| 大会名称 |
| 2021年 総合大会 |
| 大会コ－ド |
| 2021G |
| 開催年 |
|
2021
|
| 発行日 |
|
2021-02-23
|
| セッション番号 |
|
BS-7
|
| セッション名 |
|
AI technologies and their applications for future network systems and services
|
| 講演日 |
|
2021/3/9
|
| 講演場所(会議室等) |
|
Meeting 30
|
| 講演番号 |
|
BS-7-6
|
| タイトル |
|
Data Validation Scheme Considering Edge Computing for Mobile Crowdsensing Application in Smart Transportation
|
| 著者名 |
|
◎Junto Kashino, Masaki Bandai,
|
| キーワード |
|
Edge Computing, Artificial Intelligence, Smart Transportation
|
| 抄録 |
|
In the Mobile Crowdsensing application of road transportation, the users are encouraged to upload the images of reflecting the road traffic. However, people may upload the images with high similarities and uploading all would cause huge network traffic. Some may also upload the images unrelated to traffic scenes. In this paper, we consider the data validation scheme with Deep Learning and network computation. We propose that some similar images are filtered out at edges before sending them to the cloud. We evaluate how the accuracy is affected if all the similar images are uploaded to the cloud for further training.
|
| 本文pdf |
|
PDF download
|
