Дисертації з теми "Diagnostics of heart sounds"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Diagnostics of heart sounds.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Diagnostics of heart sounds".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Жемчужкіна, Т. В., та Т. В. Носова. "Сonstruction of phase portraits of PCG signals". Thesis, НТУ «ХПІ», 2021. https://openarchive.nure.ua/handle/document/17554.
Повний текст джерелаАнотація:
For PCG signals we constructed phase portraits (PP) in 2-dimensional state space. To demonstrate PP of heart sounds and murmurs we extracted main sounds from PCG signals. Different signals have different forms of PP and samples of main sounds can be separated from rest samples using PP. Showed applications of PP analysis. So, PP of PCG signals probably can be used for diagnostics of heart sounds and for segmentation of PCG signal without simultaneous ECG-recording.
2
Romero-Vivas, Eduardo. "Hidden Markovian models applied to the analysis of heart sounds for diagnostic purposes." Thesis, University of Southampton, 2006. https://eprints.soton.ac.uk/425886/.
Повний текст джерела
3
Leung, Terence Sze-tat. "Time-frequency characterisation of paediatric heart sounds." Thesis, University of Southampton, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.287001.
Повний текст джерела
4
Andersson, Gustav. "Classification of Heart Sounds with Deep Learning." Thesis, Umeå universitet, Institutionen för datavetenskap, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-149699.
Повний текст джерелаАнотація:
Health care is becoming more and more digitalized and examinations of patients from a distance are closer to reality than fiction. One of these examinations would be to automatically classify a patient-recorded audiosegment of its heartbeats as healthy or pathological. This thesis examines how it can be achieved by examining different kinds of neural networks; convolutional neural networks (CNN) and long short-term memory networks (LSTM). The theory of artificial neural networks is explained. With this foundation, the feed forward CNN and the recurrent LSTM-network have their methods described. Before these methods can be used, the required pre-processing has to be completed, which is different for the two types of networks. Using this theory, the process of how to implement the networks in Matlab is explained. Different CNN:s are compared to each other, then the best performing CNN is compared to the LSTM-network. When comparing the two different networks to each other, cross validation is used to achieve the most correct result possible. The networks are compared by accuracy, least amount of training time and least amount of training data. A final resulti s presented, to show which type of network has the best performance, together with a discussion to explain the results. The CNN performed better than the LSTM-network in all aspects. A reflection on what could have been done differently to achieve a better result is posted.
5
Thiyagaraja, Shanti. "Detection and Classification of Heart Sounds Using a Heart-Mobile Interface." Thesis, University of North Texas, 2016. https://digital.library.unt.edu/ark:/67531/metadc1159216/.
Повний текст джерелаАнотація:
An early detection of heart disease can save lives, caution individuals and also help to determine the type of treatment to be given to the patients. The first test of diagnosing a heart disease is through auscultation - listening to the heart sounds. The interpretation of heart sounds is subjective and requires a professional skill to identify the abnormalities in these sounds. A medical practitioner uses a stethoscope to perform an initial screening by listening for irregular sounds from the patient's chest. Later, echocardiography and electrocardiography tests are taken for further diagnosis. However, these tests are expensive and require specialized technicians to operate. A simple and economical way is vital for monitoring in homecare or rural hospitals and urban clinics. This dissertation is focused on developing a patient-centered device for initial screening of the heart sounds that is both low cost and can be used by the users on themselves, and later share the readings with the healthcare providers. An innovative mobile health service platform is created for analyzing and classifying heart sounds. Certain properties of heart sounds have to be evaluated to identify the irregularities such as the number of heart beats and gallops, intensity, frequency, and duration. Since heart sounds are generated in low frequencies, human ears tend to miss certain sounds as the high frequency sounds mask the lower ones. Therefore, this dissertation provides a solution to process the heart sounds using several signal processing techniques, identifies the features in the heart sounds and finally classifies them. This dissertation enables remote patient monitoring through the integration of advanced wireless communications and a customized low-cost stethoscope. It also permits remote management of patients' cardiac status while maximizing patient mobility. The smartphone application facilities recording, processing, visualizing, listening, and classifying heart sounds. The application also generates an electronic medical record, which is encrypted using the efficient elliptic curve cryptography and sent to the cloud, facilitating access to physicians for further analysis. Thus, this dissertation results in a patient-centered device that is essential for initial screening of the heart sounds, and could be shared for further diagnosis with the medical care practitioners.
6
Corona, Blanca Tovar. "Analysis and representation of heart sounds and murmurs." Thesis, University of Sussex, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.299958.
Повний текст джерела
7
Baranek, Humberto Leon. "Automatic detection and identification of cardiac sounds and murmurs." Thesis, McGill University, 1987. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=63754.
Повний текст джерела
8
Marcus, Diveena Seshetta. "Sounds from the heart: Native American language and song." Thesis, Montana State University, 2011. http://etd.lib.montana.edu/etd/2011/marcus/MarcusD0511.pdf.
Повний текст джерелаАнотація:
Our world is witnessing the rapid extinction of indigenous cultures through colonization. This thesis is presented not to amplify decolonization but to honor the value and meaning of the oral society and its indigenous peoples through their culture's traditional and necessary components of language and song. The basis of this thesis pertains to the author's tribal relatives, the Coast Miwok original people of California known as Tamal Michchawmu which literally translates as the People of the West Coast. The author chooses to use this work as an advocacy for the worldview of indigenous peoples, particularly to matriarchal societies in which the Tamal Michchawmu are included. In this thesis, stories and interviews with scholars and with Native Americans studying their language and singing their songs as well as the author's personal experiences are included as support to the theory that language and song are formed from the foundation of a philosophy that is grounded within a peoples relationship with the land. My thesis question is: If this worldview is resurrected, how can it contribute to its indigenous people in a modern society?
9
Tahmasbi, Mohammad Saeed. "VLSI implementation of heart sounds maximum entropy spectral estimation /." Title page, contents and summary only, 1994. http://web4.library.adelaide.edu.au/theses/09ENS/09enst128.pdf.
Повний текст джерела
10
Ewing, Gary John. "A new approacch to the analysis of the third heart sound." Title page, contents and summary only, 1988. http://web4.library.adelaide.edu.au/theses/09SM/09sme95.pdf.
Повний текст джерела
11
Gretzinger, David Theodor Kerr. "Analysis of heart sounds and murmurs by digital signal manipulation." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1996. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/MQ45444.pdf.
Повний текст джерела
12
Bentley, Paul Mark. "Time-frequency analysis of native and prosthetic heart valve sounds." Thesis, University of Edinburgh, 1996. http://hdl.handle.net/1842/10785.
Повний текст джерелаАнотація:
In the past, a number of researchers have applied various spectral estimation techniques in an attempt to analyse recorded heart sounds. The majority of these studies have used spectral estimation algorithms such as the Fourier transform and various autoregressive modelling techniques. Despite the definite potential these techniques have shown for the diagnosis of valvular heart disease, they are limited by their assumption of signal stationary and lack of relation to present stethoscope-based medical evaluation procedures. A solution to these limitations can be achieved by analysing the recorded sounds in the time-frequency domain rather than in the frequency-domain of time-domain independently. The research detailed in this thesis investigates the application of time-frequency techniques to the description and analysis of recorded heart sounds. Time-frequency is further investigated as a tool for the description of heart sounds in an attempt to diagnose valvular heart disease. Data used in the study was recorded from 100 subjects in four main valve populations. The four populations investigated were subjects with native heart valves, Carpentier-Edwards bioprosthetic heart valves, Bjork-Shiley metallic prosthetic heart valves and subjects before and after surgery for heart valve replacement. Prior to the analysis of these data sets, an investigation was performed into the suitability of various time-frequency techniques to the analysis of heart sounds. By comparing the short-time Fourier transform, wavelet transform, Wigner distribution and the Choi-Williams distribution it was found that the Choi-Williams distribution provides definite advantages over the other techniques due to its high resolution and reduced interference properties. Applying the Choi-Williams distribution to typical examples of each data set demonstrated that time-frequency offers definite potential as a heart sound descriptor. Typical results also demonstrate that time-frequency can be used as an aid to understanding the origins of heart sounds.
13
Feng, Shuo. "Designing for Stress Reduction by Connecting Heart Rate to Sounds." Thesis, KTH, Medieteknik och interaktionsdesign, MID, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191454.
