Analyzing Arizona OSHA Injury Reports Using Unsupervised Machine Learning
Open accessThe DOI matches its Crossref record.
Abstract
As the construction continue to be a leading industry in the number of injuries and fatalities annually, several organizations and agencies are working avidly to ensure the number of injuries and fatalities is minimized. The Occupational Safety and Health Administration (OSHA) is one such effort to assure safe and healthful working conditions for working men and women by setting and enforcing standards and by providing training, outreach, education and assistance. Given the large databases of OSHA historical events and reports, a manual analysis of the fatality and catastrophe investigations content is a time consuming and expensive process. This paper aims to evaluate the strength of unsupervised machine learning and Natural Language Processing (NLP) in supporting safety inspections and reorganizing accidents database on a state level. After collecting construction accident reports from the OSHA Arizona office, the methodology consists of preprocessing the accident reports and weighting terms in order to apply a data-driven unsupervised K-Means-based clustering approach. The proposed method classifies the collected reports in four clusters, each reporting a type of accident. The results show the construction accidents in the state of Arizona to be caused by falls (42.9%), struck by objects (34.3%), electrocutions (12.5%), and trenches collapse (10.3%). The findings of this research empower state and local agencies with a customized presentation of the accidents fitting their regulations and weather conditions. What is applicable to one climate might not be suitable for another; therefore, such rearrangement of the accidents database on a state based level is a necessary prerequisite to enhance the local safety applications and standards.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cited by
Pan, Y., & Zhang, L. (2021) · Automation in Construction · doi:10.1016/j.autcon.2020.103517 · Cited by 1,336
Construction site accident analysis using text mining and natural language processing techniques
Zhang, F., Fleyeh, H., Wang, X., & Lu, M. (2019) · Automation in Construction · doi:10.1016/j.autcon.2018.12.016 · Cited by 380
Highway Construction Safety Analysis Using Large Language Models
Smetana, M., Salles de Salles, L., Sukharev, I., & Khazanovich, L. (2024) · Applied Sciences · doi:10.3390/app14041352 · Cited by 87
Deep Learning-Based Applications for Safety Management in the AEC Industry: A Review
Hou, L., Chen, H., Zhang, G. (., & Wang, X. (2021) · Applied Sciences · doi:10.3390/app11020821 · Cited by 76
Metadata
- Authors
- Chokor, A., Naganathan, H., Chong, W. K., & Asmar, M. E.
- Venue
- Procedia Engineering
- Publisher
- Elsevier BV
- Published
- 2016
- Volume
- 145
- Pages
- 1588-1593
- ISSN
- 1877-7058 (ISSN-L)
- OpenAlex
- W2402968296
- Cited by
- 77
- References
- 0
- FWCI
- 9.62
- Type
- conference paper
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.