Enhancing extreme learning machines classification with moth-flame optimization technique

Extreme Learning Machine (ELM) algorithm assigns the input weights and biases in a “one-time stamp” fashion, this method makes to be ill-conditioned reduces its classification accuracy. The contribution of work is enhancement performance ELM with Moth-Flame Optimization (MFO) improve A hybrid (MFO-ELM) implemented MATLAB. MFO ensures concurrent simulation exploration exploitation search space select an optimum candidate solution. solution reshaped into for classification. validated on five life-selected datasets. improvement MFO-ELM compared ELM-optimized Particle Swarm (PSO-ELM) Competitive (CSO-ELM) algorithms. rates are qualitatively quantitatively evaluated show other meta-heuristic improved accuracies basic all 100% simulations performed better than algorithms 80% simulations. more competitive, it recommended solving problems.