Details

Autor(en) / Beteiligte

• Iskander, C.-D.
• Fortier, P.
• Huu Tue Huynh

Titel

Fast-converging neural equalizers for broadband QAM microcell systems

Ist Teil von

• Conference record of the annual conference - IEEE Vehicular Technology Conference, 2002, Vol.4, p.1781-1785 vol.4

Ort / Verlag

IEEE

Erscheinungsjahr

2002

Link zum Volltext

• IEEE_Xplore

Quelle

IEL

Beschreibungen/Notizen

• Many equalizers based on neural networks have been proposed across the literature. Unfortunately, the complexity and the slow convergence still have to be overcome for neural equalizers to be implemented in real time. This paper presents neural equalizers suitable for multi-level QAM constellations, and trained using complex extended Kalman and RLS algorithms, which makes them more robust against severely dispersive channels, like broadband outdoor or indoor mobile communication channels. The activation function is optimized to obtain good performance for large size signal constellations (i.e. up to 256-QAM). Extensive simulations show the benefits and limitations of these neural equalizers over traditional decision-feedback equalizers.