An Empirical Data Cleaning Technique for CFDs
Journal Title: INTERNATIONAL JOURNAL OF ENGINEERING TRENDS AND TECHNOLOGY - Year 2013, Vol 4, Issue 9
Abstract
Data cleaning is a basic data preprocessing technique for before forwarding the data to data mining approach ,but it leads to an intresting research area in the field of data mining. Data cleaning is the process of finding and deleting noisy data/records from the database. The simplest technique used for data cleaning is based on Functional Dependencies. As FDs works on entire instance of a table we introduced a new technique called Conditional Functional Dependencies. CFDs are like if then rules. The dependence between the columns of a table are represented as conditions using functions.. For example if we consider a employee table which maintains the employee name,id,city,pincode and etc. In this table the employees who are belongs to the same city, are all may have the same pincode, So that we can generate a FD that city--->pincode. CFD means using specific condition for the FD. ex:city=vizag---->pincode=531005. The main agend of our project is to find the CFD violated rows in a table using the created CFDs. These CFDs violated rows are deleted to correct data.
Authors and Affiliations
Satyanarayana Mummana1 , Ravi kiran Rompella
Keywords
Related Articles
- EP ID EP151779
- DOI -
- Views 98
- Downloads 0
A Nonlinear Controller for Photovoltaic Water Pumping System
The aim of this work is to suppy an energy for photovoltaic cell and that energy will go to the inverter and then went to induction motor to be operating certain speed then water pumb process achieved. Main target...
Improvement in the reduction of PAPR for various M-Ary Phase modulations in MIMO-OFDM systems using Orthogonal variable spreading factor (OVSF)
Orthogonal Frequency Division Multiplexing (OFDM) is regarded as one of the most eminent multicarrier modulation technique in fourth generation (4g) wireless networks, thus making it possible to transfer very high...
Analysis of Dendrogram Tree for Identifying and Visualizing Trends in Multi-attribute Transactional Data
Most of the data collected by organizations and firms contains multi-attribute and temporal data. Identifying temporal relationships (e.g., trends) in data constitutes an important problem that is relevant in&nbs...
Multi-Functional Monitoring System
Instead of having the single application in a system it is better to have multiple applications such that the user can run the vehicle safely and can avoid the accident. Here in this paper we are using a combinat...
Assessment of Basaltic Aggregate and Stone Chips In Indian Context
The producing useful shape of stone the various stone wastes are coming out from the various processes in stone industries. From the preliminary waste named as stone chips, due to minimum cost it is taken out t...