Prediction and Analysis on COVID-19 Using Positive and Negative Association Rule Mining

2021 ◽  
pp. 1-11
Author(s):  
Sujit Chakraborty ◽  
Sudarsan Biswas ◽  
Sourav Debnath
Keyword(s):  
Association Rule ◽  
Association Rule Mining ◽  
Negative Association ◽  
Rule Mining

Extracting of Positive and Negative Association Rules

2018 ◽  
Vol 6 (8) ◽  
pp. 421
Author(s):  
D. Gandhimathi ◽  
N. Anbazhagan
Keyword(s):  
Association Rules ◽  
Association Rule ◽  
Association Rule Mining ◽  
Positive Association ◽  
Current Data ◽  
Negative Association ◽  
Rule Mining ◽  
Web Usage ◽  
Log Structure ◽  
Negative Association Rules

Association rules analysis is a basic technique to expose how items/patterns are associated to each other. There are two common ways to measure association such as Support and Confidence. Several methods have been proposed in the literature to diminish the number of extracted association rules. Association Rule Mining is one of the greatest current data mining techniques designed to group objects together from huge databases aiming to take out the motivating correlation and relation with massive quantity of data. Association rule mining is used to discover the associated patterns from datasets. In this paper, we propose association rules from new methods on web usage mining. Generally, web usage log structure has several records so we have to overcome those unwanted records from large dataset. First of all the pre-processed data from the NASA dataset is clustered by the popular K-Means algorithm. Subsequently, the matrix calculation is progressed on that data. Further, the associations are performed on filtered data and get rid of the final associated page results. Positive and negative association rules are gathered by using new algorithm with Annul Object (𝒜𝒪). Wherever the object “𝒜𝒪” is presented those rules are known as negative association rule.  Otherwise, the rules are positive association rules.

An Algorithm for Mining Multidimensional Positive and Negative Association Rules

2010 ◽  
Vol 171-172 ◽  
pp. 445-449 ◽  
Author(s):  
He Jiang ◽  
Ze Bai ◽  
Guo Ling Liu ◽  
Xiu Mei Luan
Keyword(s):  
Association Rules ◽  
Association Rule ◽  
Association Rule Mining ◽  
Positive Association ◽  
Negative Association ◽  
Multidimensional Data ◽  
Rule Mining ◽  
Multidimensional Datasets ◽  
Single Positive ◽  
Negative Association Rules

Research on negative association rule in multidimensional data mining is few. In this paper, an algorithm MPNAR is put forward to mine positive and negative association rules in multidimensional data. With the help of the basis of the minimum support and minimum confidence, this algorithm divided the multidimensional datasets into infrequent itemsets and frequent itemsets. The negative association rules could be mined from infrequent itemsets. Relative to the single positive association rule mining, the new additional negative association rules need not repeatedly read database because two types of association rules were simultaneously mined. Experiments show that the algorithm method is effective and valuable.

INTEGRATING ACTION-BASED DEFECT PREDICTION TO PROVIDE RECOMMENDATIONS FOR DEFECT ACTION CORRECTION

2013 ◽  
Vol 23 (02) ◽  
pp. 147-172
Author(s):  
CHING-PAO CHANG
Keyword(s):  
Prediction Model ◽  
Association Rule ◽  
Association Rule Mining ◽  
Software Process ◽  
Negative Association ◽  
Defect Prediction ◽  
Rule Mining ◽  
Mining Technique ◽  
Software Defect ◽  
Recommendations For Action

Reducing software defects is an essential activity for Software Process Improvement. The Action-Based Defect Prediction (ABDP) approach fragments the software process into actions, and builds software defect prediction models using data collected from the execution of actions and reported defects. Though the ABDP approach can be applied to predict possible defects in subsequent actions, the efficiency of corrections is dependent on the skill and knowledge of the stakeholders. To address this problem, this study proposes the Action Correction Recommendation (ACR) model to provide recommendations for action correction, using the Negative Association Rule mining technique. In addition to applying the association rule mining technique to build a High Defect Prediction Model (HDPM) to identify high defect action, the ACR builds a Low Defect Prediction Model (LDPM). For a submitted action, each HDPM rule used to predict the action as a high defect action and the LDPM rules are analyzed using negative association rule mining to spot the rule items with different characteristics in HDPM and LDPM rules. This information not only identifies the attributes required for corrections, but also provides a range (or a value) to facilitate the high defect action corrections. This study applies the ACR approach to a business software project to validate the efficiency of the proposed approach. The results show that the recommendations obtained can be applied to decrease software defect removal efforts.

Sign in / Sign up

Export Citation Format

Share Document