scispace - formally typeset
Search or ask a question
Author

B. Parvathavarthini

Bio: B. Parvathavarthini is an academic researcher from St. Joseph's College of Engineering. The author has contributed to research in topics: Ad hoc On-Demand Distance Vector Routing & k-medians clustering. The author has an hindex of 1, co-authored 2 publications receiving 4 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: This paper proposes new modified rough fuzzy clustering algorithm based on fuzzy rough correlation factor, which can be derived directly from the results obtained thro fuzzy clustered.
Abstract: There are advantages to both fuzzy set and rough set theories, Combining these two and used for clustering gives better results. Rough clustering is less restrictive than hard clustering and less descriptive than fuzzy clustering. Rough clustering is an appropriate method since it separates the objects that are definite members of a cluster from the objects that are only possible members of a cluster. In fuzzy clustering similarities are described by membership degrees while in rough clustering definite and possible members to a cluster are detected. Fuzzy Rough Correlation Factor is the threshold for degree of fuzziness. It determines how low a DFR value shall be for it to be considered for cluster membership assignment. This paper proposes new modified rough fuzzy clustering algorithm based on fuzzy rough correlation factor. Hence rough fuzzy clustering can be derived directly from the results obtained thro fuzzy clustering.

3 citations

Journal ArticleDOI
TL;DR: This proposed work uses Exponential Weighted Moving Average (EWMA) algorithm to reduce the problem of position estimation error along with DTS to recover the delayed packets within a short period and performs better than DSR and AODV.
Abstract: DOA (DSR over AODV) is a hierarchical routing protocol which is a combination of DSR and AODV. It is used to overcome the routing issues that occur in MANETs when the network size increases. Some of the issues in MANETs are: large time consumption for either setting up a new path or to retrieve the failed path in case of link failures and scalability problem which occurs due to the increased number of nodes in MANETs resulting in additional routing overhead to the protocol. For combating the above mentioned issues in MANETs, DOA was implemented using Way Point Routing model where due to high frequency fluctuations the problems of position estimation errors appear. This proposed work uses Exponential Weighted Moving Average (EWMA) algorithm to reduce the problem of position estimation error along with DTS to recover the delayed packets within a short period. It also uses Expectation Minimization (EM) algorithm to estimate the nearest neighbor selection using probability function to enhance the performance of DOA. The performance comparison of E-DOA over DSR and AODV has been analyzed in two different scenarios irrespective of the network size and speed of nodes. The simulation results proved that by using EWMA with EM algorithm in DOA, E-DOA performs better than DSR and AODV. In scenario 1, the control overhead is observed to be much reduced in EDOA compared to DSR and AODV by 45% and 25% respectively and in scenario 2, E-DOA shows nearly 66% improvement over DSR and 55% improvement over AODV by using lesser bandwidth to transmit more packets and for the other parameters also E-DOA comparably performed better than AODV and DSR

1 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: Decision theory is propagated, an unprecedented validation scheme for Rough-Fuzzy clustering by resolving loss and probability calculations to predict the risk measure in clustering techniques, proven to deduce the optimal number of clusters overcoming the downsides of traditional validation frameworks.
Abstract: Cluster validation is an essential technique in all cluster applications. Several validation methods measure the accuracy of cluster structure. Typical methods are geometric, where only distance and membership form the core of validation. Yao's decision theory is a novel approach for cluster validation, which evolved loss calculations and probabilistic based measure for determining the cluster quality. Conventional rough set algorithms have utilized this validity measure. This paper propagates decision theory, an unprecedented validation scheme for Rough-Fuzzy clustering by resolving loss and probability calculations to predict the risk measure in clustering techniques. Experiments with synthetic and UCI datasets have been performed, proven to deduce the optimal number of clusters overcoming the downsides of traditional validation frameworks. The proposed index can also be applied to other clustering algorithms and extends the usefulness in business oriented data mining.

2 citations

Proceedings ArticleDOI
01 Dec 2013
TL;DR: Calculating cluster validity indices for a synthetic dataset and a real dataset on applying these algorithms and ensuring best soft clustering algorithm through experimental analysis are reviewed.
Abstract: Clustering is the task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups Clustering can be considered one of the most important unsupervised learning techniques so as every other problem of this kind; it deals with finding a structure in a collection of unlabelled data Clustering is of soft and hard clustering Hard clustering refers to basic partitioning algorithms where object belongs to only one cluster Soft clustering refers to data objects belonging to more than one cluster based on its membership values This paper reviews three types of Soft clustering techniques: Fuzzy C-Mean, Rough C-Mean, and Rough Fuzzy C-Mean Thereby calculating cluster validity indices for a synthetic dataset and a real dataset on applying these algorithms and ensuring best soft clustering algorithm through experimental analysis

2 citations

Proceedings ArticleDOI
08 Sep 2014
TL;DR: A feature based sentiment classification method that helps a user to make decisions easily based on their features of interest is proposed.
Abstract: The era of social networking has lead to the availability of vast amount of information in the web. People express their opinion about product, services or public issues in the forums, review sites, blogs etc. But in order to get useful data it becomes necessary to apply NLP techniques which make it easy for the people to make decisions at the time of buying products or contracting services. All the users are not concerned with all features of a product. Hence this paper proposes a feature based sentiment classification method that helps a user to make decisions easily based on their features of interest.

1 citations

Journal ArticleDOI
TL;DR: Simulation results shows RRAODV gives better performance than the existing protocols like AODV and RAODV for the above metrics.
Abstract: In high mobility, routing in Mobile Ad-Hoc Network is a very difficult task. In AODV and RAODV, all the data packets are travel through the same shorte st path so the intruders can easily trace out the d ata path. The main objective of Randomized RAODV provides the multipath and then the paths are selected randomly for security purposes. Using randomized ro uting algorithm to choose the path randomly and then the data packets are travel through different path to reach the destination, so the hackers canno t know about what are the ways the data packets trave rse. The performance of proposed RRAODV is compared with the existing routing protocol like AO DV, RAODV in mobile network environment. Performance metrics such as packet delivery ratio, end to end delay and control packet overhead are evaluated using NS-2 based on the number of nodes and speeds. Simulation results shows RRAODV gives better performance than the existing protocol s like AODV and RAODV for the above metrics. RRAODV is helpful to increase the performance of data transmission and security of data.