-
- Kawamata Koji
- Ryukoku University
-
- Oku Kenta
- Ryukoku University
この論文をさがす
抄録
<p>We propose Roadscape-based Route Recommender System (R3), which provides diversified roadscape-based routes. Given starting and destination points, R3 provides four types of roadscape-based routes: rural-, mountainous-, waterside-, and urban-prior routes. To reduce the computational cost, we propose a coarse-to-fine route search approach that consists of a roadscape-based clustering method, roadscape cluster graph, coarse-grained route search, and fine-grained route search. We evaluated the performance of R3 using network data for real roads. The experimental results qualitatively show the validity of the generated roadscape clusters by comparing them with Google satellite maps and Google Street View images. The results also show the validity of the roadscape-based route recommendations. Furthermore, the results show that using a coarse-grained route search can significantly reduce the route search time. Finally, we quantitatively evaluate R3 from the perspective of users. The results show that R3 can appropriately recommend roadscape-based routes for given scenarios.</p>
収録刊行物
-
- Journal of Information Processing
-
Journal of Information Processing 27 (0), 392-403, 2019
一般社団法人 情報処理学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282763114731520
-
- NII論文ID
- 130007649906
- 170000150234
-
- NII書誌ID
- AA11464847
-
- ISSN
- 18827799
- 18826652
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- IRDB
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可