Occupancy Estimation Using Sparse Sensor Coverage
Bibliographic record
Abstract
Estimation of occupant count in commercial and institutional buildings enables energy experts to make better decisions on which buildings to prioritize for green upgrading and retrofitting from a large building portfolio. A cheap easy-to-install solution will enable energy experts to obtain occupancy estimation by easily scaling to large building portfolios. This paper presents a method for estimating occupancy based on sparse coverage of low-cost IoT sensors. The method is tested on 2 datasets, one academic building in Denmark (DK) and one academic building in Canada (CAN). The datasets contain PIR, CO2 measurements, and electric energy data together with ground truth occupancy counts. We show that 20% sensor coverage is comparable to full sensor coverage (60%) with an NRMSE of 0.142 (DK) and 0.174 (CAN) for 20% sensor coverage and an NRMSE of 0.129 (DK) and 0.163 (CAN) for full sensor coverage. Results show that with less sensor coverage, sensor placement becomes more important and that even with 20% it is possible to get as good of an accuracy as full coverage. The occupant count is used for key performance indicators of the buildings’ energy usage which shows higher energy use per occupant at low occupancy.
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) | 0.001 | 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 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".