Data Augmentation Strategies for Improving Time Series Classification Accuracy

Time series classification is crucial in fields such as healthcare, finance, and industrial processes, but it faces challenges like temporal data ordering, class imbalance, noise, and limited data. This research explores data augmentation techniques to improve classification performance, focusing on the MiniRocket classifier across 85 UCR datasets. The study identifies conditions under which augmentation techniques, like wDBA, enhance accuracy, though overall performance may vary. A dataset-specific approach is essential for effective augmentation. The research also examines the impact of augmentation on datasets with different characteristics, providing insights into when specific strategies are most beneficial. Future work includes optimizing augmentation methods for specific domains, exploring advanced techniques like generative models, and validating results on real-world datasets to ensure practical applicability.