| Abstract |
Driven by the wave of urban informatization and the rise of data science, the development of smart city not only needs huge geospatial data as the carrier, but also needs efficient spatial retrieval technology to promote the development of smart city. As a branch of big data, geospatial big data is rising rapidly all over the world, and the era of spatial big data has come. In this paper, particle swarm optimization algorithm is introduced to improve the data clustering algorithm, and a big data optimization clustering algorithm based on particle swarm spatial reorganization is proposed. Particle swarm optimization algorithm is a population-based adaptive random optimization algorithm, which originates from Kennedy and eberbar's research on the foraging behavior of bird groups. Now particle swarm optimization algorithm is widely used in the fields of pattern recognition, data mining and intelligent control. Based on particle swarm optimization, this paper studies the efficient index and retrieval algorithm of geospatial big data. Particle swarm spatial reorganization method is used to reconstruct and extract the feature vector of big data information flow and realize optimal clustering. Finally, the performance test is carried out through the simulation experiment which shows the better data clustering performance. © 2022 Association for Computing Machinery. All rights reserved. |
