Limits...
Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment.

Espinoza-Cuadros F, Fernández-Pozo R, Toledano DT, Alcázar-Ramírez JD, López-Gonzalo E, Hernández-Gómez LA - Comput Math Methods Med (2015)

Bottom Line: Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector.A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs).Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.

View Article: PubMed Central - PubMed

Affiliation: GAPS Signal Processing Applications Group, Universidad Politécnica de Madrid, 28040 Madrid, Spain.

ABSTRACT
Obstructive sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). OSA is generally diagnosed through a costly procedure requiring an overnight stay of the patient at the hospital. This has led to proposing less costly procedures based on the analysis of patients' facial images and voice recordings to help in OSA detection and severity assessment. In this paper we investigate the use of both image and speech processing to estimate the apnea-hypopnea index, AHI (which describes the severity of the condition), over a population of 285 male Spanish subjects suspected to suffer from OSA and referred to a Sleep Disorders Unit. Photographs and voice recordings were collected in a supervised but not highly controlled way trying to test a scenario close to an OSA assessment application running on a mobile device (i.e., smartphones or tablets). Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector. A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs). Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.

No MeSH data available.


Related in: MedlinePlus

Representation of leave-one-out cross-validation and grid search process for training the regression model and predicting the AHI.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4664800&req=5

fig7: Representation of leave-one-out cross-validation and grid search process for training the regression model and predicting the AHI.

Mentions: In order to validate the regression model we employed leave-one-out cross-validation. To do this, one subject is removed from dataset for testing data and the other for training data. Then, in order to find the optimum complexity of the model, we apply a 5-fold cross-validation on training data to find the optimal parameters values of the support vector regression model. For this purpose we implement a “grid search” on the hyperparameters of the SVR model using 5-fold cross-validation. The grid search consists of an exhaustive search through specified set of hyperparameters (ϵ and C) of the SVR model. Therefore, various pairs of hyperparameters values are tried and the one with the best cross-validation MAE is picked. After finding the optimal parameter value, we train the model using the optimal hyperparameter values and the training dataset. Finally, the testing dataset is used to predict the AHI assigned to each input by using SVR models trained solely from the training dataset. The whole process is repeated for all dataset and it is depicted in Figure 7.


Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment.

Espinoza-Cuadros F, Fernández-Pozo R, Toledano DT, Alcázar-Ramírez JD, López-Gonzalo E, Hernández-Gómez LA - Comput Math Methods Med (2015)

Representation of leave-one-out cross-validation and grid search process for training the regression model and predicting the AHI.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4664800&req=5

fig7: Representation of leave-one-out cross-validation and grid search process for training the regression model and predicting the AHI.
Mentions: In order to validate the regression model we employed leave-one-out cross-validation. To do this, one subject is removed from dataset for testing data and the other for training data. Then, in order to find the optimum complexity of the model, we apply a 5-fold cross-validation on training data to find the optimal parameters values of the support vector regression model. For this purpose we implement a “grid search” on the hyperparameters of the SVR model using 5-fold cross-validation. The grid search consists of an exhaustive search through specified set of hyperparameters (ϵ and C) of the SVR model. Therefore, various pairs of hyperparameters values are tried and the one with the best cross-validation MAE is picked. After finding the optimal parameter value, we train the model using the optimal hyperparameter values and the training dataset. Finally, the testing dataset is used to predict the AHI assigned to each input by using SVR models trained solely from the training dataset. The whole process is repeated for all dataset and it is depicted in Figure 7.

Bottom Line: Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector.A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs).Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.

View Article: PubMed Central - PubMed

Affiliation: GAPS Signal Processing Applications Group, Universidad Politécnica de Madrid, 28040 Madrid, Spain.

ABSTRACT
Obstructive sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). OSA is generally diagnosed through a costly procedure requiring an overnight stay of the patient at the hospital. This has led to proposing less costly procedures based on the analysis of patients' facial images and voice recordings to help in OSA detection and severity assessment. In this paper we investigate the use of both image and speech processing to estimate the apnea-hypopnea index, AHI (which describes the severity of the condition), over a population of 285 male Spanish subjects suspected to suffer from OSA and referred to a Sleep Disorders Unit. Photographs and voice recordings were collected in a supervised but not highly controlled way trying to test a scenario close to an OSA assessment application running on a mobile device (i.e., smartphones or tablets). Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector. A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs). Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.

No MeSH data available.


Related in: MedlinePlus