Feature extraction for the differentiation of dry and wet cough sounds

Chatrzarrin, Hanieh

doi:10.22215/etd/2011-06745

Cited by 10 publications

(34 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As far as we know, this is the first attempt to develop objective technology for the dry/wet classification of pediatric cough sounds, espcially in diseases such as pneumonia. Our work is also unique for the reason that we proposed and validated methods to classify a given cough event into dry/wet groups in contrast to existing work, 5,14 which are limited to qualitaively describing chracteristics of cough events pre-classified by a human observer. The results presented in this paper are based on 536 cough events from 78 subjects, compared to existing work which use no more than 30 coughs in their descriptive analyses.…”

Section: Discussionmentioning

confidence: 99%

“…5,14 Murata et al 14 argued that cough sound frequencies can be used to discriminate between wet and dry coughs. Chatrzarrin et al 5 proposed peaks of the energy envelop and spectral features of the cough sounds for the same purpose. These studies opened up a new branch of research in respiratory sound analysis.…”

Section: Introductionmentioning

confidence: 99%

“…No definitive classification algorithm or results were presented for wet/dry differentiation. The amount of data analyzed was fairly limited, 30 cough samples from 10 subjects (5 healthy and 5 bronchitis patients) in Murata et al 14 and a total of 16 coughs in Chatrzarrin et al, 5 making the interpretation of the results difficult.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Identification of Wet and Dry Cough in Pediatric Patients with Respiratory Diseases

et al. 2013

View full text Add to dashboard Cite

Cough is the most common symptom of several respiratory diseases. It is a defense mechanism of the body to clear the respiratory tract from foreign materials inhaled accidentally or produced internally by infections. The identification of wet and dry cough is an important clinical finding, aiding in the differential diagnosis especially in children. Wet coughs are more likely to be associated with lower respiratory track bacterial infections. At present during a typical consultation session, the wet/dry decision is based on the subjective judgment of a physician. It is not available for the non-trained person, long term monitoring or in the assessment of treatment efficacy. In this paper we address these issues and develop an automated technology to classify cough into 'wet' and 'dry' categories. We propose novel features and a Logistic regression model (LRM) for the classification of coughs into wet/dry classes. The performance of the method was evaluated on a clinical database of pediatric coughs (C = 536) recorded using a bed-side non-contact microphone from N = 78 patients. Results of the automatic classification were compared against two expert human scorers. The sensitivity and specificity of the LRM in picking wet coughs were between 87 and 88% with 95% confidence interval on training/validation dataset (310 cough events from 60 patients) and 84 and 76% respectively on prospective dataset (117 cough events from 18 patients). The kappa agreement with two expert human scorers on prospective dataset was 0.51. These results indicate the potential of the method as a useful clinical tool for cough monitoring, especially at home settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Identification of Wet and Dry Cough in Pediatric Patients with Respiratory Diseases

et al. 2013

View full text Add to dashboard Cite

show abstract

“…A new technique, called "swept frequency method", based on the use of radiation force in the standing acoustic wave is also being explored in various ways [13]. A cough analysis system for tracking the recovery of pulmonary tuberculosis patient as well as feature extraction for the differentiation of dry and wet cough is also explored [14]- [16]. A lab free method for assessing patient recovery particularly that may have drug resistant tuberculosis is investigated.…”

Section: Introductionmentioning

confidence: 99%

Real time acquisition and frequency domain analysis of acoustic patterns of fluids for applications in the field of homeland security

Singh

Bansal

2014

2014 Innovative Applications of Computational Intelligence on Power, Energy and Controls With Their Impact on Humanity (CIPECH)

View full text Add to dashboard Cite

This paper investigates acoustic patterns generated by different liquids in real time based on spectral analysis technique which finds a lot of relevance in various fields related to defense and homeland security. Some of the drawbacks with existing techniques include limitations with acquisition of well defined patterns for various liquids. To overcome these limitations, this paper describes a technique which involves generation of a single frequency tone in MATLAB with the help of a program and passing that signal through the liquid and then further capturing and analyzing the received signal using a virtual spectrum analyzer. Piezoelectric sensors are used for transmission and receiving the tone through the fluid. The arrangement discussed successfully captures acoustic patterns in non destructive way for five different liquids/solutions by exciting them with various single frequency tones. Thus a low cost system that exhibits consistency in results and can quickly acquire specific acoustic patterns for various fluids is developed that also facilitates easyto-interpret measurement results.

show abstract

“…to -speaker = 250cm) 68 Table 9: Complete microphone array LSS (DMic-to-speaker = 150cm) 69 Cough sound discrimination algorithms are part of a cough sound monitoring system whereby detected cough sounds are further classified into various cough types such as wet, dry and whooping. A novel cough sound discrimination system capable of distinguishing between dry and wet cough sounds was recently developed by [16]. The mentioned cough sound discriminator algorithms were developed and tested under ideal conditions without taking into account noise and reverberation.…”

Section: Avismentioning

confidence: 99%

Cough sound discrimination in noisy and reverberant environments using microphone arrays

Moradshahi¹

View full text Add to dashboard Cite

Feature extraction for the differentiation of dry and wet cough sounds

Cited by 10 publications

References 39 publications

Automatic Identification of Wet and Dry Cough in Pediatric Patients with Respiratory Diseases

Automatic Identification of Wet and Dry Cough in Pediatric Patients with Respiratory Diseases

Real time acquisition and frequency domain analysis of acoustic patterns of fluids for applications in the field of homeland security

Cough sound discrimination in noisy and reverberant environments using microphone arrays

Contact Info

Product

Resources

About