Capturing and Explaining Trajectory Singularities using Composite Signal Neural Networks
This work addresses trajectory analysis for fields like urban planning and neuroscience, offering an incremental improvement by combining interpretable modules to enhance accuracy and explainability.
The paper tackles the problem of analyzing complex spatial trajectories by introducing a novel ANN architecture that captures spatio-temporal patterns and incorporates navigator demographics, resulting in significantly better performance than isolated modules and enabling visualization of discriminative signal parts.
Spatial trajectories are ubiquitous and complex signals. Their analysis is crucial in many research fields, from urban planning to neuroscience. Several approaches have been proposed to cluster trajectories. They rely on hand-crafted features, which struggle to capture the spatio-temporal complexity of the signal, or on Artificial Neural Networks (ANNs) which can be more efficient but less interpretable. In this paper we present a novel ANN architecture designed to capture the spatio-temporal patterns characteristic of a set of trajectories, while taking into account the demographics of the navigators. Hence, our model extracts markers linked to both behaviour and demographics. We propose a composite signal analyser (CompSNN) combining three simple ANN modules. Each of these modules uses different signal representations of the trajectory while remaining interpretable. Our CompSNN performs significantly better than its modules taken in isolation and allows to visualise which parts of the signal were most useful to discriminate the trajectories.