Objective:To explore the research landscape and hotspots of Computerized Respiratory Sound Analysis(CORSA)and provide a reference for future in-depth studies.Methods:Literature related to CORSA published up to August ...Objective:To explore the research landscape and hotspots of Computerized Respiratory Sound Analysis(CORSA)and provide a reference for future in-depth studies.Methods:Literature related to CORSA published up to August 27,2020,was retrieved from the Web of Science Core Collection.CiteSpace 5.6.R3 was used to perform co-authorship analysis,institutional collaboration analysis,keyword co-occurrence analysis,and co-citation analysis.Results:A total of 1,897 publications were included.Co-authorship analysis identified several influential contributors,including Zahra Moussavi,Kenneth Sundaraj,and H.Pasterkamp.Major research institutions included the University of Manitoba,the University of Queensland,and Aristotle University of Thessaloniki.Keyword co-occurrence analysis indicated that“respiratory sound,”“lung sound,”“asthma,”“children,”and“classification”were major research themes.The most frequently co-cited articles were published by Arati Gurung(2011),Mohammed Bahoura(2009),and H.Pasterkamp(1997).Highly cited journals included Chest,the American Journal of Respiratory and Critical Care Medicine,and IEEE Transactions on Biomedical Engineering.Conclusion:CORSA research is primarily driven by European and North American scholars and institutions,with China still in an early stage of development.Current hotspots include respiratory sound acquisition and processing,feature extraction methods such as Mel-frequency cepstral coefficients(MFCCs),and classification techniques based on machine learning and deep learning.CORSA is suitable for diverse populations and is widely applied in respiratory diseases,especially bronchial asthma.Its non-invasive nature offers particular advantages for infants and pregnant women.Although CORSA demonstrates strong clinical potential,its clinical translation remains limited.Advancing clinical applications and bridging the gap between research and practice will be key directions for future development.The prominence of top-tier respiratory and engineering journals among citations suggests that CORSA is an emerging and influential research frontier.展开更多
AIM: To determine the value of bowel sounds analysis using an electronic stethoscope to support a clinical diagnosis of intestinal obstruction. METHODS: Subjects were patients who presented with a diagnosis of possibl...AIM: To determine the value of bowel sounds analysis using an electronic stethoscope to support a clinical diagnosis of intestinal obstruction. METHODS: Subjects were patients who presented with a diagnosis of possible intestinal obstruction based on symptoms, signs, and radiological findings. A 3MTH Littmann Model 4100 electronic stethoscope was used in this study. With the patients lying supine, six 8-second recordings of bowel sounds were taken from each patient from the lower abdomen. The recordings were analysed for sound duration, soundto-sound interval, dominant frequency, and peak frequency. Clinical and radiological data were reviewed and the patients were classified as having either acute, subacute, or no bowel obstruction. Comparison of bowel sound characteristics was made between these subgroups of patients. In the presence of an obstruction, the site of obstruction was identified and bowel calibre was also measured to correlate with bowel sounds. RESULTS: A total of 71 patients were studied during the period July 2009 to January 2011. Forty patientshad acute bowel obstruction (27 small bowel obstruction and 13 large bowel obstruction), 11 had subacute bowel obstruction (eight in the small bowel and three in large bowel) and 20 had no bowel obstruction (diagnoses of other conditions were made). Twenty-five patients received surgical intervention (35.2%) during the same admission for acute abdominal conditions. A total of 426 recordings were made and 420 recordings were used for analysis. There was no significant difference in sound-to-sound interval, dominant frequency, and peak frequency among patients with acute bowel obstruction, subacute bowel obstruction, and no bowel obstruction. In acute large bowel obstruction, the sound duration was significantly longer (median 0.81 s vs 0.55 s, P = 0.021) and the dominant frequency was significantly higher (median 440 Hz vs 288 Hz, P = 0.003) when compared to acute small bowel obstruction. No significant difference was seen between acute large bowel obstruction and large bowel pseudoobstruction. For patients with small bowel obstruction, the sound-to-sound interval was significantly longer in those who subsequently underwent surgery compared with those treated non-operatively (median 1.29 s vs 0.63 s, P < 0.001). There was no correlation between bowel calibre and bowel sound characteristics in both acute small bowel obstruction and acute large bowel obstruction. CONCLUSION: Auscultation of bowel sounds is nonspecific for diagnosing bowel obstruction. Differences in sound characteristics between large bowel and small bowel obstruction may help determine the likely site of obstruction.展开更多
