Actions for Mining Behavior Based Safety Data to Predict Safety Performance [electronic resource].

Email RIS file
Bookmark
Report an Issue

Mining Behavior Based Safety Data to Predict Safety Performance [electronic resource].

Published
Idaho Falls, Idaho : Idaho National Laboratory, 2010.
Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy
Additional Creators
Idaho National Laboratory and United States. Department of Energy. Office of Scientific and Technical Information
Access Online

Availability

I Want It
I Want It

Finding items...

Restrictions on Access
Free-to-read Unrestricted online access
Summary
The Idaho National Laboratory (INL) operates a behavior based safety program called Safety Observations Achieve Results (SOAR). This peer-to-peer observation program encourages employees to perform in-field observations of each other's work practices and habits (i.e., behaviors). The underlying premise of conducting these observations is that more serious accidents are prevented from occurring because lower level “at risk” behaviors are identified and corrected before they can propagate into culturally accepted “unsafe” behaviors that result in injuries or fatalities. Although the approach increases employee involvement in safety, the premise of the program has not been subject to sufficient empirical evaluation. The INL now has a significant amount of SOAR data on these lower level “at risk” behaviors. This paper describes the use of data mining techniques to analyze these data to determine whether they can predict if and when a more serious accident will occur.
Report Numbers
E 1.99:inl/con-10-18114
inl/con-10-18114
Subject(s)
Other Subject(s)
Note
Published through SciTech Connect.
06/01/2010.
"inl/con-10-18114"
10th International Probabilistic Safety Assessment and Management Conference,Seattle, WA,06/07/2010,06/11/2010.
Jeffrey C. Joe.
OTHER
Funding Information
DE-AC07-05ID14517
View MARC record | catkey: 23780368