An Enhanced Clustering Algorithm for Agricultural Data Using FAO Heuristics

In the wake of recent advancements in digital technology in various fields including agriculture, a large set of data is produced that proves to be ineffectual until it is analyzed systematically and profoundly to augment decision-making process. The data are used through different devices, and different processing techniques are applied on it to derive meaningful results with effective decision-making. The data can be cut short, tailored or manipulated in several ways to mould the same which can give visible interpretations to the people. At the same time, complex problems can also be solved. Further, through the data cleaning and the integration processes, a large cluster of data can be made simple and easy to use for calculations. Big data pre-processing approaches are applied to improve the visibility of big data to DSS to get a more effective analytics view in order to get useful insight. The requirements of compatible data management have considerably increased in the field of agriculture in India over the years. In the backdrop of these requirements, the present paper provides a framework for the detection of duplicate data using certain measures that are trainable and manageable. Moreover, the framework has been examined a number of times based on the Precision, Recall, and F measure techniques in this paper.