Prediction of Elephant Movement Using Intellectual Virtual Fencing Model

Abstract

The capability to navigate and orientate is crucially a significant factor to determine the survival of all migratory animals like elephants. The sustainability of animals is constrained with a limited amount of techniques available for analysis of complex animals’ behavioral responses. Various approaches are used to track animals’ movement like elephants crossing the railway track, roads have to be varied based on the degree of accuracy that is needed essentially. However, the existing approaches fail to trigger an alert in some cases. To overcome these limitations, a novel Intellectual Inertial Measurement Unit (IIMU) is proposed where the data are acquired from the aerial elephant dataset with a set of training and testing image samples. Data collected with these dataset are analyzed for triggering Virtual Fencing (VF) and to alert animals to avoid danger. This work attempts to validate that this IIMU installed with animals’ bodies can be used to evaluate patterns related to the animal’s movement. The collected data are provided for filtering using Levenberg Marquardt Algorithm to reduce the noise over the data and to enhance the prediction accuracy. The pattern set undergoes training with Artificial Neural Network (ANN) and optimized with Elephant Optimization to evaluate the prediction accuracy. Based on the evaluation, the model shows better prediction accuracy in case of emergency and alert is triggered to save the life of elephants. Here, some performance metrics like accuracy, precision, F-measure, recall, ROC are evaluated to show the significance of EPO-ANN model. The model outperforms the existing standard SVM model and gives higher prediction accuracy.