請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41022完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林達德 | |
| dc.contributor.author | Tzu-Cheng Liu | en |
| dc.contributor.author | 劉子誠 | zh_TW |
| dc.date.accessioned | 2021-06-14T17:12:21Z | - |
| dc.date.available | 2008-07-30 | |
| dc.date.copyright | 2008-07-30 | |
| dc.date.issued | 2008 | |
| dc.date.submitted | 2008-07-25 | |
| dc.identifier.citation | 1. 周令儀、周玉芳。1989。心血管系統。初版。台北：牛頓出版公司。
2. 周先樂。2001。人體生理學(上冊)。台北：藝軒圖書出版社。 3. 潘震澤等人 譯。2005。人體生理學。三版。台北：合計圖書出版社。 4. 羅華強。2005。類神經網路-MATLAB的應用。二版。台北：高立圖書有限公司。 5. 蘇何名、林慶正。2002。由「我的心聲」談現代高科技產物-心臟超音波。高醫醫訊月刊 21(9)。 6. 孫殿宜、蔡孟伸。2006。架構於無線感測網路資料收集系統之設計與實現。台北科技大學學報 40(1): 1-16。 7. 林俊良。2007。研發無線感測網路用於居家健康照護。碩士論文。新竹：交通大學電機與控制工程學研究所。 8. 黃仁杰。2007。心音訊號之無線監測與分析系統。碩士論文。台北：台灣大學生物產業機電工程學研究所。 9. 連偉如。2002。腸音訊號處理技術之研究。碩士論文。台南：成功大學醫學工程研究所。 10. 廖偉舜。2002。使用轉換域可適性環境雜訊濾除器之肺音量測系統。碩士論文。台北：台灣大學電機工程研究所。 11. 歐耀中。2005。數位聽診器之心音訊號即時篩選技術研究。碩士論文。桃園：中原大學電機工程學研究所。 12. 陳炳仁。2002。類神經網路ROC曲線的設計方法。碩士論文。高雄：中山大學機械與機電工程研究所。 13. 陳豐元。2005。類神經網路用於輔助聞診辨識系統之研究。碩士論文。台中：逢甲大學自動控制工程研究所。 14. Ahlström, C. 2006. Processing of the phononcardiographic signal: methods for the intelligent stethoscope. In Cooperation with Biomedical Engineering, Sweden. 15. Akay, M., J. L. Semmlow, W. Welkowitz, M. D. Bauer, and J. B. Kostis. 1990. Detection of coronary occlusions using autoregressive modeling of diastolic heart sounds. IEEE Trans Biomed Eng. 37(4): 366-373. 16. Anand, R. S. 2005. PC based monitoring of human heart sounds. Computer and Electrical Engineering 31(2): 166-173. 17. Asada, H. H., K. J. Cho, and S. K. W. Au. 2001. A hybrid wireless stethoscope /telephone system using skin-attached passive microphone for continuous health monitoring and voice communication. MIT Home Automation and Healthcare Consortium, Progress Report 3(1): 1-19. 18. Barschdorf, D., S. Ester, T. Dorsel, and E. Most. 1990. Neural network based multi sensor heart sound analysis. In “Proc. Computers in Cardiology”, 303-306. Chicago. 19. Brown, E. M. 2002. Heart Sound Made Easy. 1st ed. Singapore: Elsevier. 20. Brusco, M., and H. Nazeran. 2004. Digital phonocardiography:a PDA-based approach. In “Proc. 26th International Conference – IEEE/EMBS”, 2299-2302. San Francisco. 21. Brusco, M., and H. Nazeran. 2005. Development of an intelligent PDA-based wearable digital phonocardiograph. In “Proc. 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society”, 3506-3509. Shanghai. 22. Chang Chien, J. R., and C. C. Tai. 2004. The implementation of a bluetooth-based wireless phonocardio-diagnosis system. In “Proc. International Conference on Networking, Sensing & Control”, 1: 170-173. Taipei. 23. DeGroff, C. G., S. Bhatikar, J. Hertzberg, R. Shandas, L. Vaides-Cruz, and R. L. Mahajan. 