Main Article Content
Fetal Heart diseases are the common problem facing by many of the pregnant woman throughout the India. These are measured through the functioning of the heart identified by the Fetal Electrocardiogram (FECG) signals. Based on the different signals identified by the FECG scan, various heart diseases can be identified. Detecting and analyzing the FECG signals is very important at labor. As heart beat is the integration of impulse wave forms generated by the various cardiac tissues. The detection of waveforms results in various status of the pregnant woman. So, classification of FECG signals plays an important role in heart disease detection. This paper addresses the classification of FECG through machine learning algorithms as intake of waveforms i.e., features as input. Using python, the machine learning algorithms are simplified when the dataset is too large. The proposed method involves two techniques i.e., Decision tree and K-NN algorithms for enhancing the accuracy rate for disease identification. The comparison of the two algorithms on the dataset FECG Heartbeat categorization results in achieving the high-level accuracy in binary level classification.