Implementation of the results of the article
Artemios-Anargyros Semenoglou, Evangelos Spiliotis, Vassilios Assimakopoulos, Image-based time series forecasting: A deep convolutional neural network approach, Neural Networks, Volume 157, 2023, Pages 39-53, ISSN 0893-6080, https://doi.org/10.1016/j.neunet.2022.10.006. (https://www.sciencedirect.com/science/article/pii/S0893608022003902) Abstract: Inspired by the successful use of deep learning in computer vision, in this paper we introduce ForCNN, a novel deep learning method for univariate time series forecasting that mixes convolutional and dense layers in a single neural network. Instead of using conventional, numeric representations of time series data as input to the network, the proposed method considers visual representations of it in the form of images to directly produce point forecasts. Three variants of deep convolutional neural networks are examined to process the images, the first based on VGG-19, the second on ResNet-50, while the third on a self-designed architecture. The performance of the proposed approach is evaluated using time series of the M3 and M4 forecasting competitions. Our results suggest that image-based time series forecasting methods can outperform both standard and state-of-the-art forecasting models. Keywords: Time series; Forecasting; Images; Deep Learning; Convolutional Neural Networks; M competitions