2001. Artificial neural network-based method of screening heart murmurs in children. Circulation. 103(22): 2711-2716. 24. Domenech-Asensi, G., J. Martinez-Alajarin, R. Ruiz-Merino, and J. A. Lopez-Alcantud. 2006. Synthesis on FPAA of a smart stethoscope analog subsystem. In “Proc. Field Programmable Logic Application”, 1-5. Madrid.. 25. Durand, L. G., and P. Pibarot. 1995. Digital signal processing of the phonocardiogram review of the most recent advancement. Critical Review in Biomedical Engineering. 23: 163-219. 26. Farshchi, S., P. H. Nuyujukian, A. Pesterev, I. Mody, and J. W. Judy. 2006. A TinyOS-enabled MICA2-based wireless neural interface. IEEE Transactions on Biomedical Eng. 53(7): 1416-1424. 27. Faizan, J., P. A. Venkatachalam, and M. H. Ahmad Fadzil. 2006. A signal processing module for the analysis of heart sounds and heart murmur. In “Proc. International MEMS Conference”, 34(1): 1098-1105. 28. Gerbarg, D. S., F. W. J. Holcomb, J. J. Hofler, C. E. Bading, G. L. Schultz, and R. E. Sears. 1962. Analysis of phonocardiogram by a digital computer. Circulation Research 11: 569-576. 29. Gill, D., N. Gavrieli, and N. Intrator. 2005. Detection and identification of heart sounds using homomorphic envelogram and self-organizing probabilistic model. In “Proc. Computers in Cardiology”, 32: 957-960. 30. Groch, M. W., J. R. Domnanovich, and W. D. Erwin. 1992. A new heart sound gating devices for medical imaging. IEEE Transactions on Biomedical Engineering 39(3): 307-310. 31. Guntheroth, W. G. 1992. Musical murmurs. Am. J. Cardiol 69: 840. 32. Gupta, C. N., R. Palaniappan, S. Rajan, S. Swaminathan, and S. M. Krishnan. 2005a. Segmentation and classification of heart sounds. In “Proc. Electrical and Computer Engineering”, 1674-1677. Canadian. 33. Gupta, C. N., R. Palaniappan, and S. Swaminathan. 2005b. Classification of homomorphic segmented phonocardiogram signal using grow and learn network. In “Proc. 27th Engineering in Medicine and Biology Society”, 4251-4254. Shanghai, China. 34. Hanley, J. A., and B. J. McNeil. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29-36. 35. Iwata, A., N. Ishii, and N. Suzumura. 1980. Algorithm for detecting the first and the second heart sounds by spectral tracking. Medical and biological engineering and computing 18(1): 19-26. 36. Kahalekar, S.G., S. J. Vaidya, B. E. Shrawagi, and Andharmule. 1995. PC based phonocardio expert system. In “Proc. 14th Engineering in Medicine and Biology Society”, 2: 64-65. New Delhi, India. 37. Kwok, T. Y., and D. Y. Yeung. 1997. Constructive algorithm for structure learning in feedforward neural networks for regression problems. IEEE Transactions on Neural Network 8(3): 630-644. 