Grey Fuzzy Neural Network-Based Hybrid Model for Missing Data Imputation in Mixed Database

Abstract

Nowadays, the missing data imputation is the novel paradigm to replace with the imputed value of the missing attribute. The missing data occurs due to bias information, non-response of the system. In the medical domain, it becomes the major challenge to impute the both categorical and numerical data. In this paper, the Grey Fuzzy Neural Network is proposed for missing data imputation in the mixed database. Initially, the WLI fuzzy clustering mechanism is utilized to generate the different clusters in which the medical data are grouped together. Then, we intend to integrate the Grey Wolf Optimizer (GWO) with the ANFIS network model, termed the Grey Fuzzy Neural Network (GFNN). The proposed method is mainly used to determine the optimal parameters to design the membership function. Finally, the hybrid prediction model is used to find out the imputed data for both categorical and numerical. In the hybrid prediction model, the categorical data is then imputed by the distance measure. The experimental results are validated, and performance is analysed by metrics such as MSE and RMSE using MATLAB implementation. The outcome of the proposed GFNN attains lower 0.13 MSE, and 0.35 RMSE ensures to impute the data significantly in the missing attribute of the mixed database.

Missing data imputation with fuzzy feature selection for diabetes dataset

“…The proposed model is also compared with another study that was applied to the diabetes dataset. The method used by previous author was Gray Fuzzy Neural Network (GFNN) [30]. It works by using optimal parameters obtained from Gray Wolf Optimizer (GWO) to optimize the membership function and then impute the data for both categorical and numerical data by using Adaptive Neuro-Fuzzy Inference System (ANFIS).…”

Contributions to the mixed data clustering problem: from a conceptual codification and classification proposal to the usage of optimization methods

“…The authors did not apply the proposed measures in any clustering algorithm, but mentioned it can be used in such methods. Kuppusamy and Paramasivam (2017) proposed a neural network-based clustering algorithm, called grey fuzzy neural network (GFNN), to fill missing data in a mixed dataset. The proposed approach is a result of the integration of the grey wolf optimizer (GWO) and adaptative neuro-fuzzy inference system (ANFIS).…”