Objective To assess the diagnostic accuracy of bowel sound analysis for irritable bowel syndrome(IBS)with a systematic review and meta-analysis.Methods We searched MEDLINE,Embase,the Cochrane Library,Web of Science,an...Objective To assess the diagnostic accuracy of bowel sound analysis for irritable bowel syndrome(IBS)with a systematic review and meta-analysis.Methods We searched MEDLINE,Embase,the Cochrane Library,Web of Science,and IEEE Xplore databases until September 2023.Cross-sectional and case-control studies on diagnostic accuracy of bowel sound analysis for IBS were identified.We estimated the pooled sensitivity,specificity,positive likelihood ratio,negative likeli-hood ratio,and diagnostic odds ratio with a 95% confidence interval(CI),and plotted a summary receiver operat-ing characteristic curve and evaluated the area under the curve.Results Four studies were included.The pooled diagnostic sensitivity,specificity,positive likelihood ratio,nega-tive likelihood ratio,and diagnostic odds ratio were 0.94(95%CI,0.87‒0.97),0.89(95%CI,0.81‒0.94),8.43(95%CI,4.81‒14.78),0.07(95%CI,0.03‒0.15),and 118.86(95%CI,44.18‒319.75),respectively,with an area under the curve of 0.97(95%CI,0.95‒0.98).Conclusions Computerized bowel sound analysis is a promising tool for IBS.However,limited high-quality data make the results'validity and applicability questionable.There is a need for more diagnostic test accuracy studies and better wearable devices for monitoring and analysis of IBS.展开更多
Auscultation is crucial for the diagnosis of respiratory system diseases.However,traditional stethoscopes have inherent limitations,such as inter-listener variability and subjectivity,and they cannot record respirator...Auscultation is crucial for the diagnosis of respiratory system diseases.However,traditional stethoscopes have inherent limitations,such as inter-listener variability and subjectivity,and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine.The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education.On this basis,machine learning,particularly deep learning,enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes.This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence(AI)in this field.We focus on each component of deep learning-based lung sound analysis systems,including the task categories,public datasets,denoising methods,and,most importantly,existing deep learning methods,i.e.,the state-of-the-art approaches to convert lung sounds into two-dimensional(2D)spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds.Additionally,this review highlights current challenges in this field,including the variety of devices,noise sensitivity,and poor interpretability of deep models.To address the poor reproducibility and variety of deep learning in this field,this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension:https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis.展开更多
For on-line monitoring of welding quality, the characteristics of the arc sound signals in short circuit CO2 GMAW were analyzed in the time and frequency domains. The arc sound presents a series of ringing-like oscill...For on-line monitoring of welding quality, the characteristics of the arc sound signals in short circuit CO2 GMAW were analyzed in the time and frequency domains. The arc sound presents a series of ringing-like oscillations that occur at the end of short circuit i. e. the moment of arc re-ignition, and distributes mainly in the frequency band below 10 kHz. A concept of the arc tone channel and its equivalent electrical model were suggested, which is considered a time-dependent distributed parametric system of which the transmission properties depend upon the geometric and physical characteristics of the arc and surroundings, and is excited by the sound source results from the change of arc energy so that results in arc sound. The linear prediction coding （ LPC ） model is an estimation of the tone channel. The radial basis function （ RBF ） neural networks were built for on-line pattern recognition of the gas-lack in welding, in which the input vectors were formed with the LPC coefficients. The test results proved that the LPC model of arc sound and the RBF networks are feasible in on-line quality monitoring.展开更多
Noise artifacts are one of the key obstacles in applying continuous monitoring and computer-assisted analysis of lung sounds. Traditional adaptive noise cancellation (ANC) methodologies work reasonably well when signa...Noise artifacts are one of the key obstacles in applying continuous monitoring and computer-assisted analysis of lung sounds. Traditional adaptive noise cancellation (ANC) methodologies work reasonably well when signal and noise are stationary and independent. Clinical lung sound auscultation encounters an acoustic environment in which breath sounds are not stationary and often correlate with noise. Consequendy, capability of ANC becomes significantly compromised. This paper introduces a new methodology for extracting authentic lung sounds from noise-corrupted measurements. Unlike traditional noise cancellation methods that rely on either frequency band separation or signal/noise independence to achieve noise reduction, this methodology combines the traditional noise canceling methods with the unique feature of time-split stages in breathing sounds. By employing a multi-sensor system, the method first employs a high-pass filter to eliminate the off-band noise, and then performs time-shared blind identification and noise cancellation with recursion from breathing cycle to cycle. Since no frequency separation or signal/noise independence is required, this method potentially has a robust and reliable capability of noise reduction, complementing the traditional methods.展开更多
