出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Due to the evolution of technology and the diffusion of digital television, many researchers havestudied more efficient transmission and reception methods. This fact occurs because of thedemand of transmitting videos with better quality using new standards such 8K SUPER Hi-VISION. In this scenario, modulation techniques such as Filter Bank Multi Carrier, associatedwith advanced coding and synchronization methods, are being applied, aiming to achieve thedesired data rate to support ultra-high definition videos. Simultaneously, it is also important toinvestigate ways of channel estimation that enable a better reception of the transmitted signal.This task is not always trivial, depending of the characteristics of the channel. Thus, the use ofartificial intelligence can contribute to estimate the channel frequency response, from thetransmitted pilots. A classical algorithm called Back-propagation Training can be applied tofind the channel equalizer coefficients, making possible the correct reception of TV signals.Therefore, this work presents a method of channel estimation that uses neural networktechniques to obtain the channel response in the Brazilian Digital System Television, calledISDB-TB, using Filter Bank Multi Carrier.
