Relief based Optimized Feature Selection for Online Sequential Extreme Learning Machine

Abstract

Extreme learning machine (ELM) is a rapid classifier, evolved for batch learning mode which is not suitable for sequential input. As retrieving of data from new inventory which is leads to time extended process. Therefore, Online sequential ELM (OSELM) algorithm is progressed by Liang et. al. which is able to handle the sequential input in which data is read 1 by 1 or chunk by chunk mode. The overall system generalization performance may devalue because of the amalgamation of random initialization of OS-ELM and the presence of redundant and irrelevant features. To resolve the said problem, this paper proposes a correspondence multimodal genetic optimized feature selection paradigm for sequential input (RF-OSELM) for radial basis or function by using clinical datasets. For performance comparison, the proposed paradigm experimented and evaluated for ELM, multimodal genetic optimized for ELM classifier (RF-ELM), OS-ELM, RF-OSELM. Experimental results are calculated and analysed accordingly. The comparative results analysis illustrates that RF-ELM provides 10.94% improved accuracy with 43.25% features as compared to ELM.