Subrata Bose - Academia.edu (original) (raw)

Papers by Subrata Bose

The Computer Journal, 2021

The study of coherent association rules based on propositional logic is an important area of asso... more The study of coherent association rules based on propositional logic is an important area of association rule mining. Users may get a large number of itemsets for low minsup and lose valuable itemsets for high minsup. Mining without minsup may cause itemset explosions that contain spurious itemsets with low correlations and take a long time to mine. For mining coherence rules, existing approaches consider only the frequent itemsets, ignoring rare itemsets. Moreover, all items in the database are regarded equally important, which is not practical in real-world applications. By using the confidence-lift specified multiple minimum supports combined with propositional logic, we propose an efficient approach called rare correlated coherent association rule mining that addresses all of the problems stated above. We define and incorporate termination bound of support (${s}_{TB}$) and termination bound of dissociation (${d}_{TB}$) for early pruning of the candidate itemsets. In the proposed...

Proceedings of the 2015 Third International Conference on Computer, Communication, Control and Information Technology (C3IT), 2015

Determination of frequent sets from a large database is the key to Association Rule mining from t... more Determination of frequent sets from a large database is the key to Association Rule mining from the point view of efficiency of algorithms to scale up and discovering frequent sets which lead to useful association rules. Some of the existing methods have either very low or very high pruning, which is the cause of generation of larger or lesser number of frequent patterns. In this paper we have adopted a balanced approach for frequent pattern selection. Our proposed measure weighted support considers association and dissociation among items as well as the impact of null transactions on them for frequent set generation. Impact of increasing itemset size on weighted support gives rise to variable threshold The experimental results obtained after implementation of the proposed algorithm justify the approach.

International Journal of Modern Trends in Engineering and Research, 2016

Query service for information on demand is a natural requirement. This paper proposes a privacy p... more Query service for information on demand is a natural requirement. This paper proposes a privacy preserving collaborative query service. A service provider provides this service to its customer by integrating data from multiple heterogeneous and autonomous data sources each of which holds a horizontal subset of the query specific data. The customer and the data sources are unknown to each other. The service provider acts as a bridge between them for servicing the query while preserving privacy. Secure data exchange by commutative encryption is the basic cryptographic approach considered in this work.

International Journal of Information Privacy, Security and Integrity

International Journal of Internet Technology and Secured Transactions

International Journal of Latest Technology in Engineering, Management & Applied Science (IJLTEMAS) Volume VII, Issue V, May 2018 | ISSN 2278-2540, 2018

Collaborative computing has set a new technology trend in recent years. It involves a large numbe... more Collaborative computing has set a new technology trend in recent years. It involves a large number of entities and shared resources, which are distributed, dynamic and heterogeneous. The range of collaborative computing is wide and expanding. Through collaboration number of services can be offered such as hospitality, tour and travel, health care etc. to name a few. In this work we have proposed a multi-party collaborative information retrieval service (CIRS). CIRS supports a long-range of queries involving text and multimedia data. The idea of CIRS is extended to a more generalized information service called collaborative information service (CIS). In CIS the collaborators share their data for serving complex and critical information need of organization or individuals. CIS provides consolidated information to the user collecting data from different data owners. In addition, different data owners are allowed to access as well as update other data owners' data in a collaborative scenario such as online stores like Amazon and Flipkart who connect different manufactures, vendors, transporter, and courier services etc. We have classified CIS in three different categories-basic, application and business. CIS can be considered to model any collaborative computing system where different partners collaborate for any joint activity by exchanging information among them.

Proceedings of the 2nd International Conference on Information Systems Security and Privacy, 2016

2016 49th Hawaii International Conference on System Sciences (HICSS), 2016

Advances in Intelligent Systems and Computing, 2015

2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS), 2015

Determination of frequent sets from a large database is the key to Association Rule mining from... more Determination of frequent sets from a
large database is the key to Association Rule mining
from the point view of efficiency of algorithms to scale
up and discovering frequent sets which lead to useful
association rules. Some of the existing methods have
either very low or very high pruning, which is the cause
of generation of larger or lesser number of frequent
patterns. In this paper we have adopted a balanced
approach for frequent pattern selection. Our proposed
measure weighted support considers association and
dissociation among items as well as the impact of null
transactions on them for frequent set generation.
Impact of increasing itemset size on weighted support
gives rise to variable threshold. The experimental
results obtained after implementation of the proposed
algorithm justify the approach.