Enhanced fish species classification using dynamic multilayer perceptron and transformer encoders with extra distribution data.
Saved in:
| Title: | Enhanced fish species classification using dynamic multilayer perceptron and transformer encoders with extra distribution data. |
|---|---|
| Authors: | Chen, Mei-Hsin1 (AUTHOR) ivy@gis.tw, Lai, Ting-Hsuan1,2 (AUTHOR) dan@gis.tw, Chen, Yao-Chung1 (AUTHOR) brucechen@gis.tw, Chou, Tien-Yin1 (AUTHOR) jimmy@gis.tw |
| Source: | Multimedia Tools & Applications. Sep2025, Vol. 84 Issue 31, p37671-37700. 30p. |
| Subjects: | Classification of fish, Geospatial data, Multilayer perceptrons, Image recognition (Computer vision), Metadata, Transformer models |
| Abstract: | This study introduces an innovative integrative framework for fine-grained fish species classification, significantly enhancing recognition accuracy by leveraging multimodal features. We combine Transformer Encoder and Dynamic Multilayer Perceptron to fuse image features with geospatial information. Utilizing data from the Taiwan Fish Database, our method not only utilizes photographs of fish and their capture locations but also incorporates non-photo extra fish distribution survey data. Initially, using only photographs, the model achieved an accuracy of 0.7433. By adding geospatial data, accuracy increased to 0.7731, marking a 3.93% improvement over the baseline. The integration of additional fish distribution data further boosted accuracy to 0.8000, an overall enhancement of 6.2% compared to the baseline. This approach underscores the potential of combining photo-included geospatial information with extra distribution data in fine-grained image classification tasks, thereby making a significant contribution to both scientific research and practical applications in the field. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 188021222 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Enhanced fish species classification using dynamic multilayer perceptron and transformer encoders with extra distribution data. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chen%2C+Mei-Hsin%22">Chen, Mei-Hsin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ivy@gis.tw</i><br /><searchLink fieldCode="AR" term="%22Lai%2C+Ting-Hsuan%22">Lai, Ting-Hsuan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> dan@gis.tw</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Yao-Chung%22">Chen, Yao-Chung</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> brucechen@gis.tw</i><br /><searchLink fieldCode="AR" term="%22Chou%2C+Tien-Yin%22">Chou, Tien-Yin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jimmy@gis.tw</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Multimedia+Tools+%26+Applications%22">Multimedia Tools & Applications</searchLink>. Sep2025, Vol. 84 Issue 31, p37671-37700. 30p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Classification+of+fish%22">Classification of fish</searchLink><br /><searchLink fieldCode="DE" term="%22Geospatial+data%22">Geospatial data</searchLink><br /><searchLink fieldCode="DE" term="%22Multilayer+perceptrons%22">Multilayer perceptrons</searchLink><br /><searchLink fieldCode="DE" term="%22Image+recognition+%28Computer+vision%29%22">Image recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Metadata%22">Metadata</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This study introduces an innovative integrative framework for fine-grained fish species classification, significantly enhancing recognition accuracy by leveraging multimodal features. We combine Transformer Encoder and Dynamic Multilayer Perceptron to fuse image features with geospatial information. Utilizing data from the Taiwan Fish Database, our method not only utilizes photographs of fish and their capture locations but also incorporates non-photo extra fish distribution survey data. Initially, using only photographs, the model achieved an accuracy of 0.7433. By adding geospatial data, accuracy increased to 0.7731, marking a 3.93% improvement over the baseline. The integration of additional fish distribution data further boosted accuracy to 0.8000, an overall enhancement of 6.2% compared to the baseline. This approach underscores the potential of combining photo-included geospatial information with extra distribution data in fine-grained image classification tasks, thereby making a significant contribution to both scientific research and practical applications in the field. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=188021222 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11042-024-20359-9 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 30 StartPage: 37671 Subjects: – SubjectFull: Classification of fish Type: general – SubjectFull: Geospatial data Type: general – SubjectFull: Multilayer perceptrons Type: general – SubjectFull: Image recognition (Computer vision) Type: general – SubjectFull: Metadata Type: general – SubjectFull: Transformer models Type: general Titles: – TitleFull: Enhanced fish species classification using dynamic multilayer perceptron and transformer encoders with extra distribution data. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chen, Mei-Hsin – PersonEntity: Name: NameFull: Lai, Ting-Hsuan – PersonEntity: Name: NameFull: Chen, Yao-Chung – PersonEntity: Name: NameFull: Chou, Tien-Yin IsPartOfRelationships: – BibEntity: Dates: – D: 25 M: 09 Text: Sep2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 13807501 Numbering: – Type: volume Value: 84 – Type: issue Value: 31 Titles: – TitleFull: Multimedia Tools & Applications Type: main |
| ResultId | 1 |
