Optimized Extreme Learning Machine using Fruit Fly Optimization for Classification

• Main Authors: Dinar Nugroho Pratomo, 南宮濤
• Other Authors: Yungho Leu
• Format: Others
• Language: en_US
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/w7vckh

碩士 === 國立臺灣科技大學 === 資訊管理系 === 107 === Extreme Learning Machine (ELM) is one of the learning methods of Artificial Neural Network, which has many advantages, such as fast learning speed, good generalization performance and high accuracy results. However, one of the weaknesses of the ELM method is that the number of hidden nodes cannot be specified without applying the trial and error manually. It is not possible to obtain the right number of hidden nodes in order to get the good result in ELM Method. In this study we propose to use a new swarm intelligence algorithm, the Fruit Fly Optimization Algorithm (FOA), to optimize ELM and to find the optimal number of hidden nodes, weights, and biases. We tested the performance of the proposed method on several datasets from the UCI repository for classification. This research compares the proposed method with other optimization algorithms. The experimental result shows that optimizing ELM by FOA results in higher accuracy compared to other methods such as PSO-ELM, E-ELM, OP-ELM, VPSO-ELM, IPSO-ELM and the original ELM.