A microcontroller-sized neural network filter is shown in simulation and on an STM32L4 testbed to cut DFT-s-OFDM PAPR by about 2 dB versus RRC, but the receiver-side mechanism for knowing the data-dependent filter is not specified.
Beaulieu et al., ”A ’better than’ Nyquist pulse,” IEEE Commun
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
TinyML-Based Adaptive Pulse Shaping for Edge Intelligence in IoT/IIoT
A microcontroller-sized neural network filter is shown in simulation and on an STM32L4 testbed to cut DFT-s-OFDM PAPR by about 2 dB versus RRC, but the receiver-side mechanism for knowing the data-dependent filter is not specified.