| Presentation | 2022-03-09 Automatic Detection of Fire Causes for Ontology Development for Automatic Understanding of Fire Situation Kento Matsuba, Masahide Nakamura, Sachio Saiki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The fire investigation report prepared by the Kobe City Fire Department contains information on the causes of the fire and the problems that led to the fire, but efforts to consolidate and utilize this information have not progressed. Since many items in fire investigation reports are recorded as text, it is difficult to extract features mechanically. By using Japanese natural language processing technology, we were able to extract the ignition source, the course of the fire, and the ignition materials from various data provided by the Kobe City Fire Department. As a result, we were able to extract the ignition source with an accuracy of 93.1% and the ignition material with 77.4%. For the extraction of the process, the results were generally reasonable in 42.4% of the cases. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | fire / cause of fire / text mining / fire research report / NLP / morphological analysis / syntax analysis |
| Paper # | KBSE2021-45 |
| Date of Issue | 2022-03-02 (KBSE) |
| Conference Information | |
| Committee | KBSE |
|---|---|
| Conference Date | 2022/3/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | General, Student |
| Chair | Hiroyuki Nakagawa(Osaka Univ.) |
| Vice Chair | Takuya Saruwatari(NTT Data) |
| Secretary | Takuya Saruwatari(Shinsｈu Univ) |
| Assistant | Hideharu Kojima(Osaka Univ.) / Yutaro Kashiwa(Kyushu Univ,) |
| Paper Information | |
| Registration To | Technical Committee on Knowledge-Based Software Engineering |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Automatic Detection of Fire Causes for Ontology Development for Automatic Understanding of Fire Situation |
| Sub Title (in English) | |
| Keyword(1) | fire |
| Keyword(2) | cause of fire |
| Keyword(3) | text mining |
| Keyword(4) | fire research report |
| Keyword(5) | NLP |
| Keyword(6) | morphological analysis |
| Keyword(7) | syntax analysis |
| 1st Author's Name | Kento Matsuba |
| 1st Author's Affiliation | Kobe University(Kobe Univ.) |
| 2nd Author's Name | Masahide Nakamura |
| 2nd Author's Affiliation | Kobe University(Kobe Univ.) |
| 3rd Author's Name | Sachio Saiki |
| 3rd Author's Affiliation | Kochi University of Technology(KUT) |
| Date | 2022-03-09 |
| Paper # | KBSE2021-45 |
| Volume (vol) | vol.121 |
| Number (no) | KBSE-424 |
| Page | pp.pp.24-29(KBSE), |
| #Pages | 6 |
| Date of Issue | 2022-03-02 (KBSE) |