Image-Based Time Series Forecasting: A Deep Convolutional Neural Network Approach

• Published in: 2024 4th International Conference on Innovative Practices in Technology and Management (ICIPTM) pp. 1 - 6
• Main Authors: Maroor, Jnaneshwar Pai, Sahu, Dillip Narayan, Nijhawan, Ginni, Karthik, A, Shrivastav, A. K., Chakravarthi, M. Kalyan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21.02.2024
• Subjects: Accuracy; Computational modeling; Data models; Deep learning; Predictive models; Statistical analysis; Time series analysis
• DOI: 10.1109/ICIPTM59628.2024.10563471

In this study, we examine the relatively new subject of image-based time series forecasting by using deep convolutional neural networks (also known as CNNs). The use of statistical methods and accurate numerical data have always been prerequisites for accurate time series forecasting. However, as a result of the accomplishments of CNNs in computer vision and the development of deep learning, a fresh approach has emerged. This work outlines a method for transforming time series data into structures that are analogous to pictures in order to facilitate the use of CNNs for the modelling of temporal patterns and the development of more accurate forecasting models. The research contributes to a greater understanding of the usefulness of deep learning in time series forecasting by providing insights into the process of picking models based on criteria such as accuracy, processing capability, and the specific dataset requirements. Keywords- Time Series Forecasting, Deep Convolutional Neural Networks, Image-based Forecasting, Deep Learning, Neural Networks, Predictive Modeling, Temporal Patterns, Model Comparison.