Enhancing Delivery Type Classification Using a Particle Swarm Optimized One-Dimensional Convolutional Neural Network

Vaginal deliveries have linked to less respiratory issues in the newborn. Vaginal delivery and on demand C section showed better outcomes than operatory vaginal delivery and intrapartum C sections. In this paper a Particle Swarm Optimization based One Dimensional Convolutional Neural Network the delivery type is proposed. Initially, the data is pre processed undergoing stages like handling missing values to analyse the missing values from input data, data encoding to convert unconditional variables into numerical representations. Then data balancing to balance the data and dimensionality reduction to visualize the data by enhancing data quality for detection. Next, the data are selected using the Chi square test score to extract independent variables from a large sample data for delivery type detection. Finally, a PSO based 1D CNN framework is processed to enhance the classification accuracy of delivery type. Using python software the proposed framework shows an improved accuracy of 96% is expert when compared to other methods.