaf A, Boufama B, Benlamri R. Non-parametric Fisher's discriminant analysis with kernels for data classification. Pattern Recogn Lett 2013;34:552–8.
• [27] Yun-Chi Yeh, Wen-June Wang, Wun Chiou Che. Cardiac arrhythmia diagnosis method using linear discriminant analysis on ECG signals. Measurement 2009;42:778–89.
• [28] Ahmet Alkan, Mücahid Günay. Identification of EMG signals using discriminant analysis and SVM classifier. Expert Syst Appl 2012;39:44–7.
• [29] Farah Nur Atiqah Francis Abdullah, Salleh Abas Fazly, Rosli Besa. ECG Classification using Wavelet Transform and Discriminant Analysis. International Conference on Biomedical Engineering (ICoBE); 2012.
• [30] Yong Xu, Qi Zhu, Zizhu Fan, Minna Qiu, Yan Chen, Hong Liu. Coarse to fine K nearest neighbor classifier. Pattern Recogn Lett 2013;34:980–6.
• [31] Sierra B, Lazkano E, Irigoien I, Jauregi E, Mendialdua I. K Nearest Neighbor Equality: Giving equal chance to all existing classes. Inform Sci 2011;181:5158–68.
• [32] Yong Xu, Qi Zhu, Zizhu Fan, Minna Qiu, Yan Chen, Liu Hong. Coarse to fine K nearest neighbor classifier. Pattern Recogn Lett 2013;34:980–6.
• [33] Mehmet Aci, Mutlu Avci. K nearest neighbor reinforced expectation maximization method. Expert Syst Appl 2011;38:12585–91.
• [34] Soo Kim Kang, Ho Choi Heung, Soo Moon Chang, Woong Mu Chi. Comparison of k-nearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions. Curr Appl Phys 2011;11:740e745.
• [35] Murata A, Hiramatsu Y. Evaluation of drowsiness by HRV measure. Proposal of prediction method of low arousal state 2009. Japan.
• [36] Murata A, Matsuda Y, Moriwaka M, Hayami T.An Attempt to Predict Drowsiness by Bayesian Estimation; 2011.
• [37] Joo Segyeong, Choi Kee-Joon, Huh Soo-Jin. Prediction of spontaneous ventricular tachyarrhythmia by an artificial neuralnetwork using parameters gleaned from short-term heart rate variability. Expert Syst Appl 2012;39:3862–6.
• [38] Mohan Rai Hari, Anurag Trivedi.ECG Signal Classification using Wavelet Transform and Back Propagation Neural Network; 2012.
• [39] Skibniewski FW, et al. Preliminary results of the LF/HF ratio as an indicator for estimating difficulty level of flight tasks. Aerosp Med Hum Perform 2015;86(6):518–23.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).