TAACKIT: Track Annotation and Analytics with Continuous Knowledge Integration Tool
It addresses a domain-specific problem for ML developers in geospatial applications, providing a new tool but with incremental impact.
The paper tackles the lack of annotation tools for geospatial track data by introducing TAACKIT, a tool for annotating and validating such data, demonstrating its use in air traffic to reduce annotation effort.
Machine learning (ML) is a powerful tool for efficiently analyzing data, detecting patterns, and forecasting trends across various domains such as text, audio, and images. The availability of annotation tools to generate reliably annotated data is crucial for advances in ML applications. In the domain of geospatial tracks, the lack of such tools to annotate and validate data impedes rapid and accessible ML application development. This paper presents Track Annotation and Analytics with Continuous Knowledge Integration Tool (TAACKIT) to serve the critically important functions of annotating geospatial track data and validating ML models. We demonstrate an ML application use case in the air traffic domain to illustrate its data annotation and model evaluation power and quantify the annotation effort reduction.