Based on measuring the cross-spectrum density of sound pressure between two hydrophones, the facility for underwater sound intensity measurement is investigated and designed. According to the principle of two-hydroph...Based on measuring the cross-spectrum density of sound pressure between two hydrophones, the facility for underwater sound intensity measurement is investigated and designed. According to the principle of two-hydrophone method for intensity measurement, the error analysis is carried out. Given the method of sound intensity measurement calibration for this underwater sound intensity measurement facility, the uncertainty of intensity measurement by this facility is evaluated. It is shown that the analysis and evaluation are agreeable to the experimental results.展开更多
Although the sonic soot cleaning techniques have been applied in boilers in power plants, petrochemical works and general industries world wide, most of the correlated basic problems have not been well solved yet. By ...Although the sonic soot cleaning techniques have been applied in boilers in power plants, petrochemical works and general industries world wide, most of the correlated basic problems have not been well solved yet. By using Helmholtz integral equation, sound wave scattered by heat-exchanger tubes is numerically calculated. Sound field distribution characteristics on the tube surfaces and around the tube group is obtained. The results can be applied to the development of sonic soot cleaning techniques in boilers.展开更多
A modeling method for irregular sound enclosures was proposed based on the Chebyshev-variational theory. A rectangular space was first assumed to bound the irregular sound space and the sound pressure in the rectangul...A modeling method for irregular sound enclosures was proposed based on the Chebyshev-variational theory. A rectangular space was first assumed to bound the irregular sound space and the sound pressure in the rectangular space expressed as a triple-Chebyshev series. Next, a coordinate transformation was performed and the Lagrangian functional of the irregular sound space obtained. Finally, the Lagrangian functional was solved under the Ritz method framework, and the enclosure＇s acoustic characteristic equation deduced and the eigenpairs obtained. The accuracy of the present method was validated according to agreement between the present results and finite element results for an enclosure with a curved surface.Furthermore, the acoustic characteristics of a trapezoidal enclosure and an enclosure with an inner groove were investigated. The results showed that the mode shapes of the trapezoidal sound space changed with increased inclination angle and the natural frequencies, except the first order, of the sound space with a rectangular inner groove decreased with increased groove depth.展开更多
The vibration and sound radiation of a submerged spherical shell are studied in the time-domain by Laplace transform method, where a CW pulse force acts at the apex of the shell. The numerical results for the case of ...The vibration and sound radiation of a submerged spherical shell are studied in the time-domain by Laplace transform method, where a CW pulse force acts at the apex of the shell. The numerical results for the case of long pulse show that the different vibrational modes and the resonant or beat radiated sound are excited for different carrier-frequencies, but litle sound is radiated for some vibrational modes. For the case of short pulse the waveforms of the pulse become widened and deformed, when the pulse propagates between apexes of the shell. Then, the Doubly Asymptotic Approximations (DAA2) and Kirchhoff's Retarded Potential Formulate (KRPF)are used to solve the same problem. It is shown that the results of DAA2 and KRPF method have a good agreement with the results of Laplace transform method.展开更多
An advanced signal processing technique, higher-order spectra, is proposed to in vestigate the nonlinear coupling phenomena of the heart sounds. To extract more higher-order information of the heart sounds, a non-Gaus...An advanced signal processing technique, higher-order spectra, is proposed to in vestigate the nonlinear coupling phenomena of the heart sounds. To extract more higher-order information of the heart sounds, a non-Gaussian AR model is selected for parametric bispectral estimation in analyzing several kinds of heart sounds. The non-Gaussian AR model of the sound signals is llsed to detect quadratic nonlinear interactions and to classify two patterns of heart sounds in terms of the parametric bispectral estimate. The bispectral cross-correlation is employed to the order determination of the model. Several real heart sound data are imple mented to show that the quadratic nonlinearity exist in both normal and clinical heart sounds.It was found that bispectral techniques are effective and useful tools in analyzing heart sounds and other acoustical signals展开更多
