seshadri rao

Followers

Following

Public Views

Julita Vassileva

University of Saskatchewan

John F Dooley

Knox College

Marc Champagne

Kwantlen Polytechnic University

Samit Chakrabarty

University of Leeds

Roshan Chitrakar

Nepal College of Information Technology

Lev Manovich

Graduate Center of the City University of New York

Rafael Pinto

Instituto Federal do Rio Grande do Sul

Viacheslav Kuleshov

Stockholm University

Han Liu

Cardiff University

PALIMOTE JUSTICE

RIVERS STATE POLYTECHNIC

Interests

Uploads

Papers by seshadri rao

An Efficient and Optimal Solution Based Document Clustering

There are two important problems worth conducting research in the fields of personalized informat... more There are two important problems worth conducting research in the fields of personalized information services based on user model. One is how to get and describe user personal information, i.e. building user model, the other is how to organize the information resources, i.e. document clustering. It is difficult to find out the desired information without a proper clustering algorithm. Several new ideas have been proposed in recent years. But most of them only took into account the text information, but some other useful information may have more contributions for documents clustering, such as the text size, font and other appearance characteristics, so called visual features.In this paper we introduce a new technique called Closed Document Clustering Method (CDCM) by using advanced clustering metrics. This method enhances the previous method of cluster the scientific documents based on visual features, so called VF-Clustering algorithm. Five kinds of visual features of documents are...

Download

Analyzing and Predicting Covid-19 epidemic using Machine Learning Techniques

IOP Conference Series: Materials Science and Engineering, 2021

The entire world is suffering from a novel disease called covid-19 caused by a coronavirus since ... more The entire world is suffering from a novel disease called covid-19 caused by a coronavirus since 2019. The main reason for the seriousness of the disease is the lack of efficient legitimate medication or vaccine. The World Health Organization (WHO) suggested several precautions to regulate the spread of disease and to reduce the contamination thereby reducing deaths. In this paper, we analysed the covid-19 dataset available in Kaggle. The previous contributions from several authors of similar work focused on covid-19 datasets having a limited number of samples. Our paper used the dataset updated till November 15th 2020. Three different aspects are considered mainly in this paper, namely the number of confirmed cases, number of recovered cases, and number of death cases. All the aspects are analysed in a daily and weekly manner. We applied linear regression, polynomial regression, and holt’s method to predict the future number of confirmed, recovered, and death cases. This analysis i...

A Novel Cosine Similarity Based Clustering Mechanism

-In our proposed approach ,apart from the traditional clustering mechanisms based on linear space... more -In our proposed approach ,apart from the traditional clustering mechanisms based on linear space. Relation exists between the pair data objects either implicitly or explicitly. In the traditional mechanism uses a single view point, In this paper we proposes a novel mechanism for n-dimensional space with different similarity measure. Using the multiple viewpoints, more informative assessment of similarity can be achieved. Different mechanisms used for efficient clustering mechanisms .

Detecting Bots inside a Host using Network Behavior Analysis

International Journal of Computer Applications

Being well aware of the drastic changes brought by the Internet to the world there exists an expl... more Being well aware of the drastic changes brought by the Internet to the world there exists an explosion of network traffic. This burst traffic brings in lots of unwanted communication as a side-effect from the infected machines also called victims. Bots are such type of infected machines which work under a super power called botmaster. A botnet is a collection of compromised machines or bots receiving and responding to commands from the Command and Control (C&C) server that serves as a rendezvous mechanism for commands from a human or controller i.e., the bot master. The aim of our work is to detect the presence of the bot in the network traffic. This is accomplished in a two-step process. The work first captures network traffic from the infected host, and second step analyzes the captured traffic and detects the presence of a bot. To meet the goal we experimented on CTU-13 data set, a data set of botnet traffic captured in the CTU University, Czech Republic. Our work uses decision trees, Naïve Bayes, SVM and K Nearest Neighbor to detect the presence of bot. We found that decision trees gives 99.9% positive detection rate compared to other algorithms.

Download

A Multilevel Image Encryption based on Duffing map and Modified DNA Hybridization for Transfer over an Unsecured Channel

International Journal of Computer Applications, 2015

It was known to us from decades it is been a factual challenge for us to transfer the privileged ... more It was known to us from decades it is been a factual challenge for us to transfer the privileged data specially images to transfer over a unsecured channel. In this paper we propose a novel image encryption technique using DNA interwearing based Hybridization along with chaotic maps to transfer image data over a unsecured channel. In the early stages we apply Duffing map(chaotic map) on the original image, the resultant image we obtain will be the scrambled original image, where pixel position will be scattered over the image plain. And in the next phase we apply the technique of modified DNA hybridization based on the interwearing on the resultant image. Finally encrypted using a modified hill cipher.By doing so we attain chaotic behavior(Butterfly effect with small change in initial condition leads to big change in resultant outcome) by using Duffing map and we achieve highely security with less processing by using DNA Hybridization based image encryption. The security analysis of proposed techniques has achieved satisfactory outcome and results were presented.

Download

Cryptography Technique for a Novel Text Using Mathematical Functions

Advances in Intelligent Systems and Computing, 2015

A Hybrid Approach for Image Edge Detection Using Neural Network and Particle Swarm Optimization

Advances in Intelligent Systems and Computing, 2015

A Hybrid Approach for Image Edge Detection Using Neural Network and Particle Swarm Optimization

Generating Digital Signature Using DNA Coding

Advances in Intelligent Systems and Computing, 2015

An Efficient and Optimal Solution Based Document Clustering

Download

Analyzing and Predicting Covid-19 epidemic using Machine Learning Techniques

IOP Conference Series: Materials Science and Engineering, 2021