


Volume 20 No 20 (2022)
Download PDF
METAHEURISTIC ENSEMBLE FEATURE SELECTION AND WEIGHTED AVERAGE LSTM NETWORK FOR RECURRENCE BREAST CANCER PREDICTION
Preetha G, Suban Ravichandran
Abstract
Now days, Breast cancer is among the extreme perilous kind of cancer in women kind throughout the world. The
sole method to enhance treatment choices, which reduces mortality rates and enhances patients' chances of survival
is early analysis. However, with the numerous characteristics in the dataset, it is a complex process. As a result,
early and precise detection and categorization of breast cancer are major study areas. The major objective of this
paper was to select important features using Metaheuristic Ensemble Feature Selection (MHEFS) before submitting
these essential features to a classification procedure. MHEFS approach is introduced to combine informative
features which are obtained using Opposition Colony Predation Algorithm (OCPA), Monarch Butterfly
Optimization (MBO), and Linear Function based Animal Migration Optimization (LFAMO). Features in the
MHEFS subset are those features which are present in features sets of individual methods. OCPA has been
introduced in order to solve an algorithm's acceleration and it is able to find a global feature selection solution. MBO
has been constructed to expedite and lionize monarch butterfly migration. The animal migratory patterns in all major
animal clusters served as the inspiration for the LFAMO algorithm. MHEFS approach could improve feature
selection led to the most robust result, and results are combined via the majority voting. Weighted Average Long
Short Term Memory Network (WALSTM) had been introduced for breast cancer recurrence forecast. The results of
the proposed classifier and existing classifiers have been experimented using MATrix LABoratory (MATLAB). The
classifier was evaluated, and experimented using the public Wisconsin Breast Cancer Dataset (WBCD).
Experimental results it concludes that the proposed system accomplishes healthier than the current system in terms
of specificity, recall, precision, accuracy, and f-measure.
Keywords
Breast cancer, Metaheuristic Ensemble Feature Selection (MHEFS), Linear Function based Animal Migration Optimization (LFAMO), Opposition Colony Predation Algorithm (OCPA), Monarch Butterfly Optimization (MBO), and Weighted Average Long Short Term Memory Networks (WALSTMs).
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.