VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/2004| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Tran Thi Khanh Linh | en_US |
| dc.date.accessioned | 2025-03-26T07:31:37Z | - |
| dc.date.available | 2025-03-26T07:31:37Z | - |
| dc.date.issued | 2024 | - |
| dc.identifier.uri | https://epub.vgu.edu.vn/handle/dlibvgu/2004 | - |
| dc.description.abstract | This thesis investigated the effectiveness of the Swin Transformer architecture at identifying mosquito species. The two distinct datasets comprised of mosquito body and wing images were used for training and evaluating the model's effectiveness. The experiment result indicated that Swin Transformer achieved high accuracy, with the best accuracy score on test set of 97.36% for body images (variant Swin-B), and 93.42% for wing images (variant SwinS). Consequently, it unveiled the capacity of Swin Transformer to precisely classify mosquitoes based on images. Furthermore, this exploration discussed the trade-offs between accuracy levels and computational efficiency in case of limited resources. Regarding prospects, the outcomes suggested an optimistic approach, where Swin Transformer could be used in a reallife mosquito surveillance framework with some additional fine-tuning | en_US |
| dc.language.iso | en | en_US |
| dc.rights | Attribution-NonCommercial 4.0 International | * |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc/4.0/ | * |
| dc.subject | Image classification | en_US |
| dc.subject | Mosquito identification | en_US |
| dc.subject | Swin transformer | en_US |
| dc.title | Identification of mosquito species by utilizing transformer models on body and wing images | en_US |
| dc.type | Thesis | en_US |
| item.fulltext | With Fulltext | - |
| item.languageiso639-1 | other | - |
| item.grantfulltext | restricted | - |
| Appears in Collections: | Business Information Systems (BIS) | |
Files in This Item:
| File | Description | Size | Format | Existing users please Login |
|---|---|---|---|---|
| Identification of mosquito species by utilizing transformer models on body and wing images.pdf | 4.1 MB | Adobe PDF |
Page view(s)
284
checked on Oct 13, 2025
Download(s)
34
checked on Oct 13, 2025
Google ScholarTM
Check
This item is licensed under a Creative Commons License