Comparative Analysis of Machine Learning Algorithms for 5G Coverage Prediction: Identification of Dominant Feature Parameters and Prediction Accuracy
Bibliographic record
Abstract
5G technology is a key factor indelivering faster and more reliable wirelessconnectivity. One crucial aspect in 5G networkplanning is coverage prediction, which enablesnetwork providers to optimize infrastructuredeployment and deliver high-quality services tocustomers. This study conducts a comprehensiveanalysis of machine learning algorithms for 5Gcoverage prediction, focusing on dominantfeature parameters and accuracy. Notably, theRandom Forest algorithm demonstrates superiorperformance with an RMSE of 1.14 dB, MAE of0.12, and R2 of 0.97. The CNN model, thestandout among deep learning algorithms,achieves an RMSE of 0.289, MAE of 0.289, andR2 of 0.78, showcasing high accuracy in 5Gcoverage prediction. Random Forest modelsexhibit near-perfect metrics with 98.4% accuracy,precision, recall, and F1-score. Although CNNoutperforms other deep learning models, itslightly trails Random Forest in performance. Theresearch highlights that the final Random Forestand CNN models outperform other models andsurpass those developed in previous studies.Notably, 2D Distance Tx Rx emerges as the mostdominant feature parameter across allalgorithms, significantly influencing 5G coverageprediction. The inclusion of horizontal andvertical distances further improves predictionresults, surpassing previous studies. The studyunderscores the relevance of machine learningand deep learning algorithms in predicting 5Gcoverage and recommends their use in networkdevelopment and optimization. In conclusion,while the Random Forest algorithm stands out asthe optimal choice for 5G coverage prediction,deep learning algorithms, particularly CNN, offerviable alternatives, especially for spatial dataderived from satellite images. These accuratepredictions facilitate efficient resource allocationby network providers, ensuring high-qualityservices in the rapidly evolving landscape of 5Gtechnology. A profound understanding ofcoverage prediction remains pivotal forsuccessful network planning and reliable serviceprovision in the 5G era.The rapid development of 5G technology istransforming industries and enhancing connectivitythrough higher data speeds, ultra-low latency, andincreased network capacity.Efficient deployment of 5G networks requiresaccurate coverage prediction, ensuring seamlessservice across diverse geographical areas.Traditional coverage prediction methods often relyon time-consuming and resource-intensivesimulations, making them impractical for large-scaledeployment.Machine learning (ML) offers promising alternativesfor real-time and scalable 5G coverage prediction byanalyzing large datasets and identifying patterns thatinfluence network performance.ML algorithms can improve the accuracy of coveragepredictions by considering complex environmental
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 | 0.005 | 0.013 |
| Meta-epidemiology (narrow) | 0.003 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".