Numerical analysis of three-dimensional sound propagation in soft-soft or soft-hard circular ducts with circumferential and axial modes of sound sources at the inlet has been carried out. In this paper , the numerical...Numerical analysis of three-dimensional sound propagation in soft-soft or soft-hard circular ducts with circumferential and axial modes of sound sources at the inlet has been carried out. In this paper , the numerical method and the samples are offered and the effects of circumferential and axial modes on numerical results are discussed in detail .展开更多
By analyzing the differences between binaural recording and real listening, it was deduced that there were some unrevealed auditory localization clues, and the sound pressure distribution pattern at the entrance of ea...By analyzing the differences between binaural recording and real listening, it was deduced that there were some unrevealed auditory localization clues, and the sound pressure distribution pattern at the entrance of ear canal was probably a clue. It was proved through the listening test that the unrevealed auditory localization clues really exist with the reduction to absurdity. And the effective frequency bands of the unrevealed localization clues were in- duced and summed. The result of finite element based simulations showed that the pressure distribution at the entrance of ear canal was non-uniform, and the pattern was related to the direction of sound source. And it was proved that the sound pressure distribution pattern at the entrance of the ear canal carried the sound source direction information and could be used as an unrevealed localization clue. The frequency bands in which the sound pressure distribution patterns had significant differences between front and back sound source directions were roughly matched with the effective frequency bands of unrevealed localization clues obtained from the listening tests. To some extent, it supports the pattern could be a kind of unrevealed auditory hypothesis that the sound pressure distribution localization clues.展开更多
Cardiovascular diseases are a prominent cause of mortality,emphasizing the need for early prevention and diagnosis.Utilizing artificial intelligence(AI)models,heart sound analysis emerges as a noninvasive and universa...Cardiovascular diseases are a prominent cause of mortality,emphasizing the need for early prevention and diagnosis.Utilizing artificial intelligence(AI)models,heart sound analysis emerges as a noninvasive and universally applicable approach for assessing cardiovascular health conditions.However,real-world medical data are dispersed across medical institutions,forming“data islands”due to data sharing limitations for security reasons.To this end,federated learning(FL)has been extensively employed in the medical field,which can effectively model across multiple institutions.Additionally,conventional supervised classification methods require fully labeled data classes,e.g.,binary classification requires labeling of positive and negative samples.Nevertheless,the process of labeling healthcare data is timeconsuming and labor-intensive,leading to the possibility of mislabeling negative samples.In this study,we validate an FL framework with a naive positive-unlabeled(PU)learning strategy.Semisupervised FL model can directly learn from a limited set of positive samples and an extensive pool of unlabeled samples.Our emphasis is on vertical-FL to enhance collaboration across institutions with different medical record feature spaces.Additionally,our contribution extends to feature importance analysis,where we explore 6 methods and provide practical recommendations for detecting abnormal heart sounds.The study demonstrated an impressive accuracy of 84%,comparable to outcomes in supervised learning,thereby advancing the application of FL in abnormal heart sound detection.展开更多
On the basis of the frequency domain acoustic solation of sources in arbitrary motion, in this paper an approximate acoustic solution of a rotating point source in near field is given, which is the superposition of th...On the basis of the frequency domain acoustic solation of sources in arbitrary motion, in this paper an approximate acoustic solution of a rotating point source in near field is given, which is the superposition of the well-Known far field solution and three near field modification items on the condition that the rotating radius is acoustically compact compared with the field sound wavelength. Accordingly the near field Green function in free space is obtained. The characteristic directionality of the sound field induced by source rotating is discussed, and the influences of source position, source frequency and rotating frequency are studied in detail.展开更多
Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade.Nevertheless,lacking on standard open...Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade.Nevertheless,lacking on standard open-access database made it difficult to maintain a sustainable and comparable research before the first release of the PhysioNet CinC Challenge Dataset.However,inconsistent standards on data collection,annotation,and partition are still restraining a fair and efficient comparison between different works.To this line,we introduced and benchmarked a first version of the Heart Sounds Shenzhen(HSS)corpus.Motivated and inspired by the previous works based on HSS,we redefined the tasks and make a comprehensive investigation on shallow and deep models in this study.First,we segmented the heart sound recording into shorter recordings(10 s),which makes it more similar to the human auscultation case.Second,we redefined the classification tasks.Besides using the 3 class categories(normal,moderate,and mild/severe)adopted in HSS,we added a binary classification task in this study,i.e.,normal and abnormal.In this work,we provided detailed benchmarks based on both the classic machine learning and the state-of-the-art deep learning technologies,which are reproducible by using open-source toolkits.Last but not least,we analyzed the feature contributions of best performance achieved by the benchmark to make the results more convincing and interpretable.展开更多
