PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
April 25, 2026Cognitive ComputationOpen Access

Dual Memory Matrix Gannet Optimization with Dynamic Weight Adjustment for Robust Feature Selection

View Full Paper
Ask AI
Bookmark
Share

Authors

ASAmir Mohammad SharafaddiniBZBehnam Mohammad Hasani ZadeNMNajme Mansouri

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates enhanced feature selection efficiency using dynamic weight adjustment in diverse datasets, implying potential in real-world applications.

Key Points

  • The aim is to enhance the Gannet Optimization Algorithm for robust feature selection across diverse datasets.
  • Introduced two population matrices in the Improved Gannet Optimization Algorithm (IGOA) for better exploration and exploitation.
  • Used fuzzy-driven fitness function with dynamic weight adjustment based on 135 rules across various performance metrics.
  • Compared IGOA with several algorithms on 17 datasets to evaluate performance.
  • IGOA outperformed GOA, achieving a 71% reduction in mean fitness value.
  • Achieved higher precision and recall metrics while selecting fewer features without compromising classification accuracy.
  • Validated using Support Vector Machines across varying data sets and feature selection challenges.

Cite This Study

Sharafaddini et al. (2026) studied this question.

synapsesocial.com/papers/69ec598788ba6daa22dab531https://doi.org/10.1007/s12559-026-10566-x
View Full Paper
Ask AI
Bookmark
Share