GRU-Attention Model for Linearizing Millimeter-Wave Transmitters in Vehicle to Satellite Communication Systems
Bibliographic record
Abstract
Recently, with the increasing deployment of vehicle-to-everything (V2X) communication systems, wireless transmitters have been extensively deployed in vehicles. And to enable high-capacity and high-speed communications everywhere in the world, the communication from vehicle to satellite (V2S) has emerged, particularly utilizing high throughput satellite (HTS) technology. However, the nonlinearity of the millimeter wave transmitter (mmWT) in a vehicle ends affects the quality of the V2S uplink transmitted signal gravely. Digital predistortion (DPD) linearization has shown promise in mitigating the nonlinearity of mmWTs. In addition, due to the powerful and complex feature fitting ability, neural networks have been used to nonlinear behavioral model and DPD linearize for broadband wireless communication systems. In this work, a gated recurrent unit (GRU) with attention mechanism (GRU-attention) model is proposed for modeling and linearizing mmWTs in V2S communication systems. The attention mechanism in the GRU-attention model calculates a distribution matrix during the training process, which is utilized to weigh the GRU-attention model parameters, thereby enhancing the modeling accuracy. The linearization performance of the GRU-attention is experimentally evaluated by using a Ka-band 29 GHz mmWT with a 100 MHz bandwidth and 64 quadrature amplitude modulation (64-QAM) 5G NR signal. The experimental results demonstrate that the GRU-attention improves the adjacent channel power ratio of the mmWT by 18 dB, which is 4 dB better than that of the conventional GRU model.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".