An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data Based on the GRNN-SGTM Ensemble

Abstract

The purpose of this paper is to improve the accuracy of solving prediction tasks of the missing IoT data recovery. To achieve this, the authors have developed a new ensemble of neural network tools. It consists of two successive General Regression Neural Network (GRNN) networks and one neural-like structure of the Successive Geometric Transformation Model (SGTM). The principle of ensemble topology construction on two successively connected general regression neural networks, supplemented with an SGTM neural-like structure, is mathematically substantiated, which improves the accuracy of prediction results. The effectiveness of the method is based on the replacement of the summation of the results of the two GRNNs with a weighted summation, which improves the accuracy of the ensemble operation in general. A detailed algorithmic implementation of the ensemble method as well as a flowchart of its operation is presented. The parameters of the ensemble operation are determined by optimization using the brute-force method. Based on the developed ensemble method, the solution of the task of completing the partially missing values ​​in the real monitoring dataset of the air environment collected by the IoT device is presented. By comparing the performance of the developed ensemble with the existing methods, the highest accuracy of its performance (by the parameters of Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) accuracy) among the most similar in this class has been proved.

Keywords: ANN techniques; GRNN; IoT sensors; Successive Geometric Transformation Model; data imputation; hybrid systems; missing data; neural-like structures; non-iterative training; weighted summation.

Figure 1

General Regression Neural Network (GRNN) topology.

Figure 2

Topology of additional correction linear neural-like structure of the Successive Geometric Transformation Model (SGTM).

Figure 3

Flowchart of the GRNN–SGTM ensemble for solving the stated task.

Figure 4

Root Mean Square Error (RMSE)-values under different combinations of smooth factors ${\sigma }_1$ та ${\sigma }_2$ of both GRNN ensemble networks: (a) in the training mode and (b) in the application mode.

Figure 5

Mean Absolute Percentage Error (MAPE)-values under different combinations of smooth factors ${\sigma }_1$ та ${\sigma }_2$ of both GRNN ensemble networks: (a) in the training mode and (b) in the application mode.