38. Lehner, R. J., and R. M. Rangayyan. 1987. A three-channel microcomputer system for segmentation and characterization of the phonocardiogram. IEEE Transactions on Biomedical Engineering 34(6): 485-489. 39. Liang, H., S. Lukkarinen, and I. Hartimo. 1997a. Heart sound segmentation algorithm based on heart sound envelogram. In “Proc. Computers in cardiology”, 105-108. Lund. 40. Liang, H., S. Lukkarinen, and I. Hartimo. 1997b. A heart sound segmentation algorithm using wavelet decomposition and reconstruction. In “Proc. 19th International Conference – IEEE/EMBS”, 4: 1630-1633. Chicago. 41. Liang, H., and I. Hartimo. 1998. A feature extraction algorithm based on wavelet packet decomposition for heart sound signals. In “Proc. IEEE-SP International Symposium”, 93-96. Pittsburgh. 42. Li, H., and J. Tan. 2006. Body sensor network based context aware ORS detection. “In Pro. Pervasive Health Conference and Workshops”, 1-8. Innsbruck. 43. Lo, B., S. Thiemjarus, R. King, and G. Z. Yang. 2005. Body sensor network – a wireless sensor platform for pervasive healthcare monitoring. “In Proc. 3rd International Conference on Pervasive Computing”. 77-80. Munich, Germany. 44. Luisada, A. A. 1982. The Heart Sounds: New Facts and Their Clinical Implications. 1st ed. New York: Praeger. 45. Moghavvemi, M., B. H. Tan, and S. Y. Tan. 2003. A non-invasive PC-based measurement of fetal phonocardiography. Sensor and Actuators A(107): 96-103. 46. Nazeran, H. 2007. Wavelet-based segmentation and feature extraction of heart sound for intelligent PDA-based phonocardiography. Methods of Information in Medicine, Schattauer 46: 135-141. 47. Nicholas, A., E. Khaled, R. G. Fernando, and A. F. Rocio. 2005. Detection of heart murmurs using wavelet analysis and artificial neural networks. Journal of Biomechanical Engineering. 127(6): 889-904. 48. Ning, T., and K. S. Hsieh. 1995. Delineation of systolic murmurs by autoregressive modeling. In “Proc. 21th Annual Northeast Bioengineering Conference”, 19-21. Bar Harbor, ME. 49. Obaidat, M. S. 1993. Phonocardiogram signal analysis: techniques and performance comparison. Journal of Medical Engineering and Technology 17(6): 221-227. 50. Patnaik, D. 2004. Design and development of heart sound monitoring system. IE(I) Journal-CP 84: 56-59. 51. Pelech, A. N. 1998. The cardiac murmur: when to refer? Pediatr Clin North Am. 45: 107-22. 52. Rashid, R. A., H. S. Ch'ng, M. A. Alias, and N. Fisal. 2005. Real time medical data acquisition over wireless ad-hoc network. In “Applied Electromagnetics APACE Conference”, 383-387. Malaysia. 53. Sava, H., and L. G. Durand. 1997. Automatic detection of cardiac cycle based on an adaptive time-frequency analysis of the phonocardiogram. In “Proc. 