New Non-invasive Automatic Cough Counting Program Based on 6 Types of Classified Cough Sounds

Murata, Akira; Ohota, Nao; Shibuya, Atsuo; Ono, Hiroshi; Kudoh, Shoji

doi:10.2169/internalmedicine.45.1449

Cited by 10 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cough sound signals were converted into absolute values. Subsequently, the absolute values of the waveform of cough sounds were smoothed using a 20 ms time window to extract the envelopes [26]. The CPSL value was calculated from the maximal value of the cough sound data obtained under the different experimental conditions using LabChart version 8 software (Figure 2b,d,e).…”

Section: Methodsmentioning

confidence: 99%

Estimation of Cough Peak Flow Using Cough Sounds

Umayahara

Soh

Sekikawa

et al. 2018

Sensors

View full text Add to dashboard Cite

Cough peak flow (CPF) is a measurement for evaluating the risk of cough dysfunction and can be measured using various devices, such as spirometers. However, complex device setup and the face mask required to be firmly attached to the mouth impose burdens on both patients and their caregivers. Therefore, this study develops a novel cough strength evaluation method using cough sounds. This paper presents an exponential model to estimate CPF from the cough peak sound pressure level (CPSL). We investigated the relationship between cough sounds and cough flows and the effects of a measurement condition of cough sound, microphone type and participant’s height and gender on CPF estimation accuracy. The results confirmed that the proposed model estimated CPF with a high accuracy. The absolute error between CPFs and estimated CPFs were significantly lower when the microphone distance from the participant’s mouth was within 30 cm than when the distance exceeded 30 cm. Analysis of the model parameters showed that the estimation accuracy was not affected by participant’s height or gender. These results indicate that the proposed model has the potential to improve the feasibility of measuring and assessing CPF.

show abstract

Section: Methodsmentioning

confidence: 99%

Estimation of Cough Peak Flow Using Cough Sounds

Umayahara

Soh

Sekikawa

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…However the method is labour-intensive and probably impractical in ambulatory conditions. For these reasons automated audiometric methods have been devised [24][25][26]. These are dealt with in detail elsewhere in this Special Issue [27].…”

Section: Frequencymentioning

confidence: 99%

What is cough and what should be measured?

Fontana

Widdicombe

2007

Pulmonary Pharmacology & Therapeutics

View full text Add to dashboard Cite

“…We determined the mean and maximal values of the sound events intensity (parameters TP mean and TP max ). The cough sound can be characterized by the sudden rise of a waveform with one or several large amplitudes, while voice sounds show a gradual rise of their waveform (10). For this reason the characteristic parameter, which can be calculated, was the parameter slope.…”

Section: Sound Events Analysismentioning

confidence: 99%

“…The obtained sound events are classified according to the mathematical sound events analysis alone (3,4), or the input data are enlarged to the EMG recordings with the aim to better distinguish the analyzed cough sounds from the other non-cough sounds (5,6). The obtained sound events are analyzed in the time and frequency domain (7,8,9,10). For sound events classification are used the classification trees (11), artificial neural networks (3), hidden Markov models (4), or a hybrid model, which is the combination of the artificial neural network and hidden Markov model (12).…”

Section: Introductionmentioning

confidence: 99%

Cough Sound Analysis

Martinek¹,

Klco²,

Vrabec³

et al. 2013

Acta Medica Martiniana

View full text Add to dashboard Cite

A b s t r a c tCough is the most common symptom of many respiratory diseases. Currently, no standardized methods exist for objective monitoring of cough, which could be commercially available and clinically acceptable. Our aim is to develop an algorithm which will be capable, according to the sound events analysis, to perform objective ambulatory and automated monitoring of frequency of cough. Because speech is the most common sound in 24-hour recordings, the first step for developing this algorithm is to distinguish between cough sound and speech. For this purpose we obtained recordings from 20 healthy volunteers. All subjects performed continuous reading of the text from the book with voluntary coughs at the indicated instants. The obtained sounds were analyzed using by linear and non-linear analysis in the time and frequency domain. We used the classification tree for the distinction between cough sound and speech. The median sensitivity was 100% and the median specificity was 95%. In the next step we enlarged the analyzed sound events. Apart from cough sounds and speech the analyzed sounds were induced sneezing, voluntary throat and nasopharynx clearing, voluntary forced ventilation, laughing, voluntary snoring, eructation, nasal blowing and loud swallowing. The sound events were obtained from 32 healthy volunteers and for their analysis and classification we used the same algorithm as in previous study. The median sensitivity was 86% and median specificity was 91%. In the final step, we tested the effectiveness of our developed algorithm for distinction between cough and non-cough sounds produced during normal daily activities in patients suffering from respiratory diseases. Our study group consisted from 9 patients suffering from respiratory diseases. The recording time was 5 hours. The number of coughs counted by our algorithm was compared with manual cough counts done by two skilled co-workers. We have found that the number of cough analyzed by our algorithm and manual counting, as well, were disproportionately different. For that reason we have used another methods for the distinction of cough sound from non-cough sounds. We have compared the classification tree and artificial neural networks. Median sensitivity was increasing from 28% (classification tree) to 82% (artificial neural network), while the median specificity was not changed significantly. We have enlarged our characteristic parameters of the Mel frequency cepstral coefficients, the weighted Euclidean distance and the first and second derivative in time. Likewise the modification of classification algorithm is under our interest.

show abstract

New Non-invasive Automatic Cough Counting Program Based on 6 Types of Classified Cough Sounds

Abstract: Abstract

Cited by 10 publications

References 24 publications

Estimation of Cough Peak Flow Using Cough Sounds

Estimation of Cough Peak Flow Using Cough Sounds

What is cough and what should be measured?

Cough Sound Analysis

Contact Info

Product

Resources

About