A Co-Optimization Algorithm Utilizing Particle Swarm Optimization for Linguistic Time Series

The linguistic time-series forecasting model (LTS-FM), which has been recently proposed, uses words of variable domains generated by hedge algebras (HAs) to describe historical numeric data. Then, the LTS-FM was established utilizing real semantics induced fuzziness parameter values (FPVs) HAs. In existing LTS-FMs, just FPVs HAs are optimized, while used word set is still chosen human experts. This paper proposes a co-optimization method selecting optimal that best describes data in parallel with choosing improve accuracy LTS-FMs particle swarm optimization (PSO). this method, outer loop optimizes HAs, inner set. experimental results on three datasets, i.e., “enrollments University Alabama” (EUA), “killed car road accidents Belgium” (CAB), and “spot gold Turkey” (SGT), showed our proposed outperformed models terms forecast accuracy.