From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929281005780992 |
|---|---|
| author | Zeng, Zhen Kaur, Rachneet Siddagangappa, Suchetha Balch, Tucker Veloso, Manuela |
| author_facet | Zeng, Zhen Kaur, Rachneet Siddagangappa, Suchetha Balch, Tucker Veloso, Manuela |
| contents | Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often employing lineplots as the visual representation of time series data. In this paper, we propose a novel approach that uses time-frequency spectrograms as the visual representation of time series data. We introduce the use of a vision transformer for multimodal learning, showcasing the advantages of our approach across diverse datasets from different domains. To evaluate its effectiveness, we compare our method against statistical baselines (EMA and ARIMA), a state-of-the-art deep learning-based approach (DeepAR), other visual representations of time series data (lineplot images), and an ablation study on using only the time series as input. Our experiments demonstrate the benefits of utilizing spectrograms as a visual representation for time series data, along with the advantages of employing a vision transformer for simultaneous learning in both the time and frequency domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11047 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting Zeng, Zhen Kaur, Rachneet Siddagangappa, Suchetha Balch, Tucker Veloso, Manuela Computer Vision and Pattern Recognition Artificial Intelligence Computational Engineering, Finance, and Science Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often employing lineplots as the visual representation of time series data. In this paper, we propose a novel approach that uses time-frequency spectrograms as the visual representation of time series data. We introduce the use of a vision transformer for multimodal learning, showcasing the advantages of our approach across diverse datasets from different domains. To evaluate its effectiveness, we compare our method against statistical baselines (EMA and ARIMA), a state-of-the-art deep learning-based approach (DeepAR), other visual representations of time series data (lineplot images), and an ablation study on using only the time series as input. Our experiments demonstrate the benefits of utilizing spectrograms as a visual representation for time series data, along with the advantages of employing a vision transformer for simultaneous learning in both the time and frequency domains. |
| title | From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2403.11047 |