Respiratory Signal Analysis using PCA, FFT and ARTFA (A Generalized Comment)
AUTHORS
Varun Gupta,NIT, Kurukshetra
Monika Mitta,
ABSTRACT
Sinus patient are increasing day by day in the world, may be human as well as animals. That’s why today signal analysis has been the need to know the diseases in the patient. Biomedical signal processing has great importance in the life of every human and animals. In absence of biomedical signal processing (BSP) signals cannot be analysed resulting in failure of disease acknowledgment. In this paper we have analysed the respiratory signals of Sinus and Normal Person using principal component analysis (PCA), Fast Fourier Transform (FFT) and Autoregressive Time-Frequency Analysis (ARTFA). PCA is used to derive a relatively small number of decor related linear combinations (principal components) of a set of random zero-mean variables while also retaining the signal information as much as possible. Autoregressive time-frequency analysis allows us to follow the changes in frequencies involved in the signal through time. For this we require to see the frequency changes in time. FFT examine the signal in frequency domain that calculates the spectral function. This paper describes the application of principal component analysis (PCA), a technique allowing the reduction of the data set dimensionality. In this paper we have calculated the variance of First Principal Component and Second Principal Component in Sinus and Normal Person and these are 86.94%, 13.05% and 92.733%, 7.266% respectively.
KEYWORDS
Biomedical signal processing, Principal Component Analysis (PCA), Autoregressive Time-Frequency Analysis (ARTFA), Fast Fourier Transform (FFT), variance.
REFERENCES
[1] A. Hyvarinen, J. Karhunen and E. Oja, “Independent Component Analysis”, John Wiley & Sons Inc., New York, (2001).
[2] R. Vigario, V. Jousmaki, M. Hamalainen, R. Hari, and E. Oja, “Independent component analysis for identification of artifacts in magneto encephalographic recordings”, In Advances in Neural Information Processing Systems, MIT Press, Vol. 10, pp. 229-235, (1998).
[3] S. Makeig, A. J. Bell, T. P. Jung, and T. Sejnowski, “Independent component analysis of electro encephalographic data” Advances in Neural Information Processing Systems, MIT Press, Vol. 8, 145-151, (1996)
[4] G. D. Brown, S. Yamada and T. J Sejnowski, “Independent components analysis (ica) at the neural cocktail party”, Trends in neuroscience, Vol. 24, pp. 54-63, (2001).
[5] P.O. Hoyer and A. Hyvarinen, “Independent component analysis applied to feature extraction fromcolour and stereo images”, Network: Computation in Neural Systems, Vol. 11, pp. 191-210, (2000).
[6] P. Langley, E.J. Bowers, and A. Murray, “Principal Component Analysis as a Tool for Analyzing Beat-to-Beat Changes in ECG Features: Application to ECG-Derived Respiration”, Vol. 57, No. 4, pp. 821-829, (2010).
[7] M Emdin, A Taddei and M Varanini, “Compact Representation of Autonomic Stimulation on Cardiorespiratory Signals by Principal Component Analysis”, (1993).
[8] X. Zhaoyan, X. Shiman and S. Qiuyan. “The Empirical Mode Decomposition Process of nonstationary signals”.
[9] R. Yan and R.X. Gao “A Tour of the Hilbert-Huang Transform: An Empirical Tool for SignalAnalysis”, Vol. 10, No. 5, pp. 40-45, (2007).
[10] V. Gupta, M. Mittal, G. Singh and S. Kumar Pahuja, “Fourier Transform of Untransformable signals using Pattern Recognition Technique”, Indonesia IEEE, (2010).
[11] Z. Huang “A Novel spectral Analysis Method of Atrial Fibrillation Signal Based on Hilbert-HuangTransform”, Vol. 1, pp. 825-828, (2005).
[12] E. Gottlieb and S.M. Armour, “Mitochondrial respiratory control is lost during growth factor deprivation”, Vol. 99, No. 20, pp. 12801-12806, (2002).
[13] A. Otero, “Palliative Performance Status, Heart Rate and Respiratory Rate as Predictive Factors ofSurvival Time in Terminally Ill Cancer Patients”, Vol. 31, pp. 485-492, (2006).
[14] M.P.S. Chawla, “A comparative analysis of principal component and independent component techniques for electrocardiograms”, Neural Computing & Applications, (2008).
[15] M. Taheri, B. Ahmadi, R. Amirfattahi and M. Mansouri, “Assessment of depth of anaesthesia using Principal Component Analysis”, Journal of Biomedical Science and Engineering, Vol. 2, pp. 9-15, (2009).
[16] http://news.mit.edu.
[17] Neural Networks. Theory and Applications, Adaptive and Learning Systems for Signal Processing, Communications and Control, John Wiley & Sons Inc., New York.
[18] M. Turk and A. Pentland, “Eigenfaces for recognition”, Journal of Cognitive Neuroscience, pp.71-86, (1991).
[19] S. Y. Kung, K. Diamantaras, and J. Taur, “Neural networks for extracting pure/constrained/oriented principal components. In J. R. Vaccaro, editor”, SVD and Signal Processing Elsevier Science, Amsterdam, pp. 57-81, (1991).
[20] I. Feigler, “Time frequency analysis of ECG signals,” Computational Biology, (2013).
[21] J.L.A. Carvalho1, A.F. Rocha1, L.F. Junqueira, Jr, J. Souza Neto, I. Santos and F.A.O. Nascimento, “A Tool for Time-Frequency Analysis of Heart Rate Variability”, EMBC, pp. 2574-2577, (2003).
[22] J. Muthuswamy, “BIOMEDICAL SIGNAL ANALYSIS”, The McGraw-Hill Companies, (2004).