Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

The Internet of Things (IoT) is a model of future Internet and pervasive computing that has its own particular difficulties gained from the Internet as far as adaptability, vague topology, and so on are concerned. The proposed work means to determine the difficulties posed by IoT in the service discovery field. Most of the data analytics algorithms applied for data collected through sensors and actuators assume that the data are complete such that each property of the instances is filled with the appropriate value. These data have temporal and spatial correlation between them, and missing such data results in a significant decrease in accuracy and reliability of data analysis performed. Considering the importance of estimating the spatial data and the intricacies involved in estimating it using interpolation techniques, the proposed work bases its system development using an aspect-oriented programming improvement technique, thereby addressing the interpolation strategy as a cross-cutting aspect and reducing the complexity involved thereof. The proposal analyzes the situation of missing data and appropriately weaves the aspect and the application together, thereby decreasing the complexity in handling the interpolating data. The woven aspect estimates the missing data using an inverse distance weighting method and updates the information. Observation of the experimental results reveals significant improvement in response time compared with estimating the unknown value in a conventional manner. © 2019 by ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959

Department of Computer Applications

School of Information Technology and Engineering

Vellore Campus

Journal of Testing and Evaluation

Aspect-Oriented Modeling of Spatial Data Interpolation for Estimating Missing Data in Internet of Things (IoT) Service Discovery

World University root node

VIT Unitversity

Fulltext

IEEE Access

Segmentation by Fractional Order Darwinian Particle Swarm Optimization Based Multilevel Thresholding and Improved Lossless Prediction Based Compression Algorithm for Medical Images

Twitter, the social network which evolving faster and regular usage by millions of people and who become addicted to it. So spam playing a major role for Twitter users to distract them and grab their attention over them. Spammers actually detailed like who send unwanted and irrelevant messages or websites and promote them to several users. To overcome the problem many researchers proposed some ideas using some machine learning algorithms to detect the spammers. In this research work, a new hybrid approach is proposed to detect the streaming of Twitter spam in a real-time using the combination of a Decision tree, Particle Swarm Optimization and Genetic algorithm. Twitter has given access to the researchers to get tweets from its Twitter-API for real-time streaming of tweet data which they can get direct access to public tweets. Here 600 million tweets are created by using URL based security tool and further some features are extracted for representation of tweets in real-time detection of spam. In addition, our research results are compared with other hybrid algorithms which a better detection rate is given by our proposed work. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.

Department of Information Technology

Wireless Personal Communications

Detecting Streaming of Twitter Spam Using Hybrid Method

Rapid development in the functionalities and innovations of Internet of Things (IoT) have made more openings of IoT applications in various sectors like transportation, healthcare, buildings, infrastructure and logistics field. Considering the pervasive and context dependent nature of IoT, the applicability in multiple domains generates a lot of urgent issues, and one of these problems is missing data imputation, due to that fact some experimental data are incomplete. The IoT research carried out with such an experimental data results in significant decrease in accuracy and reliability of data analysis performed. Most of the big data analytics algorithms applied for data collected through sensors and actuators assume that the data is complete such that each property of the instances are filled with appropriate value. These data has temporal and spatial correlation between them. Most of the research carried out in the context of missing value imputation did not consider the characteristics of IoT data itself. The planned work bases its development using an aspect oriented software development approach and addresses the issues involved in the estimation of missing data point during the service discovery. The proposal analyses the situation of missing data completely at random and appropriately weaves the aspect and the application together thereby decreasing the complexity in handling the missing data issues. The woven aspect estimates the missing data using context and linear mean technique and updates the information. The observation on experimental results reveals significant improvement in response time compared to deriving the missing data in a conventional manner. © 2018 Elsevier Inc. All rights reserved.

