IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 9 - Issue 11, November 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Analysis Of Respiratory Signal For Anxiety Disorder Identification

[Full Text]

 

AUTHOR(S)

H. Haritha, C. Santhosh Kumar, A. Anand Kumar

 

KEYWORDS

Anxiety Disorder Identification, Machine Learning, RRV, Respiratory Signal, SVM.

 

ABSTRACT

Anxiety disorder identification (ADI) is becoming increasingly important in addressing mental health across the population. Traditionally, ECG has been found to be effective as a means to estimate stress and anxiety, and the effect of respiratory signal has been considered as undesirable. In this work, we study how respiratory signal can be effectively used for ADI. The data for this study was collected from normal population, subjects with anxiety disorders and regular meditators, at the Department of Neurology and the Department of Psychiatry, Amrita Institute of Medical Sciences (AIMS), Kerala, over a period of 1.5 years. We used respiratory rate variability (RRV) features as input to support vector machine (SVM) classifier for our baseline ADI system. We noticed that the baseline ADI gave very low classification performance, 63.88%, 83.43% and 69.23% absolute respectively, for sensitivity, specificity and accuracy. We observed large within class person specific variations (PSV) in the RRV features among the controls and the effect of these variations in the RRV features is a nuisance factor affecting the performance of the ADI adversely. To minimize the effect of PSV, we explored several techniques such as covariance normalization (CVN) and Fisher vector encoding (FVE), and on combining CVN and FVE (RFE-CVN-FVE-SVM-ADI), we obtained a sensitivity of 91.66% absolute, specificity of 95.23% absolute and accuracy of 92.30% absolute, which is an improvement of 27.78% absolute sensitivity, 11.80% absolute specificity and 23.07% absolute accuracy, over the baseline ADI. The optimum sets of features were selected using recursive feature elimination (RFE) algorithm. Respiratory signal can be effectively used in ADI. The study scientifically establishes the role of meditation and yoga in reducing anxiety and stress disorders, thus helping in the overall wellness of patients with psychiatric disorders, in their speedy recovery.

 

REFERENCES

[1] Haritha, H., Swati Negi, R. Sarath Menon, A. Anand Kumar, and C. Santhosh Kumar. ”Automating anxiety detection using respiratory signal analysis.” In IEEE Region 10 Symposium (TENSYMP), 2017, pp. 1-5. IEEE, 2017.
[2] Zhang, Bo, Yann Morre, Loc Sieler, Ccile Langlet, Benot Bolmont, and Guy Bourhis. ”Reaction time and physiological signals for stress recognition.” Biomedical Signal Processing and Control 38 (2017): 100-107
[3] Ciabattoni, Lucio, Francesco Ferracuti, Sauro Longhi, Lucia Pepa, Luca Romeo, and Federica Verdini. ”Real-time mental stress detection based on smartwatch.” In Consumer Electronics (ICCE), 2017 IEEE International Conference on, pp. 110-111. IEEE, 2017.
[4] Gjoreski, Martin, Hristijan Gjoreski, Mitja Lutrek, and Matja Gams. ”Continuous stress detection using a wrist device: in laboratory and real life.” In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct, pp. 11851193. ACM, 2016.
[5] Dahale, Ajit Bhalchandra, Jaideep C. Menon, and T. S. Jaisoorya. ”A Narrative Review of the Relationship Between Coronary Heart Disease and Anxiety.” Iranian Journal of Psychiatry and Behavioral Sciences 11, no. 3 (2017).
[6] Choi, Jongyoon, and Ricardo Gutierrez-Osuna. ”Removal of respiratory influences from heart rate variability in stress monitoring.” IEEE Sensors Journal 11, no. 11 (2011): 2649-2656.
[7] Lenis, Gustavo, Michael Kircher, Jess Lzaro, Raquel Bailn, Eduardo Gil, and Olaf Doessel. ”Separating the effect of respiration on the heart rate variability using Granger’s causality and linear filtering.” Biomedical Signal Processing and Control 31 (2017): 272-287.
[8] Chang, Chih-Chung, and Chih-Jen Lin. ”LIBSVM: a library for support vector machines.” ACM Transactions on Intelligent Systems and Technology (TIST) 2, no. 3 (2011): 27. G. O. Young, “Synthetic structure of industrial plastics (Book style with paper title and editor),” in Plastics, 2nd ed. vol. 3, J. Peters, Ed. New York: McGraw-Hill, 1964, pp. 15–64.
[9] Louw, Nelmarie, and S. J. Steel. ”Variable selection in kernel Fisher discriminant analysis by means of recursive feature elimination.” Computational Statistics and Data Analysis 51, no.3 (2006): 2043-2055.
[10] Chen, Xue-wen, and Jong Cheol Jeong. ”Enhanced recursive feature elimination.” In icmla, pp. 429-435. IEEE, 2007.
[11] Ramshur, John T. ”Design, evaluation, and application of heart rate variability software (HRVAS).” Master’s thesis. The University of Memphis, Memphis, TN: Master’s thesis (2010).
[12] Simoes, E. A., R. Roark, S. Berman, L. L. Esler, and J. Murphy. ”Respiratory rate: measurement of variability over time and accuracy at different counting periods.” Archives of disease in childhood 66, no. 10 (1991): 1199-1203.
[13] Karlen, Walter, Srinivas Raman, J. Mark Ansermino, and Guy A. Dumont. ”Multiparameter respiratory rate estimation from the photoplethysmogram.” IEEE Transactions on Biomedical Engineering 60, no. 7 (2013): 1946-1953.
[14] Zhai, Jing, and A. R. M. A. N. D. O. Barreto. ”Stress detection in computer users through non-invasive monitoring of physiological signals.” Blood 5, no. 0 (2008).
[15] Toneatto, Tony, and Linda Nguyen. ”Does mindfulness meditation improve anxiety and mood symptoms? A review of the controlled research.” The Canadian Journal of Psychiatry 52, no. 4 (2007): 260-266.
[16] Arlington, VA., 2013. Diagnostic and statistical manual of mental disorders (5th edition).
[17] Vandana, B., Kannan, V., Saraswathy, L.A., Sundaram, K.R., Kumar, H., 2011. Impact of integrated amrita meditation technique on adrenaline and cortisol levels in healthy volunteers. Evidence-Based Complementary and Alternative Medicine, 2011.
[18] Badra, Leslie J., William H. Cooke, Jeffrey B. Hoag, Alexandra A. Crossman, Tom A. Kuusela, Kari U. O. Tahvanainen, and Dwain L. Eckberg, 2001. Respiratory modulation of human autonomic rhythms. American Journal of Physiology-Heart and Circulatory Physiology 280, 2674-2688.
[19] Carry, Pierre-Yves, Pierre Baconnier, Andre Eberhard, Pierre Cotte, Gila Benchetrit, 1997. Evaluation of respiratory inductive plethysmography: accuracy for analysis of respiratory waveforms. Chest 111, 910-915.
[20] Chen, L., Andrew T. Reisner, Andrei Gribok, Thomas M. McKenna, Jaques Reifman, 2009. Can we improve the clinical utility of respiratory rate as a monitored vital sign?. Shock 31, 575-581.
[21] Martinez, J.M., Papp, L.A., Coplan, J.D., Anderson, D.E., Klein, D.F., Gorman, J.M., 1996. Ambulatory monitoring of respiration in panic disorder. Biological Psychology 43, 262-263.