Auxiliary-LSTM based floor-level occupancy prediction using Wi-Fi access point logs
Bibliographic record
Abstract
Smart city concepts have gained increased traction over the years. The advances in technology such as the Internet of things (IoT) networks and their large-scale implementation has facilitated data collection, which is used to obtain valuable insights towards managing, improving, and planning for services. One key component in this process is the understanding of human mobility behaviour. Traditional data collection methods such as surveys and GPS data have been extensively used to study human mobility. However, a key concern with such data is the protection of user privacy. This study aims to overcome those concerns using Wi-Fi access point logs and demonstrate their utility by creating building occupancy prediction models using advanced machine learning techniques. The floor level occupancy counts and auxiliary variable for a campus building are extracted from the Wi-Fi logs. They are used to develop specifications of Long-Short Term Memory network (LSTM), Auxiliary LSTM (Aux-LSTM), Autoregressive Integrated Moving Average (ARIMA), and Multi-layer Perceptron (MLP) models. The LSTM performed better than the other models and can efficiently capture peak values. Aux-LSTM was shown to increase the reliability in prediction and applicability in the context of facilities management. Results show the effectiveness of the Wi-Fi dataset in capturing trends, providing supplementary information, and highlight the ability of LSTM to adequately model time-series data.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".