On the Performance of Deep Learning Models for Uplink CSI Prediction in Vehicular Environments
Bibliographic record
Abstract
Recently, there had been several proposals to use deep-learning based prediction models in estimating channel state information (CSI). However, all of these proposals were investigated under a fixed indoor-outdoor environment. In this paper, we propose two models to perform uplink CSI prediction in dynamic vehicular environments. One of these models is a tailoring of an existing state-of-the-art deep learning model, based on a combination of convolutional and recurrent neural networks (CNN-RNN), so as to suit the mobility factor in vehicular environments. The other model is a proposed simpler artificial neural network (ANN) model, again tailored to cope with the vehicular settings. We perform a comparative sensitivity analysis of the two models, in which we investigate the effect of changing vehicle speed, prediction horizon, and history horizons on the performance of both models. Interestingly, we have show that the simpler ANN model performs much better than the more sophisticated CNN-RNN model at broad range of vehicular driving speeds as long as the prediction horizon is smaller than the history horizon in the prediction process. The CNN-RNN becomes naturally more efficient in the opposite scenarios.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| 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 | 0.002 |
| 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".