Повний текст джерелаАнотація:
With the progress of society, an increasing number of people pay close attention to their health. In this study, we designed a Heart Rate based interactive sound to investigate how biodata-based interactive sounds can affect the well-being of people. We used a variety of approaches to analyzing the data and feedback from users. Firstly, the Trier Social Stress Test protocol was employed as a basis for the test. Also, a package of cultural probes such as photos, diaries and cards were used to collect data from users' everyday life. Recruited by using a snowball sampling technique, five users took and completed the test. From the analysis, we identified problems with our design and realized how to potentially improve the device in the future. The main conclusion that could be drawn was that Heart Rate-based interactive sounds can help users to reduce stress, but that most individuals were more willing to listen to steady sounds in order to relax.I takt med att samhället utvecklas, utvecklas också ett hälsomedvetet tänkande bland samhällets individer. I denna studie designade vi ett ljud baserad på hjärtfrekvens för att undersöka hur ljud baserade på biodata kan påverka välmåendet hos individer. Vi använde oss av en mängd tillvägagångssätt för att analysera data och återkopplingen från användarna. Det så kallade ”Trier Social Stress Test” protokollet utgjorde testets grund. Därtill användes en samling kulturella stimulis som exempelvis foton, dagböcker och kort, vilka användes för att samla data från användarnas vardagliga liv. Fem användare rekryterades genom snöbollsmetoden, och genomförde sedan testet. Utifrån analysen fann vi problem med vår design och insåg hur vi eventuellt kunde förbättra apparaten i framtiden. Den huvudsakliga slutsatsen som kan dras var att ljud baserad på hjärtfrekvens kan hjälpa användare att minska stress, fastän de flesta individer hellre ville lyssna på mer konstanta ljud för att slappna av.
14
Moukadem, Ali. "Segmentation et classification des signaux non-stationnaires : application au traitement des sons cardiaque et à l'aide au diagnostic." Phd thesis, Université de Haute Alsace - Mulhouse, 2011. http://tel.archives-ouvertes.fr/tel-00713820.
Повний текст джерелаАнотація:
Cette thèse dans le domaine du traitement des signaux non-stationnaires, appliqué aux bruits du cœur mesurés avec un stéthoscope numérique, vise à concevoir un outil automatisé et " intelligent ", permettant aux médecins de disposer d'une source d'information supplémentaire à celle du stéthoscope traditionnel. Une première étape dans l'analyse des signaux du cœur, consiste à localiser le premier et le deuxième son cardiaque (S1 et S2) afin de le segmenter en quatre parties : S1, systole, S2 et diastole. Plusieurs méthodes de localisation des sons cardiaques existent déjà dans la littérature. Une étude comparative entre les méthodes les plus pertinentes est réalisée et deux nouvelles méthodes basées sur la transformation temps-fréquence de Stockwell sont proposées. La première méthode, nommée SRBF, utilise des descripteurs issus du domaine temps-fréquence comme vecteur d'entré au réseau de neurones RBF qui génère l'enveloppe d'amplitude du signal cardiaque, la deuxième méthode, nommée SSE, calcule l'énergie de Shannon du spectre local obtenu par la transformée en S. Ensuite, une phase de détection des extrémités (onset, ending) est nécessaire. Une méthode d'extraction des signaux S1 et S2, basée sur la transformée en S optimisée, est discutée et comparée avec les différentes approches qui existent dans la littérature. Concernant la classification des signaux cardiaques, les méthodes décrites dans la littérature pour classifier S1 et S2, se basent sur des critères temporels (durée de systole et diastole) qui ne seront plus valables dans plusieurs cas pathologiques comme par exemple la tachycardie sévère. Un nouveau descripteur issu du domaine temps-fréquence est évalué et validé pour discriminer S1 de S2. Ensuite, une nouvelle méthode de génération des attributs, basée sur la décomposition modale empirique (EMD) est proposée.Des descripteurs non-linéaires sont également testés, dans le but de classifier des sons cardiaques normaux et sons pathologiques en présence des souffles systoliques. Des outils de traitement et de reconnaissance des signaux non-stationnaires basés sur des caractéristiques morphologique, temps-fréquences et non linéaire du signal, ont été explorés au cours de ce projet de thèse afin de proposer un module d'aide au diagnostic, qui ne nécessite pas d'information à priori sur le sujet traité, robuste vis à vis du bruit et applicable dans des conditions cliniques.
15
Visagie, Claude. "Screening for abnormal heart sounds and murmurs by implementing neural networks." Thesis, Stellenbosch : University of Stellenbosch, 2007. http://hdl.handle.net/10019.1/3119.
Повний текст джерелаАнотація:
Thesis (MScEng (Mechanical and Mechatronic Engineering))--University of Stellenbosch, 2007.This thesis is concerned with the testing of an “auscultation jacket” as a means of recording heart sounds and electrocardiography (ECG) data from patients. A classification system based on Neural Networks, that is able to discriminate between normal and abnormal heart sounds and murmurs, has also been developed . The classification system uses the recorded data as training and testing data. This classification system is proposed to serve as an aid to physicians in diagnosing patients with cardiac abnormalities. Seventeen normal participants and 14 participants that suffer from valve-related heart disease have been recorded with the jacket. The “auscultation jacket” shows great promise as a wearable health monitoring aid for application in rural areas and in the telemedicine industry. The Neural Network classification system is able to differentiate between normal and abnormal heart sounds with a sensitivity of 85.7% and a specificity of 94.1%.
16
Tinati, Mohammad Ali. "Time-frequency and time-scale analysis of phonocardiograms with coronary artery disease before and after angioplasty /." Title page, contents and abstract only, 1998. http://web4.library.adelaide.edu.au/theses/09PH/09pht587.pdf.
Повний текст джерела
17
Bedi, Rajan. "Signal processing and frequency analysis of Carpentier-Edwards bioprosthetic heart valve sounds." Thesis, University of Edinburgh, 1994. http://hdl.handle.net/1842/10770.
Повний текст джерелаАнотація:
As a result of the inevitable patient risk associated with the Carpentier-Edwards bioprosthesis, reliable, periodic, post-operative evaluation of the integrity of the implanted valve is essential. The research detailed in this thesis proposes a method whereby diagnostic information concerning the functionality of the valve is extracted from the acoustic output produced by the operation of the prosthesis. This is achieved by analysing the spectral characteristics of the principal heart sound components contained within this acoustic signal. Results show that normally functioning, leaky and stiffening prostheses each exhibit unique spectral characteristics. Normally functioning aortic prostheses are characterised by four to five dominant frequency peaks, with the major concentration of spectral energy occurring in the region between 25Hz and 125Hz. Normally functioning mitral prostheses are characterised by two to three dominant peaks with the major concentration of spectral energy occurring in the region between d.c. and 100Hz. For leaky regurgitant bioprostheses and prostheses diagnosed as having stiffening calcified cusps, a shift was observed in spectral energy. For leaky mitral and aortic prostheses, the major distribution of spectral energy now occurs in the region between d.c. and 75Hz, whereas for stiffening aortic prostheses, the major concentration of spectral energy now occurs in the region between 50Hz and 200Hz. It was observed that the highest frequency which occurs at a level of -10dB below the maximum spectral response (0dB), may be used to discriminate between normally functioning, leaky and stiffening aortic prostheses, where mean frequencies for these conditions at the -10dB level were observed to be 113.6Hz, 53.7Hz and 238.1Hz respectively. A single discriminating parameter was not observed from the analysis of mitral sounds.
18
Daura, Ashiru Sani. "A wavelet-based method for the classification of PCG signals." Thesis, University of Newcastle Upon Tyne, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.244474.
Повний текст джерела
19
Hult, Peter. "Bioacoustic principles used in monitoring and diagnostic applications /." Linköping : Univ, 2002. http://www.bibl.liu.se/liupubl/disp/disp2002/tek778s.pdf.
Повний текст джерела
20
Haghighi-Mood, Ali. "Analysis of phonocardiographic signals using advanced signal processing techniques." Thesis, University of Sussex, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.321465.
Повний текст джерела
21
Vadali, Venkata Akshay Bhargav Krishna. "A Comparative Study of Signal Processing Methods for Fetal Phonocardiography Analysis." Scholar Commons, 2018. https://scholarcommons.usf.edu/etd/7373.
Повний текст джерелаАнотація:
More than one million fetal deaths occur in the United States every year [1]. Monitoring the long-term heart rate variability provides a great amount of information about the fetal health condition which requires continuous monitoring of the fetal heart rate. All the existing technologies have either complex instrumentation or need a trained professional at all times or both. The existing technologies are proven to be impractical for continuous monitoring [2]. Hence, there is an increased interest towards noninvasive, continuous monitoring, and less expensive technologies like fetal phonocardiography.
