Font Size: 

The sound of crying babies is one-way babies express physical and psychological conditions that are being experienced. But parents still lack knowledge about understanding the baby's condition from the sound of crying. Therefore, research needs to be done about the characteristics of baby crying sound in terms of mathematical that is based on fractal dimension values. The data used in this study amounted to 80 data consisting of 4 types of crying babies, they are hunger, fatigue, stomach ache, and discomfort obtained from the website https://github.com/gveres/donateacry-corpus/. In this study k-max values ​​of 10, 16, and 50 were selected as experiments. The results of the fractal dimension value of each sound signal are then carried out in the process of data sharing. In this study using the method of data distribution k-fold cross validation with values ​​k = 5 and 10. Then the classification process is carried out using the K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) methods. Based on the research results obtained the best accuracy that is equal to 78.75% at level 5 decomposition with 5-fold cross validation, k-max value = 10, and K = 9 value on the KNN method. Whereas the SVM method obtained the best accuracy of 80% at level 5 decomposition with 10-fold cross validation, k-max value = 10 and c = 10 and using RBF kernel with γ = 10. So in this study, the Support Vector Machine (SVM) method is better than the K-Nearest Neighbor (KNN) method.

Baby crying sound, Higuchi fractal dimension; K-Nearest Neighbor (KNN); Support Vector Machine (SVM).