A Time-Series Data Augmentation Model through Diffusion and Transformer Integration
This addresses a gap in data augmentation for time-series tasks, which is incremental as it applies existing models to a less-explored domain.
The paper tackles the lack of data augmentation methods for time-series data by proposing a hybrid model combining Diffusion and Transformer models to generate large volumes of high-quality augmented data, showing effectiveness through performance improvements compared to no augmentation or traditional methods.
With the development of Artificial Intelligence, numerous real-world tasks have been accomplished using technology integrated with deep learning. To achieve optimal performance, deep neural networks typically require large volumes of data for training. Although advances in data augmentation have facilitated the acquisition of vast datasets, most of this data is concentrated in domains like images and speech. However, there has been relatively less focus on augmenting time-series data. To address this gap and generate a substantial amount of time-series data, we propose a simple and effective method that combines the Diffusion and Transformer models. By utilizing an adjusted diffusion denoising model to generate a large volume of initial time-step action data, followed by employing a Transformer model to predict subsequent actions, and incorporating a weighted loss function to achieve convergence, the method demonstrates its effectiveness. Using the performance improvement of the model after applying augmented data as a benchmark, and comparing the results with those obtained without data augmentation or using traditional data augmentation methods, this approach shows its capability to produce high-quality augmented data.