Deep Learning-Based MIMO Detection under Power-Amplifier Nonlinearity and Channel Memory for 5G Networks
Bibliographic record
Abstract
Realistic fifth-generation (5G) deployments must contend with time-correlated fading and power amplifier (PA) nonlinearity impairments that are often studied in isolation. This work introduces a unified MATLAB 5G-Toolbox framework and custom dataset for deep learning (DL)-based multiple-input multiple-output (MIMO) detection under power amplifier (PA) nonlinearity and channel memory. Specifically, we implement four detectors based on a fully connected neural network (FCNN), a convolutional neural network (CNN), a residual network (ResNet), and a long-short-term memory (LSTM) network to evaluate their bit error rate (BER) under quadrature amplitude modulation (QAM). A sphere decoding (SD) algorithm, which employs minimum mean squared error (MMSE) initialization and Schnorr–Euchner (SE) ordering, is used as a near maximum likelihood (ML) benchmark. Extensive Monte Carlo simulations are performed over an Eb/N0range of 0 to 18 dB (with an effective 6 dB signal-to-noise ratio (SNR) shift for 16-QAM). Our results demonstrate that CNN- and ResNet-based detectors achieve competitive performance within 2–3 dB of ML performance under severe nonlinearity, while reducing inference run-time by more than 50% on an Intel i7 CPU compared to ML and SD algorithms. In the urban macro-scenario, where rapid temporal variations and channel memory degrade conventional models, an LSTM-based detector demonstrates superior robustness by explicitly leveraging time-series dependencies. A detailed cost–complexity analysis is also provided, reporting floating point operations (FLOPs) and the actual run-time per block on specified hardware to quantify the trade-off between detection accuracy and computational effort. .
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 | 0.001 | 0.003 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".