基金Beijing Hospitals Authority Clinical Medicine Development of Special Funding Support,Code(Project No.:YGLX202514)。
文摘Objective:To explore the research landscape and hotspots of Computerized Respiratory Sound Analysis(CORSA)and provide a reference for future in-depth studies.Methods:Literature related to CORSA published up to August 27,2020,was retrieved from the Web of Science Core Collection.CiteSpace 5.6.R3 was used to perform co-authorship analysis,institutional collaboration analysis,keyword co-occurrence analysis,and co-citation analysis.Results:A total of 1,897 publications were included.Co-authorship analysis identified several influential contributors,including Zahra Moussavi,Kenneth Sundaraj,and H.Pasterkamp.Major research institutions included the University of Manitoba,the University of Queensland,and Aristotle University of Thessaloniki.Keyword co-occurrence analysis indicated that“respiratory sound,”“lung sound,”“asthma,”“children,”and“classification”were major research themes.The most frequently co-cited articles were published by Arati Gurung(2011),Mohammed Bahoura(2009),and H.Pasterkamp(1997).Highly cited journals included Chest,the American Journal of Respiratory and Critical Care Medicine,and IEEE Transactions on Biomedical Engineering.Conclusion:CORSA research is primarily driven by European and North American scholars and institutions,with China still in an early stage of development.Current hotspots include respiratory sound acquisition and processing,feature extraction methods such as Mel-frequency cepstral coefficients(MFCCs),and classification techniques based on machine learning and deep learning.CORSA is suitable for diverse populations and is widely applied in respiratory diseases,especially bronchial asthma.Its non-invasive nature offers particular advantages for infants and pregnant women.Although CORSA demonstrates strong clinical potential,its clinical translation remains limited.Advancing clinical applications and bridging the gap between research and practice will be key directions for future development.The prominence of top-tier respiratory and engineering journals among citations suggests that CORSA is an emerging and influential research frontier.
文摘AIM: To determine the value of bowel sounds analysis using an electronic stethoscope to support a clinical diagnosis of intestinal obstruction. METHODS: Subjects were patients who presented with a diagnosis of possible intestinal obstruction based on symptoms, signs, and radiological findings. A 3MTH Littmann Model 4100 electronic stethoscope was used in this study. With the patients lying supine, six 8-second recordings of bowel sounds were taken from each patient from the lower abdomen. The recordings were analysed for sound duration, soundto-sound interval, dominant frequency, and peak frequency. Clinical and radiological data were reviewed and the patients were classified as having either acute, subacute, or no bowel obstruction. Comparison of bowel sound characteristics was made between these subgroups of patients. In the presence of an obstruction, the site of obstruction was identified and bowel calibre was also measured to correlate with bowel sounds. RESULTS: A total of 71 patients were studied during the period July 2009 to January 2011. Forty patientshad acute bowel obstruction (27 small bowel obstruction and 13 large bowel obstruction), 11 had subacute bowel obstruction (eight in the small bowel and three in large bowel) and 20 had no bowel obstruction (diagnoses of other conditions were made). Twenty-five patients received surgical intervention (35.2%) during the same admission for acute abdominal conditions. A total of 426 recordings were made and 420 recordings were used for analysis. There was no significant difference in sound-to-sound interval, dominant frequency, and peak frequency among patients with acute bowel obstruction, subacute bowel obstruction, and no bowel obstruction. In acute large bowel obstruction, the sound duration was significantly longer (median 0.81 s vs 0.55 s, P = 0.021) and the dominant frequency was significantly higher (median 440 Hz vs 288 Hz, P = 0.003) when compared to acute small bowel obstruction. No significant difference was seen between acute large bowel obstruction and large bowel pseudoobstruction. For patients with small bowel obstruction, the sound-to-sound interval was significantly longer in those who subsequently underwent surgery compared with those treated non-operatively (median 1.29 s vs 0.63 s, P < 0.001). There was no correlation between bowel calibre and bowel sound characteristics in both acute small bowel obstruction and acute large bowel obstruction. CONCLUSION: Auscultation of bowel sounds is nonspecific for diagnosing bowel obstruction. Differences in sound characteristics between large bowel and small bowel obstruction may help determine the likely site of obstruction.
