Research on Geographic Location Prediction Algorithm Based on Improved Teaching and Learning Optimization ELM

• Main Authors: Zhen Yang, Zengwu Sun
• Format: Article
• Language: English
• Published: Frontiers Media S.A. 2020-07-01
• Series: Frontiers in Physics
• Subjects: GPS; learning optimization algorithm; ITLBO algorithms; ELM; prediction method
• Online Access: https://www.frontiersin.org/article/10.3389/fphy.2020.00259/full

With the rapid development of vehicle-mounted communication technology, GPS data is an effective method to predict the current road vehicle track based on vehicle-mounted data. GPS-oriented vehicle-mounted data position prediction method is currently a hot research work and an effective method to realize intelligent transportation. In this paper, an improvement scheme is proposed based on the problem of falling into local optimization existing in the basic algorithm of teaching and learning optimization algorithm. An interference operator is used to disturb teachers to enhance the kinetic energy of the population to jump out of local optimization. By comparing the performance of GA, PSO, TLBO, and ITLBO algorithms with four test functions, the results show that ITLBO has efficient optimization effect and generalization ability. Finally, the ITLBO-ELM algorithm has the best prediction effect by comparing the vehicle GPS data and comparing the experimental algorithms.