MétaCan
Menu
Back to cohort

Low False Alarm Rate Model for Unsafe-Proximity Detection in Construction

2015· article· en· W2135623443 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Computing in Civil Engineering · 2015
Typearticle
Languageen
FieldHealth Professions
TopicOccupational Health and Safety Research
Canadian institutionsMcMaster University
Fundersnot available
KeywordsHeading (navigation)Global Positioning SystemReal-time computingPosition (finance)False alarmField (mathematics)Computer scienceWarning systemALARMKalman filterTracking (education)Tracking systemEngineeringSimulationArtificial intelligence

Abstract

fetched live from OpenAlex

The research reported in this paper proposes and develops an unsafe-proximity detection model focused on decreasing false alarms. By considering three types of entity attributes [i.e., (1) position, (2) heading/moving direction, and (3) speed], more accurate unsafe-proximity identifications with reduced false alarms can be achieved. The proposed and developed model works via two modules, as follows: (1) state tracking module, and (2) safety rules module. The state tracking module collects construction entities’ states (position, heading, and speed) in real time. The collected states information is analyzed in the safety rules module for unsafe-proximity identifications. Five common situations on construction jobsites are extracted and studied for the development of the safety rules, as follows: (1) static equipment and moving worker, (2) moving equipment and moving worker, (3) moving equipment and static worker, (4) two pieces of moving equipment, and (5) moving equipment and static equipment. The unsafe area around equipment is divided into alert and warning areas which are quantified using forklift as sample equipment. The localization accuracy of the state tracking module and the functional effectiveness of the safety rules module are evaluated, through simulation and a field experiment. Twelve scenarios and 13 subscenarios were designed and incorporated, in the simulation and the field experiment, respectively. The extended Kalman filter combined with the nearest-neighbor method was used in the simulation and a global positioning system (GPS)-aided inertial navigation system sensor was used in the field experiment as the state tracking module. The results suggest that the magnitude of localization accuracy of the extended Kalman filter combined with the nearest-neighbor method and the adopted sensor both are less than 0.7 m. Such an accuracy level is acceptable for construction applications. Moreover, the developed safety rules have a strong capability in avoiding false alarms. In some scenarios the developed model can avoid one false alarm for each scan. The research reported in this paper also demonstrates the applicability and feasibility of implementing the model for real applications. The developed model has great promise to enhance construction safety and mobility by timely avoiding collisions, while reducing false alarms and interruptions to work.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.402
Threshold uncertainty score0.410

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.077
GPT teacher head0.402
Teacher spread0.326 · 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