Fetal Phonocardiography (FPCG) signal is obtained by placing an acoustic transducer on the abdomen of the mother. FPCG is rich in physiological bio-signals and can continuously monitor the fetal heart rate non-invasively. Despite its high diagnostic potential, it is still not being used as the secondary point of care. There are two challenges as to why it is still being considered as the secondary point of care; in the data acquisition system and the signal processing methodologies. The challenges pertaining to data acquisition systems are but not limited to sensor placement, maternal obesity and multiple heart rates. While, the challenges in the signal processing methodologies are dynamic nature of FPCG signal, multiple known and unknown signal components and SNR of the signal.
Hence, to improve the FPCG based care, challenges in FPCG signal processing methodologies have been addressed in this study. A comparative evaluation was presented on various advanced signal processing techniques to extract the bio-signals with fidelity. Advanced signal processing approaches, namely empirical mode decomposition, spectral subtraction, wavelet decomposition and adaptive filtering were used to extract the vital bio-signals. However, extracting these bio-signals with fidelity is a challenging task in the context of FPCG as all the bio signals and the unwanted artifacts overlap in both time and frequency. Additionally, the signal is corrupted by noise induced from the fetal and maternal movements as well the background and the sensor.
Empirical mode decomposition algorithm was efficient to denoise and extract the maternal and fetal heart sounds in a single step. Whereas, spectral subtraction was used to denoise the signal which was later subjected to wavelet decomposition to extract the signal of interest. On the other hand, adaptive filtering was used to estimate the fetal heart sound from a noisy FPCG where maternal heart sound was the reference input.
The extracted signals were validated by obtaining the frequency ranges computed by the Short Time Fourier Transform (STFT). It was observed that the bandwidths of extracted fetal heart sounds and maternal heart sounds were consistent with the existing gold standards. Furthermore, as a means of additional validation, the heart rates were calculated. Finally, the results obtained from all these methods were compared and contrasted qualitatively and quantitatively.
22
Einstein, Daniel Richard. "Nonlinear acoustic analysis of the mitral valve /." Thesis, Connect to this title online; UW restricted, 2002. http://hdl.handle.net/1773/8064.
Повний текст джерела
23
Klavebäck, Kerstin. "A Rude Awakening to Sounds : A Study of the Soundscape in Joseph Conrad’s Heart of Darkness." Thesis, Högskolan i Halmstad, Sektionen för humaniora (HUM), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-23633.
Повний текст джерелаАнотація:
This study examines the significance of sounds and silence in Joseph Conrad’s novella Heart of Darkness (1902). The importance of visual effects has repeatedly been analyzed and therefore, it is high time to explore the text from an auditory perspective. By comparing and contrasting Victorian city sounds to sounds in the wilderness, I show that the urban and rural worlds have a great deal in common. Furthermore, by deconstructing the seemingly stable binary opposition of sound and silence as well as that of civilization and wilderness, it becomes evident that they are related and depend on one another. This paper also examines noise and how it is used as a means of power. Moreover, it deals with Thomas Edison’s invention, the phonograph, as an implicit discursive device in the text. In conclusion, it is argued that the sonic environment is of high significance and should therefore not be ignored and readers must try to close their eyes in order to hear what is said.
24
Hudson, Erik Mark. "A Portable Computer System for Recording Heart Sounds and Data Modeling Using a Backpropagation Neural Network." UNF Digital Commons, 1995. http://digitalcommons.unf.edu/etd/158.
Повний текст джерелаАнотація:
Cardiac auscultation is the primary tool used by cardiologists to diagnose heart problems. Although effective, auscultation is limited by the effectiveness of human hearing. Digital sound technology and the pattern classification ability of neural networks may offer improvements in this area. Digital sound technology is now widely available on personal computers in the form of sound cards. A good deal of research over the last fifteen years has shown that neural networks can excel in diagnostic problem solving. To date, most research involving cardiology and neural networks has focussed on ECG pattern classification. This thesis explores the prospects of recording heart sounds in Wave format and extracting information from the Wave file for use with a backpropagation neural network in order to classify heart patterns.
25
Tan, Zhen. "Low noise heart sound acquisition in wearable system for individual-centered CVD diagnosis." Thesis, University of Macau, 2017. http://umaclib3.umac.mo/record=b3691773.
Повний текст джерела
26
Gigstad, Lynda Lynell. "A comparison of an acoustic stethoscope and an amplified stethoscope in white noise and cafeteria noise during cardiac auscultation." PDXScholar, 1990. https://pdxscholar.library.pdx.edu/open_access_etds/3974.
Повний текст джерелаАнотація:
A basic relationship between stethoscopic auscultation and background noise interference was reviewed and examined in this study. The principle experimental design of the study questioned whether hospital background noise levels are capable of masking the threshold of detection for auscultated heart sounds. Several cited studies monitoring background noise levels in various hospital locations have reported averages exceeding the U.S. Environmental Protection Agency (EPA) (1974) and World Health Organization (WHO) (1980) recommendations of "quiet", namely 35 to 40 dBA (Falk & Woods, 1973; Hilton, 1985, 1987; Shapiro & Berland, 1972; Turner, et al., 1975; Woods & Falk, 1974) by as much as 46 to 51 dB, i.e., up to 86 dBA (Shapiro & Berland 1972). In addition to the previous query, a review of the literature reflected a lack of implementatory standards regarding the acoustic stethoscopic output and the masking effects of noise during the auscultation process. Specifically, this study ascertained the effective masking level (EML) intensities of two noise environments, white noise and cafeteria noise, for cardiac auscultation through an acoustic stethoscope and an amplified stethoscope. Two principle measurements were employed in the experimental protocol: an objective measurement employing a method of adjustment detection identification task of the EML, and subjective responses solicited by a forced-choice questionnaire. Sixteen normal hearing listener's were selected to participate in the experiment. Objective measures were analyzed using a MANOVA and a Pearson Product Moment Coefficient of correlation. The subjective questionnaire data were analyzed with a two-tailed T-test. All analyses were based on a .05 level of confidence.
27
Koegelenberg, Suretha. "Application of laser doppler vibrocardiography for human heart auscultation." Thesis, Stellenbosch : Stellenbosch University, 2014. http://hdl.handle.net/10019.1/86649.
Повний текст джерелаАнотація:
Thesis (MScEng)--Stellenbosch University, 2014.ENGLISH ABSTRACT: This thesis investigates the feasibility of the laser Doppler vibrometer (LDV) for use in the autonomous auscultation of the human heart. As a non-contact measurement device, the LDV could become a very versatile biomedical sensor. LDV, stethoscope, piezoelectric accelerometer (PA) and electrocardiogram (ECG) signals were simultaneously recorded from 20 volunteers at Tygerberg Hospital. Of the 20 volunteers, 17 were confirmed to have cardiovascular disease. 3 patients with normal heart sounds were recorded for control data. The recorded data was successfully denoised using soft threshold wavelet denoising and ensemble empirical mode decomposition. The LDV was compared to the PA in common biomedical applications and found to be equally accurate. The heart sound cycles for each participant were segmented using a combination of ECG data and a simplicity curve. Frequency domain features were extracted from each heart cycle and input into a k-nearest neighbours classifier. It was concluded that the LDV can form part of an autonomous, non-contact auscultation system.
AFRIKAANSE OPSOMMING: Hierdie tesis ondersoek die haalbaarheid daarvan om die laser Doppler vibrasiemeter (LDV) vir die outonome beluistering van die menslike hart te gebruik. As 'n kontaklose meettoestel kan die LDV werklik 'n veelsydige biomediese sensor word. Twintig vrywilligers by die Tygerberg Hospitaal se LDV-, stetoskoop-, piësoelektriese versnellingsmeter (PV)- en elektrokardiogram (EKG) seine is gelyktydig opgeneem. Uit die 20 vrywilligers was daar 17 bevestigde gevalle van kardiovaskulêre siektes. Die data van drie pasiënte met normale hartklanke is as kontroledata opgeneem. Geraas is suksesvol uit die opgeneemde data verwyder deur 'n kombinasie van sagtedrempelgolf en saamgestelde empiriese modus ontladingstegnieke. Die LDV was vergelyk met die PV vir algemene biomediese gebruike en daar was gevind dat dit vergelykbare akkuraatheid het. Die hartklanksiklusse van elke deelnemer is gesegmenteer deur EKG data en 'n eenvoudskromme te kombineer. Frekwensiegebiedskenmerke is uit elke hartsiklus onttrek en in 'n k-naastebuurpunt klassifiseerder ingevoer. Daar is tot die gevolgtrekking gekom dat die LDV deel van 'n outonome, kontaklose beluisteringstelsel kan uitmaak.
28
De, Vos Jacques Pinard. "Automated pediatric cardiac auscultation." Thesis, Link to the online version, 2005. http://hdl.handle.net/10019/1008.
