An IoT‐based water contamination analysis for aquaculture using lightweight multi‐headed GRU model

Arepalli, Peda Gopi; Naik, K. Jairam

doi:10.1007/s10661-023-12126-4

Cited by 8 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference Material and novelty covered [24] The authors present their thoughts on the potential of digital twin technology as a key component in ushering in Industry 4.0 in aquaculture and outline a pathway toward achieving this goal. [62] This mechanism directs the model's focus toward salient features associated with water contamination, while the AODEGRU architecture captures temporal patterns within the data. The experimental results underscore the effectiveness of the proposed model.…”

Section: Theory a Previous Researchmentioning

confidence: 99%

Innovative Monitoring of Water Environment in Vaname Shrimp Farming Based on Lorawan

2024

Journal of Southwest Jiaotong University

View full text Add to dashboard Cite

The sudden vaname shrimp death factors are overfeeding, disease infection, failure to mount, shrimp stress, and high rainfall, which cause potential changes in water pH that trigger anxiety in shrimp. The next factor is turbid or dirty water. Other factors include insufficient oxygen content in the water. Therefore, to overcome these issues, a sensor that explicitly handles water conditions is needed. The system built in this research still has two stages, namely real-time monitoring and automatic actuators, which are still being developed. The sensor is placed in water in a floating condition with specific materials so that it is impossible to sink. Some tested sensors include salinity, water pH, turbidity, and dissolved oxygen sensors. Its wireless telecommunication system uses LoRa with frequencies of 920-923

show abstract

Section: Theory a Previous Researchmentioning

confidence: 99%

Innovative Monitoring of Water Environment in Vaname Shrimp Farming Based on Lorawan

2024

Journal of Southwest Jiaotong University

View full text Add to dashboard Cite

show abstract

“…The intricate balance within aquatic ecosystems, crucial for the well-being and survival of these species, hinges significantly on water quality [1]. Accurate assessment of water quality is imperative as it provides insights into the suitability of a habitat for aquatic life [2][3][4][5][6]. The multifaceted nature of water quality, stemming from the delicate interplay of environmental factors, underscores the complexity inherent in its classification.…”

Section: Introductionmentioning

confidence: 99%

An IoT Based Water Quality Classification Framework for Aqua-Ponds through Water and Environmental Variables using CGTFN Model

AREPALLI,

Amgoth

2024

Preprint

Self Cite

View full text Add to dashboard Cite

Maintaining water quality in aquatic habitats is critical for the health of aquatic species, particularly for fish. This study pioneers an innovative method to water quality classification, leveraging IoT-driven data acquisition and meticulous data labelling with the Aqua-Enviro Index (AEI) by considering the fish habitats. Existing mechanisms fail to capture complex temporal dynamics and depend largely on large amounts of labelled data, exposing fundamental limits. In response, we describe the Deep learning based Convolutional Gated Recurrent Unit Tempo Fusion Network (CGTFN) model, which represents a considerable development in the evaluation of water quality. The model addresses these restrictions by seamlessly merging Convolutional Neural Networks (CNNs) for spatial pattern recognition and Gated Recurrent Units (GRUs) for temporal interactions. The Tempo Fusion mechanism combines spatial, temporal, and contextual data harmoniously, allowing for more sophisticated classifications by recognizing subtle interdependencies among environmental elements. The pioneering CGTFN model outperforms previous models, achieving 99.71% and 99.81% accuracy on both public-env and real-time-env datasets, respectively, exceeding established models at 98.2%. These remarkable findings highlight CGTFN's disruptive potential in water quality evaluation, bridging the gap between technology and environmental management, with ramifications ranging from aquaculture to resource sustainability.

show abstract

“…Sensors are also categorized as alternative traditional methods. But, with the help of sensors can be deliberated expensive to test each WQ sample and frequently indicate lower accuracy [9]. One more solution for monitoring WQ can be predictable modeling using machine learning (ML) and deep learning (DL) models.…”

Section: Introductionmentioning

confidence: 99%

Water Quality Index Prediction and Classification using Hyperparameter Tuned Deep Learning Approach

2024

Global NEST Journal

View full text Add to dashboard Cite

<p>Water quality (WQ) is hugely important for animals, humans, plants, industries, and the environment. In the past few years, the WQ has been compressed by pollution and contamination. Usually, WQ is assessed utilizing costly laboratory and arithmetical processes, making real observation ineffective. Whereas, the poor WQ wants a more real and cost-effective resolution. Water pollution is a critical problem, so, it is vital to generate a method that estimates WQ in order to manage water pollution and notify users on the occasion of the recognition of poor water superiority. For effectual WQ management, it is vital to precisely estimate the WQ type. We use the advantage of machine learning (ML) models to build a model proficient in forecasting the WQ index and class. Therefore, this paper presents an automated Water Quality Index Prediction and Classification using Hyperparameter Tuned Deep Learning (WQIPC-HTDL) Approach. The purpose of the WQIPC-HTDL technique is to estimate WQI and classify the WQ into multiple levels. In the WQIPC-HTDL technique, the linear scaling normalization (LSN) approach is used. Besides, the long short-term memory (LSTM) technique is employed for the prediction and classification process. To enhance the efficacy of the LSTM model, the grasshopper optimizer algorithm (GOA) can be used. To point out the enhanced performance of the WQIPC-HTDL technique, a detailed simulation analysis was made. The obtained values inferred the rule of the WQIPC-HTDL technique when equated to other models.</p>

show abstract

An IoT‐based water contamination analysis for aquaculture using lightweight multi‐headed GRU model

Cited by 8 publications

References 38 publications

Innovative Monitoring of Water Environment in Vaname Shrimp Farming Based on Lorawan

Innovative Monitoring of Water Environment in Vaname Shrimp Farming Based on Lorawan

An IoT Based Water Quality Classification Framework for Aqua-Ponds through Water and Environmental Variables using CGTFN Model

Water Quality Index Prediction and Classification using Hyperparameter Tuned Deep Learning Approach

Contact Info

Product

Resources

About