首页|Tianjin University Details Findings in Support Vector Machines (Broadcasting Map Construction Method Based On Particle Swarm Optimization-assisted Support Vecto r Machine Integrated Model)
Tianjin University Details Findings in Support Vector Machines (Broadcasting Map Construction Method Based On Particle Swarm Optimization-assisted Support Vecto r Machine Integrated Model)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Support Vector Machin es have been presented. According to news reporting out of Tianjin, People's Rep ublic of China, by NewsRx editors, research stated, "The rapid development of te rrestrial broadcasting services has heightened the demands for terrestrial broad casting coverage capabilities and system planning. This article proposed an inte grated prediction method suitable for multiband and multiscene applications to c onstruct high-quality radio maps in frequency modulation (FM) bands, defined as FM broadcasting maps (BMs)." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Tianjin University, "The method is based on particle swarm optimization (PSO)-assisted support vect or machines (SVMs) and takes Beijing and its surrounding areas as an example for practice. FM BMs are constructed based on three typical propagation prediction models and measurements collected in Beijing and its surrounding areas. The meas urements encompass 11 frequencies ranging from 86.7 to 106.6 MHz, encompassing v arious reception scenarios such as rural and urban areas. The proposed method co nsiders factors such as the receiving location, terrain, frequency, and other re levant information specific to the Beijing area. It matches different areas with suitable propagation models to construct the FM BMs, combining the strengths of the three models. To verify the proposed method, we employ the relative error a s the evaluation criterion to evaluate the prediction performance of the propose d and the typical model. The comparison demonstrates the significant advantages of the proposed method in terms of prediction accuracy and stability. This resea rch is a valuable reference for regional application and localization research o f radio wave propagation prediction methods in the FM broadcasting band."
TianjinPeople's Republic of ChinaAsi aEmerging TechnologiesMachine LearningParticle Swarm OptimizationSupport Vector MachinesVector MachinesTianjin University
NETL
NSTL
