Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Freshwater Microscopic Algae Detection Based on Deep Neural Network with GAN-Based Augmentation for Imbalanced Algal Data
https://orcid.org/0000-0003-2463-4844
https://orcid.org/0000-0002-7001-6900
Identifying and quantifying algal genera in images are crucial for understanding their ecological impact. Algal data are often imbalanced, limiting detection model accuracy. This paper presents a novel data augmentation method using StyleGAN2-ADA to enhance algal image instance segmentation. StyleGAN2-ADA generates artificial single-algal images to address data scarcity and imbalance. We train a Cascaded Mask R-CNN with Swin Transformer on a combined data set of real and artificial multigenera algal images and evaluate performance using the COCO mAP metric. The approach improves bounding box detection performance by 17.9% on all genera and 32.1% on rare genera compared with the baseline model. Additionally, 50% more artificial data yield significant enhancements without excessive artificial data use. The GAN-based augmentation technique shows a performance improvement in both Swin-Tiny and ResNet-50 backbone models, suggesting adaptability for various machine learning models. The increased mAP leads to the accurate identification of harmful algae genera, allowing for better prevention and mitigation. This method offers a superior data augmentation solution for accurate algal instance segmentation and can benefit applications challenged by imbalanced and scarce data.
This work uses GAN-based data augmentation and machine learning to improve freshwater algal image detection, which could aid in identifying harmful algal blooms and water quality monitoring.
Freshwater Microscopic Algae Detection Based on Deep Neural Network with GAN-Based Augmentation for Imbalanced Algal Data
https://orcid.org/0000-0003-2463-4844
https://orcid.org/0000-0002-7001-6900
Identifying and quantifying algal genera in images are crucial for understanding their ecological impact. Algal data are often imbalanced, limiting detection model accuracy. This paper presents a novel data augmentation method using StyleGAN2-ADA to enhance algal image instance segmentation. StyleGAN2-ADA generates artificial single-algal images to address data scarcity and imbalance. We train a Cascaded Mask R-CNN with Swin Transformer on a combined data set of real and artificial multigenera algal images and evaluate performance using the COCO mAP metric. The approach improves bounding box detection performance by 17.9% on all genera and 32.1% on rare genera compared with the baseline model. Additionally, 50% more artificial data yield significant enhancements without excessive artificial data use. The GAN-based augmentation technique shows a performance improvement in both Swin-Tiny and ResNet-50 backbone models, suggesting adaptability for various machine learning models. The increased mAP leads to the accurate identification of harmful algae genera, allowing for better prevention and mitigation. This method offers a superior data augmentation solution for accurate algal instance segmentation and can benefit applications challenged by imbalanced and scarce data.
This work uses GAN-based data augmentation and machine learning to improve freshwater algal image detection, which could aid in identifying harmful algal blooms and water quality monitoring.
Freshwater Microscopic Algae Detection Based on Deep Neural Network with GAN-Based Augmentation for Imbalanced Algal Data
https://orcid.org/0000-0003-2463-4844
https://orcid.org/0000-0002-7001-6900
Identifying and quantifying algal genera in images are crucial for understanding their ecological impact. Algal data are often imbalanced, limiting detection model accuracy. This paper presents a novel data augmentation method using StyleGAN2-ADA to enhance algal image instance segmentation. StyleGAN2-ADA generates artificial single-algal images to address data scarcity and imbalance. We train a Cascaded Mask R-CNN with Swin Transformer on a combined data set of real and artificial multigenera algal images and evaluate performance using the COCO mAP metric. The approach improves bounding box detection performance by 17.9% on all genera and 32.1% on rare genera compared with the baseline model. Additionally, 50% more artificial data yield significant enhancements without excessive artificial data use. The GAN-based augmentation technique shows a performance improvement in both Swin-Tiny and ResNet-50 backbone models, suggesting adaptability for various machine learning models. The increased mAP leads to the accurate identification of harmful algae genera, allowing for better prevention and mitigation. This method offers a superior data augmentation solution for accurate algal instance segmentation and can benefit applications challenged by imbalanced and scarce data.
This work uses GAN-based data augmentation and machine learning to improve freshwater algal image detection, which could aid in identifying harmful algal blooms and water quality monitoring.
Freshwater Microscopic Algae Detection Based on Deep Neural Network with GAN-Based Augmentation for Imbalanced Algal Data
Fung, Benjamin S. B. (Autor:in) / Chan, Wang Hin (Autor:in) / Lo, Irene M. C. (Autor:in) / Tsang, Danny H. K. (Autor:in)
ACS ES&T Water ; 4 ; 982-990
08.03.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Forest Fire Prediction with Imbalanced Data Using a Deep Neural Network Method
| DOAJ | 2022
Urban Flood Prediction Using Deep Neural Network with Data Augmentation
| DOAJ | 2020
| Elsevier | 2023
| British Library Online Contents | 2019