Simultaneous Dual-Band Classification for WLAN Band Selection
Bibliographic record
Abstract
Accurate classification of dual-band Wi-Fi signals is essential for improving adaptive band selection and maintaining quality of service in complex indoor wireless environments. Although several efforts have addressed propagation modeling, only few works simultaneously examined dual-band classification across both 2.4 GHz and 5 GHz frequencies in realistic scenarios. In this work, we use the measurements data conducted in the Deutsches Museum Bonn, which captures both line-of-sight (LoS) and non-LoS (NLoS) propagation conditions in a complex indoor environment. Ten statistical features are extracted from the received signal data, including mean, standard deviation, and skewness. To classify the signals, multiple machine learning models are evaluated, including k-nearest neighbors, support vector machines, and two deep learning architectures. Among these, model 3A, which is a fully connected neural network comprising three hidden layers using ReLU activation with 64, 32, and 16 neurons, respectively, and a softmax output layer, achieves the best performance. Trained with the Adam optimizer and categorical cross-entropy loss, model 3A attains an overall classification accuracy of 93 \% at the optimal window, thus outperforming the baseline models in terms of precision, recall, and F1-score across all classes. These results highlight the model’s robustness for simultaneous dual-band classification and its potential application in intelligent band selection for next generation Wi-Fi systems.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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 | 0.001 |
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".