電機資訊學院: 電子工程學研究所指導教授: 呂學士黃詠揚Huang, Yung-YangYung-YangHuang2017-03-062018-07-102017-03-062018-07-102016http://ntur.lib.ntu.edu.tw//handle/246246/276461中文摘要 隨著全世界人口的高齡化,遠端照護系統也越來越重要,遠端照護使老化人口可以較為方便的接受醫療,而生理訊號的監控亦是遠端照護相當重要的一環,本篇論文主要探討的生理訊號為心音及肺音。 傳統上來講,病患去醫院就診,醫生會使用聽診器來聆聽心音以及肺音,並以聆聽的方式觀察有無異樣,主要依據醫生的經驗進行較為主觀的分析。而在遠端照護系統當中,醫療人員可能會需要取得使用者的心音及肺音以進行分析,病患在家中需要自行選擇聽診器放置的位置,以獲得心音及肺音,但是往往病患沒有這方面經驗,不知道該如何擺放聽診器於正確的位置,我們的情境是在家中的病患可以任意擺放多個聽診器在胸腔上,因為心音及肺音的位置極為相近,如果沒有放置到正確的位置,往往會錄到心肺音的混合訊號,此外,使用者在家中有可能受到環境雜訊的影響,這篇論文要解決的問題有兩個,分離混合的心肺音訊號以得到乾淨的心音以及肺音,以及除去背景噪音,透過我們分離以及除噪的演算法,可以得到乾淨的心音以及肺音,再把這兩種生理訊號回傳回醫院以進行分析。 本篇論文主要在研究各種心肺音分離以及除噪的演算法,並分析各種演算法的優缺點。ABSTRACT Ageing population is a commonly observed phenomenon in most developed countries. Telemedicine system is becoming increasingly important due to the aging population around the world. In a telemedicine system, the monitoring of physiological signal is an important part. This thesis emphasizes on the heart sound and lung sound. Traditionally, patient will go to a hospital to examine their heart function or lung function. Doctor in the hospital use a stethoscope to listen to heart sound or lung sound and analyze the patients’ heart function or lung function mainly base on subjective consciousness. In a telemedicine system, when medical personnel need heart sound or lung sound, patients in their own houses need to place the stethoscope. However, patients might lack of the experiences of placing the stethoscopes in the right positions. In our scenario, patients in their houses will have multiple stethoscopes and all the thing patients need to do is place these stethoscopes randomly on the chest. However, because of the position of heart and lung which is very close from each other, we might record the mixture of heart sound and lung sound. Besides, we still have another problem that patients’ house might be in a noisy environment. Therefore, this thesis mainly deal with these two problems. After our algorithm to separate the mixture of heart sound and lung sound into heart sound and lung sound. After using separation algorithm, we use the denoise algorithm to deal with the problem of noisy environments. After the denoise algorithm, we can get the pure heart sound and lung sound and send both of these signals back to hospitals to analyze. The thesis put emphasis on the separation algorithms and denoise algorithms and also analyze the advantages and the disadvantages of these algorithms.4847525 bytesapplication/pdf論文公開時間: 2021/8/24論文使用權限: 同意有償授權(權利金給回饋學校)心音肺音心肺音分離演算法生理訊號的除噪演算法Heart SoundLung SoundHeart Lung Sound Separation, Separation AlgorithmPhysiological Denoise Algorithm在吵雜環境下完善心肺音分離之探討A Study on Post-filtering Technique for Robust Heart Sound and Lung Sound Separation in Noisy Environmentsthesis10.6342/NTU201602081http://ntur.lib.ntu.edu.tw/bitstream/246246/276461/1/ntu-105-R03943110-1.pdf