Deep Learning Assisted Neonatal Cry Classification via Support Vector Machine Models

Abstract

Neonatal infants communicate with us through cries. The infant cry signals have distinct patterns depending on the purpose of the cries. Preprocessing, feature extraction, and feature selection need expert attention and take much effort in audio signals in recent days. In deep learning techniques, it automatically extracts and selects the most important features. For this, it requires an enormous amount of data for effective classification. This work mainly discriminates the neonatal cries into pain, hunger, and sleepiness. The neonatal cry auditory signals are transformed into a spectrogram image by utilizing the short-time Fourier transform (STFT) technique. The deep convolutional neural network (DCNN) technique takes the spectrogram images for input. The features are obtained from the convolutional neural network and are passed to the support vector machine (SVM) classifier. Machine learning technique classifies neonatal cries. This work combines the advantages of machine learning and deep learning techniques to get the best results even with a moderate number of data samples. The experimental result shows that CNN-based feature extraction and SVM classifier provides promising results. While comparing the SVM-based kernel techniques, namely radial basis function (RBF), linear and polynomial, it is found that SVM-RBF provides the highest accuracy of kernel-based infant cry classification system provides 88.89% accuracy.

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

“…We utilized the following machine learning methods to develop prediction models for POD in patients with VHD, respectively using full variables and selected variables as input features: Random Forest Classifier [ 37 ], Logistic Regression [ 38 , 39 ], SVC [ 40 ], K-nearest Neighbors Classifier [ 41 ], Gaussian Naive Bayes [ 42 ], Gradient Boosting Decision Tree [ 43 ] and Perceptron [ 44 ]. These algorithmic models were then validated in the validation group to assess their performance.…”

“…We applied several supervised machine learning methods to both the full and selected feature sets to construct predictive models of delirium, Specifically, we utilized classical machine learning algorithms commonly employed for classification problems, including Random Forest Classifier [ 37 ], Logistic Regression [ 38 , 39 ], Support Vector Machine Classifier (SVC) [ 40 ], K-nearest Neighbors Classifier [ 41 ], Gaussian Naive Bayes [ 42 ], Gradient Boosting Decision Tree [ 43 ] and Perceptron [ 44 ]. The selection of these algorithms was determined by factors such as the sample size and number of features.…”

A noval pulmonary function evaluation method based on ResNet50 + SVR model and cough

“…Support vector regression (SVR) model uses hyperplane as the decision boundary to find the optimal support vector and to build the segmentation plane. In order to realize linearly separation, kernel function is applied to map the linear inseparable data to a higher-level high-dimensional feature space 35 . The final decision only needs a small number of support vectors, and is not restricted by the number of samples.…”

Machine learning-based infant crying interpretation

“…Multi-class classification on infant cry data was performed by Vincent et al ( 2021 ) with pain, hunger, and sleepiness classes. The audio signal was primarily converted to a spectrum image using an STFT method.…”