簡易檢索 / 詳目顯示

研究生: 陳維盛
Wisena - Aditya Tanumihardja
論文名稱: 基於噪音協助多元經驗模態分析之肺心音分離
LUNG-HEART SOUND SEPARATION USING NOISE ASSISTED MULTIVARIATE EMPIRICAL MODE DECOMPOSITION
指導教授: 林敬舜
Ching-Shun Lin
口試委員: 吳乾彌
Chen-Mie Wu
陳維美
Wei-Mei Chen
林淵翔
Yuan-Hsiang Lin
王煥宗
Huan-Chun Wang
學位類別: 碩士
Master
系所名稱: 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年: 2013
畢業學年度: 101
語文別: 英文
論文頁數: 87
中文關鍵詞: Breath sound recordingsLung sound extractionEmpirical mode decompositionEnsemble empirical mode decompositionMultivariate empirical mode decompositionNoise-assisted multivariate EMD
外文關鍵詞: Breath sound recordings, Lung sound extraction, Empirical mode decomposition, Ensemble empirical mode decomposition, Multivariate empirical mode decomposition, Noise-assisted multivariate EMD
相關次數: 點閱:248下載:2
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • Separating lung sound (LS) in heart sound (HS)-interfered recordings has been of interest to doctors and researchers in the last two decades. Many
    algorithms have been developed to solve this question, one of them
    is based on the empirical mode decomposition (EMD). Due to the
    notorious mode mixing issue in the standard EMD, in this study we survey
    LS extraction based on EMD extensions, including ensemble EMD
    (EEMD), multivariate EMD (M-EMD), and noise assisted M-EMD
    (NAM-EMD). The algorithm for LS extraction is composed of heart sound (HS) segmentation, LS separation, and components reconstruction. The performance evaluation by auditory, visual, and numerical analyses reveals that NAM-EMD with brown noise as noise assisted data is the most suitable method for LS separation algorithm among the standard EMD and other EMD extensions.


    Separating lung sound (LS) in heart sound (HS)-interfered recordings has been of interest to doctors and researchers in the last two decades. Many
    algorithms have been developed to solve this question, one of them
    is based on the empirical mode decomposition (EMD). Due to the
    notorious mode mixing issue in the standard EMD, in this study we survey
    LS extraction based on EMD extensions, including ensemble EMD
    (EEMD), multivariate EMD (M-EMD), and noise assisted M-EMD
    (NAM-EMD). The algorithm for LS extraction is composed of heart sound (HS) segmentation, LS separation, and components reconstruction. The performance evaluation by auditory, visual, and numerical analyses reveals that NAM-EMD with brown noise as noise assisted data is the most suitable method for LS separation algorithm among the standard EMD and other EMD extensions.

    Abstract i Contents ii List of Tables iv List of Figures v 1 Introduction 1 1.1 Backgrounds and Aim . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Scope of Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2 Empirical Mode Decomposition and Its Extensions 5 2.1 Empirical Mode Decomposition . . . . . . . . . . . . . . . . . . . . . 6 2.2 Ensemble EMD . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.3 Multivariate EMD . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.4 Noise Assisted Multivariate EMD . . . . . . . . . . . . . . . . . . . . 21 3 Color Noise 24 3.1 White Noise . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.2 Pink Noise . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 3.3 Brown Noise . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4 LS Separation Algorithm 35 4.1 HS-Localization Technique . . . . . . . . . . . . . . . . . . . . . . . . 35 4.2 LS Separation and Reconstruction . . . . . . . . . . . . . . . . . . . . 38 4.2.1 Standard EMD and EEMD Based Algorithm . . . . . . . . . . 38 4.2.2 M-EMD and NAM-EMD Based Algorithm . . . . . . . . . . . 40 5 Experimental Results 45 5.1 Experimental Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 5.2 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 6 Conclusion and Future Research 59 References 61 Appendix A Signal Spectrum Dependent Noise 67

