A Multi-attribute Classification Method to Solve the Problem of Dimensionality

Várkonyi-Kóczy, A. R.; Tusor, Balazs; Tóth, János T.

doi:10.1007/978-3-319-46490-9_54

Cited by 13 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [36], Varkonyi et al introduced a structure called Sequential Indexing Tables (SIT) to detect an FD regarding the last attribute in their sequence. SIT is a fast approach so it can process large data quickly.…”

Section: Algorithmic Approachesmentioning

confidence: 99%

Approximate Integrity Constraints in Incomplete Databases With Limited Domains

Sali,

Munqath

2024

Preprint

View full text Add to dashboard Cite

In case of incomplete database tables, a possible world is obtained by replacing any missing value by a value from the corresponding attribute's domain that can be infinite. A possible key or possible functional dependency constraint is satisfied by an incomplete table if we can obtain a possible world that satisfies the given key or functional dependency. On the other hand, a certain key or certain functional dependency holds if all possible worlds satisfy the constraint, A strongly possible constraint is an intermediate concept between possible and certain constraints, based on the strongly possible world approach (a strongly possible world is obtained by replacing \nul's by a value from the ones appearing in the corresponding attribute of the table).A strongly possible key or functional dependency holds in an incomplete table if there exists a strongly possible world that satisfies the given constraint. In the present paper, we introduce strongly possible versions of multivalued dependencies and cross joins, and we analyse the complexity of checking the validity of a given strongly possible cross joins.We also study approximation measures of strongly possible keys (spKeys), functional dependencies (spFDs), multivalued dependencies (spMVDs) and cross joins (spCJs). $g_3$ and $g_5$ measures are used to measure how close a table $Y$ satisfies a constraint if it is violated in $T$. Where the two measures $g_3$ and $g_5$ represent the ratio of the minimum number of tuples that are required to be removed from or added to, respectively, the table so that the constraint holds. Removing tuples may remove the cases that caused the constraint violation and adding tuples can extend the values shown on an attribute. For spKeys and spFDs, We show that the $g_3$ value is always an upper bound of the $g_5$ value for a given constraint in a table. However, there are tables of arbitrarily large number of tuples and a constant number of attributes that satisfy $g_3-g_5=\frac{p}{q}$ for any rational number $0\le\frac{p}{q}<1$. On the other hand, we show that the two measures values are independent of each other in the case of spMVDs and spCJs.We also treat complexity questions of determination of the approximation values.

show abstract

Section: Algorithmic Approachesmentioning

confidence: 99%

Approximate Integrity Constraints in Incomplete Databases With Limited Domains

Sali,

Munqath

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In [26], Varkonyi et al introduced a structure called Sequential Indexing Tables (SIT) to detect an FD regarding the last attribute in their sequence. SIT is a fast approach so it can process large data quickly.…”

Section: Related Workmentioning

confidence: 99%

Approximate Keys and Functional Dependencies in Incomplete Databases with Limited Domains

Al-atar

Sali

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A possible world of an incomplete database table is obtained by imputing values from the attributes (infinite) domain to the place of NULLs. A table satisfies a possible key or possible functional dependency constraint if there exists a possible world of the table that satisfies the given key or functional dependency constraint. A certain key or functional dependency is satisfied by a table if all of its possible worlds satisfy the constraint. Recently, an intermediate concept was introduced. A strongly possible key or functional dependency is satisfied by a table if there exists a strongly possible world that satisfies the key or functional dependency. A strongly possible world is obtained by imputing values from the active domain of the attributes, that is from the values appearing in the table. In the present paper, we study approximation measures of strongly possible keys and FDs. Measure g3 is the ratio of the minimum number of tuples to be removed in order that the remaining table satisfies the constraint. We introduce a new measure g5, the ratio of the minimum number of tuples to be added to the table so the result satisfies the constraint. g5 is meaningful because the addition of tuples may extend the active domains. We prove that if g5 can be defined for a table and a constraint, then the g3 value is always an upper bound of the g5 value. However, the two measures are independent of each other in the sense that for any rational number 0 ≤ p q < 1 there are tables of an arbitrarily large number of rows and a constant number of columns that satisfy g3 − g5 = p q . A possible world is obtained usually by adding many new values not occurring in the table before. The measure g5 measures the smallest possible distortion of the active domains.

show abstract

“…Sequential Indexing Tables and Sequential Fuzzy Indexing Tables (SITs and SFITs [14]) have been proposed in order to implement a classifier that uses the bare minimal steps necessary to classify patterns (i.e. find the known pattern (class) that is the most similar to the input values).They are based on the idea of Lookup Tables ( [15] LUTs), which store the precalculated value or class label for all possible input value combinations in suitable arrays [16].…”

Section: Introductionmentioning

confidence: 99%

SIT-based Functional Dependency Extraction

Tusor¹,

Tóth²,

Várkonyi-Kóczy³

2019

ACTA POLYTECH HUNG

View full text Add to dashboard Cite

In the digital age, being able to determine the relationships between attributes in datasets is advantageous for many fields of information technology, such as data mining, machine learning, etc. There are inherent rules, functional dependencies that are derived from the nature of the data, of which many are not trivially obvious to the human data manager. This paper presents a new method to extract such relationships. It uses Sequential Indexing Table structures that can implicitly indicate if the values of an attribute are determined by the combination of the values of the attributes preceding it in the layered architecture, i.e. is functionally dependent on those attributes. A new algorithm is given to use this feature to extract functional dependencies, and the performance is analyzed using real-life datasets.

show abstract

A Multi-attribute Classification Method to Solve the Problem of Dimensionality

Cited by 13 publications

References 7 publications

Approximate Integrity Constraints in Incomplete Databases With Limited Domains

Approximate Integrity Constraints in Incomplete Databases With Limited Domains

Approximate Keys and Functional Dependencies in Incomplete Databases with Limited Domains

SIT-based Functional Dependency Extraction

Contact Info

Product

Resources

About