Department of Information Security

School of Computer Science and Engineering

Computational Intelligence for Multimedia Big Data on the Cloud with Engineering Applications

Aspect Oriented Modeling of Missing Data Imputation for Internet of Things (IoT) Based Healthcare Infrastructure

Service Oriented Architecture (SOA) approaches are presently getting to be appropriate to embedded devices that feature embedded processing and communication. As a result these services get the ability to be hosted on high end machines to wireless resource constrained devices and on any physical object supported with communication ability. This creates the Internet of Services (IoS) environment. Services from multiple owners can be assembled into a composite service irrespective of their specific Quality of Service (QoS) and related properties for implementing a complex business process. In this context service consumer comes against the problem of selecting best service and for which providing QoS relevant guarantees leads to many challenging issues. One among them is determining a feasible service composition that fulfils a set of conditions while maintaining a good Quality of User Experience (QoUE). The last goal suggests the requirement to enforce an extra optimality prerequisite on the feasibility problem. In this paper, an optimization strategy oriented to efficient composite service selection for IoS model is designed through use of Particle Swarm Optimization (PSO) technique. Furthermore, prior to optimization, the services are assured of rich QoUE, especially trustworthiness in terms of reputation. The proposed work evaluates QoUE using the fuzzy based inference algorithm for identifying QoUE satisfied composite service. Experimental evaluation on a set of real world web services demonstrates the effectiveness of our proposed methodology. © 2016, Springer Science+Business Media New York.

Multimedia Tools and Applications

Integrated QoUE and QoS approach for optimal service composition selection in internet of services (IoS)

Internet is shifting at a rapid pace and evolving into a trend called as “Future Internet (FI)”. It can be defined as the union and cooperation of paradigms such as Internet of Things (IoT), Internet of Services (IoS) and Internet of Content (IoC). In these paradigms, the role of Service oriented Computing (SoC) deserves special attention. FI can be defined as an association of web services encompassing innovative services such as converged services, intelligent services and related smart services for overcoming the structural limitations of the current internet. Among many key concerns in the services environment, service discovery and optimal service selection are considered to be vital. Service discovery enables the client to get access to the right service at the right time to complete the requested tasks while service selection determines the feasible service composition that fulfils a set of conditions while maintaining a rich Quality of User Experience (QoUE) and good Quality of Service (QoS). This paper proposes the FI middleware named MIFIM (MIddleware for Future Internet Models) incorporated with Aspect Oriented Module (AOM) for addressing the challenges in particular related to the unknown topology and missing data estimation present in IoT service discovery and optimal service selection routine named Composite Service Selection Module (CSSM) for deriving the best service composition in IoS paradigm. The AOM is evaluated in accordance with MUSIC pervasive computing middleware while CSSM is compared with the other optimality approaches. Experimental results were found encouraging and the proposed components were performing reasonably well when compared to the similar solutions. © 2016 Elsevier B.V.

Future Generation Computer Systems

MIFIM—Middleware solution for service centric anomaly in future internet models

Discovery and retrieval of an ideal service in an SOA-like infrastructure comprising a resource-constrained hosting platform is really a challenging job. In this paper, we propose the simple service selection component for IoS, which selects the services that have maximum utility value over Quality of Services (QoS) and Quality of User Experience (QoUE) attributes. The novelty behind the proposed middleware development is in achieving high-degree configuration and customisability by selecting a subset of middleware functionality depending on the need. The conventional service selection approaches do not consider QoUE and QoS as a whole; they expect the user to provide a set of QoS constraints. The selection approach is based on the MAUT (Multi-Attribute Utility Theory) decision-making method. The experimental results are encouraging and the middleware performs well when compared to the constraint model and linear programming models. Copyright © 2017 Inderscience Enterprises Ltd.

International Journal of Grid and Utility Computing

Integrated quality of user experience and quality of service approach to service selection in internet of services

Internet of Things (IoT) is a model of future internet and pervasive computing which have its own challenges derived from the internet in terms of scalability, undefined topology and so on. The proposed work aims to resolve the challenges posed by IoT in service discovery functionality. Considering the pervasive and context dependent nature of IoT the planned work bases its development strategy using an aspect oriented software development methodology. The novelty lies in achieving high degree configuration and customisability by selecting subset of middleware functionality depending on the need. The performance is compared with MUSIC pervasive computing middleware and Android built-in configuration. The result reveals 6.5% decrease on average boot up and reconfiguration time for smart phones and 11.6% percentage decrease in Android tablets. In the context of boot up and reconfiguration time the middleware brings out 5% decrease for smart phones and 3% for Android tablets when compared with MUSIC middleware. The middleware shows 6.3% and 4% reduction in execution time of applications on smart phones and tablets when assessed with MUSIC middleware. Copyright © 2016 Inderscience Enterprises Ltd.

