Total views : 217

Comparative Analysis of DTW based Outlier Segregation Algorithms for Wrist Pulse Analysis

Affiliations

  • UIET, Panjab University, Chandigarh – 160014, Punjab, India
  • BBSBEC Fatehgarh Sahib, Chandigarh – 140407, Punjab, India
  • Central Scientific Instruments Organisation (CSIRCSIO), Chandigarh – 160030, Punjab, India

Abstract


Background/Objectives: Quantification of Wrist Pulse Signals is helpful to take benefit of ancient approach i.e. Pulse Diagnosis. The objective of this paper is to effectively segregate outliers present within wrist pulses. Methods/Statistical Analysis: This work presents modification in Dynamic Time Warping (DTW) algorithm. The existing DTW algorithm searches for an optimal path using squared Euclidean distance to measure the local distance between segments. Here, we are discussing and integrating different local distance measures such as Correlation Distance, Manhattan Distance, Kendall’s τ Distance and Canberra Distance with DTW. All the discussed local distance measures were compared with existing Euclidean based DTW algorithm on the basis of Similarity Index parameter. Findings: Results shown that Manhattan Distance and Canberra Distance based DTW algorithm was efficient in optimal path selection and segregation of segments which lose their shape characteristics. In euclidean based DTW, outlier segregation was difficult as all values lied between 0 to 1.Correlation distance and Kendall’s tau distance algorithm were inappropriate in detecting outliers as results were not matched with visual observations. It was noticed that combination of Manhattan Distance and Canberra Distance based DTW algorithm were giving better outlier finding.

Keywords

Canberra Distance, DTW, Euclidean Distance, Manhattan Distance, Similarity Index, Wrist Pulse outliers.

Full Text:

 |  (PDF views: 153)

References


  • Thakkar S, Thakker B. Wrist Pulse Acquisition and Recording System. Communications on Applied Electronics (CAE). Foundation of Computer Science FCS, New York, USA. 2015 Apr; 1(6). ISSN: 2394-4714.
  • Kyung-Won K, Woo-Gwun N. Comparison of Pulse Diagnosis in Oriental and Western Medicine. Indian Journal of Science and Technology. 2015 Aug; 8(18).
  • Abhinav, Sareen M, Kumar M, Jayashree. Nadi yantra: a robust system design to capture the signal from the radial artery assessment of the autonomic nervous system. Journal of Biomedical Science and Engineering. 2009; 471–9.
  • Bisht A, Garg N. Quantification of wrist pulse signal : An Overview. Proceedings of 4th international conference on Advancements in Engineering and Technology ICAET.2016.
  • Wang D, Zhang D, Lu G. A robust signal pre-processing framework for wrist pulse analysis. Biomedical Signal Processing and Control. 2016; 23:62–75.
  • Xia C, Li Y, Yan J, Wang Y, Yan H, Guo R. A practical approach to wristpulse segmentation and single-period average waveform estimation. Int Conf BioMed Eng Inf 2008. BMEI 2008. 2008. p. 334–8.
  • Xia C, Li Y, Yan J, Wang Y, Yan H, Guo R, Li F. A Practical Approach to Wrist Pulse Segmentation and Single-period Average Waveform Estimation. International Conference on BioMedical Engineering and Informatics. 2008.
  • Magdy AK, Khadragi A, Saeb M, Baith Mohamed A.Analysis of DNA Signal Representation Applying Dynamic Time Warping (DTW) and Derivative Dynamic Time Warping (DDTW). The International Journal of Computer Science and Communications Security (IJCSCS). 2013 Jan; 3.
  • Thakkar B, Vyas AL. Outlier pulse Detection and Feature extraction for wrist pulse analysis. International Conference on Biological Science and Technologies (ICBST). 2009 Jul; 3.
  • Available from: https://lemonzi.files.wordpress.com/2013/ 01/dtw.pdf
  • Akila A, Chandra E. Slope Finder – A Distance Measure for DTW based Isolated Word Speech Recognition.International Journal of Engineering and Computer Science. 2013 Dec; 2(12).
  • Available from: http://mmc.tudelft.nl/sites/default/files/ DTW-vASCI.pdf.
  • Wang L , Wang K-Q, Xu L-S. Recognizing wrist pulse waveforms with improved dynamic time warping algorithm.Proceedings of 2004 International Conference on Machine Learning and Cybernetics. 2004; 6.
  • Islam MK, Haque ANMM, Tangim G, Ahammad T, Khondokar MRH. Study and Analysis of ECG Signal Using MATLAB and LABVIEW as Effective Tools. International Journal of Computer and Electrical Engineering. 2012 Jun; 4(3).
  • Wang D, Zhang D. Analysis of pulse waveforms preprocessing.2012 International Conference on Computerized Healthcare (ICCH). 2012 Dec 17-18. p. 175–80.
  • Jayant A, Singh T, Kaur M. Different techniques to remove baseline wander from ECG signal. International Journal of Emerging Research in Management and Technology. 2013 Jun; 2.
  • Mishra U, Verma L. Noise Removal from ECG Signal by Thresholding with Comparing Different Types of Wavelet.International Journal of Application or Innovation in Engineering and Management. 2014 Mar; 3(3).
  • Wang D, Zhang D, Chan JCN. Feature Extraction of Radial Arterial Pulse. International Conference on Medical Biometrics. 2014May-Jun. p. 41–6.
  • Thakker B, Vyas AL, Tripathi DM. Time and Frequency Domain Analysis of Wrist Pulse Signals. International Journal of Biomedical Engineering and Technology (IJBET), Inderscience Publishers. 2014; 15(3):273–87.
  • Vasimalla K, Challa N, Naik S. Efficient Dynamic Time Warping for Time Series Classification. Indian Journal of Science and Technology. 2016 Jun; 9(21).
  • Cha S-H. Comprehensive Survey on Distance/Similarity Measures between Probability Density Functions.International Journal of Mathematical Models and Methods in Applied Sciences. 2007; 1(4).
  • Lascu M, Lascu D. LabVIEW Based Biomedical Signal Acquisition and Processing. Proceedings of the 7th WSEAS Int Conf on Signal Processing, Computational Geometry and Artificial Vision, Athens, Greece. 2007Aug 24-26.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.