RETRACTED ARTICLE: Monitoring the quality of water in shrimp ponds and forecasting of dissolved oxygen using Fuzzy C means clustering based radial basis function neural networks

Rozario, A. P. Roger; Devarajan, N.

doi:10.1007/s12652-020-01900-8

Cited by 30 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Monitoring is important as a successful key in shrimp culture activities (Xiao et al, 2017;Mohanty et al, 2018;Zainuddin et al, 2019;Rozario & Devarajan, 2021). Monitoring contains shrimp growth, shrimp health, water quality (Encinas et al, 2017;Zainuddin et al, 2019), and pond sediments based on the redox potential, total P, total S, total Mn, and other mineral contents (Wiyoto et al, 2016;Widigdo et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

“…Monitoring can be performed daily or periodically at a certain time following the shrimp culture condition (Ariadi et al, 2019;Silva et al, 2021). The water quality parameter monitoring is performed daily, such as dissolved oxygen (Mohanty et al, 2018;Ariadi et al, 2019;Rozario & Devarajan, 2021), pH (Ariadi et al, 2019;Zainuddin et al, 2019), temperature (Mohanty et al, 2018) (Zainuddin et al, 2019), and salinity (Mohanty et al, 2018;Ariadi et al, 2019); while parameters that can be measured weekly contain total ammonia-nitrogen (TAN) (Ariadi et al, 2019), nitrite (Ariadi et al, 2019;Silva et al, 2021), and parameters observed among 7-10 days contain shrimp growth and health conditions (Tong et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of water and sediment quality in Pacific white leg shrimp Litopenaeus vannamei culture with different sediment redox potential

Wiyoto¹,

Hendriana

Siskandar

et al. 2022

Jurnal Akuakultur Indonesia

View full text Add to dashboard Cite

ABSTRAK Pengamatan parameter kualitas air, tanah, kesehatan dan pertumbuhan merupakan hal yang penting untuk dilakukan dalam budidaya udang vaname. Keterkaitan antar parameter tersebut perlu untuk diketahui dan dianalisis lebih lanjut. Penelitian ini bertujuan untuk melihat keterkaitan antara berbagai parameter kualitas air, kualitas tanah, koefisien teknis budidaya dan parameter kesehatan udang dalam kegiatan budidaya udang dengan nilai sedimen redok potensial yang berbeda. Penelitian ini dilakukan dengan perbedaan nilai sedimen redok potensial yaitu 69,33 ± 14,5 mV, 151,00 ± 8,89 mV, dan 210,00 ± 17,32 mV dengan empat ulangan. Udang sebanyak 25 ekor dengan bobot rata rata 1,37 ± 0,04 g dan padat tebar 144 ekor/m2 digunakan dalam penelitian selama 30 hari. Selama penelitian parameter yang diamati meliputi parameter kualitas air, kesehatan dan pertumbuhan. Parameter kualitas air tidak menunjukkan perbedaaan nyata antar perlakuan kecuali nilai pH dan oksigen terlarut. Pada nilai redok potensial yang rendah nilai pH air cenderung lebih tinggi sedangkan pada nilai redok potensial yang lebih tinggi nilai oksigen terlarut lebih tinggi. Parameter kualtias air yang menunjukkan keterkaitan berdasarkan analisis komponen utama (PCA) dan klaster adalah konduktivitas dan TDS sedangkan parameter kualitas tanah yang saling berkaitan adalah total P, total Fe, total Mn dan total S. Adapun parameter pertumbuhan dan kesehatan udang tidak memenuhi syarat untuk diuji lanjut dengan PCA. Kata kunci: kualitas air, PCA, redok potensial, sedimen, udang putih.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analysis of water and sediment quality in Pacific white leg shrimp Litopenaeus vannamei culture with different sediment redox potential

Wiyoto¹,

Hendriana

Siskandar

et al. 2022

Jurnal Akuakultur Indonesia

View full text Add to dashboard Cite

show abstract

“…proposed a new clustering-based softplus class-specific extreme learning machine to predict DO changes in time series. Rozario and Devarajan (2021) used a fuzzy C-means clustering method to construct a radial basis function neural network to predict changes in DO. Wu et al (2018) presented a new model for DO content prediction based on a sliding window, particle swarm optimization, and error backpropagation.…”

Section: Introductionmentioning

confidence: 99%

Utilizing a Two-Dimensional Data-Driven Convolutional Neural Network for Long-Term Prediction of Dissolved Oxygen Content

Zhang²

2022

Front. Environ. Sci.

