| Project/Area Number |
05680290
|
|---|
| Research Category |
Grant-in-Aid for General Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Japan Advanced Institute of Science and Technology, Hokuriku |
|---|
Principal Investigator |
OCHIMIZU Koichiro Japan Advanced Institute of Science and Technology, Hokuriku, School of Information Science, Professor, 情報科学研究科, 教授 (10022310)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
NAKAJIMA Tatsuo Japan Advanced Institute of Science and Technology, Hokuriku, Information Scienc, 情報科学センタ, 助教授 (10251977)
YAMAGUTI Takahira Shizuoka University, Faculty of Engineering, Associate Professor, 工学部, 助教授 (20174617)
SHINODA Youichi Japan Advanced Institute of Science and Technology, Hokuriku, School of Informat, 情報科学研究科, 助教授 (50206108)
|
|---|
| Project Period (FY) |
1993 – 1994
|
| Project Status |
Completed (Fiscal Year 1994)
|
| Budget Amount *help |
¥2,000,000 (Direct Cost: ¥2,000,000)
Fiscal Year 1994: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 1993: ¥1,500,000 (Direct Cost: ¥1,500,000)
|
|---|
| Keywords | expert system / network fault diagnosis / deep knowledge / protocol stack / network configuration / knowledge compiling / fault diagnostic tree |
|---|
| Research Abstract |
The new research results obtained through the project are as follows;
1.Analysis of network diagnosis expertise In the early stage of our research, we performed several case studies to collect expertise of network diagnosis by interviewing an expert. We succeeded in formalizing reasoning processes and knowledge types used in his fault diagnosis processes.
2.Construction of Conceptual Model for a fault diagnostic expert system We identified the background principle of the expert system as a protocol stack search problem, and constructed the conceptual model for a fault diagnostic expert system.
3.Development of prototype system We developed a prototype of the expert system which produces a fault diagnostic tree representing all of possible cause-effect relationships between symptoms and fault hypotheses. The capability of the first prototype system was, however, limited, because it works on a fixed hardware configuration.
4.Refinement of the Fault Diagnosis Model We refined the model to deal with the fault hypotheses changes on the objective hardware configurations related to symptoms by incorporating knowledge about network hardware configuration.
5.Improvement of the prototype We enhanced the capability of the prototype by incorporating with the diagnosis model mentioned in item (4).
|
