Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Tengtrairat, Naruephorn; Woo, Wai Lok; Parathai, Phetcharat; Rinchumphu, Damrongsak; Chaichana, Chatchawan

doi:10.3390/s22145161

Cited by 20 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep-learning-based regression has the advantage of being able to model the situation, even in reality situations where modeling is difficult with a data-driven approach. 25 be used as deep-learning-based regression to weigh fish in turbid water reflecting reality situations. However, modeling these reality situations requires redefining optimization variables.…”

Section: Problem Definition (Trained Dnn Objective Optimization)mentioning

confidence: 99%

Deriving Controllable Local optimal Solutions through an Environment Parameter Fixed Algorithm (EPFA-CLS)

Jang

Kim

2023

Preprint

View full text Add to dashboard Cite

In many engineering problems, an optimal solution must be derived by considering reality situations that reflect actual measured data. In the optimization problem, the objective function is modeled through a formula. Such modeling is difficult in reality situations that are affected by multiple environments, such as temperature and humidity. Therefore, this paper models the objective function as a data-driven approach under deep-learning-based nonlinear regression analysis, and we then propose the constraint optimization problem in a specific environment (trained DNN objective optimization). We define the solution to this problem as a controllable local-optimal solution (CLS) and propose an environment parameter fixed algorithm (EPFA) to derive the CLS. This changes constraint optimization into an unconstrained optimization problem by pinning down environment parameters to reflect constraints in a particular environment. After that, the proposed approach is combined with conventional Gradient Descent and algorithms such as Adagrad to derive the CLS. The situation is explained through an example of an optimal course model created for use in this study. In addition, we verify that the CLS can be derived through experiment by using an optimal course dataset and a Boston house price dataset.

show abstract

Section: Problem Definition (Trained Dnn Objective Optimization)mentioning

confidence: 99%

Deriving Controllable Local optimal Solutions through an Environment Parameter Fixed Algorithm (EPFA-CLS)

Jang

Kim

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the context of aquaculture, the assessment of aquatic animals' weight holds paramount importance [6]. This process entails strategic planning of production and the management of factors such as size selection for breeding and evaluation of feeding practices [7,8].…”

Section: Introductionmentioning

confidence: 99%

“…Rančić et al [22] employed CNNs for the detection and counting of wild animals. In the context of fish weight estimation, CNNs have been utilized in studies focused on species such as Asian seabass [15] and tilapia [6].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Convolutional Neural Networks, XGBoost, and Hybrid CNN-XGBoost for Precise Red Tilapia (Oreochromis niloticus Linn.) Weight Estimation in River Cage Culture with Aerial Imagery

Taparhudee,

Jongjaraunsuk,

Nimitkul

et al. 2024

AgriEngineering

View full text Add to dashboard Cite

Accurate feeding management in aquaculture relies on assessing the average weight of aquatic animals during their growth stages. The traditional method involves using a labor-intensive approach and may impact the well-being of fish. The current research focuses on a unique way of estimating red tilapia’s weight in cage culture via a river, which employs unmanned aerial vehicle (UAV) and deep learning techniques. The described approach includes taking pictures by means of a UAV and then applying deep learning and machine learning algorithms to them, such as convolutional neural networks (CNNs), extreme gradient boosting (XGBoost), and a Hybrid CNN-XGBoost model. The results showed that the CNN model achieved its accuracy peak after 60 epochs, showing accuracy, precision, recall, and F1 score values of 0.748 ± 0.019, 0.750 ± 0.019, 0.740 ± 0.014, and 0.740 ± 0.019, respectively. The XGBoost reached its accuracy peak with 45 n_estimators, recording values of approximately 0.560 ± 0.000 for accuracy and 0.550 ± 0.000 for precision, recall, and F1. Regarding the Hybrid CNN-XGBoost model, it demonstrated its prediction accuracy using both 45 epochs and n_estimators. The accuracy value was around 0.760 ± 0.019, precision was 0.762 ± 0.019, recall was 0.754 ± 0.019, and F1 was 0.752 ± 0.019. The Hybrid CNN-XGBoost model demonstrated the highest accuracy compared to using standalone CNN and XGBoost models and could reduce the time required for weight estimation by around 11.81% compared to using the standalone CNN. Although the testing results may be lower than those from previous laboratory studies, this discrepancy is attributed to the real-world testing conditions in aquaculture settings, which involve uncontrollable factors. To enhance accuracy, we recommend increasing the sample size of images and extending the data collection period to cover one year. This approach allows for a comprehensive understanding of the seasonal effects on evaluation outcomes.

show abstract

“…They use stacked autoencoders (SAE) to extract the deep spectral features and then pass them to a deep learning model to estimate the firmness and pH. Other than using a deep learning model to estimate the value, another work used regression models to estimate the weight of Tilapia fish in turbid water environments for efficiently feeding and harvesting fish [11]. They use a mask recurrent-convolutional neural network (R-CNN) model to detect and extract the fish image and then pass it to a regression model for weight estimation.…”

Section: Introductionmentioning

confidence: 99%

Muscle Estimation using Stacked-LSTM Multivariate Regression Model

Siow,

Wang,

Chuquirachi

et al. 2023

Preprint

View full text Add to dashboard Cite

Muscle estimation is required to estimate the muscle activity of older adults, and a real-time process can influence the effectiveness of monitoring applications. However, using simulation tools to assess muscle activity consumes much computation energy, which is ineffective for long term monitoring. In this paper, we proposed a novel method named Stacked-LSTM (S-LSTM) multivariate regression model for muscle estimation. S-LSTM contributes to resolving the local information lost in the sequence to-sequence architecture. To validate the proposed model, we recorded human walking on a treadmill using multiple Kinect Azure to form the 3D skeleton joints as the input to our model to predict muscle activity. These skeleton data are passed to Human Musculoskeletal Simulation based on Mujoco Engine to generate the desired outputs for training and testing. Through the experiment, S-LSTM outperforms other multivariate regression models. We measured computation time, and our proposed model runs 0.25 milliseconds faster than the MuJoCo simulation tool.

show abstract

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Cited by 20 publications

References 44 publications

Deriving Controllable Local optimal Solutions through an Environment Parameter Fixed Algorithm (EPFA-CLS)

Deriving Controllable Local optimal Solutions through an Environment Parameter Fixed Algorithm (EPFA-CLS)

Optimizing Convolutional Neural Networks, XGBoost, and Hybrid CNN-XGBoost for Precise Red Tilapia (Oreochromis niloticus Linn.) Weight Estimation in River Cage Culture with Aerial Imagery

Muscle Estimation using Stacked-LSTM Multivariate Regression Model

Contact Info

Product

Resources

About