基金funded by the National Natural Science Foundation of China(No.32170788)National High Level Hospital Clinical Research Funding(No.2022-PUMCH-B-023)Beijing Natural Science Foundation(No.7232123).
文摘Objective To assess the diagnostic accuracy of bowel sound analysis for irritable bowel syndrome(IBS)with a systematic review and meta-analysis.Methods We searched MEDLINE,Embase,the Cochrane Library,Web of Science,and IEEE Xplore databases until September 2023.Cross-sectional and case-control studies on diagnostic accuracy of bowel sound analysis for IBS were identified.We estimated the pooled sensitivity,specificity,positive likelihood ratio,negative likeli-hood ratio,and diagnostic odds ratio with a 95% confidence interval(CI),and plotted a summary receiver operat-ing characteristic curve and evaluated the area under the curve.Results Four studies were included.The pooled diagnostic sensitivity,specificity,positive likelihood ratio,nega-tive likelihood ratio,and diagnostic odds ratio were 0.94(95%CI,0.87‒0.97),0.89(95%CI,0.81‒0.94),8.43(95%CI,4.81‒14.78),0.07(95%CI,0.03‒0.15),and 118.86(95%CI,44.18‒319.75),respectively,with an area under the curve of 0.97(95%CI,0.95‒0.98).Conclusions Computerized bowel sound analysis is a promising tool for IBS.However,limited high-quality data make the results'validity and applicability questionable.There is a need for more diagnostic test accuracy studies and better wearable devices for monitoring and analysis of IBS.
基金This work is supported by the National Key Research and Development Program of China(2022YFC2407800)the General Program of National Natural Science Foundation of China(62271241)+1 种基金the Guangdong Basic and Applied Basic Research Foundation(2023A1515012983)the Shenzhen Fundamental Research Program(JCYJ20220530112601003).
文摘Auscultation is crucial for the diagnosis of respiratory system diseases.However,traditional stethoscopes have inherent limitations,such as inter-listener variability and subjectivity,and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine.The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education.On this basis,machine learning,particularly deep learning,enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes.This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence(AI)in this field.We focus on each component of deep learning-based lung sound analysis systems,including the task categories,public datasets,denoising methods,and,most importantly,existing deep learning methods,i.e.,the state-of-the-art approaches to convert lung sounds into two-dimensional(2D)spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds.Additionally,this review highlights current challenges in this field,including the variety of devices,noise sensitivity,and poor interpretability of deep models.To address the poor reproducibility and variety of deep learning in this field,this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension:https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis.
基金The work was supported by National Natural Science Foundation of China (No. 50275028).
文摘For on-line monitoring of welding quality, the characteristics of the arc sound signals in short circuit CO2 GMAW were analyzed in the time and frequency domains. The arc sound presents a series of ringing-like oscillations that occur at the end of short circuit i. e. the moment of arc re-ignition, and distributes mainly in the frequency band below 10 kHz. A concept of the arc tone channel and its equivalent electrical model were suggested, which is considered a time-dependent distributed parametric system of which the transmission properties depend upon the geometric and physical characteristics of the arc and surroundings, and is excited by the sound source results from the change of arc energy so that results in arc sound. The linear prediction coding （ LPC ） model is an estimation of the tone channel. The radial basis function （ RBF ） neural networks were built for on-line pattern recognition of the gas-lack in welding, in which the input vectors were formed with the LPC coefficients. The test results proved that the LPC model of arc sound and the RBF networks are feasible in on-line quality monitoring.
基金Hong Wang's research was supported in part by the Anesthesiology Department at Wayne State University and in part by Wayne State University Research Enhancement ProgramLeyi Wang" s research was supported in part by the National Science Foundation ( No.
文摘Noise artifacts are one of the key obstacles in applying continuous monitoring and computer-assisted analysis of lung sounds. Traditional adaptive noise cancellation (ANC) methodologies work reasonably well when signal and noise are stationary and independent. Clinical lung sound auscultation encounters an acoustic environment in which breath sounds are not stationary and often correlate with noise. Consequendy, capability of ANC becomes significantly compromised. This paper introduces a new methodology for extracting authentic lung sounds from noise-corrupted measurements. Unlike traditional noise cancellation methods that rely on either frequency band separation or signal/noise independence to achieve noise reduction, this methodology combines the traditional noise canceling methods with the unique feature of time-split stages in breathing sounds. By employing a multi-sensor system, the method first employs a high-pass filter to eliminate the off-band noise, and then performs time-shared blind identification and noise cancellation with recursion from breathing cycle to cycle. Since no frequency separation or signal/noise independence is required, this method potentially has a robust and reliable capability of noise reduction, complementing the traditional methods.
