Infant cry classification by using different deep neural network models and hand-crafted features

Özseven, Turgut

doi:10.1016/j.bspc.2023.104648

Cited by 12 publications

(1 citation statement)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have also explored TSI methods for feature extraction, as shown in The final goal of this study was to bring a solution to the research community with better performance than previous studies. Ozseven (2023) conducted state-of-the-art research and studied the extraction of infant cry signals. The author tested their solution on different ML and DL pretrained models.…”

Section: Resultsmentioning

confidence: 99%

Machine learning-based infant crying interpretation

Hammoud,

Getahun,

Baldycheva

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Crying is an inevitable character trait that occurs throughout the growth of infants, under conditions where the caregiver may have difficulty interpreting the underlying cause of the cry. Crying can be treated as an audio signal that carries a message about the infant's state, such as discomfort, hunger, and sickness. The primary infant caregiver requires traditional ways of understanding these feelings. Failing to understand them correctly can cause severe problems. Several methods attempt to solve this problem; however, proper audio feature representation and classifiers are necessary for better results. This study uses time-, frequency-, and time-frequency-domain feature representations to gain in-depth information from the data. The time-domain features include zero-crossing rate (ZCR) and root mean square (RMS), the frequency-domain feature includes the Mel-spectrogram, and the time-frequency-domain feature includes Mel-frequency cepstral coefficients (MFCCs). Moreover, time-series imaging algorithms are applied to transform 20 MFCC features into images using different algorithms: Gramian angular difference fields, Gramian angular summation fields, Markov transition fields, recurrence plots, and RGB GAF. Then, these features are provided to different machine learning classifiers, such as decision tree, random forest, K nearest neighbors, and bagging. The use of MFCCs, ZCR, and RMS as features achieved high performance, outperforming state of the art (SOTA). Optimal parameters are found via the grid search method using 10-fold cross-validation. Our MFCC-based random forest (RF) classifier approach achieved an accuracy of 96.39%, outperforming SOTA, the scalogram-based shuffleNet classifier, which had an accuracy of 95.17%.

show abstract

Section: Resultsmentioning

confidence: 99%