Повний текст джерела
29
Brites, Ivo Sérgio Guimarães [UNESP]. "Análise de bulhas cardíacas usando wavelets visando auxiliar no diagnóstico médico." Universidade Estadual Paulista (UNESP), 2014. http://hdl.handle.net/11449/111108.
Повний текст джерелаАнотація:
Made available in DSpace on 2014-12-02T11:16:55Z (GMT). No. of bitstreams: 0
Previous issue date: 2014-02-14Bitstream added on 2014-12-02T11:20:54Z : No. of bitstreams: 1
000796411.pdf: 2346587 bytes, checksum: 4c090312f84027a406b4735ddd531092 (MD5)A presente dissertação teve como objetivo apresentar uma proposta de análise de bulhas cardíacas (sons produzidos pelo fechamento das válvulas do coração) usando Transformada Discreta de Wavelet. Neste trabalho as bulhas cardíacas, gravadas em um arquivo digital, foram processadas através da Transformada Discreta de Wavelet nível 6 da db7 e da db6 de Daubechies e feita uma análise de sua média e do seu desvio padrão. Com a métrica desvio padrão aplicada ao sexto nível da db6 de Daubechies para classificação de sinais normais e anormais em um banco de dados de 70 amostras obteve-se um acerto da ordem de 95,71%
This dissertation aims to present a proposal for interpretation of heart sounds using Discrete Wavelet Transform. The heart sounds recorded in a digital file were processed using level 6 of db7 and level 6 of db6 Daubechies Discrete Wavelet Transform and extracting the media and standard deviation features. The standard deviation of level6 of db6 Daubechies Discrete Wavelet is are able to differentiate between normal and abnormal from database of 70 heart sound signals with 95.71% of correct classifications
30
Brites, Ivo Sérgio Guimarães. "Análise de bulhas cardíacas usando wavelets visando auxiliar no diagnóstico médico /." Ilha Solteira, 2014. http://hdl.handle.net/11449/111108.
Повний текст джерелаАнотація:
Orientador: Nobuo OkiBanca: Suely Cunha Amaro Mantovani
Banca: Carlos Aurélio Faria da Rocha
Resumo: A presente dissertação teve como objetivo apresentar uma proposta de análise de bulhas cardíacas (sons produzidos pelo fechamento das válvulas do coração) usando Transformada Discreta de Wavelet. Neste trabalho as bulhas cardíacas, gravadas em um arquivo digital, foram processadas através da Transformada Discreta de Wavelet nível 6 da db7 e da db6 de Daubechies e feita uma análise de sua média e do seu desvio padrão. Com a métrica desvio padrão aplicada ao sexto nível da db6 de Daubechies para classificação de sinais normais e anormais em um banco de dados de 70 amostras obteve-se um acerto da ordem de 95,71%
Abstract: This dissertation aims to present a proposal for interpretation of heart sounds using Discrete Wavelet Transform. The heart sounds recorded in a digital file were processed using level 6 of db7 and level 6 of db6 Daubechies Discrete Wavelet Transform and extracting the media and standard deviation features. The standard deviation of level6 of db6 Daubechies Discrete Wavelet is are able to differentiate between normal and abnormal from database of 70 heart sound signals with 95.71% of correct classifications
Mestre
31
Keršulytė, Gintarė. "Širdies signalų analizės metodų paieška ir kūrimas." Master's thesis, Lithuanian Academic Libraries Network (LABT), 2007. http://vddb.library.lt/obj/LT-eLABa-0001:E.02~2007~D_20070816_142805-77618.
Повний текст джерелаАнотація:
Didelė dalis širdies susirgimų diagnostinių kriterijų gaunama registruojant ir analizuojant kardiosignalus, kurie atspindi tiek elektrinės širdies veiklos sutrikimus (EKG), tiek ir hemodinaminės bei mechaninės veiklos pokyčius, t.y. impedanskardiograma (IKG) ir seismokardiograma (SKG). Dar daugiau, efektyvus širdies susirgimų diagnostikos problemų sprendimas yra naujų kardiosignalų analizės technologijų kūrimas. Jau kelis dešimtmečius Furjė transformacija taikoma EKG dažnumų analizei, tuo tarpu kai IKG ir SKG dažnio charakteristikų vertinimui šis metodas nebuvo naudojamas. Darbo tikslas buvo pritaikyti Furjė analizę įvertinant bei palyginant tris sinchroniškai užregistruotus kardiosignalus, nes jie atspindi elektrinės širdies, hemodinaminės bei mechaninės širdies veiklos pokyčius geriau nei vienas EKG signalas. Kitas darbo tikslas buvo pritaikyti Furjė analizę įvertinant bei palyginant trijų sinchroniškai užregistruotų signalų - EKG, IKG ir SKG dažnio charakteristikas ir koherenciją bei klasifikuoti dvi grupes - "sveikas" ir "ligonis". Rezultatai rodo, kad koherencijos vertinimas ir spektrinė analizė gali būti naudinga gali būti naudingas širdies kraujagyslių bei plaučių sistemų ligų diagnostikai.A big part of heart disease diagnostics criteria is collected by registration and analysis of cardio signals that reflect the disturbances of the electric heart activity – electrocardiogram (EСG), changes of hemodynamic - impedance cardiograms (IСG) and mechanic activity - seismocardiogram (SСG). ECG analysis is generally applying in clinic practice, but usually in visual way only. Due to the development of the technologies, the bigger amount of data could be stored and more exact analysis of information could be carried out. Therefore, a solution of problem of effective diagnostics of heart diseases is the creation of new technologies for analysis of cardio signals. Previously Fourier series were applied to frequency analysis of ECG, but this method was not applied for estimation of ICG and SCG frequency characteristics. In this thesis the frequency analysis method was applied to three cardio signals, because they reflect the electrical and mechanical work of the human heart better as entirely ECG signal. The main aim of this work was to adapt Fourier transformation to assessing and comparing some characteristics of hereinbefore signals, such as coherence and classify two searching groups - “healthy” and “sick”. Results showed that rating of coherence and spectral analysis could be useful for rightly analyzing and classifying the searching groups.
32
Tran, Merry Thi. "Applications of Digital Signal Processing with Cardiac Pacemakers." PDXScholar, 1992. https://pdxscholar.library.pdx.edu/open_access_etds/4582.
Повний текст джерелаАнотація:
Because the voltage amplitude of a heart beat is small compared to the amplitude of exponential noise, pacemakers have difficulty registering the responding heart beat immediately after a pacing pulse. This thesis investigates use of digital filters, an inverse filter and a lowpass filter, to eliminate the effects of exponential noise following a pace pulse. The goal was to create a filter which makes recognition of a haversine wave less dependent on natural subsidence of exponential noise. Research included the design of heart system, pacemaker, pulse generation, and D sensor system simulations. The simulation model includes the following components: \ • Signal source, A MA TLAB generated combination of a haversine signal, exponential noise, and myopotential noise. The haversine signal is a test signal used to simulate the QRS complex which is normally recorded on an ECG trace as a representa tion of heart function. The amplitude is approximately 10 mV. Simulated myopotential noise represents a uniformly distributed random noise which is generated by skeletal muscle tissue. The myopotential noise has a frequency spectrum extending from 70 to 1000Hz. The amplitude varies from 2 to 5 mV. Simulated exponential noise represents the depolarization effects of a pacing pulse as seen at the active cardiac lead. The amplitude is about -1 volt, large in comparison with the haversine signal. • AID converter, A combination of sample & hold and quantizer functions translate the analog signal into a digital signal. Additionally, random noise is created during quantization. • Digital filters, An inverse filter removes the exponential noise, and a lowpass filter removes myopotential noise. • Threshold level detector, A function which detects the strength and amplitude of the output signal was created for robustness and as a data sampling device. The simulation program is written for operation in a DOS environment. The program generates a haversine signal, myopotential noise (random noise), and exponential noise. The signals are amplified and sent to an AID converter stage. The resultant digital signal is sent to a series of digital filters, where exponential noise is removed by an inverse digital filter, and myopotential noise is removed by the Chebyshev type I lowpass digital filter. The output signal is "detected" if its waveform exceeds the noise threshold level. To determine what kind of digital filter would remove exponential noise, the spectrum of exponential noise relative to a haversine signal was examined. The spectrum of the exponential noise is continuous because the pace pulse is considered a non-periodic signal (assuming the haversine signal occurs immediately after a pace pulse). The spectrum of the haversine is also continuous, existing at every value of frequency co. The spectrum of the haversine is overlapped by the spectrum of and amplitude of the exponential, which is several orders of magnitude larger. The exponential cannot be removed by conventional filters. Therefore, an inverse filter approach is used to remove exponential noise. The transfer function of the inverse filter of the model has only zeros. This type of filter is called FIR, all-zero, non recursive, or moving average. Tests were run using the model to investigate the behavior of the inverse filter. It was found that the haversine signal could be clearly detected within a 5% change in the time constant of the exponential noise. Between 5% and 15% of change in the time constant, the filtered exponential amplitude swamps the haversine signal. The sensitivity of the inverse filter was also studied: when using a fixed exponential time constant but changing the location of the transfer function, the effect of the exponential noise on the haversine is minimal when zeros are located between 0.75 and 0.85 of the unit circle. After the source signal passes the inverse filter, the signal consists only of the haversine signal, myopotential noise, and some random noise introduced during quantization. To remove these noises, a Chebyshev type I lowpass filter is used.
