An investigation into infant cry and Apgar score using principle component analysis

In this paper, the cry characteristics of newborn infant were investigated and correlated with Apgar score. The Apgar score is a rapid method to evaluate the physical condition of newborn infants at 1 and 5 minutes after birth, and may be repeated later if the score is and remains low. The cry of premature and mature infants with low and normal Apgar scores was analyzed using principle component analysis (PCA). Pre-processing of the voice or unvoiced segments of cry signals include zero rate crossing, short time energy and filtering. Through principle component analysis, the reduced dimension cry signal is investigated to extract features to be correlated with Apgar scores. This work provides the foundation for the design of an automatic algorithm to replace the manual Apgar scoring system.