Quorum sensing is a decentralized biological process, by which a community of cells with no global awareness can coordinate their functional behaviors based on cell-medium interaction and local decision making. This paper draws inspirations from quorum sensing and colony competition to study the clustering problem. We propose an algorithm treating each data as a single cell, utilizing the knowledge of local connectivity to cluster cells into multiple colonies simultaneously. The algorithm

more »

... ts of two stages: first, it spots sparsely distributed "core cells" and determines for each cell its influence radius; second, core cells secrete "auto-inducers" that diffuse into the environment to form colonies. Interactions between colonies eventually determine each cell's identity. We combine the two steps into a dynamic process, which gives the algorithm flexibility to analyze both static and time-varying data. Finally, we test our algorithm on several applications, including synthetic and real benchmarks datasets, alleles clustering, and dynamic systems grouping and identification. The results suggest that our algorithm performs as well as other cutting-edge methods on static data, while applications on time-varying data like locations of swarms of robots are also promising.