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society”, 3: 1316-1319. Chicago. 54. Say, O., Z. Dokur, and T. Olmez. 2002. Classification of heart sound by using wavelet transform. In “Proc. 24th Engineering in Medicine and Biology Society”, 1: 128-129. 55. Sharif, Z., S. Daliman, A. Z. Sha’ameri, and S. H. S. Salleh. 2001. An expert system approach for classification of heart sounds and murmurs. In “Proc. Signal Processing and its Applications, Sixth International, Symposium”, 2: 739-740. Kuaia Lumpur. 56. Shamsuddin, N., M. N. Mustafa, S. Husin, and M. N. Taib. 2005. Classification of heart sounds using a multilayer feed-forward neural network. In “Proc. Sensors and the International Conference on new Techniques in Pharmaceutical and Biomedical Research Conference”, 87-90. Malaysia. 57. Shen, M. F., and L. S. Sun. 1995. Modelling and processing of phonocardiogram via parametric bispectral approach. In “Proc. 14th Engineering in Medicine and Biology Society”, 2: 76-77. New Delhi, India. 58. Shino, H., H. Yoshida, K. Yana, K. Harada, J. Sudoh and, E. Harasawa. 1996. Detection and classification of systolic murmur for phonocardiogram Screening. In “Proc. 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society”, 123-124. Amsterdam. 59. Shnayder, V., B. Chen, K. Lorincz, Thaddeus R. F. Fulford-Jones, and M. Welsh. 2005. Sensor networks for medical care. Technical Report TR-08-05, Division of Engineering and Applied Sciences, Harvard University: 1-14. 60. Tamer, Ö., and D. Zümray. 2003. Classification of heart sounds using an artificial neural network. Elsevier Science Inc. Pattern Recognition Letters 24: 617-629. 61. Tilkian, A. G., and M. Boudreau. 2001. Understanding heart sound and murmur: with an introduction to lung sounds. 4th ed. Philadelphia: W.B Saunders Company. 62. Turkoglu, I., and A. Arslan. 2001. An intelligent pattern recognition system based on neural network and wavelet decomposition for interpretation of hearts sounds. In “Proc. 23th Annual International Conference of the IEEE Engineering in Medicine and Biology Society”, 2: 1747-1750. 63. Várady, P., L. Wildt, Z. Benyó, and A. Hein. 2003. An advanced method in fetal phonocardiography. Computer Methods and Programs in Biomedicine 71: 283-296. 64. Zhang, X., L. G. Durand, L. Senhadji, H. C. Lee, and J. L. Coatrieux. 1998. Analysis-synthesis of the phonocardiogram based on the matching pursuit method. IEEE Transaction on Biomedical Engineering 45(8): 962-971. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/41022 | - |
