| Project/Area Number |
11832021
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Institution | Meiji University |
|---|
Principal Investigator |
TAKAGI Tomohiro Department of Computer Science, Meiji University, Professor, 理工学部, 教授 (90308065)
|
|---|
| Project Period (FY) |
1999 – 2000
|
| Project Status |
Completed (Fiscal Year 2000)
|
| Budget Amount *help |
¥3,200,000 (Direct Cost: ¥3,200,000)
Fiscal Year 2000: ¥1,300,000 (Direct Cost: ¥1,300,000)
Fiscal Year 1999: ¥1,900,000 (Direct Cost: ¥1,900,000)
|
|---|
| Keywords | Fuzzy / Ontology / Conceptual matching / TV programs recommendation / Music retrieval / Search engine / Test Clustering / Image Data Retrieval / 状態センサー |
|---|
| Research Abstract |
(1) Theoretical works
Investigation of theoretical works on associative memories.
Investigation of fundamental concepts of ontology.
Proposal of a method for representing common concepts by fusing conceptual fuzzy sets with ontology including
- usage of various associative memories
- temporal descriptions.
Proposal of a method of conceptual matching between texts to texts and texts to patterns for retrieving information that meets a user's intentions.
(2) Development of prototype systems
We developed following prototype systems.
a. An agent recommends TV programs to watch : It recommends TV programs which have EPGs (Electronic Program Guide) similar to those of previously watched programs or that contain words matching the learning data.
b. Music Selection System : It selects music matching the tone of a text composition. Selection of music for two email notes shows that the proposed system can select music that matches human feelings.
c. Search Engine : It expand the meaning of the keywords inputs by a searcher and find new keywords using ontology ; for example, "ski" or "skate" from "winter" and "sports."
d. Test Clustering System : It extracts meaning information form plain documents, and classifies disconnected documents into similar conceptual document group. It aims at this grouping is closely resembled that is classified by person as much as possible.
e. Image Data Retrieval System : It retrieves images that conceptually fit the meanings of the entered keyword based on the atmosphere understood from the characteristic values of the images.
|
