Swallowing Sound Recognition at Home Using GMM

Khlaifi, Hajer; Istrate, Dan; Demongeot, Jacques; Malouche, Dhafer

doi:10.1016/j.irbm.2018.10.009

Cited by 6 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A model including MFCC features, in particular, demonstrated good performance. The MFCC is a feature that is widely used for voice recognition [30,31] and for identifying swallowing sounds [23,36]. In this study, feature patterns using the MFCC as the basis showed the most superior performance.…”

Section: Discussionmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

“…Advances in machine learning confer the possibility of further improvement of accuracy when detecting swallowing sounds [22][23][24][25]. Khlaifi et al combined the Mel Frequency Cepstral Coefficient (MFCC) and a Gaussian Mixture Model (GMM) to achieve an 84.57% recognition rate [23]. In a study by Kuramoto et al, a recording database of healthy persons and patients with dysphagia was used to apply a deep learning model wherein the swallowing sounds versus noise were distinguished with a high accuracy of 97.3%, and showed that deep learning can effectively support a diagnosis of dysphagia [24].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Novel Approach Combining Shallow Learning and Ensemble Learning for the Automated Detection of Swallowing Sounds in a Clinical Database

Kimura,

Emoto,

Suzuki

et al. 2024

Sensors

View full text Add to dashboard Cite

Cervical auscultation is a simple, noninvasive method for diagnosing dysphagia, although the reliability of the method largely depends on the subjectivity and experience of the evaluator. Recently developed methods for the automatic detection of swallowing sounds facilitate a rough automatic diagnosis of dysphagia, although a reliable method of detection specialized in the peculiar feature patterns of swallowing sounds in actual clinical conditions has not been established. We investigated a novel approach for automatically detecting swallowing sounds by a method wherein basic statistics and dynamic features were extracted based on acoustic features: Mel Frequency Cepstral Coefficients and Mel Frequency Magnitude Coefficients, and an ensemble learning model combining Support Vector Machine and Multi-Layer Perceptron were applied. The evaluation of the effectiveness of the proposed method, based on a swallowing-sounds database synchronized to a video fluorographic swallowing study compiled from 74 advanced-age patients with dysphagia, demonstrated an outstanding performance. It achieved an F1-micro average of approximately 0.92 and an accuracy of 95.20%. The method, proven effective in the current clinical recording database, suggests a significant advancement in the objectivity of cervical auscultation. However, validating its efficacy in other databases is crucial for confirming its broad applicability and potential impact.

show abstract

Section: Discussionmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Novel Approach Combining Shallow Learning and Ensemble Learning for the Automated Detection of Swallowing Sounds in a Clinical Database

Kimura,

Emoto,

Suzuki

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The regulation at the inspiratory-expiratory transition is ensured by these pI neurons in the pontine Kölliker-Fuse nucleus, providing an eupneic inspiratory-expiratory transition; pI neurons start the post-inspiratory vagal nerve activity, when they are no more inhibited by the early inspiratory neurons eI: that occurs when eI neurons (which have a constant basal activity) are inhibited by the expiratory E neurons, these last being triggered by eI neurons and by the decrease of the pI neurons inhibition. The role of swallowing is partly unknown but the loss of the swallowing reflex after a brain stroke provokes a dyspneic breathing [3,24].…”

Section: 1mentioning

confidence: 99%

From conservative to dissipative non-linear differential systems. An application to the cardio-respiratory regulation

Demongeot¹,

Istrate²,

Khlaifi³

et al. 2020

Discrete &Amp; Continuous Dynamical Systems - S

View full text Add to dashboard Cite

We start by coupling negative 2-circuits, which are characteristic of the presence of a regulation loop in a dynamical system. This loop can be modelled with coupled differential equations represented in a first approach by a conservative differential system. Then, an example of regulation loop with a dissipative component will be given in human physiology by the vegetative system regulating the cardio-respiratory rhythms.

show abstract

“…GMM is a linear weighted combination of a certain number of Gaussian probability density functions. The probability density function of an N-order GMM is a linear combination of N single Gaussian distributions, which is used to describe the distribution of frame features in the feature space [33], as shown in (11).…”

Section: Sound Trainingmentioning

confidence: 99%

Research on Audio-Visual Detection Method for Conveyor Belt Longitudinal Tear

Hou

Qiao

et al. 2019

IEEE Access

View full text Add to dashboard Cite

As a key equipment for production and transportation, conveyor belts are widely used in the coal mining industry. Once the conveyor belt longitudinal tear occurs, it will seriously affect the production and even cause personal injury. Therefore, the longitudinal tear detection of the conveyor belt is extremely important. In this paper, the sound detection is introduced into the longitudinal tear detection of the conveyor belt, and an audio-visual detection method for conveyor belt longitudinal tear is proposed. Camera and microphone array are used to collect the image and sound signals of conveyor belt, and the conveyor belt is detected from both image and sound, respectively. Then the image and sound analysis results are combined to comprehensively judge the status of the conveyor belt. The experimental results show that the audiovisual detection method can accurately identify the normal, abnormal, and longitudinal tear of the conveyor belt. The detection accuracy is over 86.72% and the sensitivity of longitudinal tear detection is greater than 92.59%. The proposed audio-visual detection method is verified to meet the requirements of longitudinal tear detection of coal mining industry conveyor belts.

show abstract

Swallowing Sound Recognition at Home Using GMM

Cited by 6 publications

References 24 publications

Novel Approach Combining Shallow Learning and Ensemble Learning for the Automated Detection of Swallowing Sounds in a Clinical Database

Novel Approach Combining Shallow Learning and Ensemble Learning for the Automated Detection of Swallowing Sounds in a Clinical Database

From conservative to dissipative non-linear differential systems. An application to the cardio-respiratory regulation

Research on Audio-Visual Detection Method for Conveyor Belt Longitudinal Tear

Contact Info

Product

Resources

About