Abstract
A new neural equalizer is proposed in order to compensate for intersymbol interference (ISI) and to mitigate nonlinear distortions in digital magnetic recording systems and to strengthen the BER performance of conventional neural decision feedback equalizer (NDFE). The proposed quadratic sigmoid neural decision feedback equalizer (QSNDFE) uses a quadratic sigmoid function as the activation function of the neural networks. We present some computer simulation results of the bit error rate (BER) performance in nonlinear digital magnetic recording channels - the nonlinear Lorentzian channel model and the partial erasure model. The BER performance of QSNDFE is compared to that of conventional decision feedback equalizer (DFE) and conventional NDFE. And the characteristics of MSE (mean square error) of each equalizer is analyzed. It is shown that the QSNDFE outperforms both DFE and NDFE.
Original language | English |
---|---|
Pages | 1735-1740 |
Number of pages | 6 |
Publication status | Published - 1998 Dec 1 |
Event | Proceedings of the IEEE GLOBECOM 1998 - The Bridge to the Global Integration - Sydney, NSW, Aust Duration: 1998 Nov 8 → 1998 Nov 12 |
Other
Other | Proceedings of the IEEE GLOBECOM 1998 - The Bridge to the Global Integration |
---|---|
City | Sydney, NSW, Aust |
Period | 98/11/8 → 98/11/12 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
- Global and Planetary Change
Cite this
}
Quadratic sigmoid neural decision feedback equalizer for nonlinear digital magnetic recording channels. / Choi, Sooyong; Ong, Sunghwan; You, Cheolwoo; Hong, Daesik.
1998. 1735-1740 Paper presented at Proceedings of the IEEE GLOBECOM 1998 - The Bridge to the Global Integration, Sydney, NSW, Aust, .Research output: Contribution to conference › Paper
TY - CONF
T1 - Quadratic sigmoid neural decision feedback equalizer for nonlinear digital magnetic recording channels
AU - Choi, Sooyong
AU - Ong, Sunghwan
AU - You, Cheolwoo
AU - Hong, Daesik
PY - 1998/12/1
Y1 - 1998/12/1
N2 - A new neural equalizer is proposed in order to compensate for intersymbol interference (ISI) and to mitigate nonlinear distortions in digital magnetic recording systems and to strengthen the BER performance of conventional neural decision feedback equalizer (NDFE). The proposed quadratic sigmoid neural decision feedback equalizer (QSNDFE) uses a quadratic sigmoid function as the activation function of the neural networks. We present some computer simulation results of the bit error rate (BER) performance in nonlinear digital magnetic recording channels - the nonlinear Lorentzian channel model and the partial erasure model. The BER performance of QSNDFE is compared to that of conventional decision feedback equalizer (DFE) and conventional NDFE. And the characteristics of MSE (mean square error) of each equalizer is analyzed. It is shown that the QSNDFE outperforms both DFE and NDFE.
AB - A new neural equalizer is proposed in order to compensate for intersymbol interference (ISI) and to mitigate nonlinear distortions in digital magnetic recording systems and to strengthen the BER performance of conventional neural decision feedback equalizer (NDFE). The proposed quadratic sigmoid neural decision feedback equalizer (QSNDFE) uses a quadratic sigmoid function as the activation function of the neural networks. We present some computer simulation results of the bit error rate (BER) performance in nonlinear digital magnetic recording channels - the nonlinear Lorentzian channel model and the partial erasure model. The BER performance of QSNDFE is compared to that of conventional decision feedback equalizer (DFE) and conventional NDFE. And the characteristics of MSE (mean square error) of each equalizer is analyzed. It is shown that the QSNDFE outperforms both DFE and NDFE.
UR - http://www.scopus.com/inward/record.url?scp=0032281159&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0032281159&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0032281159
SP - 1735
EP - 1740
ER -