文摘Based on measuring the cross-spectrum density of sound pressure between two hydrophones, the facility for underwater sound intensity measurement is investigated and designed. According to the principle of two-hydrophone method for intensity measurement, the error analysis is carried out. Given the method of sound intensity measurement calibration for this underwater sound intensity measurement facility, the uncertainty of intensity measurement by this facility is evaluated. It is shown that the analysis and evaluation are agreeable to the experimental results.
文摘Although the sonic soot cleaning techniques have been applied in boilers in power plants, petrochemical works and general industries world wide, most of the correlated basic problems have not been well solved yet. By using Helmholtz integral equation, sound wave scattered by heat-exchanger tubes is numerically calculated. Sound field distribution characteristics on the tube surfaces and around the tube group is obtained. The results can be applied to the development of sonic soot cleaning techniques in boilers.
基金supported by the National Natural Science Foundation of China(51505237,51279035,51675286)sponsored by K.C.Wong Magna Fund in Ningbo University
文摘A modeling method for irregular sound enclosures was proposed based on the Chebyshev-variational theory. A rectangular space was first assumed to bound the irregular sound space and the sound pressure in the rectangular space expressed as a triple-Chebyshev series. Next, a coordinate transformation was performed and the Lagrangian functional of the irregular sound space obtained. Finally, the Lagrangian functional was solved under the Ritz method framework, and the enclosure＇s acoustic characteristic equation deduced and the eigenpairs obtained. The accuracy of the present method was validated according to agreement between the present results and finite element results for an enclosure with a curved surface.Furthermore, the acoustic characteristics of a trapezoidal enclosure and an enclosure with an inner groove were investigated. The results showed that the mode shapes of the trapezoidal sound space changed with increased inclination angle and the natural frequencies, except the first order, of the sound space with a rectangular inner groove decreased with increased groove depth.
文摘The vibration and sound radiation of a submerged spherical shell are studied in the time-domain by Laplace transform method, where a CW pulse force acts at the apex of the shell. The numerical results for the case of long pulse show that the different vibrational modes and the resonant or beat radiated sound are excited for different carrier-frequencies, but litle sound is radiated for some vibrational modes. For the case of short pulse the waveforms of the pulse become widened and deformed, when the pulse propagates between apexes of the shell. Then, the Doubly Asymptotic Approximations (DAA2) and Kirchhoff's Retarded Potential Formulate (KRPF)are used to solve the same problem. It is shown that the results of DAA2 and KRPF method have a good agreement with the results of Laplace transform method.
文摘An advanced signal processing technique, higher-order spectra, is proposed to in vestigate the nonlinear coupling phenomena of the heart sounds. To extract more higher-order information of the heart sounds, a non-Gaussian AR model is selected for parametric bispectral estimation in analyzing several kinds of heart sounds. The non-Gaussian AR model of the sound signals is llsed to detect quadratic nonlinear interactions and to classify two patterns of heart sounds in terms of the parametric bispectral estimate. The bispectral cross-correlation is employed to the order determination of the model. Several real heart sound data are imple mented to show that the quadratic nonlinearity exist in both normal and clinical heart sounds.It was found that bispectral techniques are effective and useful tools in analyzing heart sounds and other acoustical signals
基金The project is supported by National Natural Science Foundation of China and National Education Commission Foundaion of China
文摘Numerical analysis of three-dimensional sound propagation in soft-soft or soft-hard circular ducts with circumferential and axial modes of sound sources at the inlet has been carried out. In this paper , the numerical method and the samples are offered and the effects of circumferential and axial modes on numerical results are discussed in detail .
基金supported by the Science and Engineering Project of Communication University of China(3132016XNG1625)
文摘By analyzing the differences between binaural recording and real listening, it was deduced that there were some unrevealed auditory localization clues, and the sound pressure distribution pattern at the entrance of ear canal was probably a clue. It was proved through the listening test that the unrevealed auditory localization clues really exist with the reduction to absurdity. And the effective frequency bands of the unrevealed localization clues were in- duced and summed. The result of finite element based simulations showed that the pressure distribution at the entrance of ear canal was non-uniform, and the pattern was related to the direction of sound source. And it was proved that the sound pressure distribution pattern at the entrance of the ear canal carried the sound source direction information and could be used as an unrevealed localization clue. The frequency bands in which the sound pressure distribution patterns had significant differences between front and back sound source directions were roughly matched with the effective frequency bands of unrevealed localization clues obtained from the listening tests. To some extent, it supports the pattern could be a kind of unrevealed auditory hypothesis that the sound pressure distribution localization clues.
