An Incremental Partial Periodic Mining Over Medical Infertility Dataset to Mine High Utility Patterns
Suvarna U1, Srinivas Y2

1Suvarna U, Department of Information Technology, Gitam University, vishakapatnam (A.P), India.
2Srinivas Y, Department of Information Technology, Gitam University, vishakapatnam (A.P), India.

Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 675-687 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7202068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Data mining has always been a source for researchers to explore mining techniques. The current curve of mining is tending towards the utility itemset mining algorithms where the most utility (profitable) items or patterns are discovered. The article aims at mining the dynamic databases over a period to find high utility patterns (we used medical infertility dataset to find the complex combination of anti oxidants and its dosage involved in success of treatment for male infertility or andrology).The proposed algorithm uses an incremental transaction database where we mine partial periodic patterns using a list structure in just one database scan, called the IPP_HUIM. The IPP_HUIM algorithm (Incremental Partial Periodic High Utility Itemset Mining) is implemented in three phases. In phase 1, the IHUIM performs the Construction of List structure for items, Transaction weighted utility & periodicity follows a reorder and a restructure of the reordered list. Phase 2 IPHUIM algorithm, finds the periodic high utility itemset mining for K-itemset and prunes with search strategies & novel periodic list for optimization and the Phase 3 obtaining partial periodic patterns resulting the best utility patterns which is the IPPHUIM algorithm. The experimental results show high performance and accuracy compared to previous periodic algorithms over incremental databases.
Keywords: Incremental, Perioidic, Partial Periodic, High Utility Itemset Mining HUIM), Transactional Data Base.

Scope of the Article: Pattern Recognition