Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 7 (2022) > Article

DOI: 10.14704/nq.2022.20.7.NQ33473

Local binary fitting Median Filter for noise reduction in lung image datasets and classification

Ms. C. Keerthana, Dr. B. Azhagusundari

Abstract

The classification of medical data is the most difficult problem to solve among all research problems since it has more commercial significance in the context of health analytics. Data are labelled by classification, which enables efficient and productive performance in worthwhile analysis. According to research, the effectiveness of the categorization may be negatively impacted by the quality of the characteristic. This research work initiate a proposed method named modified Local Binary Fitting Median Filter with Artificial Neural Network (LBFMF/ANN) for identifying appropriate feature subsets related to detect the person weather he/she is affected by Lung disease. Local Binary Fitting Median Filter algorithm is derived based on deterministic and mathematical properties of the Local Binary Fitting median filter and Artificial Neural Network, a deep learning method makes an efficient classification of the prediction of Lungs disease in patient. The suggested research study examines the effects of feature selection as effectiveness is essential when a user shares a sample lung disease feature for the selection of pertinent features from a databank, and vice versa. Qualitative assessment of proposed the Local Binary Fitting Median Filter with Artificial Neural Network classification mechanism has been made with classification Accuracy 87.30%, Sensitivity 87.50%, Specificity 87.50% and better precision than the existing method respectively. A statistical examination of accuracy ratings and performance duration shows that the suggested systems outperform conventional methods.

Keywords

Lungs Disease dataset, Local Binary Fitting Median Filter with Artificial Neural Network, confusion matrix, classifier, segmentation.

Full Text

PDF

References

?>