透過您的圖書館登入
IP:18.217.194.39
  • 學位論文

中醫聞診檢測記錄器之設計

The Design of the Recording Gauge for Chinese Medical Auscultation

指導教授 : 林康平
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


本論文主要研究目的,是以中醫聞診檢測記錄器針對氣虛證型受測者之語音訊號與一般健康之正常人進行分類與辨識。中國傳統醫學以「望、聞、問、切」四診合參,進行臨床病症辨證診斷。聞診方面的診斷,主要以聽聲音與嗅氣味為診斷方法。由於診斷過程往往須憑藉中醫師臨床經驗進行辨症,導致結果不夠客觀且缺乏說服力。 本研究與台北市立聯合醫院中興院區合作,收錄52 名正常人、11 名氣虛患者的語音訊號。以中醫聞診檢測紀錄器,擷取受測者語音訊號之母音/a/聲語音訊號,並以此語音訊號,深入分析聞診氣虛病症聲音參數。本研究以自行設計的中醫聞診檢測紀錄器進行實際人體檢測及驗證。中醫聞診檢測紀錄器之設計以MSP430單晶片微處理器為架構,透過定距麥克風擷取語音訊號,並進行建檔分析。而訊號分析方面,則使用四個語音特徵參數,分別為:過零點平均數、峰谷值變異數、高頻能量比及低頻能量比,進行分析,找出語音訊號差異性。正常與氣虛識別方面,氣虛患者語音波形在副波強度部份明顯較正常人來得弱,並發現兩者語音波形之間,在頻譜能量方面有較顯著差異。分析結果,平均正確率為78%,結果有76% 與中醫師臨床辨證的結果一致。

並列摘要


The main goal of this thesis is to use the Recording Gauge for Chinese Medical Auscultation Examination and Diagnosis to classify and identify the voice signal between the healthy people and the deficiency of vital energy patients. The traditional Chinese Medicine doctor uses the major methods of diagnosis “observing, auscultation and smelling, enquiry and feeling patients’ pulse “to discriminate and diagnose symptoms of a disease clinically. In listening examination, the method used in diagnosis is divided into listening and smelling. Because the diagnosis process usually needs to be judged by the Chinese Medicine doctor with enough clinical experience, it leads to the diagnosis which is not objective. Up to now, the major study in listening examination still emphasizes on analyzing patients’ voices. We collected 63 patients’ voice samples (There were 52 healthy people and 11 deficiency of vital energy patients). We recorded the voice signals of English vowel /a/ and let these signals to be analyzed by 4 deficiency of vital energy disease parameters. We use the Recording Gauge for Chinese Medical Auscultation Examination and Diagnosis to examine and record human data. Our research uses the Recording Gauge for Chinese Medical Auscultation Examination and Diagnosis to examine and record human data. The main structure of the Recording Gauge for Chinese Medical Auscultation Examination and Diagnosis is based on MSP430 microprocessor. The Recording Gauge for Chinese Medical Auscultation Examination and Diagnosis uses its microphone which can fix distance to record voice signals of healthy people and patients, establishes signal files, then analyzes these data. We use four parameters(Average zero-crossing rates, variations in local peaks and valleys, and Spectral energy ratio of high frequency region and low frequency region ) to analyze signals and find difference property of signals. According to recognizing vital energy patients and healthy people, The voice waveform of deficiency of vital energy patients is weaker than healthy people in minor-wave intensity. We also find out that the power spectrum has clear difference between the two voice waveform. As the analysis result, we came up with a 76% accuracy comparing to physician’s diagnosis.

參考文獻


[7].語音訊號應用於中醫過敏性鼻炎病患之研究,黃耀德,中原大學醫學工程所
[1].中醫聞診自動分析-虛證患者語音之分類辨識,林耿弘,中原大學電機工程所.
[8].光體積變化描記圖之心血管功能診斷應用, 詹皓羽, 中原大學
[11].Signal Processing Algorithms In Matlab, Samuel D. Stearns, Ruth A.David, Prentice Hall.
[13].Digital Methods for Signal Analysis, K. Beaucham, C. Yuen, Rainbow-Bridge Book Co.

延伸閱讀