Adaptive Gradient Driven Momentum Optimized Transfer learning for pregnancy patient risk level prediction

Author(s)	Ms C MidhunaMurali, Prof. Dr. P Senthil Vadivu
Country	India
Abstract	Maternal health is vital aspect of public health that affects health of mothers and unborn child. Conventional methods introduced but accurate prediction with minimal error rate remains challenges. Adaptive Gradient Driven Momentum Optimized Transfer Learning (AGMODTL) model is introduced for pregnancy patient risk level prediction. The AGMODTL model consists of different processes namely data acquisition, preprocessing, feature selection, classification and fine tuning. Initially, the number of maternal data samples is considered as an input layer for transfer learning. Then, the collected input maternal data points are collected from the dataset. Fine-tuning the layers of pre-trained model is a vital step using the elitist elephant herd metaheuristic algorithm thereby reducing errors and increasing the accuracy of the pregnancy patient risk level prediction. Experimental evaluation is carried out on the factor such as forecasting accuracy, precision, recall, F1 score, RMSE, specificity, confusion matrix with respect to the number of data samples.
Keywords	Pregnancy patient risk level prediction, Transfer Learning, SACCC.
Field	Computer Applications
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-23
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.79399

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research