Ebin Deni Raj

A firefly swarm approach for establishing new connections in social networks based on big data analytics

Social networking generates a huge amount of data which can throw useful insights if processed at the right time. Social computing is another emerging technique where social networking is made use for computational purpose. Cloud storage plays an important role in social computing. Privacy in social computing is still a debated issue. The privacy concerns and possible loopholes are discussed in detail. In this paper we are proposing some mathematical models to compute the probability of staying in social network and proposing an algorithm named firefly inspired algorithm for establishing connections FIAEC.

A fuzzy adaptive resonance theory inspired overlapping community detection method for online social networks

There has been a surge in the research of complex network analysis in the recent years. This paper engages with online social network, which is the most popular complex network in the modern world. Network communities help to understand the organization of real world networks. Accordingly, this paper proposes and validates a novel algorithm for overlapping community detection in online social networks. We focus on the stability-plasticity problem in complex networks and attempt to solve it using a Fuzzy Adaptive resonance theory inspired algorithm. The algorithm consists of two stages namely prediction stage and comparison stage. The proposed algorithms make use of network measures such as Edge betweenness, Betweenness centrality, and pair betweenness. The algorithm has been tested and compared with other algorithms using benchmark datasets, artificial datasets and real network datasets. The experimental results obtained were better than other overlapping community detection algorithms. The entropy of the proposed model has been evaluated using Overlapping normalized information, omega index, F-score and the cumulative performance value is 2.42 out of 3, which is better than other community detection algorithm.

A scalable cloud computing deployment framework for efficient MapReduce operations using Apache YARN

Cloud computing has become the buzz word since many years. The importance of data storage and processing in cloud has increased since the past two years. The digital data growth has contributed significantly for cloud storage. Hadoop is being used for data intensive computations and the latest Hadoop version YARN is more efficient than its predecessors. In this paper we are proposing a framework which will help in deploying cloud over YARN architecture. The paper also deals with the bulk creation of virtual machines in cloud.

A neural network based framework for apache YARN

Hadoop has become the most used framework for data intensive processes such as mapreduce. Business intelligence and technology forecasting has played a big part in enhancing the popularity of Hadoop framework. In this paper we have proposed an improvement for apache Hadoop yarn (also known as Hadoop 2.0) architecture. Container nodes, application master, resource manager and the pool of resources are arranged and used in a more efficient way in this framework. We are proposing two new algorithms for selection of application master and for selection of container nodes.

Effective Detection of Modular and Granular Overlaps in Online Social Networks Using Fuzzy ART

There has been lot of research endeavours in detecting overlapping community structures in complex networks. This paper concentrates on one of the most popular complex networks of recent times—online social networks. Some of the existing methodologies in community detection for online social networks are discussed. The goal of the proposed algorithm is to solve the stability–plasticity dilemma and to suggest a new technique for detecting modular and granular overlaps in community detection. The stability–plasticity dilemma is solved using a Fuzzy ART-inspired algorithm for overlapping community detection for detecting modular and granular overlaps. The algorithm is designed by making use of network measures such as vertex betweenness, betweenness centrality, and split betweenness. The validation metrics used for testing the algorithm were sensitivity, specificity, accuracy and normalized mutual information. The algorithm has been tested and validated using benchmark datasets and real network datasets and gives a cumulative performance of 3.1/4.0.

A Fuzzy Approach to Centrality and Prestige in Online Social Networks

Online Social networks have become popular with the increased use of mobile devices. Online Social network analysis alleviates the quantitative as well as qualitative analysis of online social networks. Online social networks deals with human emotions and communications, the vagueness in the process is more and is a hindrance in computation. We analyze two network measures namely centrality and prestige by developing a fuzzy rule based inference system. We obtained the relation between interaction, centrality and prestige in online social networks. The paper describes in detail, the need for a fuzzy approach in online social network analysis and analyzes the network measures.

A Hybrid Approach for Big Data Analysis of Cricket Fan Sentiments in Twitter

Twitter has become one of the most widely used social networks, and its popularity is increasing day by day as the number of tweets grows exponentially each day in the order of millions. The twitter data is used widely for personal, academic, and business purpose. In this paper, we collected real-time tweets from Indian Cricket Team fans during the eight matches of ICC Cricket World Cup (CWC) 2015 (here 8 matches means the total number of games India played in CWC) using the social media twitter. We performed sentiment analysis on the tweets to test emotions of Indian Cricket Lovers. The analysis is based on the fact that the emotions of fans change frequently with each event such that when home country is batting and scoring runs, they will be happy, and for every loss of wicket they will be sad. When the team is bowling, they will be sad for ‘six’ and happy for Wickets. So when Fans are happy, they react with positive tweets and accordingly when they are sad they react with negative tweets. We analyzed that, when India is batting, people use fear, anger, nervousness, and tension which are the most frequently used negative words and words like awesome, happy, and love are the most used positive words. All emotions are entirely dependent on team India’s performance. All negative emotions are increased when opponent team hit runs or when they achieve HIGH SCORE” and is decreased when the Indian team hit runs or when they take wickets’. This paper uses tweets and captures emotions for big data analytics and analyzes emotional quotient.

Analysis on enhancing storm to efficiently process big data in real time

The rapid growth of huge data has become a challenge to the data analysts in recent time. As the data is growing exponentially many techniques are on the rise, for processing the real time data. Many data processing models like Hadoop, Apache YARN, Mapreduce, Storm,and Akka are leading the Big Data domain. This paper analyses and compares all the data processing models stated above. Researchers are trying to increase the efficiency of the algorithms used in the data processing. In this paper, we propose two algorithms namely JATS and SD, which will enhance the efficiency of the storm data processing architecture.

A survey on topological properties, network models and analytical measures in detecting influential nodes in online social networks

There has been a surge in the usage and spread of online social networks in the past few years. This paper focuses on online social networks, which is the most prominent complex network in the modern world. People use online social networks for making friendships, learning, for entertainment and to review product items. This expanded impact of online social networks has prompted the rise of a research area named online social network analysis. This paper reflects the research aspects in the detection of influential nodes in online social networks with respect to topological properties, network generation models and analytical measures in online social networks. We have clearly presented the concepts, issues and future research directions in the influential node detection in online social network analysis. The factors and conditions for the evolution and growth of online social networks and the pre-requisites for generating a random graph for simulation of online social networks have been discussed. The paper gives a clear direction on the relation between computation of influential users and the properties, models and measures in online social networks.