| dc.description.abstract | 本研究針對上一代無線聽診器進行效能提升，並且開發新一代的可攜式智慧型心音聽診系統。此系統包含一個無線聽診裝置與一套心音訊號處理軟體，主要目的為瓣膜性心臟病的自動診斷。無線聽診裝置以MICAz無線感測網路模組為核心，搭配其他自製的模組所構成，包括心音感測模組和雙模式(充電/執行)電源管理模組。相較於前一代裝置，本裝置增加了心音即時監聽功能，也提高了訊號處理電路之頻寬，並將無線傳輸模組之參數最佳化。量測到的心音訊號，可以透過ZigBee無線通訊協定傳輸到個人電腦進行處理。在後端診斷系統中，利用C++ Builder撰寫使用者介面，具有心音訊號時頻域之即時顯示、多種檔案格式之儲存與讀取等功能。此外我們蒐集了網路上的心音資料庫進行分析，在MATLAB程式環境下建立異常心音偵測及心音分類演算法，使用滑動視窗之正規化平均夏儂能量擷取出心音包絡線，並執行心動週期分離以自動化閾值將連續的心音訊號切割出數個單一週期，分割出之心動週期具有93.37%的正確率。接著將心音包絡線轉換至頻域，使用正常心音的頻率特徵建立一個比對樣板，透過樣板比對與相關係數運算來偵測異常心音。在以接受者操作特性曲線(receiver operating characteristic curve, ROC curve)分析兩種方法的整體辨識能力下，兩者差異並不大，都可以用來偵測異常心音，在ROC曲線上選擇一適當閾值當作診斷標準，兩種偵測方法的偵測率分別為82.46%與81.20%。另外，結合心音包絡線特徵和基於短時傅立葉轉換的時頻域統計特徵，透過多層感知器倒傳遞類神經網路進行正常心音、舒張期心雜音及收縮期心雜音分類，其正確率分別為96.67%、94.19%、95.56%。 | zh_TW |
| dc.description.abstract | The objective of this research is to improve the previously developed wireless stethoscope and to develop a newer portable intelligent auscultation system for heart sound signals. The system which includes a wireless auscultation device and a heart sound signal processing software is designed and implemented to diagnose valvular heart disease automatically. The auscultation device is based on a MICAz wireless sensor network module, a heart sound sensing module, and a power management module. For the new auscultation system, real-time heart sound auscultation is added, the bandwidth of signal processing is improved, and the parameters of wireless transmission are also optimized. Heart sound signals can be sent to personal computer via ZigBee communication protocol. The diagnosis system witch is developed with Borland C++ Builder provides some functions, such as displaying real-time heart sound signal in time-frequency domain, and saving and loading different file formats. Besides, two algorithms for abnormal heart sound detection and heart sound classification are constructed in MATLAB by analyzing heart sound samples collected from internet databases. Normalized average Shannon energy with sliding window is applied to extract heart sound envelope, and then the continuous heart sound signal is segmented to individual heart cycles by heart cycle segmentation based on auto-threshold with accuracy of 93.37%. After above procedures, those envelopes are transferred to frequency domain and compared with a pattern constructed from frequency feature of normal heart sounds by pattern matching and correlation coefficient operation for detecting abnormal heart sounds. In this study, receiver operating characteristic curve (ROC curve) is used to analyze the identification ability of two methods. The correlation coefficient operation and pattern matching are similar in the identification capability, and accuracies of abnormal detection are 82.46% and 81.20%, respectively, based on suitable threshold recommended by the ROC