@article{10.11648/j.ajnna.20261202.15,
  author = {Hariniony Bienvenu Rakotonirina and Randriana Heritiana Nambinina Erica and Marie Emile Randrianandrasana and Ando Nirina Andriamanalina},
  title = {Joint Compressive Sensing, LDPC Coding, and Neural Network-Based Predistortion for 6G Networks OTFS Transmission System Optimization},
  journal = {American Journal of Neural Networks and Applications},
  volume = {12},
  number = {2},
  pages = {99-109},
  doi = {10.11648/j.ajnna.20261202.15},
  url = {https://doi.org/10.11648/j.ajnna.20261202.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20261202.15},
  abstract = {Orthogonal Time Frequency Space (OTFS) modulation has recently emerged as a promising waveform for next-generation wireless communications, particularly in high-mobility environments characterized by doubly selective channels. However, the practical deployment of OTFS systems faces three major challenges: the high Peak-to-Average Power Ratio (PAPR) of multicarrier signals, which induces severe nonlinear distortions in the High-Power Amplifier (HPA); the growing demand for high-data-rate transmission requiring efficient data compression; and the inherently noisy transmission channel that degrades signal integrity. This paper proposes a comprehensive optimization of the OTFS transmission system by synergistically combining three complementary techniques. First, a neural network-based predistortion model is employed to linearize the HPA, enabling high-efficiency operation without signal degradation. Second, Compressive Sensing based on the Lifting Wavelet Transform (LWT) and the ALISTA algorithm is integrated to drastically reduce the volume of transmitted data, down to 10%–30% of the original signal, while ensuring fast and accurate reconstruction. Third, Low-Density Parity-Check (LDPC) coding is incorporated to enhance robustness against channel noise. Simulation results demonstrate that the joint application of these techniques successfully compensates for amplifier nonlinearity, corrects transmission errors even in severely noisy environments (achieving near-perfect image reconstruction at SNR > 10 dB over Rayleigh fading channels), and significantly reduces the data volume without compromising throughput. Furthermore, the rapid convergence of the ALISTA algorithm offsets the additional LDPC decoding complexity, validating the real-time feasibility of the proposed approach. The proposed framework thus enables OTFS systems to simultaneously achieve high data rates, low error rates, and energy efficiency, making it a strong candidate for future 6G communication systems.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Joint Compressive Sensing, LDPC Coding, and Neural Network-Based Predistortion for 6G Networks OTFS Transmission System Optimization
AU  - Hariniony Bienvenu Rakotonirina
AU  - Randriana Heritiana Nambinina Erica
AU  - Marie Emile Randrianandrasana
AU  - Ando Nirina Andriamanalina
Y1  - 2026/11/11
PY  - 2026
N1  - https://doi.org/10.11648/j.ajnna.20261202.15
DO  - 10.11648/j.ajnna.20261202.15
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 99
EP  - 109
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20261202.15
AB  - Orthogonal Time Frequency Space (OTFS) modulation has recently emerged as a promising waveform for next-generation wireless communications, particularly in high-mobility environments characterized by doubly selective channels. However, the practical deployment of OTFS systems faces three major challenges: the high Peak-to-Average Power Ratio (PAPR) of multicarrier signals, which induces severe nonlinear distortions in the High-Power Amplifier (HPA); the growing demand for high-data-rate transmission requiring efficient data compression; and the inherently noisy transmission channel that degrades signal integrity. This paper proposes a comprehensive optimization of the OTFS transmission system by synergistically combining three complementary techniques. First, a neural network-based predistortion model is employed to linearize the HPA, enabling high-efficiency operation without signal degradation. Second, Compressive Sensing based on the Lifting Wavelet Transform (LWT) and the ALISTA algorithm is integrated to drastically reduce the volume of transmitted data, down to 10%–30% of the original signal, while ensuring fast and accurate reconstruction. Third, Low-Density Parity-Check (LDPC) coding is incorporated to enhance robustness against channel noise. Simulation results demonstrate that the joint application of these techniques successfully compensates for amplifier nonlinearity, corrects transmission errors even in severely noisy environments (achieving near-perfect image reconstruction at SNR > 10 dB over Rayleigh fading channels), and significantly reduces the data volume without compromising throughput. Furthermore, the rapid convergence of the ALISTA algorithm offsets the additional LDPC decoding complexity, validating the real-time feasibility of the proposed approach. The proposed framework thus enables OTFS systems to simultaneously achieve high data rates, low error rates, and energy efficiency, making it a strong candidate for future 6G communication systems.
VL  - 12
IS  - 2
ER  - 

Copy | Download