    [1] W. K. Blake, Mechanics of Flow-Induced Sound and Vibration. Orlando, FL: Academic Press, 1986.
    [2] J. C. Hardin and J. L. Patterson, “Monitoring the state of the human airways by analysis of respiratory sound,” Acta Astronautica, vol. 6, no. 9, pp. 1137-1151, Sep. 1979.
    [3] I. V. Vovk, V. T. Grinchenko, and V. N. Oleinik, “Modeling the acoustic properties of the chest and measuring breath sounds,” Acoustical Physics, vol. 41, no. 5, pp. 667-676, 1995.
    [4] N. Gavriely, Y. Palti, and G. Alroy, “Spectral characteristics of normal breath sounds,” J. Applied Physiology, vol. 50, no. 2, pp. 307-314, Feb. 1981.
    [5] A. Sovijarvi, L. Malmberg, G Charbonneau, J. Vanderschoot, F. Dalmasso, C. Sacco, M. Rossi, and J. Earis, “Characteristic of breath sounds and adventitious respiratory sounds,” Eur. J. Respiratory Review, pp. 591596, 2000.
    [6] G. R. Manecke, J. P. Dilger, L. J. Kutner, and P. J. Poppers, “Auscultation revisited: The waveform and spectral characteristics of breath sounds during general anesthesia,” Int. J. Clinical Monitoring and Computing, vol. 14, no. 4, pp. 231-240, Nov. 1997.
    [7] N. Gavriely, M. Nissan, A. H. Rubin, and D. W. Cugell, “Spectral characteristics of chest wall breath sounds in normal subjects,” Thorax, vol. 50, no. 12, pp. 1292-1300, Dec. 1995.
    [8] I. Hossain and Z. Moussavi, “Relationship between airow and normal lung sounds,” Proc. IEEE Int. Conf. Engineering Medicine and Biology Society, vol. 2, pp. 11201122, Oct. 2002.
    [9] N. Gavriely and D. W. Cugell, “Airflow effects on amplitude and spectral content of normal breath sounds,” J. Applied Physiology, vol. 80, no. 1, pp. 5-13, Jan. 1996.
    [10] A. A. Luisada, “The areas of auscultation and the two main heart sounds,” Med. Times, vol. 92, pp. 811, Jan. 1964.
    [11] J. Gnitecki and Z. M. K. Moussavi, “Separating heart sounds from lung sounds: Accurate diagnosis of respiratory disease depends on understanding noises,” IEEE Mag. Engineering Medicine and Biology, vol. 26, No. 1, pp. 20-29.
    [12] P. J. Arnott, G. W. Pfeiffer, and M. E. Tavel, “Spectral analysis of heart sounds: Relationships between some physical characteristics and frequency spectra of first and second heart sounds in normals and hypertensives,” J. Biomedical Engineering, vol. 6, no. 2, pp. 121-128, Apr. 1984.
    [13] H. Pasterkamp, S. S. Kraman, and G. R. Wodicka, “Respiratory sounds: Advances beyond the stethoscope,” Amer. J. Respiraroty and Critical Care Medicine, vol. 156, No. 3, pp. 974-987, 1997.
    [14] M. T. Pouzard, Z. K. Moussavi, and G. Thomas, “Heart sound cancelation from lung sound recordings using adaptive threshold and 2D interpolation in time-frequency domain,” Proc. IEEE Int. Conf. Engineering Medicine and Biology Society, vol. 3, pp. 2586-2589, Sep. 2003.
    [15] V. K. Iyer, P. A. Ramamoorthy, H. Fan, and Y. Ploysongsang, “Reduction of heart sounds from lung sounds by adaptive filtering,” IEEE Trans. Biomedical Engineering, vol. BME-33, no. 12, pp. 1141-1154, Dec. 1986.
    [16] J. Gnitecki, I. Hossain, H. Pasterkamp, and Z. Moussavi, “Qualitative and quantitative evaluation of heart sound reduction from lung sound recordings,” IEEE Trans. Biomedical Engineering, vol. 52, pp. 1788-1792, Oct. 2005.