curve. Furthermore, the multiple layer perceptron back-propagation (MLP-BP) neural network is used as a heart sound classification algorithm. The input of this neural network is heart sound envelope feature which combines statistic information of time-frequency domain based on short-time Fourier transform (STFT). The neural network can classify normal heart sound, diastolic murmur, and systolic murmur, with accuracies of 96.67%, 94.19%, and 95.56%, respectively. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-14T17:12:21Z (GMT). No. of bitstreams: 1 ntu-97-R95631012-1.pdf: 7847859 bytes, checksum: 9838b5210f492788b5d540135b6bd14b (MD5) Previous issue date: 2008 | en |
| dc.description.tableofcontents | 目錄
誌謝 i 摘要 ii ABSTRACT iii 目錄 v 圖目錄 vii 表目錄 x 第一章 緒論 1 1.1前言 1 1.2研究背景 3 1.3研究目的 5 第二章 文獻探討 8 2.1心音概論 8 2.1.1心臟結構 8 2.1.2心音的產生 9 2.1.3心雜音的產生 10 2.1.4心音的頻率特性 12 2.2聽診系統的發展 13 2.2.1聽診器與心音圖 13 2.2.2新一代聽診系統 17 2.3數位心音訊號處理 20 2.3.1數位心音訊號處理概論 21 2.3.2心音成份分離 22 2.3.3心音特徵擷取 25 2.3.4心音模型建立與辨識 27 2.4無線感測網路概論 28 2.4.1無線感測網路與TinyOS簡介 28 2.4.2無線感測網路在醫療上的應用 29 第三章 研究設備與方法 31 3.1系統描述 31 3.2無線聽診裝置 32 3.2.1心音感測模組 33 3.2.2 MICAz無線傳輸模組 39 3.2.3電源管理模組 41 3.3自動診斷系統 43 3.3.1 MICAz無線接收模組與MIB510介面板 44 3.3.2心音分析軟體 45 3.4系統性能測試規劃 46 3.4.1無線聽診裝置測試 46 3.4.2無線傳輸效能評估 47 3.5異常心音偵測 50 3.5.1心音訊號前處理 52 3.5.2心音包絡線擷取 54 3.5.3心動週期分離 56 3.5.4偵測系統建立 58 3.6心音分類 60 3.6.1時頻域綜合特徵擷取 60 3.6.2分類系統建立 63 第四章 結果與討論 65 4.1系統性能分析結果 65 4.1.1無線聽診裝置測試結果 65 4.1.2無線傳輸效能結果 69 4.2系統成品 76 4.2.1無線聽診裝置 76 4.2.2自動診斷系統 80 4.2.3實際量測人體心音訊號 82 4.3異常心音偵測結果 83 4.3.1心音訊號前處理結果 83 4.3.2心音包絡線擷取結果 84 4.3.3心動週期分離結果 87 4.3.4偵測結果 91 4.4心音分類結果 99 4.4.1心音包絡線波形特徵擷取結果 99 4.4.2心音包絡線波形特徵分類結果 100 4.4.3時頻域統計特徵擷取結果 101 4.4.4時頻域統計特徵分類結果 107 4.4.5時頻域綜合特徵分類結果 108 第五章 結論與建議 109 5.1結論 109 5.2建議 111 參考文獻 112 圖目錄 圖2-1 人體心臟示意圖 9 圖2-2 心音聽診區域(Brown, 2002) 12 圖2-3 人耳與心音聽力閾值的頻率分佈圖(Várady et al., 2001) 12 圖2-4 心音圖 14 圖2-5 多種生理訊號對應圖(Ahlström, 2006) 16 圖2-6 現代聽診系統的發展重點 17 圖2-7 心音訊號處理方塊圖 22 圖2-8 心音訊號的主要成份圖 23 圖2-9 類神經網路架構圖 27 圖3-1 智慧型心音聽診系統架構圖 31 圖3-2 無線聽診裝置(HSmote)架構圖 32 圖3-3 CK-M600GP型聽診器 33 圖3-4 心音擷取單元電路圖 34 圖3-5 前級放大器電路圖 35 圖3-6 Sallen-Key二階主動式低通濾波器電路圖 36 圖3-7 音頻放大電路圖 37 圖3-8 心音感測模組的完整電路圖 38 圖3-9 MICAz無線傳輸模組實體圖 39 圖3-10 MICAz無線傳輸模組規格介紹 39 圖3-11 Cygwin開發環境 40 圖3-12 電源管理模組電路圖 42 圖3-13 自動診斷系統(HSanalyser)架構圖 43 圖3-14 MIB510介面板實體圖 44 圖3-15 心音分析軟體架構圖 46 圖3-16 無線傳輸效能之實驗架構圖 49 圖3-17 心音訊號處理完整架構圖 51 圖3-18 心音檔案類別之使用分配圖 52 圖3-19 不同心音包絡線擷取方法比較圖 54 圖3-20 滑動視窗示意圖 55 圖3-21 心動週期分離演算法 57 圖3-22 建立比對樣板與比對閾值流程圖 59 圖3-23 異常心音偵測方法流程圖 59 圖3-24 時頻域綜合特徵擷取流程圖 62 圖3-25 正切雙彎曲轉移函數 64 圖3-26 線性轉移函數 64 圖4-1 心音擷取單元測試結果圖 65 圖4-2 前級放大電路之輸出入波形圖 66 圖4-3 前級放大電路之頻率響應圖 67 圖4-4 Sallen-Key二階主動低通濾波器之頻率響應圖 68 圖4-5 訊號處理單元之頻率響應圖 68 圖4-6 無線傳輸測試介面 69 圖4-7 Set_1頻率-相關係數圖 75 圖4-8 Set_2頻率-相關係數圖 75 圖4-9 