33
Minardi, Gabriele. "Progettazione e sviluppo di un prototipo di dispositivo wearable per il monitoraggio dell'attivita elettro-meccanica del cuore." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2014. http://amslaurea.unibo.it/7898/.
Повний текст джерелаАнотація:
Il presente lavoro di tesi è finalizzato allo sviluppo di un dispositivo indossabile, e minimamente invasivo, in grado di registrare in maniera continua segnali legati all’attività elettromeccanica del muscolo cardiaco, al fine di rilevare eventuali anomalie cardiache.
In tal senso il sistema non si limita alla sola acquisizione di un segnale ECG, ma è in grado di rilevare anche i toni cardiaci, ovvero le vibrazioni generate dalla chiusura delle valvole cardiache, la cui ampiezza è espressione della forza contrattile (funzione meccanica) del cuore. Il presente lavoro di tesi ha riguardato sia la progettazione che la realizzazione di un prototipo di tale dispositivo ed è stato svolto presso il laboratorio di Bioingegneria del Dipartimento di Medicina Specialistica Diagnostica e Sperimentale dell’Università di Bologna, sito presso l’Azienda Ospedaliero-Universitaria Policlinico Sant’Orsola-Malpighi. Il sistema finale consiste in un dispositivo applicabile al torace che, attraverso una serie di sensori, è in grado di rilevare dati legati alla meccanica del cuore (toni cardiaci), dati elettrici cardiaci (ECG) e dati accelerometrici di attività fisica. Nello specifico, il sensing dei toni cardiaci avviene attraverso un accelerometro in grado di misurare le vibrazioni trasmesse al torace. I tracciati, raccolti con l’ausilio di una piattaforma Arduino, vengono inviati, tramite tecnologia Bluetooth, ad un PC che, attraverso un applicativo software sviluppato in LabVIEW™, ne effettua l’analisi, il salvataggio e l’elaborazione in real-time, permettendo un monitoraggio wireless ed in tempo reale dello stato del paziente.
34
Soukup, Ladislav. "Vyhodnocení srdečního výdeje bioimpedanční metodou u pacientů se stimulátorem." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2012. http://www.nusl.cz/ntk/nusl-219749.
Повний текст джерелаАнотація:
This thesis deals with the possibility of using impedance cardiography for calculating cardiac output. Kubicek’s, Sramek‘s and Sramek-Bernstein‘s methods are discussed here. These methods were applied to a data set, obtained by measuring on subjects with implanted cardiostimulators. The subjects’ heart rate was being changed by the programing of cardiostimulators. Thanks to this procedure the measured data were not affected by artifacts, connected with the heart rate change caused by a body stress, or other influences. An influence of heart rate on a cardiac output value based on the statistical processing of the data set was studied.
35
Chitnis, Anurag Ashok. "Mobile-Based Smart Auscultation." Thesis, University of North Texas, 2017. https://digital.library.unt.edu/ark:/67531/metadc1011820/.
Повний текст джерелаАнотація:
In developing countries, acute respiratory infections (ARIs) are responsible for two million deaths per year. Most victims are children who are less than 5 years old. Pneumonia kills 5000 children per day. The statistics for cardiovascular diseases (CVDs) are even more alarming. According to a 2009 report from the World Health Organization (WHO), CVDs kill 17 million people per year. In many resource-poor parts of the world such as India and China, many people are unable to access cardiologists, pulmonologists, and other specialists. Hence, low skilled health professionals are responsible for screening people for ARIs and CVDs in these areas. For example, in the rural areas of the Philippines, there is only one doctor for every 10,000 people. By contrast, the United States has one doctor for every 500 Americans. Due to advances in technology, it is now possible to use a smartphone for audio recording, signal processing, and machine learning. In my thesis, I have developed an Android application named Smart Auscultation. Auscultation is a process in which physicians listen to heart and lung sounds to diagnose disorders. Cardiologists spend years mastering this skill. The Smart Auscultation application is capable of recording and classifying heart sounds, and can be used by public or clinical health workers. This application can detect abnormal heart sounds with up to 92-98% accuracy. In addition, the application can record, but not yet classify, lung sounds. This application will be able to help save thousands of lives by allowing anyone to identify abnormal heart and lung sounds.
36
Горбенко, А. В. "Дослідження механічної роботи серця та гемодинаміки кровоносної системи людини". Thesis, Сумський державний університет, 2015. http://essuir.sumdu.edu.ua/handle/123456789/43970.
Повний текст джерела
37
Wong, Spencer Geng. "DESIGN, CHARACTERIZATION AND APPLICATION OF A MULTIPLE INPUT STETHOSCOPE APPARATUS." DigitalCommons@CalPoly, 2014. https://digitalcommons.calpoly.edu/theses/1307.
Повний текст джерелаАнотація:
For this project, the design, implementation, characterization, calibration and possible applications of a multiple transducer stethoscope apparatus were investigated. The multi-transducer sensor array design consists of five standard stethoscope diaphragms mounted to a rigid frame for a-priori knowledge of their relative spatial locations in the x-y plane, with compliant z-direction positioning to ensure good contact and pressure against the subject’s skin for reliable acoustic coupling. When this apparatus is properly placed on the body, it can digitally capture the same important body sounds investigated with standard acoustic stethoscopes; especially heart sounds. Acoustic signal inputs from each diaphragm are converted to electrical signals through microphone pickups installed in the stethoscope connective tubing; and are subsequently sampled and digitized for analysis. With this system, we are able to simultaneously interrogate internal body sounds at a sampling rate of 2 KHz, as most heart sounds of interest occur below 200 Hz.
This system was characterized and calibrated by chirp and impulse signal tests. After calibrating the system, a variety of methods for combining the individual sensor channel data to improve the detectability of different signals of interest were explored using variable-delay beam forming. S1 and S2 heart sound recognition with optimized beam forming delays and inter-symbol noise elimination were investigated for improved discernment of the S1 or S2 heart sounds by a user. Also, stereophonic presentation of heart sounds was also produced to allow future investigation of its potential clinical diagnostic efficacy.
38
Chemin, Nadine. "Synthèse de ligands mono- et polyisonitriles : marquage par 99mTc et biodistribution." Université Joseph Fourier (Grenoble ; 1971-2015), 1997. http://www.theses.fr/1997GRE10066.
Повний текст джерелаАнотація:
Les maladies cardiovasculaires sont l'une des principales cause de mortalite dans les pays industrialises, aussi est-il important de diagnostiquer a temps les insuffisances d'irrigation du myocarde. Nous avons donc recherche de nouveaux traceurs techneties du debit myocardique, analogues de tc-mibi. Nous avons realise la synthese de dix nouveaux ligands, mono ou polydentes, fonctionnalises par des ethers et/ou des thioethers. La preparation d'une nouvelle classe de complexant, les phosphine-isonitriles, a ete abordee et nous avons montre que seule une synthese convergente faisant intervenir dans la derniere etape un phosphidure et un -haloisonitrile etait susceptible d'aboutir. Les conditions de complexation de #9#9#mtc par les ligands isonitriles ont ete optimisees. Par ailleurs, ces travaux constituent le deuxieme exemple de complexation de #9#9#mtc par les polyisonitriles au niveau des traces. La structure des complexes obtenus a l'echelle des traces a ete approchee par une etude au niveau macroscopique de la chelation du rhenium avec un des ligands diisonitrile. Le complexe isole re(l)#3#+ demontre qu'il est possible d'obtenir un chelate avec des ligands bidentes, meme si l'espaceur est souple et ne preorganise pas le ligand. L'evaluation biologique des complexes techneties a ete effectuee chez la souris swiss ; les traceurs donnant les meilleurs resultats ont ete testes sur chien.
39
da, Cunha Daise Nunes Queiroz. "Properties of Flow Through the Ascending Aorta in Boxer Dogs with Mild Aortic Stenosis: Momentum, Energy, Reynolds Number, Womersley’s, Unsteadiness Parameter, Vortex Shedding, and Transfer Function of Oscillations from Aorta to Thoracic Wall." The Ohio State University, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=osu1243910694.
