Abstract
Although expert systems are usually thought of as decision aids for human users, they may also serve as training aids for situations in which humans must make quick decisions and computer-based decision aids would not be viable. This paper describes an exploratory study of the application of expert system-based training for an emergency management of a hazardous chemical spill. Human factors methodologies are employed to define the training, control, and test conditions needed to quantify the significance of using an expert system for training human decision makers for an emergency management application. The results confirmed the hypothesis that the natural human tendency in processing rules would be to resort to a data-driven strategy. The expert system-based training can deter the human from employing such a strategy and can improve his performance, especially as the complexity in rule-chaining increases. Overall, the results of this study are supportive of the use of artificial intelligence-based techniques for training humans in the emergency management of risk.
| Original language | English |
|---|---|
| Pages (from-to) | 6-22 |
| Number of pages | 17 |
| Journal | Journal of Computing in Civil Engineering |
| Volume | 7 |
| Issue number | 1 |
| State | Published - Jan 1 1993 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Computer Science Applications
- Civil and Structural Engineering
Cite this
Expert system based training for emergency management. / Sharit, Joseph; Chen, S.; Lin, D. Y M.
In: Journal of Computing in Civil Engineering, Vol. 7, No. 1, 01.01.1993, p. 6-22.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Expert system based training for emergency management
AU - Sharit, Joseph
AU - Chen, S.
AU - Lin, D. Y M
PY - 1993/1/1
Y1 - 1993/1/1
N2 - Although expert systems are usually thought of as decision aids for human users, they may also serve as training aids for situations in which humans must make quick decisions and computer-based decision aids would not be viable. This paper describes an exploratory study of the application of expert system-based training for an emergency management of a hazardous chemical spill. Human factors methodologies are employed to define the training, control, and test conditions needed to quantify the significance of using an expert system for training human decision makers for an emergency management application. The results confirmed the hypothesis that the natural human tendency in processing rules would be to resort to a data-driven strategy. The expert system-based training can deter the human from employing such a strategy and can improve his performance, especially as the complexity in rule-chaining increases. Overall, the results of this study are supportive of the use of artificial intelligence-based techniques for training humans in the emergency management of risk.
AB - Although expert systems are usually thought of as decision aids for human users, they may also serve as training aids for situations in which humans must make quick decisions and computer-based decision aids would not be viable. This paper describes an exploratory study of the application of expert system-based training for an emergency management of a hazardous chemical spill. Human factors methodologies are employed to define the training, control, and test conditions needed to quantify the significance of using an expert system for training human decision makers for an emergency management application. The results confirmed the hypothesis that the natural human tendency in processing rules would be to resort to a data-driven strategy. The expert system-based training can deter the human from employing such a strategy and can improve his performance, especially as the complexity in rule-chaining increases. Overall, the results of this study are supportive of the use of artificial intelligence-based techniques for training humans in the emergency management of risk.
UR - http://www.scopus.com/inward/record.url?scp=0027239344&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027239344&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:0027239344
VL - 7
SP - 6
EP - 22
JO - Journal of Computing in Civil Engineering
JF - Journal of Computing in Civil Engineering
SN - 0887-3801
IS - 1
ER -