Low complexity single channel ICA architecture design methodology for pervasive healthcare applications

Swati Bhardwaj, Adapa Bhagyaraja, R. Shashank, Pranit Jadhav, Dwaipayan Biswas, Amit Acharyya, Ganesh R. Naik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper, we propose a low-complexity architecture design methodology for the Single Channel Independent Component Analysis (SCICA) algorithm targeting pervasive personalized healthcare. SCICA, unlike the conventional ICA, separates the signal from multiple sources using only a single sensor that has tremendous potential for reducing the number of body-worn sensors. However, such applications are constrained by power consumption limitation due to the battery backup necessitating low-complexity system design and the on-chip area requirement. On the other hand, SCICA, involving computationally intensive stages including ICA, Fast Fourier Transform (FFT), Eigen Value Decomposition (EVD) and k-means clustering, is not possible to be mapped onto the low-complexity architecture directly from the algorithmic level. Hence, in this paper, adopting algorithm-architecture holistic approach, we introduce the Coordinate Rotation Digital Computer (CORDIC) based low-complexity SCICA architecture design methodology suitable for such resource constrained applications. K-means architecture used for low-complex SCICA based on the proposed methodology consumes core silicon area of 0.28mm2 and power of 0.25mW at 1.2 V, 1-MHz frequency using 0.13μm standard cell technology library (TSMC) that is about 50% less than that of the state-of-the art approaches. The functionality has been compared favorably with the conventional SCICA and hardware analysis has also cross-verified the lowcomplexity nature of the proposed methodology.

Original languageEnglish
Title of host publication2016 IEEE International Workshop on Signal Processing Systems (SiPS)
Place of PublicationTexas
PublisherIEEE
Pages39-44
Number of pages6
ISBN (Electronic)9781509033614
ISBN (Print)9781509033621
DOIs
Publication statusPublished - 12 Dec 2016
Externally publishedYes
Event2016 IEEE International Workshop on Signal Processing Systems, SiPS 2016 - Dallas, United States
Duration: 26 Oct 201628 Oct 2016

Publication series

NameIEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
ISSN (Print)1520-6130

Conference

Conference2016 IEEE International Workshop on Signal Processing Systems, SiPS 2016
CountryUnited States
CityDallas
Period26/10/1628/10/16

Keywords

  • CORDIC
  • EVD
  • FFT
  • K-means clustering
  • Pervasive healthcare
  • SCICA

Fingerprint Dive into the research topics of 'Low complexity single channel ICA architecture design methodology for pervasive healthcare applications'. Together they form a unique fingerprint.

  • Cite this

    Bhardwaj, S., Bhagyaraja, A., Shashank, R., Jadhav, P., Biswas, D., Acharyya, A., & Naik, G. R. (2016). Low complexity single channel ICA architecture design methodology for pervasive healthcare applications. In 2016 IEEE International Workshop on Signal Processing Systems (SiPS) (pp. 39-44). (IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation). IEEE. https://doi.org/10.1109/SiPS.2016.15