Cookies?
Library Header Image
LSE Research Online LSE Library Services

Optimal tuning of support vector machines and k-NN algorithm by using Bayesian optimization for newborn cry signal diagnosis based on audio signal processing features

Lahmiri, Salim, Tadj, Chakib, Gargour, Christian and Bekiros, Stelios (2023) Optimal tuning of support vector machines and k-NN algorithm by using Bayesian optimization for newborn cry signal diagnosis based on audio signal processing features. Chaos, Solitons and Fractals, 167. ISSN 0960-0779

Full text not available from this repository.
Identification Number: 10.1016/j.chaos.2022.112972

Abstract

Recently, the number of machine learning models used to classify cry signals of healthy and unhealthy newborns has been significantly increasing. Various works have already reported encouraging classification results; however, fine-tuning of the hyper-parameters of machine leaning algorithms is still an open problem in the context of newborn cry signal classification. This paper proposes to use Bayesian optimization (BO) method to optimize the hyper-parameters of Support Vector Machine (SVM) with radial basis function (RBF) kernel and k-nearest neighbors (kNN) trained with different audio features separately or combined; namely, mel-frequency cepstral coefficients (MFCC), auditory-inspired amplitude modulation (AAM), and prosody. Particularly, the chi-square test is applied to each set of features to retain the ten most significant ones used to train optimal classifiers. The accuracy, sensitivity, and specificity of each experimental model are computed following the standard 10-fold cross-validation protocol. One of the contributions is an improvement over previous works on newborn cry signal classification used to distinguish between healthy and unhealthy ones over the same database, in terms of performance. The best model is the SVM trained with AAM ten most significant features achieved 83.62 % ± 0.022 accuracy, 59.18 % ± 0.0469 sensitivity, and 93.87 % ± 0.0190 specificity followed by kNN trained with ten most features from MFCC, AAM, and prosody to obtain 82.88 % ± 0.0144 accuracy, 55.34 % ± 0.0350 sensitivity, and 94.42 % ± 0.0075 specificity. These results outperformed existing works validated on the same database. In addition, optimally tuned SVM and kNN are fed with a restricted number of selected patterns so as the processing time for training and testing is significantly limited. This means that the RBF-SVM-BO classifier trained with AAM ten most significant features is more able to distinguish between healthy and unhealthy newborns.

Item Type: Article
Additional Information: © 2022 Elsevier Ltd
Divisions: LSE Health
Subjects: Q Science > QA Mathematics
Q Science > QC Physics
R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
Date Deposited: 05 Jan 2023 11:15
Last Modified: 04 Nov 2024 08:00
URI: http://eprints.lse.ac.uk/id/eprint/117715

Actions (login required)

View Item View Item