Mining fuzzy association rules from low-quality data

Gacto, María José; Alcalá‐Fdez, Jesús

doi:10.1007/s00500-011-0775-3

Cited by 16 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The interest in using this structure is that we can obtain the credibility for the rules that we write from real-world data, although this time we do not focus in that advantage nor in the existence of other mechanisms for this purpose, as the one proposed in [29]. We simply highlight this fact so the reader knows why this structure and not some other one.…”

Section: Fig 2: Examples Of Conjunctors Disjunctors and Implicatorsmentioning

confidence: 92%

On modelling real-world knowledge to get answers to fuzzy and flexible searches without human intervention

Pablos-Ceruelo

Muñoz-Hernández

2014

2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

The Internet has become a place where massive amounts of information and data are being generated every day. This information is most of the times stored in a nonstructured way, but the times it is structured in databases it cannot be retrieved by using easy fuzzy queries. Being the information in the database the distance to the city center of some restaurants (and their names) by easy fuzzy queries we mean queries like "I want a restaurant close to the center". Since the computer does not have knowledge about the relation between being close to the center and the distance to the center (of a restaurant) it does not know how to answer this query by itself. We need human intervention to tell the computer from which database column it needs to retrieve data (the one with the restaurant's distance to the center), and how this nonfuzzy information is fuzzified (applying the close function to the retrieved value). Once this is done it can give an answer, just ordering the database elements by this new computed attribute. This example is very simple, but there are others not so simple, as "I want a restaurant close to the center, not very expensive and whose food type is mediterranean". Doing this for each existing attribute does not seem to be a very good idea. We present a web interface for posing fuzzy and flexible queries and a search engine capable of answering them without human intervention, just from the knowledge modelled by using the framework's syntax. We expect this work contributes to the development of more human-oriented fuzzy search engines.

show abstract

Section: Fig 2: Examples Of Conjunctors Disjunctors and Implicatorsmentioning

confidence: 92%

On modelling real-world knowledge to get answers to fuzzy and flexible searches without human intervention

Pablos-Ceruelo

Muñoz-Hernández

2014

2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

show abstract

“…The Hybrid approach using both fuzzy and apriori algorithm is an efficient method for handling time series data to find linguistic association rules [1] [11]. The time series data used here is the same Real homeprice data over years from 1999 to 2012 in order to compare the performance with respect to single approach and are shown in the Table 8: Table 8: Time series data Years Home price Years Homeprice 1999 127 2006 124 2000 129 2007 118 2001 132 2008 121 2002 130 2009 120 2003 126 2010 115 2004 132 2011 113 2005 129 2012 119 The time series data is transformed into subsequences according to the window size which is predefined.…”

Section: Experimental Analysismentioning

confidence: 99%

Analysis of Time Series Rule Extraction Techniques

Suresh¹

2013

IOSR-JCE

View full text Add to dashboard Cite

In Data mining, the sequence of data points are measured typically at successive time instants spaced at uniform time intervals are called time series. The real applications of time series are frequent pattern analysis, bioinformatics, medical treatment, meteorology, sociology and economics. Frequent patterns can be analyzed to give explanatory rules and this rule extraction can be done using many algorithms like Genetic Algorithm, Fuzzy Logic , Support Vector Machine etc. Rule induction is an area of machine learning in which rules are extracted from collective set of observations. The rules extracted may represent complete scientific model of the data, or simply represent local patterns in the data. A brief overview of some of the most common rule extraction techniques and a comparison between single and hybrid rule approaches comprise in this survey.

show abstract

“…Inexpert-57.dat 19,33 is a dataset for unsupervised learning with low quality data. It contains data of schoolchildren with dyslexia.…”

Section: Case 1: Inexpert-57dat Datasetmentioning

confidence: 99%

NIP - An Imperfection Processor to Data Mining datasets

Cadenas¹,

Garrido²,

Martínez³

2013

IJCIS

View full text Add to dashboard Cite

Every day there are more techniques that can work with low quality data. As a result, issues related to data quality have become more crucial and have consumed a majority of the time and budget of data mining projects. One problem for researchers is the lack of low quality data in order to test their techniques with this data type. Also, as far as we know, there is no software tool focused on the create/manage low quality datasets which treats, in the widest possible way, the low quality data and helps us to create repositories with low quality datasets for testing and comparison of data mining techniques and algorithms. For this reason, we present in this paper a software tool which can create/manage low quality datasets. Among other things, the tool can transform a dataset by adding low quality data, removing and replacing any data, constructing a fuzzy partition of the attributes, etc. It also allows different input/output formats of the dataset.

show abstract

Mining fuzzy association rules from low-quality data

Cited by 16 publications

References 27 publications

On modelling real-world knowledge to get answers to fuzzy and flexible searches without human intervention

On modelling real-world knowledge to get answers to fuzzy and flexible searches without human intervention

Analysis of Time Series Rule Extraction Techniques

NIP - An Imperfection Processor to Data Mining datasets

Contact Info

Product

Resources

About