Multivariate Time-Series Imagification with Time Embedding in Constrained Environments (Student Abstract)
Abstract
We present an imagification approach for multivariate time-series data tailored to constrained NN-based forecasting model training environments. Our imagification process consists of two key steps: Re-stacking and time embedding. In the Re-stacking stage, time-series data are arranged based on high correlation, forming the first image channel using a sliding window technique. The time embedding stage adds two additional image channels by incorporating real-time information. We evaluate our method by comparing it with three benchmark imagification techniques using a simple CNN-based model. Additionally, we conduct a comparison with LSTM, a conventional time-series forecasting model. Experimental results demonstrate that our proposed approach achieves three times faster model training termination while maintaining forecasting accuracy.
BibTeX
@article{Kang_Jo_2024, title={Multivariate Time-Series Imagification with Time Embedding in Constrained Environments (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30461}, DOI={10.1609/aaai.v38i21.30461}, abstractNote={We present an imagification approach for multivariate time-series data tailored to constrained NN-based forecasting model training environments. Our imagification process consists of two key steps: Re-stacking and time embedding. In the Re-stacking stage, time-series data are arranged based on high correlation, forming the first image channel using a sliding window technique. The time embedding stage adds two additional image channels by incorporating real-time information. We evaluate our method by comparing it with three benchmark imagification techniques using a simple CNN-based model. Additionally, we conduct a comparison with LSTM, a conventional time-series forecasting model. Experimental results demonstrate that our proposed approach achieves three times faster model training termination while maintaining forecasting accuracy.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Kang, Seung Woo and Jo, Ohyun}, year={2024}, month={Mar.}, pages={23535-23536} }