Set_3頻率-相關係數圖 75 圖4-10 Set_4頻率-相關係數圖 75 圖4-11 心音擷取單元實體圖 76 圖4-12 訊號處理單元實體圖 76 圖4-13 音頻放大單元實體圖 77 圖4-14 MICAz無線傳輸模組實體圖 77 圖4-15 電源管理模組實體圖 77 圖4-16 心音擷取單元與訊號處理單元結合圖 78 圖4-17 訊號處理單元與音頻放大單元結合圖 78 圖4-18 MICAz模組與訊號處理單元、音頻放大單元之結合圖 78 圖4-19 HSmote之頂層實體圖 79 圖4-20 HSmote之底層實體圖 79 圖4-21 HSmote完整實體圖 79 圖4-22 HSanalyser之心音分析軟體 80 圖4-23 HSanalyser之各項參數設定表單 81 圖4-24 HSanalyser之各項分析結果表單 81 圖4-25 實際量測人體心音訊號圖 82 圖4-26 加入四種不同等級雜訊的正常心音訊號時頻域圖 83 圖4-27 Butterworth低通濾波器頻率響應圖 84 圖4-28 正常心音封包絡線擷取結果圖(例1) 85 圖4-29 正常心音包絡線擷取結果圖(例2) 85 圖4-30 異常心音包絡線擷取結果圖(例1) 86 圖4-31 異常心音包絡線擷取結果圖(例2) 86 圖4-32 正常心音之心動週期分離結果圖(例1) 88 圖4-33 正常心音之心動週期分離結果圖(例2) 88 圖4-34 異常心音之心動週期分離結果圖(例1) 89 圖4-35 異常心音之心動週期分離結果圖(例2) 89 圖4-36 心音包絡線之頻率特徵圖 92 圖4-37 所有正常心音特徵與比對樣板圖 92 圖4-38 未加入雜訊之正常心音診斷指標分佈圖(使用樣板比對計算) 93 圖4-39 未加入雜訊之正常心音診斷指標分佈圖(使用相關係數計算) 93 圖4-40 樣板比對之診斷指標分佈圖 95 圖4-41 相關係數運算之診斷指標分佈圖 95 圖4-42 樣板比對與相關係數運算之ROC曲線圖 97 圖4-43 三類型心音包絡線擷取結果圖 100 圖4-44 心音包絡線特徵-決定隱藏層神經元個數測試圖 101 圖4-45心音包絡線特徵-網路訓練次數與均方差之關係圖 101 圖4-46 正常心音之時頻域統計特徵擷取結果圖 102 圖4-47 舒張期心雜音之時頻域統計特徵擷取結果圖 103 圖4-48 收縮期心雜音之時頻域統計特徵擷取結果圖 104 圖4-49 低頻部分之收縮期與舒張期統計特徵分佈圖 106 圖4-50 高頻部分之收縮期與舒張期統計特徵分佈圖 106 圖4-51 時頻域統計特徵-決定隱藏層神經元個數測試圖 107 圖4-52 時頻域統計特徵-網路訓練次數與均方差之關係圖 107 圖4-53 時頻域綜合特徵-決定隱藏層神經元個數測試圖 108 圖4-54 時頻域綜合特徵-網路訓練次數與均方差之關係圖 108 表目錄 表1-1 96年度國人死因統計列表(衛生署，2008) 2 表1-2 市面上之新型聽診器的網站連結列表 4 表3-1 無線傳輸效能之測試參數表 50 表3-2 心音資料庫網路連結參考表 50 表3-3 心音訊號之檔案格式正規化參數表 53 表3-4 目標樣板分配表 64 表4-1 MICAz無線傳輸模組之參數組合定義表 70 表4-2 Set_1與Set_2之測試結果 70 表4-2 Set_1與Set_2之測試結果(續) 71 表4-3 Set_3與Set_4之測試結果 72 表4-3 Set_3與Set_4之測試結果(續) 73 表4-4 人工訊號的頻率資料表 74 表4-5 Set_1與Set_2的相關係數指標定義表 74 表4-6 Set_3與Set_4的相關係數指標定義表 74 表4-7 以相關係數評估訊號還原程度結果表 74 表4-8 心音訊號之心動週期分離結果統計表 90 表4-9 心音封包的心動週期長度統計表(單位：資料點) 91 表4-10 未加入雜訊之正常心音進行比對程序比較表 94 表4-11 ROC曲線相關名詞定義表 96 表4-12 樣板比對偵測結果表 (msse: 0.1758) 98 表4-13 相關係數運算偵測結果表 (mcc: 0.9577) 98 表4-14 類神經網路之資料分配表 99 表4-15 心音包絡線波形特徵之分類結果 101 表4-16 時頻域統計特徵之分類結果 107 表4-17 時頻域綜合特徵之分類結果 108 | |
| dc.language.iso | zh-TW | |
| dc.title | 可攜式智慧型心音聽診系統 | zh_TW |
| dc.title | A Portable Intelligent Auscultation System
for Heart Sound Signals | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 96-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 江昭皚,鄭宗記 | |
| dc.subject.keyword | 智慧型聽診系統,無線感測網路,心音訊號處理,特徵擷取, | zh_TW |
| dc.subject.keyword | intelligent auscultation system,wireless sensor network,heart sound signal processing,feature extraction, | en |
| dc.relation.page | 115 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2008-07-28 | |
| dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
| dc.contributor.author-dept | 生物產業機電工程學研究所 | zh_TW |
| 顯示於系所單位： | 生物機電工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-97-1.pdf 目前未授權公開取用 | 7.66 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。