Fish Biomass Estimation Under Occluded Features: A Framework Combining Imputation and Regression
Abstract
In biomass estimation based on size-related features, regression models are commonly used to predict fish mass. However, in real-world scenarios, fish are often partially occluded by others, resulting in missing or corrupted features. To address this issue, we propose a robust framework that integrates feature imputation with regression. Missing features are first reconstructed through imputation, followed by regression for biomass prediction. We evaluated various imputation and regression methods and found that the autoencoder achieved the best performance in imputation. Among regression models, SVR, Extra Trees, and MLP performed best in their respective categories. These three models, combined with the autoencoder, were selected to construct the final framework. Experimental results demonstrate that the proposed framework significantly improves performance. For instance, the RMSE of SVR, Extra Trees, and MLP decreased from 21.10 g, 2.49 g, and 18.40 g to 6.53 g, 1.95 g, and 5.09 g, respectively.
BibTeX
@article{zhang2024,
title = {Fish Biomass Estimation Under Occluded Features: A Framework Combining Imputation and Regression},
author = {Zhang, Xu and Yang, Wentao and Liu, Haoran and Fang, Yuan and Chen, Chao and Yang, Xian},
journal = {Journal of Marine Science and Engineering},
volume = {10},
number = {7},
pages = {306},
year = {2024},
publisher = {MDPI},
abstract = {In biomass estimation based on size-related features, regression models are commonly used to predict fish mass. However, in real-world scenarios, fish are often partially occluded by others, resulting in missing or corrupted features. To address this issue, we propose a robust framework that integrates feature imputation with regression. Missing features are first reconstructed through imputation, followed by regression for biomass prediction. We evaluated various imputation and regression methods and found that the autoencoder achieved the best performance in imputation. Among regression models, SVR, Extra Trees, and MLP performed best in their respective categories. These three models, combined with the autoencoder, were selected to construct the final framework. Experimental results demonstrate that the proposed framework significantly improves performance. For instance, the RMSE of SVR, Extra Trees, and MLP decreased from 21.10 g, 2.49 g, and 18.40 g to 6.53 g, 1.95 g, and 5.09 g, respectively.},
}