Dragonfly Political Optimizer Algorithm-Based Rider Deep Long Short-Term Memory for Soil Moisture and Heat Level Prediction in IoT

Abstract Different computerized technologies to monitor plant health in the Internet of Things (IoT) paradigm gained various benefits but generating accurate result in the soil moisture and heat level prediction is the potential challenge. Thus, an effective Dragonfly Political Optimizer Algorithm-based Rider Deep Long Short-Term Memory (DPOA-based Rider Deep LSTM) is developed for generating better prediction results of soil moisture and heat level. The proposed DPOA is the integration of the Dragonfly Algorithm and Political Optimizer. The proposed system maintains the Base Station (BS) that collects the information from the IoT nodes through Cluster Head. At BS, the data transformation is carried out using Yeo Johnson transformation. The transformed result is transferred to feature selection, which is evaluated by holoentropy, and finally, the prediction process of soil moisture and the heat level is done at BS using the proposed method. The proposed method achieved higher performance in terms of Packet Delivery Ratio, energy, accuracy, sensitivity and specificity with the values of 0.7156, 0.7123, 0.9474, 0.9523 and 0.9254, respectively.