Multimodal Genetic Optimized Feature Selection for Online Sequential Extreme Learning Machine

Extreme learning machine (ELM) is a rapid classifier evolved for batch learning mode unsuitable for sequential input. Retrieving data from the new inventory leads to a time-extended process. Therefore, online sequential extreme learning machine (OSELM) algorithms were proposed by Liang et al.. The OSELM is able to handle the sequential input by reading data 1 by 1 or chunk by chunk mode. The overall system generalization performance may devalue because of the amalgamation of the 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 (MG-OSELM) for radial basis function by using clinical datasets. For performance comparison, the proposed paradigm is implemented and evaluated for ELM, multimodal genetic optimized for ELM classifier (MG-ELM), OS-ELM, MG-OSELM. Experimental results are calculated and analysed accordingly. The comparative results analysis illustrates that MG-ELM provides 10.94% improved accuracy with 43.25% features compared to ELM.