基金partially supported by the National Natural Science Foundation of China(grant number 62272044)the Ministry of Science and Technology of the People’s Republic of China with the STI2030-Major Projects(grant number 2021ZD0201900)+5 种基金the Teli Young Fellow Program from the Beijing Institute of Technology,Chinathe Grants-in-Aid for Scientific Research(grant number 20H00569)from the Ministry of Education,Culture,Sports,Science and Technology(MEXT),Japanthe JSPS KAKENHI(grant number 20H00569),Japanthe JST Mirai Program(grant number 21473074),Japanthe JST MOONSHOT Program(grant number JPMJMS229B),Japanthe BIT Research and Innovation Promoting Project(grant number 2023YCXZ014).
文摘Cardiovascular diseases are a prominent cause of mortality,emphasizing the need for early prevention and diagnosis.Utilizing artificial intelligence(AI)models,heart sound analysis emerges as a noninvasive and universally applicable approach for assessing cardiovascular health conditions.However,real-world medical data are dispersed across medical institutions,forming“data islands”due to data sharing limitations for security reasons.To this end,federated learning(FL)has been extensively employed in the medical field,which can effectively model across multiple institutions.Additionally,conventional supervised classification methods require fully labeled data classes,e.g.,binary classification requires labeling of positive and negative samples.Nevertheless,the process of labeling healthcare data is timeconsuming and labor-intensive,leading to the possibility of mislabeling negative samples.In this study,we validate an FL framework with a naive positive-unlabeled(PU)learning strategy.Semisupervised FL model can directly learn from a limited set of positive samples and an extensive pool of unlabeled samples.Our emphasis is on vertical-FL to enhance collaboration across institutions with different medical record feature spaces.Additionally,our contribution extends to feature importance analysis,where we explore 6 methods and provide practical recommendations for detecting abnormal heart sounds.The study demonstrated an impressive accuracy of 84%,comparable to outcomes in supervised learning,thereby advancing the application of FL in abnormal heart sound detection.
文摘On the basis of the frequency domain acoustic solation of sources in arbitrary motion, in this paper an approximate acoustic solution of a rotating point source in near field is given, which is the superposition of the well-Known far field solution and three near field modification items on the condition that the rotating radius is acoustically compact compared with the field sound wavelength. Accordingly the near field Green function in free space is obtained. The characteristic directionality of the sound field induced by source rotating is discussed, and the influences of source position, source frequency and rotating frequency are studied in detail.
基金partially supported by the Ministry of Science and Technology of the People's Republic of China with the STI2030-Major Projects(2021ZD0201900)the National Natural Science Foundation of China(No.62227807 and 62272044)+3 种基金the Teli Young Fellow Program from the Beijing Institute of Technology,Chinathe Natural Science Foundation of Shenzhen University General Hospital(No.SUGH2018QD013),Chinathe Shenzhen Science and Technology Innovation Commission Project(No.JCYJ20190808120613189),Chinathe Grants-in-Aid for Scientific Research(No.20H00569)from the Ministry of Education,Culture,Sports,Science and Technology(MEXT),Japan.
文摘Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade.Nevertheless,lacking on standard open-access database made it difficult to maintain a sustainable and comparable research before the first release of the PhysioNet CinC Challenge Dataset.However,inconsistent standards on data collection,annotation,and partition are still restraining a fair and efficient comparison between different works.To this line,we introduced and benchmarked a first version of the Heart Sounds Shenzhen(HSS)corpus.Motivated and inspired by the previous works based on HSS,we redefined the tasks and make a comprehensive investigation on shallow and deep models in this study.First,we segmented the heart sound recording into shorter recordings(10 s),which makes it more similar to the human auscultation case.Second,we redefined the classification tasks.Besides using the 3 class categories(normal,moderate,and mild/severe)adopted in HSS,we added a binary classification task in this study,i.e.,normal and abnormal.In this work,we provided detailed benchmarks based on both the classic machine learning and the state-of-the-art deep learning technologies,which are reproducible by using open-source toolkits.Last but not least,we analyzed the feature contributions of best performance achieved by the benchmark to make the results more convincing and interpretable.
