Analysis of green manure decomposition parameters in northeast Brazil using association rule networks

Abstract

A B S T R A C TThe food sector is one of the most critical areas of the economy, and consumers are seeking safer, more readily available, more affordable, and better quality food. Therefore, organic agriculture has become a possible approach for optimizing the characteristics of processed foods. Vegetables have essential uses as green manure, but the greatest difficulty encountered when using these species is related to the time required for their residues to decompose. Computational intelligence and data mining techniques are used widely in agricultural studies and for process improvement purposes. Association rules are used as data mining techniques to identify patterns in large databases, where the patterns identified are analyzed and transformed into a graph to facilitate further analyses. In this study, we employed the patterns identified by association rule networks (ARNs) to determine directly the key parameters related to the half-life decomposition times of legumes used as green manure in northeast Brazil. We validated this method by comparing the results obtained by the ARNs and a decision tree. The proposed approach obtained promising results, thereby demonstrating its capacity to describe a set of objective items and facilitate the development of more integrated hypotheses. Thus, it was possible to optimize the discovery of the key parameters related to green fertilizers in order to identify the best species according to its culture requirements and to enhance productivity.

Filtered-ARN: Asymmetric objective measures applied to filter Association Rules Networks

“…Filtered -ARN is very successful in presenting such cases, allowing the user to see the items that produce variations in the Figure 10: ARN with "HalfLife=6" as target item. Adapted from [34]. target item.…”

“…To validate the benefits of using the Filtered -ARN in real data some experiments were carried out on the Organic Manure dataset collected from EMBRAPA Meio Norte. This dataset has already been used by [34] in the construction of ARNs for information exploitation. The extracted knowledge was analyzed and validated by specialists.The extracted knowledge was analyzed and validated by specialists.…”

“…Since the dataset has six classes related to the legume decomposition half-life, 11 attributes, and 28 instances, the characteristics being formed by categories of values referring to the field research performed by EMBRAPA Meio Norte, we set the minimum support to 0.3, and the minimum confidence to 0.5 for benchmarking with the studies of [34]. Besides, the size of the rule was specified in two, considering one item in the LHS and one item in the RHS.…”

Seleção Objetiva De Suporte E Confiança Mínimos Em Mineração De Regras De Associação

“…We collected the data from the research of Calçada, Rezende and Teodoro (2019). The authors conducted an agricultural experiment that determined the factors connected to the half-life of various species of organic fertilizers used in Northeast Brazil.…”

Spatial Relationship of Drug Smuggling in Northern Thailand Using GIS-based Knowledge Discovery

“…Clustering means could be also applied in environmental study, as seen in the study of Ge et al (2019), who used clustering in an unsupervised learning technique to extract soil structure information. Calçada et al (2019) studied the relationship of parameters in fertilizer using the association rule to discover the appropriate parameters of decomposition. Xu et al (2018) employed the association rule to investigate the relationship for factors affecting traffic congestion.…”