Повний текст джерела
40
Henry, Christelle. "Etude du comportement biologique de nouveaux analogues iodés du glucose, proposés comme marqueurs de la captation du glucose." Université Joseph Fourier (Grenoble), 1995. http://www.theses.fr/1995GRE10029.
Повний текст джерелаАнотація:
Le glucose est un substrat energetique pour la totalite des tissus de l'organisme et l'appreciation de sa captation revet une grande importance en medecine en particulier en cardiologie, en neurologie et en cancerologie. Actuellement, pour etudier le metabolisme du glucose chez l'homme, on utilise le #1#8f fluorodeoxyglucose (fdg). Le fdg presente des inconvenients majeurs qui limitent son emploi a 3 centres en france. C'est pourquoi notre travail s'est oriente vers la recherche de nouveaux analogues du glucose marques a l'iode radioactif emetteur et utilisables dans tous les services de medecine nucleaire. Trois modeles experimentaux ont ete choisis: la biodistribution chez la souris (in vivo), le cur isole et perfuse de rat (ex vivo) et les erythrocytes humains en suspension (in vitro). Sur l'ensemble des modeles biologiques, nous avons etabli les protocoles experimentaux et les valeurs de reference de la captation du 1-#1#4c-2-deoxy-d-glucose (2-dg) qui entre dans la cellule par le transporteur du d-glucose et du l-#1#4c-glucose qui entre par diffusion passive. Des analogues du glucose marques a l'iode 123 en position -1, -2, -3 ou -6 de la molecule de glucose ont ete etudies sur les differents modeles experimentaux et selon les protocoles valides avec les molecules de reference. Pour servir a l'etude de la captation cellulaire du glucose, l'analogue iode doit imperativement entrer dans la cellule grace au transporteur du glucose. Trois analogues du glucose (big7, big9 et bigac1) se sont reveles potentiellement tres interessants puisque leur fixation est augmentee en presence d'insuline et diminuee en presence d'inhibiteur du transport du glucose. Big7 et big9 ont presente un comportement biologique comparable a celui du 3-o-methyl-d-glucose qui entre dans la cellule comme le glucose sans y etre metabolise. De plus, injectes chez le chien in vivo, ces analogues iodes du glucose permettent d'obtenir des images scintigraphique de bonne qualite
41
Chou, Cheng-Han, and 周承漢. "Application of artificial intelligent technology in diagnostics the pulmonary sounds." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/67258081416635028562.
Повний текст джерелаАнотація:
碩士國立臺灣師範大學
機電科技研究所
98
Chest auscultation is a main and efficient way to diagnose lung disease, it is a subjective process that depending on the physician’s experience and ability to differentiate between different sound patterns. Because physiological signals composed of heart sound and pulmonary sound are above 120HZ and the in sensitive of the human ear to the lower frequency, it is not easy to make diagnostic classification successful. In order to solve this problem, this study aims to construct a variety of pulmonary sound (PS) recognition system for classification of six different PS classes: Vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, stridor sounds. First, we use the piezoelectric microphone and data acquisition card NI-PXI 4472B to acquire PS signals, and signals preprocessing. The wavelet transform as feature extraction method, the PS signals were decomposed into the frequency subbands. Through statistical method we get the seventeen feature vectors which are used the neural network's input vector. This research used back-propagation (BP) neural network and learning vector quantization (LVQ) neural network to be subsystem, and the two neural networks are integrated together as a two stage system that can increase the reliability. The neural networks' performance is verified by the receiver operating characteristic (ROC) curve. Comparing with traditional auscultation method, this study successfully construct a variety of pulmonary sound diagnostic system can correctly classify the six common pulmonary sounds. In this study, can be improved that human ear’s insensitive to the lower frequency, and show its pulmonary sounds wave, characteristic value and spectral analysis chart are shown by the human-machine interface design. By the research of this paper, the recognition rate of system is up to 95%.
42
Tseng, Yi-Li, and 曾乙立. "Early Detection of Ischemic Heart Disease Using Multi-lead ECG and Heart Sounds." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/87080356466389715644.
Повний текст джерелаАнотація:
博士國立臺灣大學
醫學工程學研究所
100
Ischemic heart disease has become the first place of ten leading causes of death for many years. According to the statistic results from WHO, up to 16% of mortality is due to ischemic heart disease. The main reason of high death rate is its lack of early symptoms. Patients suffer from sudden death only after a short period of the occurring of acute coronary syndromes. Some even die without any early symptoms. Therefore, early detection of myocardial ischemia has become an important issue recently. In this study, we implemented a non-invasive 12-lead electrocardiogram (ECG) and a phonocardiogram (PCG) monitoring system, and high-accuracy analyzing methods are also proposed for the early detection of ischemic heart diseases. By the detection of the ischemia of cardiac muscles in its early stage, ischemic heart disease can be detected before the occurring of acute symptoms. Myocardial ischemia commonly manifests as ST- and T-wave changes on the ECG, or the third heart sound (S3) and the fourth heart sound (S4) of the PCG. For the analysis of ECG signals, we proposed two methods, support vector machine (SVM) and sparse representation-based classification (SRC), to detect abnormal ST-T complex. It integrates knowledge-based and novel classifying methods to extract essential information from ECG signals. In comparison with previous methods, the sensitivity for detecting myocardial ischemia is greatly improved using our methods. For the detection of S3 and S4, a time-frequency analysis method, Hilbert-Huang transform (HHT), was used to analyze non-linear and non-stationary PCG signals. This method can decompose the signal adaptively and acquire the instantaneous frequency. Therefore, all the abnormal components of PCG signals correlated to myocardial dysfunction can be detected simultaneously. The design of the monitoring of these non-invasive signals is based on remote home health care concepts. The recording of 12-lead ECG is designed using multiplexing technique suitable for wireless transmission. Moreover, the design of the electronic stethoscope is based on medical concepts with modulated equalizer. In this investigation, both analyzing methods and monitoring systems for 12-lead ECG and heart sound are proposed. The sensitivity and accuracy of the proposed methods are of better performance compared to previous methods. Furthermore, the whole monitoring system is aimed for remote home health care. With these concepts, detection of myocardial ischemia in its early stage using non-invasive home health care system could be feasible.
43
Chiang, Meng-Ling, and 蔣孟伶. "Development of a fetal heart sounds monitor using microphone array." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/49851619132666001453.
Повний текст джерелаАнотація:
碩士中原大學
生物醫學工程研究所
103
Fetal heart rate monitoring is one of the main approaches for obstetricians to determine the fetal well-being during pregnancy. Since different fetal position results in different position for heart sound monitoring. This study develops a prototype of fetal heart sound monitor system using microphone array. The system uses the statistical results of the energy of signal from microphone array to detect the main fetal position, so that we can acquire fetal signal with the best signal quality and obtain more accurate fetal heart rate. Furthermore, with the android application, developed in this study, the fetal heart sound signal and fetal heart rate that are transmitted using Bluetooth module can be displayed in real-time. In addition, the APP can storage records and establishes a database to provide user the capability to view past records. There are three stages in real signal acquisition. In total, 18 subjects were recruited with different weeks of pregnancy in the test. The results not only demonstrate that the proposed system is capable of recording high quality fetal heart sound but also prove the main position of the fetal determines the quality of the signal. That is, with only 5 cm off center, the impact on the signal quality is significant. In the area of MATLAB algorithm validation, using the acquired real signal, the accuracy of fetal main position determination and the fetal heart rate computation are compared with the expert. The result shows that our algorithm can determine the fetal main position correctly and the averaged accuracy of extracting fetal heart rate can reach 98.6%. In the system integration, this study realizes a real time system on the DSP. In a 5 minutes test session, the system can determine the fetal main position correctly. While illustrating the results of fetal heart rate using the Bland-Altman difference plot, the fetal heart rate differences between real-time system and the MATLAB are within 3bpm. In conclusion, this study develops a prototype for fetal heart sound monitor system using microphone array. Using the proposed algorithm the system can successfully extract high quality fetal signal and obtain more reliable fetal heart rate.
44
Liu, Chun-Wei, and 劉俊緯. "Mobile Buletooth based Electronic Stethoscope for Heart and Lung Sounds." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/86905703052830758155.