View full text Add to dashboard Cite

It is significant to establish a precise dissolved oxygen (DO) model to obtain clear knowledge ablout the prospective changing conditions of the aquatic environment of marine ranches and to ensure the healthy growth of fisheries. However Do in marine ranches is affected by many factors. DO trends have complex nonlinear characteristics. Therefore, the accurate prediction of DO is challenging. On this basis, a two-dimensional data-driven convolutional neural network model (2DD-CNN) is proposed. In order to reduce the influence of missing values on experimental results, a novel sequence score matching-filling (SSMF) algorithm is first presented based on similar historical series matching to provide missing values. This paper extends the DO expression dimension and constructs a method that can convert a DO sequence into two-dimensional images and is also convenient for the 2D convolution kernel to further extract various pieces of information. In addition, a self-attention mechanism is applied to construct a CNN to capture the interdependent features of time series. Finally, DO samples from multiple marine ranches are validated and compared with those predicted by other models. The experimental results show that the proposed model is a suitable and effective method for predicting DO in multiple marine ranches. The MSE MAE, RMSE and MAPE of the 2DD-CNN prediction results are reduced by 51.63, 30.06, 32.53, and 30.75% on average, respectively, compared with those of other models, and the R2 is 2.68% higher on average than those of the other models. It is clear that the proposed 2DD-CNN model achieves a high forecast accuracy and exhibits good generalizability.

show abstract

“…Those features are selected from diverse automated monitoring systems and weather stations including more than 10 different types of measurements. Currently, neural network-type models, such as LTSM and deep belief networks [ 13 ] are considered an appropriate solution to solve the forecasting problem in long-term horizons [ 14 , 15 ]. Also, forecasting of other water-quality related variables has been studied, not as much as dissolved oxygen though.…”

Section: Introductionmentioning

confidence: 99%

Machine learning for manually-measured water quality prediction in fish farming

et al. 2021

View full text Add to dashboard Cite

Monitoring variables such as dissolved oxygen, pH, and pond temperature is a key aspect of high-quality fish farming. Machine learning (ML) techniques have been proposed to model the dynamics of such variables to improve the fish farmer’s decision-making. Most of the research on ML in aquaculture has focused on scenarios where devices for real-time data acquisition, storage, and remote monitoring are available, making it easy to develop accurate ML techniques. However, fish farmers do not necessarily have access to such devices. Many of them prefer to use equipment to manually measure these variables limiting the amount of available data to process. In this work, we study the use of random forests, multivariate linear regression, and artificial neural networks in scenarios with limited amount of measurements to analyze data from water-quality variables that are commonly measured in fish farming. We propose a methodology to build models in two scenarios: i) estimation of unobserved variables based on the observed ones, and ii) forecasting when a low amount of data is available for training. We show that random forests can be used to forecast dissolved oxygen, pond temperature, pH, ammonia, and ammonium when the water pond variables are measured only twice per day. Moreover, we showed that these prediction models can be implemented on a mobile-based information system and run in an average smartphone that fish farmers can afford.

show abstract

RETRACTED ARTICLE: Monitoring the quality of water in shrimp ponds and forecasting of dissolved oxygen using Fuzzy C means clustering based radial basis function neural networks

Cited by 30 publications

References 17 publications

Analysis of water and sediment quality in Pacific white leg shrimp Litopenaeus vannamei culture with different sediment redox potential

Analysis of water and sediment quality in Pacific white leg shrimp Litopenaeus vannamei culture with different sediment redox potential

Utilizing a Two-Dimensional Data-Driven Convolutional Neural Network for Long-Term Prediction of Dissolved Oxygen Content

Machine learning for manually-measured water quality prediction in fish farming

Contact Info

Product

Resources

About