LIKFCM: Linear interpolation-based kernelized FCM imputation method for handling incomplete data

What is it about?

This paper presents a novel approach for imputing missing values that incorporates Kernelized Fuzzy C-Means (KFCM) clustering and proposes a method termed LIKFCM, which combines its benefits with Linear Interpolation (LI). The proposed method has been compared with eight other existing methods across ten publicly accessible real-world datasets for experimentation in terms of two evaluation criteria: RMSE and MAE. Sixty missing combinations based on different missing ratios as 5%, 10%, 15%, 20%, 25%, and 30% have been considered for all ten datasets to examine imputation methods’ performance.

Featured Image

Photo by Markus Spiske on Unsplash

Photo by Markus Spiske on Unsplash

Why is it important?

Addressing missing values is a persistent challenge in the field of data mining. The presence of incomplete data can significantly compromise the overall data quality. Consequently, it is crucial to handle incomplete data efficiently. This paper proposes the LIPFCM method for imputing missing values by hybridizing LI and PFCM to handle incomplete data. From the experimental results, it is evident that our proposed method outperforms the existing imputation methods with significant improvements in terms of RMSE & MAE for these datasets across different missing ratios. The performance validation of the proposed approach against other state-of-the-art imputation methods has been conducted utilizing a Kendall’s W statistical test, involving a comparison of their mean ranks across different missing ratios. The outcomes indicate that LIKFCM has outperformed other imputation methods, attaining the highest rank in terms of different evaluation criteria.

Perspectives