Повний текст джерелаАнотація:
碩士國立聯合大學
電機工程學系碩士班
102
During the process of heart and lungs, there are unique physiological heart and lung sounds which are collected clinically for doctors to judge if related diseases are affiliated. Electronic stethoscope with Bluetooth transmission function was built in this study. The device allows the the heart and lung sounds to be converted to electric signals by condenser microphone. The sounds not only can be collected through the amplification and filter circuits but also recorded when connecting the audio cables to computers. Furthermore, the sound data can be submitted to computers with bluetooth transmission or saved in SD card, and can be applied for disease analysis within the man-machine interface. In addition, the filter circuits allows users to alter from heart to lung sound based on their needs. When connecting the audio cables to the computer, the sounds can be recorded and the recorded sounds can also be heard promptly. This function remits greatly the pain of the doctors' from long time use of the traditional stethoscope and improves the disadvantage of not being able to record the heart and lung sounds from the patients. Bluetooth transmission allows users to save data wirelessly. Labview man-machine interface was developed for sound recording and data analysis that is based on empirical mode decomposition and FFT to identify the diseases, avoiding the possibility of the doctor’s misjudge from subjective factors.
45
Li, SIH-SYUAN, and 李思璇. "Classification of Bluetooth stethoscopic heart sounds using convolution neural network." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/02228847741429050026.
Повний текст джерелаАнотація:
碩士國立東華大學
應用數學系
105
In this thesis we describe our methodology for heart sounds classification (categories for sounds : Normal, Murmur and Extra-systole) based on the sound signals using the Convolution Neural Network (CNN). The general strategy is to transform heart sounds into Mel-Frequency Cepstral Coefficients (MFCCs) which consider human ear perception in different frequency and have been also the most commonly used acoustic features. Stratified sampling is employed to randomly select Normal and Murmur acoustic features, and divide into training and testing set which ratio of two is 4 to 1. Labeled MFCCs features are employed to construct a network for classifying heart sounds. The experiment result shows this CNN can effectively classify heart sounds.
46
Belinha, Solange Maria Teixeira. "Congenital Heart Disease Detection Using Clinical Data and Auscultation Heart Sounds: a Machine Learning Approach." Master's thesis, 2021. https://hdl.handle.net/10216/139714.
Повний текст джерелаАнотація:
Introdução: A doença cardíaca congénita (DCC) é a malformação congénita mais comum no mundo, com incidência e prevalência crescentes. Está associada a maior morbilidade e mortalidade, relacionadas com o diagnóstico tardio. Apesar da disponibilidade de protocolos de rastreio, aproximadamente 75% das DCC não são detetadas ao nascimento. A auscultação cardíaca pode detetar a presença de um sopro. Contudo, apenas 1% de todos os sopros estão associados a DCC. Além disso, estudos mostram um declínio nas capacidades auscultatórias dos médicos. Estudos anteriores nesta área focaram-se na classificação de sons cardíacos em normais ou anormais e utilizaram coeficientes cepstrais nas frequências de Mel (MFCC) extraídos de sons cardíacos.
Objetivo: O objetivo deste estudo é criar e avaliar modelos para a deteção de DCC utilizando dados clínicos e características dos sons, que seriam extraídos usando quer MFCC convencionais, quer MFCC selecionados por pesquisa de motifs usando a inovação do matrix profiling.
Métodos: Neste estudo retrospetivo usámos uma base de dados colhida no contexto de um rastreio voluntário, formando uma série de conveniência. O critério de elegibilidade para rastreio foi idade inferior a 21 anos. Os critérios de exclusão para o estudo foram serem fetos, terem uma cirurgia cardíaca prévia e não terem um diagnóstico ecocardiográfico, que foi usado como referência standard. A informação clínica foi pré-processada e recodificada. Os MFCC foram extraídos das gravações de auscultação de segmentos de batimento cardíaco e de segmentos de motif identificados. Combinações diferentes dos dados foram usadas para treinar árvores de decisão (AD) e redes neuronais artificiais (RNA), e a área sob a curva (AUC) foi comparada. Posteriormente, treinámos modelos para a deteção de qualquer patologia no dataset.
Resultados: Este estudo incluiu 1655 indivíduos, 459 (27.73%) com DCC e 1196 (72.27%) sem DCC. Começando pela DCC, ambos os tipos de modelos dos dados clínicos mostraram uma AUC de 0.747. Os modelos de AD e RNA dos dados clínicos e ambos os tipos de dados do som tiveram AUC de 0.713 e 0.759, respetivamente. Embora, o modelo da RNA treinada usando dados clínicos e MFCC convencionais a mostrar a maior AUC (0.762). Para qualquer patologia, os modelos de dados clínicos mostraram AUC de 0.733 para a AD e 0.789 para a RNA. Quando todos os dados do som são incluídos, AUC cai para ambos (0.676 e 0.784, respetivamente). Novamente, o melhor modelo foi a RNA treinada com dados clínicos e MFCC convencionais (0.791).
Conclusão: Esperávamos que os dados do som melhorassem a performance dos modelos. Contudo, os resultados parecem indicar que estes produzem apenas uma ligeira melhoria. Adicionalmente, a inclusão dos MFCC extraídos de motifs parecem piorar a performance do modelo. Mais investigação é necessária para melhor selecionar as características extraídas dos sons e otimizá-los para patologias específicas. Isto tem o potencial de se tornar uma ferramenta de rastreio para DCC, que seria útil para médicos dos cuidados de saúde primários.Background: Congenital heart disease (CHD) is the most common congenital malformation in the world, with increasing incidence and prevalence. It is associated with high morbidity and mortality, related to late diagnosis. Despite the availability of a screening protocols, approximately 75% of CHD is not detected at birth. Cardiac auscultation can detect the presence of a murmur. However, only 1% of all murmurs are associated with CHD. Moreover, studies show a decline in the auscultation skills of doctors, which highlights the need for screening tools. Previous studies in this area focused on classifying heart sounds as normal or abnormal and used Mel-frequency cepstral coefficients (MFCC) extracted from heart sounds. Objective: The aim of this study is to create and evaluate models for the detection of CHD using clinical data and sound features, which would be extracted using either conventional MFCC or MFCC selected through motif search using the innovation of matrix profiling. Methods: In this retrospective study we used a dataset collected on a volunteer screening setting, forming a convenience series. Eligibility criteria for screening was age under 21. Exclusion criteria for the study was being a fetus, having previous cardiac surgery, and having no echocardiogram result, which was used as reference standard. Clinical data was preprocessed and recoded. MFCC were extracted from the auscultation recordings from heartbeat segments and from motif segments identified. Different combinations of data were used to train decision trees (DT) and artificial neural networks (ANN), and the area under the curve (AUC) was compared. Posteriorly, we trained models for the detection of any pathology in the dataset. Results: This study included 1655 individuals, 459 (27.73%) with CHD and 1196 (72.27%) without CHD. Starting with CHD, both types of models of the clinical data showed AUC of 0.747. The DT and ANN models of clinical data and both types of sound features had AUC of 0.713 and 0.759, respectively. Although, the ANN model trained using clinical data and conventional MFCC showed the highest AUC (0.762). For any pathology, the clinical data models showed AUC of 0.733 for DT and 0.789 for ANN. When all sound features are included, AUC fall for both (0.676 and 0.784, respectively). Again, the best model was the ANN trained with clinical data and conventional MFCC (0.791). Conclusions: We expected that sound features would improve the performance of the models. However, the results seem to indicate they produce only a slight improvement. Additionally, the inclusion of MFCC extracted from motifs seems to worsen the model performance. Further research is needed to better select the sound features extracted and optimize them for specific pathologies. This has the potential of becoming a screening tool for CHD, which would be useful for primary care physicians.
47
Shiu, Shr-ting, and 許時挺. "Reducing heart sound interference from lung sounds by Hilbert-Huang transform." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/33285381065777052430.
Повний текст джерелаАнотація:
碩士國立中央大學
電機工程研究所
100
In this research, we take heart sound signals as interference to lung sounds and propose a method to reduce the interfering heart sounds in lung sounds. The lung sounds were obtained by placing an electronic stethoscope head on the chest of the subject and recording the output signal of the microphone in the stethoscope head. We incorporated Hilbert-Huang Transform (HHT) in our heart sound reduction. HHT was proposed by Norden E. Huang. It is especially suitable for processing non-stationary and non-linear signals, such as physiological signals. In HHT, the target signal can be decomposed into a number of intrinsic mode functions (IMFs) by empirical mode decomposition (EMD).These IMFs can be transformed into the Hilbert space, and then their instantaneous frequencies can be observed in the time domain. The performance of our heart sound reduction algorithm was evaluated in terms of the heart-sound-noise reduction percentage (HNRP), which .is about 80% in our experiments. This result is comparatively better than that of a wavelet-based method shown in the literature.
48
高璽豐. "The Time-Frequency Analysis of Heart Sounds Using the Orthogonal Property." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/23385050319706727243.
Повний текст джерела
49
ShovanBarma and 蕭巴馬. "Nonlinear Methods for Analyzing Second Heart Sounds and Applications in Clinical Diagnosis." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/wr9up4.