    [17] M. Kompis and E. Russi, “Adaptive heart noise reduction of lung sounds recorded by a single microphone,” Proc. IEEE Int. Conf. Engineering Medicine and Biology Society, vol. 2, pp. 691-692, Oct. 1992.
    [18] M. T. Pourazad, Z. Moussavi, F. Farahmand1, and R. K. Ward, “Heart sounds separation from lung sounds using independent component analysis,” Proc. IEEE Int. Conf. Engineering Medicine and Biology Society, pp. 2736-2739, Jan. 2006.
    [19] F. Ayari, M. Ksouri, and A. T. Aulani, “Lung sound extraction from mixed lung and heart sounds FASTICA algorithm,” IEEE Conf. Mediterranean Electrotechnical, pp. 339-342, Mar. 2012.
    [20] A. Mondal, P. S. Battacharya, and G. Saha, “Reduction of heart sound interference from lung sound signals using empirical mode decomposition technique,” J. Medical Engineering and Technology, vol. 35, pp. 344-353, Aug. 2011.
    [21] N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N. C. Yen, C. C. Tung, and H. H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Proc. Royal Society A, vol. 454, pp. 903-995, 1997.
    [22] T. Schlurmann. “The empirical mode decomposition and the Hilbert spectra to analyze embedded characteristic oscillations of extreme waves,” Proc. Ifremer Rogue Waves, pp. 157-165, Nov. 2000.
    [23] Z. Wu and N. E. Huang, “Ensemble empirical mode decomposition: A noise-assisted data analysis method,” Advances in Adaptive Data Analysis, vol. 1, no. 1, pp. 1-41, 2009.
    [24] N. Rehman and D. P. Mandic, “Multivariate empirical mode decomposition,” Proc. The Royal Society A, vol. 466, no. 2117, pp. 1291-1302, 2010.
    [25] N. Rehman and D. P. Mandic, “Filter bank property of multivariate empirical mode decomposition,” IEEE Trans. Signal Processing, vol. 59, no. 5, pp. 2421-2426, 2011.
    [26] F. Caglar and I. Y. Ozbek, “Heart sound localization in chest sound using convex-hull algorithm,” IEEE Int. Conf. Electrical and Electronics Engineering, pp. 319-322, Dec. 2011.
    [27] N. J. Kasdin, “Discrete simulation of colored noise and stochastic processes and 1/f power law noise generation,” Proc. IEEE, vol. 83, no. 5, pp. 802-827, May 1995.
    [28] C. S. Lin, J. S. Wang, and Z. C. Cheng, “Fast ensemble empirical mode decomposition for speech-like signal analysis using shaped noise addition,” Int. Conf. Interaction Sciences: IT, Human and Digital Content, pp. 112-117, Aug. 2011.
    [29] A. Yadollahi and Z. Moussavi, “A robust method for heart sounds localization using lung sounds entropy,” IEEE Trans. Biomedical Engineering, vol. 53, no. 3, pp. 497-502, Mar 2006.
    [30] F. Jin, F. Sattar, S. G. Razul, and D. Y. T. Goh, “Heart sound localization from respiratory sound using a robust wavelet based approach,” IEEE Int. Conf. Multimedia and Expo, pp. 381-384, 2008.
    [31] H. Shamsi and I. Y. Ozbek, “Heart Sound Localization in Chest Sound Using Temporal Fuzzy C-Means Classification,” IEEE Int. Conf. Engineering Medicine and Biology Society, pp. 5286-5289, Sep. 2012
    [32] “ITU-T Test Signal for Telecommunication Systems”[Online]. Available: http://www.itu.int/net/itu-t/sigdb/menu.aspx.
    [32] “Heart and Lung Sounds: 3M Littmann Stethoscopes” [Online]. Available: http://solutions.3m.com/wps/portal/3M/enUS/3M- Littmann/stethoscope/littmann-learning-institute/heart-lung-sounds/
    [33] “University of Michigan Heart Sound and Murmur Library” [Online]. Available: http://www.med.umich.edu/lrc/psb/heartsounds/

    QR CODE