Channel Prediction Using Adaptive Bidirectional GRU for Underwater MIMO Communications
Bibliographic record
Abstract
As the Internet of Things (IoT) continues to expand and reshape our world, new vertical application scenarios have emerged, such as underwater communications, leading to increased interest in academia and industries. The multiple-input–multiple-output (MIMO) technology plays a critical role in enhancing channel capacity for underwater acoustic (UWA) communications, where accurate channel prediction is essential for system performance. In this article, we propose a novel efficient channel impulse response (CIR) prediction model for the UWA MIMO communications with a small adaptive bidirectional gated recurrent unit (ABiGRU) network. The proposed model can capture the channel information without additional knowledge of the internal properties of the channel itself. Moreover, it first utilizes preceding short-term CIR data from the channel estimation for online training, and then exploits the trained model for the CIR prediction, which tracks time-varying UWA channels. To verify the effectiveness of the predicted CIRs, we design a scheme combining a space-time block coding (STBC) and minimum mean square error (MMSE) pre-equalization for the UWA MIMO system. Our proposed STBC-MMSE pre-equalization scheme has demonstrated practical feasibility and low-bit-error rate (BER) in numerical simulations. In addition, we evaluate the prediction error performance of the proposed ABiGRU network through comparison with the widely used MMSE algorithm and two common recurrent neural networks (RNNs) predictors, i.e., the gated recurrent unit and long short term memory (LSTM) network. Finally, we conduct realistic in-field UWA MIMO experiments to demonstrate and justify the superiority of the proposed ABiGRU network, which can lay the solid foundation for cost-effective UWA MIMO communications for building promising underwater IoT sensor networks.
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) | 0.000 | 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".