Publication

Abstract : Agriculture Specific Land or crop monitoring-based Networking technology has played an essential role in the current farming system. Because Farmers can manage their activity even more efficiently, work and water management in irrigation systems make it possible to make decisions even when farmers are not present. The Internet of Things (IoT) monitors real-time data analysis collected through sensors and devices from each agricultural crop. The patterns of Wireless Sensor Networks (WSN), in which nodes are separated to separate data from the different crops. Sequential learning is a supervised technique using a parameter with drawbacks such as uncalculating error, Time delay, and low sensitivity data from getting sensors. To overcome these drawbacks, intelligent irrigation systems are developed using the Adaptive Radial Deep Neural Network (ARDNN) algorithm and the Internet of Things (IoT). Each sensor remains analyzed from root depth and soil water level based on the first step. Developers of the Arduino Controller have discussed utilizing IOT technology to help farmers find important environmental issues including temperature, humidity, soil moisture, and water level. The Arduino Controller analyzes different sensor setups and signal from the sensor and the Arduino controller are used to drive a water pump, which opens and closes the flow in response to the signal. Water is given to the plant's roots by a rain gun drop by drop, and when the moisture level returns to normal, the sensor recognizes it and signals the controller to cut off the water pump. Additionally, utilizing Wireless Sensor Networks (WSNs) powered by the Internet of Things (IoT), Smart Farming is used to monitor plant status. Adaptive Radial Deep Neural Network (ARDNN) algorithm aggregate classifier-based classification algorithm. The dataset will be split into training and testing data. The decision tree is constructed using the additional training dataset. To create an extra substantial prototype, the model resolve considers preparation data and then removes the weaker node from the training data before making a decision tree. The output results from gain accuracy and reliability and enables a more accurate data management system, getting proper water management and specific crops in agriculture.