# Compressed Domain Feature Extraction

## Abstract

This chapter introduces feature extraction techniques that extract relevant features of interest from compressively sampled biosignals directly from compressed data circumventing the computationally complex reconstruction process. State-of-the-art compressed domain feature extraction process for that leverages on Johnson–Lindenstrauss lemma is presented. It is also shown that such approach is inadequate in the context of feature extraction for compressively sampled photoplethysmogram (PPG) signals. Lomb-Scargle periodogram (LSP) is introduced as an alternate approach for extracting the spectral features from compressively sampled PPG signals, which is then used to estimate the average heart rate (HR) and heart rate variability (HRV). The efficacy of the proposed approach is demonstrated through simulations which indicate that the average HR estimated is accurate within ±5 beats per minute (bpm) while HRV exhibits a correlation coefficient of > 0.90 at 30 × compression ratio (CR) compared to time domain HR and HRV estimation performed on Nyquist sampled PPG signals.

## References

- 10.N. Verma, A. Shoeb, J. Bohorquez, J. Dawson, J. Guttag, A.P. Chandrakasan, A micro-power EEG acquisition SoC with integrated feature extraction processor for a chronic seizure detection system. IEEE J. Solid State Circuits
**45**(4), 804–816 (2010)CrossRefGoogle Scholar - 17.J. Allen, Photoplethysmography and its application in clinical physiological measurement. Physiol. Meas.
**28**(3), R1 (2007)CrossRefGoogle Scholar - 37.G.B. Moody, R.G. Mark, MIT-BIH arrhythmia database (1992) [Online]. Available: https://www.physionet.org/physiobank/database/mitdb/
- 65.F. Ren, D. Marković, 18.5 A configurable 12-to-237kS/s 12.8 mW sparse-approximation engine for mobile ExG data aggregation, in
*2015 IEEE International Solid-State Circuits Conference-(ISSCC) Digest of Technical Papers*(IEEE, Piscataway, 2015), pp. 1–3Google Scholar - 77.P.V. Rajesh, J.M. Valero-Sarmiento, L. Yan, A. Bozkurt, C. Van Hoof, N. Van Helleputte, R.F. Yazicioglu, M. Verhelst, A 172
*μ*W compressive sampling photoplethysmographic readout with embedded direct heart-rate and variability extraction from compressively sampled data, in*2016 IEEE International Solid-State Circuits Conference (ISSCC)*(IEEE, Piscataway, 2016), pp. 386–387Google Scholar - 80.T. Moy, L. Huang, W. Rieutort-Louis, C. Wu, P. Cuff, S. Wagner, J.C. Sturm, N. Verma, An EEG acquisition and biomarker-extraction system using low-noise-amplifier and compressive-sensing circuits based on flexible, thin-film electronics. IEEE J. Solid State Circuits
**52**(1), 309–321 (2017)CrossRefGoogle Scholar - 86.M. Shoaib, Design of energy-efficient sensing systems with direct computations on compressively-sensed data, Ph.D. dissertation, Princeton University, 2013Google Scholar
- 87.A. Csavoy, G. Molnar, T. Denison, Creating support circuits for the nervous system: considerations for brain-machine interfacing, in
*2009 Symposium on VLSI Circuits*(Jun 2009)Google Scholar - 88.J. Yoo, C. Turnes, E.B. Nakamura, C.K. Le, S. Becker, E.A. Sovero, M.B. Wakin, M.C. Grant, J. Romberg, A. Emami-Neyestanak, E. Candes, A compressed sensing parameter extraction platform for radar pulse signal acquisition. IEEE J. Emerging Sel. Top. Circuits Syst.
**2**(3), 626–638 (2012)CrossRefGoogle Scholar - 89.M. Shoaib, N.K. Jha, N. Verma, A compressed-domain processor for seizure detection to simultaneously reduce computation and communication energy, in
*Proceedings of the IEEE 2012 Custom Integrated Circuits Conference*(Sep 2012), pp. 1–4Google Scholar - 90.M. Shoaran, C. Pollo, K. Schindler, A. Schmid, A fully integrated IC with 0.85-
*μ*W/channel consumption for epileptic iEEG detection. IEEE Trans. Circuits Syst. Express Briefs**62**(2), 114–118 (2015)CrossRefGoogle Scholar - 91.A. Jafari, A. Page, C. Sagedy, E. Smith, T. Mohsenin, A low power seizure detection processor based on direct use of compressively-sensed data and employing a deterministic random matrix, in
*2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)*(Oct 2015), pp. 1–4Google Scholar - 92.V.R. Pamula, M. Verhelst, C. Van Hoof, R.F. Yazicioglu, A novel feature extraction algorithm for on the sensor node processing of compressive sampled photoplethysmography signals, in
*SENSORS, 2015 IEEE*(IEEE, Piscataway, 2015), pp. 1–4Google Scholar - 93.V.R. Pamula, System and method for heart rate detection, Jun. 2 2016. US Patent App. 14/938,102Google Scholar
- 94.S. Dasgupta, A. Gupta, An elementary proof of a theorem of Johnson and Lindenstrauss. Random Struct. Algoritm.
**22**(1), 60–65 (2003)MathSciNetCrossRefGoogle Scholar - 95.J.H. Horne, S.L. Baliunas, A prescription for period analysis of unevenly sampled time series. Astrophys. J.
**302**, 757–763 (1986)CrossRefGoogle Scholar - 96.N.R. Lomb, Least-squares frequency analysis of unequally spaced data. Astrophys. Space Sci.
**39**(2), 447–462 (1976)CrossRefGoogle Scholar - 97.P. Laguna, G. Moody, R. Mark, Power spectral density of unevenly sampled heart rate data, in
*Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society*(1995), pp. 157–158Google Scholar - 98.P. Laguna, G. Moody, R. Mark, Power spectral density of unevenly sampled data by least-square analysis: performance and application to heart rate signals. IEEE Trans. Biomed. Eng.
**45**(6), 698–715 (1998)CrossRefGoogle Scholar - 99.W.H. Press, S.A. Teukolsky, W.T. Vetterling, B.P. Flannery,
*Numerical Recipes in C*, vol. 2 (Cambridge University Press, Cambridge, 2002)zbMATHGoogle Scholar - 100.W. Zong, T. Heldt, G. Moody, R. Mark, An open-source algorithm to detect onset of arterial blood pressure pulses, in
*Computers in Cardiology, 2003*(IEEE, Piscataway, 2003), pp. 259–262Google Scholar