A deep neural networks based model for uninterrupted marine environment monitoring

In the last few decades, there is a massive increase in population and hence increase in societal development. Concerning environmental change as a result of development in society and the economy, the marine environment plays a significant role in global climatic change. Hence recent Information and Communication Technologists are attracted towards monitoring the marine environment. Various marine monitoring systems are developed in the past few years. Out of these, the Internet of Things (IoT) plays a significant role. In IoT based Marine monitoring systems, various sensors are deployed in the real-time environment for monitoring and measuring various physical parameters. These sensors work on battery power. When the battery drains, there is a possibility of interruption in the monitoring activity until the battery is replaced. This research paper focuses on developing a prediction model for predicting the life of battery well ahead and alert the technologists so that the monitoring will not be interrupted using Principal Component Analysis (PCA) and Deep Neural Network (DNN). The model is evaluated using raw data collected from a real-time marine monitoring system which is deployed at Chicago Park District along the beach water. The results obtained are compared and analyzed with the widely used state of art techniques namely Linear Regression and XGBoost. The results show that the proposed PCA based DNN Prediction Model outperforms the other techniques by an increase of 12% in accuracy and 30% in reduction of time complexity.