Analysis of iron deficiency anemia in Pregnant women using Modular neural network (MNN)
Ms.Priyanka M. Mule
Student of HVPM’S College of Engineering and Technology Amravati (India) , IN
Dr. Ujwala A. Kshirsagar
Student of HVPM’S College of Engineering and Technology Amravati (India) , IN
Keywords: Neural solution, MatLab, Microsoft excel, all five types of abnormal Red Blood Cells (RBCs)
Abstract
In this paper a new classification algorithm is proposed for the Classification of five types of abnormal Red Blood Cells (RBCs) called Poikilocytes in Iron deficient blood smears in pregnant women . In order to develop algorithm 160 five type of abnormal Red Blood Cells images have been considered, With a view to extract features from the images after image processing, an algorithm proposes WHT transformed coefficients. The Efficient classifiers based on Modular Neural network(MNN) Neural Network. A separate Cross-Validation dataset is used for proper evaluation of the proposed classification algorithm with respect to important performance measures, such as MSE and classification accuracy. The Average Classification Accuracy of GFF Neural Network comprising of one hidden layers with 28 PE’s organized in a typical topology is found to be superior (94.22 %) for Training and cross-validation. Finally, optimal algorithm has been developed on the basis of the best classifier performance. The algorithm will provide an effective alternative classification method of five types of abnormal Red Blood Cells (RBCs) in Iron deficient blood smears in pregnant women.
How to Cite
References
NA