A hybrid deep learning and companding technique for distortion-resilient optical NOMA VLC with 1024-QAM modulation
Bibliographic record
Abstract
Abstract Visible light communication (VLC) has gained significant attention as a next-generation wireless technology due to its unlicensed bandwidth, high security, and seamless integration with LED illumination. To support high data rates and user scalability, power-domain non-orthogonal multiple access (NOMA) with 1024-QAM modulation enhances spectral efficiency; however, this combination introduces high peak-to-average power ratio (PAPR), resulting in nonlinear signal distortion and degraded bit error rate (BER) performance in intensity-modulated optical systems. To overcome these limitations, this paper proposes a deep learning-based nonlinear companding framework for waveform optimization in Optical NOMA. The proposed technique significantly reduces PAPR, achieving 3.2 dB, 4.4 dB, and 5.3 dB at a CCDF of 10 −3 for 256, 512, and 1024 subcarriers, respectively, outperforming A-Law, μ-Law, and PTS by up to 7.5 dB improvement. BER analysis further confirms its superiority, achieving a BER of 10 −3 at only 8.9 dB SNR, compared to 15.2 dB (A-Law), 13.1 dB (μ-Law), 11.4 dB (PTS), and 17.8 dB for the unprocessed Optical NOMA waveform. These results demonstrate improved power efficiency, reduced nonlinear distortion, and enhanced detection reliability, making the proposed method a strong candidate for high-speed VLC-based NOMA systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".