Information Science focuses on the study of application and knowledge in an organization. It also includes study of communication between people, organizations and any other existing information systems. The department of Information Science & Engineering provides broad based foundation in information technology for those who seek careers in IT industry. The department is actively involved in research areas encompassing recent trends in computer science and technology, big data analytics, data mining, image processing and fuzzy logic. The research focus is on:
The study of medical imaging is concerned with the interaction of all forms of radiation with tissue.
The development of appropriate technologies to extract clinically useful information, usually in the form of an image from the observed technology.
Non-invasive visualization of internal organs, tissue etc.
Image segmentation is an important and challenging factor in the field of medical science. It is widely used for the detection of tumors. This paper deals with detection of brain tumor from MR images of the brain. The brain is the anterior most part of the nervous system. Tumor is a rapid uncontrolled growth of cells. Magnetic Resonance Imaging (MRI) is the device required to diagnose brain tumor. The normal MR images are not that suitable for fine analysis, so segmentation is an important process required for efficiently analyzing the tumor images. Clustering is suitable for biomedical image segmentation as it uses unsupervised learning.
The main aim is to sort out the particular abnormal cells in human brain using combination of image segmentation and morphological operations. In the brain, it is the anterior most part of the nervous system.
Tumor is a rapid uncontrolled growth of cells. Magnetic Resonance Imaging (MRI) is the device required to diagnose brain tumor.
Two-dimensional magnetic resonance images of brain are processed and subsequently used to detect the tumor using the Image Segmentation approach.
Big data is a part of storage effect indicating the importance of identifying the way to handle huge data of size Exabyte (1018) and more. Typically such datum is generated from different applications like Social Networks, Government Sectors, Aviation Sectors, Radio Communications and so on. There are many active research and developments are happening both at research labs and industries to come out with effective and efficient Big Data analytics to solve real-world problems.
The main outcome of this research is to provide a tool which assists the faculty members to keep themselves up to date about the recent research trends in their respective area of research without spending time significantly in browsing or searching for research updates.
The developed tool or prototype reduces the searching time of an individual in large repositories and they can upgrade their skills with the latest information on their areas of interest in very less time even in their busy schedule and other personal constraints. The module can be used in real-time filtering and the document gist generation.
In the modern computational era, the emergence of service-oriented architecture and the grid computing has evolved into a new computing paradigm called as Cloud Computing. All the type of computing needs such as software, hardware etc., is made available from cloud servers. In cloud computing, normally the services are provided under three layers such as software as a service (SaaS), platform as a service (PaaS), and infrastructure as a service (IaaS). Web services like E-mail, File Conversion, Word Processor etc., are provided as Software as a Service (SaaS) through different cloud service providers. PaaS services provide support for constructing and delivering web applications and internet-based services. IaaS provides computing infrastructure like a Virtual Machine, Computer Hardware, and Database as service. Apart from the above said layers cloud computing has evolved to provide a different kind of services like Security as a Service, Network as a Service and Framework as a Service etc.
The problem of web-based service selection involves multi-criteria decision-making scenario and there have been many research methods proposed by many researchers, and still is an open issue under academic and industrial sectors.
Skilled users of cloud computing can easily select the service they need by analyzing the cloud service properties through the cloud service description documents, service level agreements which are all provided by the cloud service provider itself. For unskilled users, it is a difficult task and still an open issue of discovering a cloud service.
The usage of specialized query languages for service discovery does not support Natural Language Processing technique.
Semantic Web can be described as “knowledge representation meets the web” to enable automatic processing and composition of information in the web by means of ontology. By utilizing semantic web technologies on cloud service discovery an unskilled user will be able to search and find the appropriate cloud services according to the requirement.
WSDL files that are collected from “Investigating Web Services on the World Wide Web, 17th International Conference on World Wide Web (WWW), Beijing, April 2008, pp. 795-804”
CODE - CMU’S OWL - S Development Environment is an Integrated Development Environment that supports the developer through the whole process from the Java generation, to the compilation of OWL-S description to the deployment and registration with UDDI.
From the above performance comparisons, the fuzzy service clustering ontology based system provides consistent and efficient results than the other two systems.
The cloud computing is a new computing model which comes from grid computing, distributed computing, parallel computing, virtualization technology, utility computing and other computer technologies and it has more advantage characters such as large-scale computation and data storage, virtualization, high expansibility, high reliability and low price service. The cloud system could improve its capacity through adding more hardware to deal with the increased load effectively when the workload is growing. Cloud resources are provided as a service on a need basis. The cloud itself typically includes large numbers of commodity-grade servers, harnessed to deliver highly scalable and reliable on-demand services.
The main outcome of this research is to provide cloud security for the cloud tenants as the users can use the cloud services anywhere anytime without any conflict. There is a continuous effort in the research community to explore the challenges of trust and reputation models. This can be seen from the existing trust models. Still, there are several issues or challenges yet to be tackled which can be seen from the following survey on trust and reputations models as presented in the literature.
The development of cloud service reduces the time required for the deployment of infrastructure and also reduces the data redundancy and such issues should be effectively handled in the forthcoming trust models to provide smooth trustworthy transactions or interactions in a P2P networking environment.
Software-defined networking providers offer a wide selection of competing architectures, but at its most simple, the Software-Defined Networking method centralizes control of the network by separating the control logic to off-device computer resources. Software Defined Network (SDN) enables the direct control of a computer network that is under a single administrative domain. A clean separation of functions is paramount to SDN resources.
The main objective is to separate control plane from data plane and forwarding into dissemination paths that are maintained separately from data paths so they can be operated without requiring configuration at every switch or router and this 4D centralized control plane will be able to reduce operational at router and provides minimal switching configuration, high-speed data plane and support multiple data planes.
The possible outcome of the 4D control plane is a high-speed forwarding of data plane by separating from control plane which gives minimal configuration at the switch and the router by keeping centralized SDN controller and reduced impact of the hardware and software failures in the control plane. Data plane, which processes packets with local forwarding state and control plane, it puts the forwarding state in the networking device.
|Scalability related measures||Ability of Distributed SDN||Ability of Centralized SDN|
|Administrative||Increasing number of organizations or users to
share a single distributed system
|Increasing number of organizations or users are restricted|
|Functional||Enhanced by adding new functionality at minimal effort||Simplify the design and implementation|
|Geographic||Local area to a more distributed geographic pattern||Maintain enough visibility over network flows|
|Load scalability||Easily expand and contract its resource pool to
|Easily expand with limited power|
|Generation scalability||New generations of
|Better management of new generation of components|
|Reliability||Very Low||Better reliability|
Fuzzy sets & systems theory is a relatively new area of research and many researchers from various disciplines, get captivated by it. Fuzzy logic is a precise logic of imprecision and approximate reasoning. Research gets instigated by formal languages and fuzzy automata provides a real formal base for it. The research aims to characterize the languages recognized by these automations and establishes the relationship between them. To demonstrate the usefulness of the results, it is planned to develop intelligent and adaptive fuzzy controller for learning analytics that will study the students’ learning of a chosen engineering subject and provides early warning about performance.