VannameiVision: An Optimized Probabilistic Deep Learning for Susceptible Shrimp Larvae Detection
Issued Date
2023-01-01
Resource Type
Scopus ID
2-s2.0-85178165590
Journal Title
2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023
Rights Holder(s)
SCOPUS
Bibliographic Citation
2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023 (2023)
Suggested Citation
Tiyapunjanit P., Siammai T., Klaythong K., Jantrachotechatchawan C., Duangrattanalert K. VannameiVision: An Optimized Probabilistic Deep Learning for Susceptible Shrimp Larvae Detection. 2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023 (2023). doi:10.1109/eSmarTA59349.2023.10293495 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/91348
Title
VannameiVision: An Optimized Probabilistic Deep Learning for Susceptible Shrimp Larvae Detection
Other Contributor(s)
Abstract
Detecting susceptible shrimp larvae presents a significant challenge that requires dedicated effort, skill, and expertise. In this study, we propose an advanced approach that combines probabilistic deep learning with transfer learning and deep metric learning using a triplet loss function. To obtain an optimal solution, we employed 5-fold cross-validation to conduct a rigorous comparison among different variations of the model. Our results showed that integrating transfer learning and deep metric learning provides significant improvements to our system. Through our experiment, we observed that DenseNet121 appeared to become more effective when incorporated with the proposed techniques, achieving an accuracy of 92%, sensitivity of 87%, and specificity of 97%. Importantly, after tuning, the model gained an exciting ability to generalize to previously unseen datasets, surpassing an accuracy of 90% on different background settings (i.e., varying colors and textures). These findings have undoubtedly demonstrated the efficacy of our methodology in accurately and robustly identifying susceptible shrimp larvae. Source code and sample data for our study can be downloaded directly from our GitHub repository (https://github.com/patipond-tiy/vannameivision).