Machine learning based Acoustic Analysis and Classification of Infant cry to Identify Baby needs

The study investigates the use of machine learning to categorize baby cries in order to determine the underlying demands based on auditory characteristics. A dataset of baby screams was used to test a number of algorithms, including K-Nearest Neighbors, Support Vector Machines, Decision Trees, Random Forest, and XGBoost. Outperforming other techniques, the XGBoost model obtained the maximum accuracy of 99.79%. Confusion matrices are used to facilitate comparisons based on F1-score, recall, and precision in the analysis. The findings show how machine learning can be used to enhance cry analysis systems for healthcare professionals and caregivers. Subsequent research endeavors will center around the integration of wearable technology, dataset growth, and real-time deployment.