A New Approach for Finding Maximally Frequent Set in Transactional Database
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2016, Vol 4, Issue 1
Abstract
Data mining is a methodology with the ability to extract information from large data sets and transforming it into understandable form for further use. The information obtained is of great value and has proven to be advantageous in various business applications. Apriori algorithm is one of the most fascinating and thoroughly investigated area in the field of data mining. It is used to identify frequent item sets in a transactional database. There exist many implementations for this algorithm using different data structures and methods for generating candidate sets. In our work instead of generating candidate sets and scanning the entire transactional database multiple times, we will be introducing the concept of base table and we will be scanning the entire transactional database only once. Beginning with item set containing one element and gradually increasing size of item set, we have created base tables. These tables contain subsets of fixed size. Later, we apply Binary search on array of base tables. In order to reduce the large size of transaction database, we use map (STL) to record frequency of all distinct transaction. For the purpose evaluating frequent item set, we use longest common subsequence algorithm. It improves the performance of proposed algorithm to a great extent over classical Apriori algorithm. Our algorithm gives better performance than most of the versions of Apriori algorithm proposed till date for transactional database which have dense matrix representation.
Authors and Affiliations
Rahul Last Name, Sharad Chauhan, Kamal Sharma
Keywords
Related Articles
- EP ID EP21536
- DOI -
- Views 265
- Downloads 3
slugAndroid Environment Security Through Penetration Testing Methodology
The fluidity of application markets complicate Smartphone security. Although recent efforts have shed light on particular security issues, there remains little insight into broader security characterist...
Synthesis, Characterization and Magnetic Properties of Mn2+ Doped Cdga2-2xo4 Oxide Spinels
Mn2+ doped CdGa2-2xO4 oxide spinels with ‘x’ values ranging from 0.15, 0.30, 0.45, and 0.60 were synthesized by sol – gel method via nitrate citrate route. X-ray powder diffraction analysis confirms the presence of cubi...
Perfect Degree Support Product Graphs
For a graph G(V,E), the support s(v) of a vertex v is defined as the sum of degrees of its neighbours. A graph G is said to be balanced (highly unbalanced), if the support of all the vertices are same (distinct). Let k...
Area efficient DA based Fir filter for EEG Classification
Due to the recent development of digital signal processing algorithms and very large-scale integrated circuit technologies, the initial implementation obstacles of the orthogonal frequency division multiplexing (OFDM) n...
PCA-Recommend: Increasing Trust on Recommendation models using the Similarity prediction on User rating and Item Rating
The recommendation modelling is challenging issue in the research of collaborative filtering model by integrating the user rating and item rating from the different source with rating sparsity and high dimensional struc...