Fusion of Image Transformation Techniques for IoT-based Multivariate Time-Series

Abstract

The emergence of the Internet of Things (IoT) has ushered in a new era of data generation, with the opportunity for data to become a key element of connected devices. This study investigates new methods to bridge the realms of multivariate time-series data and image analysis, paying special attention to Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), Markov Transition Field (MTF), and Recurrence Plot (RP) transformation techniques. These techniques serve to convert raw time-series data into visual representations, laying the foundation for deeper analysis and predictive modeling. The study introduces a novel paradigm by not only employing individual image transformation techniques but also fusing them in both horizontal and square orientations. By leveraging Convolutional Neural Networks (CNNs), this study demonstrates the efficiency of innovative fused oriented image transformation techniques in predicting complex patterns within a multivariate time-series dataset related to electricity distribution and transformer oil temperature. Experimental results demonstrate that the fusion of image transformation techniques yields notably enhanced performance compared to employing each technique individually. Fused-Horizontal techniques exhibit the highest performance, while Fused-Square techniques show the second best performance among all fused oriented and individual techniques. This emphasizes the importance of fused oriented image transformation techniques in prediction tasks.