Low-Error Indoor Positioning via Synthetic RSSI Augmentation and Zx–WKNN Hybrid Model
Bibliographic record
Abstract
Indoor Localization Systems (ILS) are critical for applications requiring high positioning accuracy, such as emergency response. However, traditional fingerprinting-based methods face challenges including multipath interference and the need for labor-intensive site surveys using Received Signal Strength Indicators (RSSIs). To address these limitations, this paper proposes two key contributions: (1) A data augmentation framework using Autoencoders (AE) and Variational Autoencoders (VAE) to expand RSSI datasets and reduce manual survey efforts; and (2) a hybrid localization model, Zonal-Weighted K-Nearest Neighbours (Zx-WKNN), which first classifies the target’s probable sub-area (zone) and then refines the location using a regression model. Each zone is defined around a reference point and contains RSSI fingerprints with corresponding coordinates. Unlike traditional WKNN, which considers all reference points, Zx-WKNN focuses on a limited number of zones (x = 1, 2, or 3) to enhance accuracy. Experimental results demonstrate that incorporating synthetic data from our generative models reduces Root Mean Squared Error (RMSE) by 6–25% and improves R-squared (R2) by 11–400%. Compared to baseline models such as WKNN and Random Forest, Zx-WKNN achieves 2.1–18.8% lower RMSE and 3.2–29% higher R2. Overall, our approach significantly improves localization accuracy while addressing the scalability limitations of traditional fingerprinting methods.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".