Clustering via torque balance with mass and distance
This addresses clustering challenges in fields like biology and astronomy by offering a versatile, parameter-free approach, though it appears incremental as it builds on gravitational analogies.
The paper tackles the problem of clustering objects regardless of shape, size, or density by proposing a novel method inspired by gravitational torque balance, resulting in a parameter-free algorithm that demonstrates versatility on benchmark datasets.
Grouping similar objects is a fundamental tool of scientific analysis, ubiquitous in disciplines from biology and chemistry to astronomy and pattern recognition. Inspired by the torque balance that exists in gravitational interactions when galaxies merge, we propose a novel clustering method based on two natural properties of the universe: mass and distance. The concept of torque describing the interactions of mass and distance forms the basis of the proposed parameter-free clustering algorithm, which harnesses torque balance to recognize any cluster, regardless of shape, size, or density. The gravitational interactions govern the merger process, while the concept of torque balance reveals partitions that do not conform to the natural order for removal. Experiments on benchmark data sets show the enormous versatility of the proposed algorithm.