International Journal of Internet Protocol Technology

Aspect-oriented middleware framework for resolving service discovery issues in Internet of Things

Cloud computing has arisen a new model of computing. As its growing day by day, it has gained a lot of attention from researchers. Cloud computing is a utility based means pay per use model. Cloud users can execute their applications by requesting virtualized resources according to their need. But these resources are very limited in order to satisfy the need for all the cloud users. A resource provision should be done in a manner that it can satisfy the need for all the users in an efficient way. The resource allocation methods widely available considers various parameters such as cost, average waiting time, QoS, resource utilization etc. for effective and efficient virtualized resources management and allocation. Resources can also be allocated to user request by taking deadline parameter into consideration. When resources are not available to user request, users have to wait for stipulated amount of time. So deadline parameter need to be addressed while resource allocation in cloud environment. By considering all of these problems we have proposed an algorithm for allocating the virtualized resources in cloud environment on basis of deadline. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

An approach for deadline based resource allocation in cloud

In this paper, we have analysed load balancing algorithms named as ACO and Genetic optimization, which are used for distribution of workload among the servers. Load balancing is major problem in cloud computing environment. We have proposed Load Balancing Unit which will be responsible to assign incoming tasks to appropriate server based on maximum capacity of each server. The main objective of our paper is to achieve Load balancing among various servers and optimize execution time of tasks. We have analysed performance of these algorithm based on parameters such as execution time, priority, cost and QoS. In ACO algorithm we are able to assign priority to important tasks and execute these tasks according to their priority. Providers must deal with load balancing problem otherwise client will switch for better service from another service provider. We compared these algorithms to get best load balancing solution based on execution time and cost. We try to give better QoS in peak usage hours based on analysis results. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

Performance analysis of ant colony optimization and genetic algorithm for cloud load balancing

Internet of Things refers to a paradigm consisting of a variety of uniquely identifiable day to day things communicating with one another to form a large scale dynamic network. The integration of these heterogeneous things in the constrained network is a challenging issue, for which service oriented and architecture based solutions are considered to be useful. The key element of any service oriented paradigm is service discovery which allows the client to get access to the right service at the right time to complete the requested tasks. This paper presented a comprehensive survey of major solutions for service and resource discovery detailing techniques and features used in existing systems. The survey presented the findings in tabular representation and outlined the proposed aspect oriented middleware framework for IoT highlighting context awareness and solving certain pitfalls in the existing service discovery approaches. The survey results might be helpful in deriving the limitations of the existing protocols in literature and identify future research opportunities in service discovery.

International Journal of Intelligent Engineering and Systems

Aspect oriented middleware for internet of things: A state-of-the art survey of service discovery approaches

The objective of the proposed work is to develop a SVM based classification system that identifies the state and type of the coral reef images using Support Vector Machine (SVM) classifier. Many conservation programs and monitoring surveys are conducted around the world to preserve coral reefs which play an important role in marine biodiversity and human livelihood. A basic way of monitoring reefs is to determine the population of different "benthos" or organisms in a reef area such as living or dead corals, algae, etc.. It is utilized by marine scientists to deduce if a reef ecosystem is healthy, dying or at risk. The proposed work describes the classification procedure for processing coral reef images and rendering the required data through proper visualization tools.

International Journal of Pharma and Bio Sciences

Benthic classification of coralreefs using SVM classfier

With increased usage of IT solutions, a huge volume of data is generated from different sources like social networks, CRM, and healthcare applications, to name a few. The size of the data that is generated grows exponentially. As cloud computing provides an optimized, shared, and virtualized IT infrastructure, it is better to leverage the cloud services for storing and processing such Big Data. Securing the data is one of the major challenges in all the domains. Though security and privacy have been talked about for decades, there is still a growing need for high end methods for securing the rampant growth of data. The privacy of personal data, and to be more specific the health data, continues to be an important issue worldwide. Most of the health data in today’s IT world is being computerized. A patient’s health data may portray the different attributes such as his physical and mental health, its severity, financial status, and much more. Moreover, the medical data that are collected from the patients are being shared with other stakeholders of interest like doctors, insurance companies, pharmacies, researchers, and other health care providers. Individuals raise concern about the privacy of their health data in such a shared environment.