🤖 AI Summary
This work addresses the performance instability and data sparsity issues arising from random trajectory selection in trajectory data augmentation by proposing a scalable framework that systematically evaluates five trajectory selection strategies—abnormality, diversity, representativeness, uncertainty, and randomness—for the first time. Integrating geometric perturbation-based augmentation with Optuna-driven hyperparameter optimization, the framework is validated across multiple domains. Experimental results demonstrate that abnormality- and uncertainty-based strategies significantly enhance model stability and repair topological fragmentation in sparse data, yet may introduce noise when applied to dense, high-quality datasets. The efficacy of augmentation is shown to be highly dependent on data density and quality, while also revealing inherent physical limitations of standard perturbation methods in highly dynamic scenarios.
📝 Abstract
Trajectory data augmentation is a promising approach to mitigate data scarcity in machine learning applications, but its utility has been limited by the complexity of preserving spatio-temporal coherence. Although prior work demonstrated the viability of geometric perturbation, it relied on naive random selection, leaving a critical gap in understanding which trajectories should be augmented for maximal benefit. This thesis addresses this gap by developing a systematic and scalable framework to evaluate five systematic selection strategies: Outlierness, Diversity, Representativeness, Uncertainty, and Random selection. These strategies were rigorously tested across four datasets covering animal behavior (Foxes and Starkey), maritime traffic (AIS), and urban traffic (Car) using a suite of linear and non-linear machine learning models. As part of this evaluation, an Optuna-based hyperparameter optimization loop was integrated to empirically identify the best-performing augmentation parameters for each dataset within the explored search space. The results indicate that, while systematic selection is not a universal solution, it offers distinct advantages over the random baseline. Systematic strategies, particularly Outlierness and Uncertainty, demonstrated higher stability and were less prone to performance degradation observed with random sampling in dense datasets. However, the findings also reveal that the value of augmentation is strictly conditional. Visual analysis via UMAP demonstrates that while systematic augmentation successfully repairs topological fragmentation in sparse datasets, it can act as a corrupting noise signal in high-quality, dense datasets. Furthermore, the study identified physical limitations in high-velocity domains, where standard perturbation techniques lead to divergence in feature space...