MétaCan
Menu
← Back to cohort
Record W7132143057

Wi-Fi based occupancy clustering and motif identification: a case study

2020· article· en· W7132143057 on OpenAlexvenueno aff
Brodie W. Hobson, H. Burak Gunay, Araz Ashouri, Guy R. Newsham

Bibliographic record

VenueNPARC · 2020
Typearticle
Languageen
FieldEngineering
TopicBuilding Energy and Comfort Optimization
Canadian institutionsnot available
Fundersnot available
KeywordsOccupancyCluster analysisHierarchical clusteringHVACEnergy (signal processing)Time series
DOInot available

Abstract

fetched live from OpenAlex

The energy use of many buildings is significantly influenced by the presence and number of occupants. The prevalence of personal mobile devices has highlighted Wi-Fi data as a strong indicator of occupancy levels, with a strong correlation between the number of occupants and the number of Wi-Fienabled devices in a building. With accurate occupancy-count estimations, occupancy-based controls for building HVAC systems have the potential to realize energy savings. However, reactive controls based on instantaneous occupancy-count estimates are not sufficient for optimal operation. Instead, characterizing occupancy patterns can allow building operators to make proactive and informed decisions about equipment schedules, which has the potential to reduce energy use. This paper presents a Wi-Fi based approach for occupancy pattern detection, using an academic office building as a case study. Occupancy in many buildings - including the case study building - is not entirely stochastic; a visual inspection of Wi-Fi time series data will reveal repetitious patterns throughout the year, such as several distinct weekday and weekend profiles, called motifs. Seven months of continuous Wi-Fi time series data is processed through an occupancy-count estimation function to develop predicted occupancy profiles for each day. These occupancy profiles are clustered using several different approaches, including hierarchical agglomerative clustering with different dissimilarity metrics and k-means clustering. The results and performance indices for different clustering techniques are discussed. Based on this analysis, typical cluster profiles are extracted. Each typical profile is quantized using alphabetic characters and a character is assigned to each day. These characters are combined into corresponding words for each week. Frequently repeated weekly words are identified, and rule extraction is performed using a classification tree to develop a day-ahead occupancy forecast. The results show that this methodology can be used on Wi-Fi data to generate insights into occupancy patterns in the case study building. The forecastingframework can also be used to accurately forecast occupancy over the 24-hour prediction horizon. Future work will implement a control scheme based on the results from this study in a real-world air handling unit to quantify energy savings.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.025
Threshold uncertainty score0.050

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0020.000
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.019
GPT teacher head0.221
Teacher spread0.202 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2020
Admission routes1
Has abstractyes

Explore more

Same venueNPARC→Same topicBuilding Energy and Comfort Optimization→French-language works237,207→