Deep residual network-based data streaming approach for soil type application under IoT-based big data environment

The agriculture acquires more portions in Gross Domestic Product in the developed countries. However, analysis of the soil properties is a costly and time-consuming process. In this research, a new technique for classifying soil types on an IoT platform is developed. This method simulates the Internet of Things in order to transmit data. The Multi-verse Firefly algorithm (MVFA), which has been proposed, is used for clustering and routing. I n this case, the Multi-Verse Optimizer and Firefly algorithm are used to generate the proposed MVFA. At base station, the soil type classification is carried out utilizing the soil data. A selection of feature is done using an entropy factor and the type of soil is classified using Deep Residual Network considering spark architecture. The proposed MVFA trains the Deep Residual Network. The data stream is effectively handled with concept drift detection, and retraining of deep residual network is carried out utilizing Mutual information and Loss function-based thresholding. The proposed MVFA-enabled Deep Residual Network bestowed enhanced performance with an accuracy of 96%, sensitivity of 94.1%, specificity of 95.4%, delay of 90.6% and throughput of 0.0084.