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

Maintaining the quality of water is essential for the health and productivity of aquatic organisms, including fish in aquaculture ponds. However, water contamination can severely impact fish health and survival, making it necessary to develop monitoring systems that can detect early signs of water contamination. Initial deep learning models had limitations in capturing the temporal and spatial dependencies of time-series data, which can lead to inaccurate predictions. In this paper, we propose a smart monitoring system that uses IoT devices to collect water quality data and segment it into contaminated and non-contaminated categories based on a water toxic index (WTI), a measure of water contamination levels. To address the limitations of early deep learning models for classification of toxic and non-toxic water quality, an enhanced light-weight multi-headed gated recurrent unit (MHGRU) model that captures the spatial and temporal dependencies of water quality parameters. Our study demonstrates that the proposed model outperforms existing models, achieving an impressive accuracy of 99.7% when evaluated on real-time data. Notably, our model also excels when tested on a public dataset, achieving an accuracy of 99.12%. In comparison, best performed existing ANN models achieve accuracies of 99.52% and 98.71% on the respective datasets.

An IoT framework for quality analysis of aquatic water data using time-series convolutional neural network.

Water quality monitoring and analysis in fish farms are of paramount importance for the aquaculture sector; however, traditional methods can pose difficulties. To address this challenge, this study proposes an IoT-based deep learning model using a time-series convolution neural network (TMS-CNN) for monitoring and analyzing water quality in fish farms. The proposed TMS-CNN model can handle spatial-temporal data effectively by considering temporal and spatial dependencies between data points, which allows it to capture patterns and trends that would not be possible with traditional models. The model calculates the water quality index (WQI) using correlation analysis and assigns class labels to the data based on the WQI. Then, the TMS-CNN model analyzed the time-series data. It produces high accuracy of 96.2% in analysis of water quality parameters for fish growth and mortality conditions. The proposed model accuracy is higher than the current best model MANN, which has only had an accuracy of 91%.