A Multi-ELM Model for Incomplete Data

Our research involves the creation of a novel model of Extreme Learning Machines (ELMs) for incomplete data. ELMs are fast accurate randomized neural networks that is commonly used in the industry. However, ELM can only be applied on the complete dataset. In reality, it's common to have incomplete values due to human errors, device malfunction or intentional missing. Therefore, a novel Multi-ELM Model for incomplete data is proposed, consisting of multiple secondary ELMs and one primary ELM. The secondary ELMs are approximating the hidden layer output in the primary ELM for the data with missing values. This model can be applied on data with any missing patterns, without using imputations and can outperform the traditional imputation methods such as K Nearest Neighbor (KNN) imputation and Mean Imputation (MI) within a reasonable fraction of missing values (0% to 20%), as it avoids the noises intruded by imputations.