Enriched Quantum Artificial Ant Colony based Breast Cancer Prediction G.Sumalatha, Research scholar (PhD), Sri Krishna arts and science college, Coimbatore

  • Dr. N. Kavitha et al.

Abstract

One of the leading causes of death for women around the world is due to breast cancer. Diagnosing
presence of breast cancer in earlier stages would increase the survival rate of the victim and assist the
experts to diagnose the presence of breast cancer more accurately. As the medical dataset grows rapidly
in nature, there is a need for maintaining the quality assured information about the patients by
overcoming two major issues such as presence of incomplete information about the patient and storing
the same patient details multiple copies by interpreting them are different due to some typing mistakes or
human error. This paper handles the problem of data quality in breast cancer dataset, so that prediction
model can improve their detection rate considerable and false classification can be controlled. This work
introduced weight boosted naïve bayes imputation model which handle the problem of missing value
among the instances of breast cancer dataset more appropriately and it uses the weighting factor of
instances to choose them as nearest neighbors instead of using probability distribution alone. The
presence of duplicate records in dataset are discovered by introduction quantum ant colony optimization
which perform deduplication in an optimized way and overcomes the problem of earlier convergence and
local optima to determine the best solution in record deduplication of breast cancer dataset. The
simulation results proved the performance of producing better results by the proposed models both in
imputation method and deduplication process very effectively.

Published
2020-02-17
How to Cite
et al., D. N. K. (2020). Enriched Quantum Artificial Ant Colony based Breast Cancer Prediction G.Sumalatha, Research scholar (PhD), Sri Krishna arts and science college, Coimbatore. International Journal of Control and Automation, 13(1), 262 - 271. Retrieved from https://sersc.org/journals/index.php/IJCA/article/view/5217
Section
Articles