Повний текст джерелаАнотація:
博士國立成功大學
電機工程學系
103
The second heart sounds (S2s) are a short burst of auditory vibration of varying frequencies and it includes two components, called aortic (A2) and pulmonic (P2) closure sounds. The clinical evaluations of the S2s have been recognized as “key to auscultation to the heart.” The delay between the A2s and P2s is called split in medical term, which carries significant clinical clues. Besides, the other parameters such as duration of the S2s (i.e., A2s, P2s and split) and energy of instantaneous frequencies (EIF) of the A2s and P2s can provide significant clinical clues. However, the detection of split is obscured due to overlap between A2–P2 and low energy model of the P2. In this regard, there is a chance of misreading the S3 (third heart sounds) as an abnormal S2 with “fixed split” problem. In literature, the previous works were focused only the measurement of the split empirically based on the visual inspections of the time-frequency representation (TFR) of the S2s only and two vital issues A2–P2 overlap and low energy model of P2s were ignored. Besides, the durations of the S2s, A2s, and P2s were not taken into account. Moreover, the methods could not provide any diagnostic principle based on the analysis of the S2s. Furthermore, the misreading issue between the S3 and abnormal S2s (especially “fixed split” problem) was not addressed. The aforementioned issues were handled in this dissertation by developing methods based on nonlinear signal processing which include nonlinear signal decomposition, instantaneous frequency estimation, and nonlinear time-frequency localization. In accordance, the developed methods could tackle the two serious issues of the S2s — Overlap between A2s and the P2s and low energy model of P2s very efficiently. This dissertation achieves these goals in three main parts. Before describing the methods all the theories concerned with the developed methods are enlightened in particulars. After that, the developed methods are explained including methods, experiments, results and discussions in subsequent chapters with full details. In the first part, the developed method can measure the split of the S2s quantitatively based on nonlinear signal decomposition called Hilbert vibration decomposition (HVD). The HVD decomposes the S2 into certain number of components while preserving the phase information intact. Further, A2s and P2s are localized by using smoothed pseudo Wigner-Ville distribution (SPWVD) followed by reassignment method. Finally, the split is calculated by taking the differences between the means of time indices of A2s and P2s. The result shows that the mean ± standard deviations (SD) of the split is 34.7±46 ms. The method measures the split efficiently, even when A2–P2 overlap is ≤ 20ms and the normalized peak temporal ratio of P2 to A2 is low (≥0.22). In the second part, the developed method can measure the duration, splits, and energy of instantaneous frequency by identifying start and end positions of the A2s and P2s. The diagnosis related to duration and energy of IFs (EIFs) of A2s-P2s is also examined. The developed method explicitly guides to distinguish the normal/abnormal S2s including the types of S2 splits. The method is characterized by Hilbert transform-based IF estimation as well as the localization technique based on the reassignment of SPWVD. The results show that the mean ± SD of the duration of A2s and P2s are 46.7±2.5ms and 41.8±2.4ms, respectively for normal subjects. The mean ± SD of the EIFs of A2s and P2s are 13.8±2.4 and 10.5±1.7, respectively. The third part, the detection of the S3 has been developed which could solve the misreading problem between the S3 and the abnormal S2 with ‘fixed split’ problem. The developed method detects the S3 based on nonlinear single decomposition and time-frequency localization. Based on the positional information, the S3 is distinguished and confirmed by measuring time delay between S2–S3. The result analysis shows that the method can detect the S3s correctly, even when normalized temporal energy and frequency of S3s are 〉 0.15, and 〉 35 Hz respectively. Finally the conclusions are drawn mentioning the limitation followed by future scopes.
50
"A new stethoscope for reduction of heart sounds from lung sound recordings." 2001. http://library.cuhk.edu.hk/record=b5890844.
Повний текст джерелаАнотація:
Yip Lung.Thesis (M.Phil.)--Chinese University of Hong Kong, 2001.
Includes bibliographical references.
Abstracts in English and Chinese.
Chapter 1 --- Introduction
Chapter 1.1 --- Heart and Lung Diseases --- p.1
Chapter 1.1.1 --- Hong Kong --- p.1
Chapter 1.1.2 --- China --- p.2
Chapter 1.1.3 --- the United States of America (USA) --- p.3
Chapter 1.2 --- Auscultation --- p.3
Chapter 1.2.1 --- Introduction of Auscultation --- p.4
Chapter 1.2.2 --- Comparison between Auscultation and Ultrasound --- p.6
Chapter 1.3 --- Stethoscope --- p.7
Chapter 1.3.1 --- History of Stethoscope --- p.7
Chapter 1.3.2 --- New Electronic Stethoscope --- p.14
Chapter 1.4 --- Main Purpose of the Study --- p.16
Chapter 1.5 --- Organization of Thesis --- p.16
References --- p.18
Chapter 2 --- A New Electronic Stethoscope's Head
Chapter 2.1 --- Introduction --- p.20
Chapter 2.2 --- Biopotential Electrode --- p.21
Chapter 2.2.1 --- Flexible Electrode --- p.21
Chapter 2.2.2 --- Laplacian Electrocardiogram --- p.22
Chapter 2.3 --- Transducer --- p.25
Chapter 2.4 --- Design of the Head of Stethoscope --- p.26
Chapter 2.5 --- Experimental Results --- p.27
Chapter 2.5.1 --- Bias Voltage of Condenser Microphone --- p.27
Chapter 2.5.2 --- Frequency Response of New Stethoscope's Head --- p.29
Chapter 2.6 --- Discussion --- p.30
Chapter 2.7 --- Section Summary --- p.31
References --- p.33
Chapter 3 --- Signal Pre-processing Unit
Chapter 3.1 --- Introduction --- p.35
Chapter 3.2 --- High Input Impedance IC Amplifier --- p.36
Chapter 3.3 --- Voltage Control Voltage Source High Pass Filter Circuit --- p.37
Chapter 3.4 --- Multiple Feed Back Low Pass Filter Circuit --- p.39
Chapter 3.5 --- Overall Circuit --- p.41
Chapter 3.6 --- Experimental Results --- p.43
Chapter 3.7 --- Discussion --- p.46
Chapter 3.8 --- Section Summary --- p.47
References --- p.48
Chapter 4 --- Central Platform
Chapter 4.1 --- Introduction --- p.49
Chapter 4.2 --- Adaptive Filter --- p.49
Chapter 4.2.1 --- Introduction to Adaptive Filtering --- p.49
Chapter 4.2.2 --- Least-Mean-Square (LMS) Algorithm --- p.51
Chapter 4.2.3 --- Applications --- p.52
Chapter 4.3 --- Offline Processing --- p.54
Chapter 4.3.1 --- WINDAQ and MATLAB --- p.55
Chapter 4.3.2 --- Direct Reference Algorithm --- p.57
Chapter 4.3.3 --- Determination of Parameters in DRA --- p.62
Chapter 4.3.4 --- Experimental Results of DRA --- p.67
Chapter 4.3.5 --- Acoustic Waveform Based Algorithm --- p.72
Chapter 4.3.6 --- Experimental Results of AWBA --- p.81
Chapter 4.4 --- Online Processing --- p.85
Chapter 4.4.1 --- LABVIEW --- p.85
Chapter 4.4.2 --- Automated Gain Control --- p.88
Chapter 4.4.3 --- Implementation of LMS adaptive filter --- p.89
Chapter 4.4.4 --- Experimental Results of Online-AGC --- p.92
Chapter 4.5 --- Discussion --- p.93
Chapter 4.6 --- Section Summary --- p.97
References --- p.98
Chapter 5 --- Conclusion and Further Development
Chapter 5.1 --- Conclusion of the Main Contribution --- p.100
Chapter 5.2 --- Future Works --- p.102
Chapter 5.2.1 --- Modification of the Head of Stethoscope --- p.102
Chapter 5.2.2 --- Validation of Abnormal Breath --- p.102
Chapter 5.2.3 --- Low Frequency Analysis --- p.102
Chapter 5.2.4 --- AGC-AWBA Approach --- p.102
Chapter 5.2.5 --- Standalone Device --- p.103
Chapter 5.2.6 --- Demand on Stethoscope --- p.109
References --- p.110
Appendix
Chapter A.1 --- Determination of parameters in VCVS High Pass Filter --- p.106
Chapter A.2 --- Determination of parameters in MFB Low Pass Filter --- p.110
Chapter A.3 --- Source code of DRA (MATLAB) --- p.114
Chapter A.4 --- Source code of AWBA (MATLAB) --- p.129
Chapter A.5 --- Source code of online AGC (LABVIEW) --- p.134