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

Department of Smart Computing

Secondary Users (SU) are guided by Cognitive Radio Device in identifying a channel licensed to Primary Users (PU) when it is free. Whenever PU arrives, SU shall vacate and search for the alternate band by a conditional handoff. Existing handoff methods reduce the network’s efficiency. The proposed stochastic approach under hybrid Spectrum Hand-off is (SHO) employing the Invasive Weed Optimization (IWO) algorithm thus increasing the SHO efficiency in CR Networks. The proposed Centralized Cognitive Device monitors load balancing, minimizes handoff delay as well as the SU’s service time, conserves energy, speeds up the data transmission, supports the Internet of Things, multimedia applications including audio, live video streaming and still images over resource constrained WSNs. This algorithm is compared with the existing Genetic algorithm and Particle Swarm Optimization. The channel selection accuracy of the proposed IWO method is found to be 97.8% and it outperforms conventional methods. Besides, the pre-emptive resume priority M/G/1 queuing model is also utilized. This paper presents a complete system model along with a detailed study of its parameters proving the technique’s effectiveness.

School of Information Technology and Engineering

Vellore Campus

Department of Computer Applications

Telecommunication Systems

Stochastic approach for channel selection in cognitive radio networks using optimization techniques

Chaotic maps play an important role in information sharing. In this paper a grey wolf optimiser used with reduced entropy-based 3D chaotic map. The selection and high coefficients are selected based on the reduced entropy value to identify the optimised parameters to get unpredictable random values. Time complexity, autocorrelation of V, H and D elements, histogram of original and cipher images, peak signal to noise ratio and NPCR and UACI values are computed from the cipher image. The empirical results show the proposed method provides good, better imperceptibility and defends various attacks. To prove this accomplishment of the method, several experiments were conducted and compared the results with existing systems.

Department of Information Security

School of Computer Science and Engineering

International Journal of Computer Aided Engineering and Technology

<figure class="table"><table><tbody><tr><td> </td><td> </td></tr><tr><td> </td><td><figure class="image"><img src="file:///C:\Users\Admin\AppData\Local\Temp\msohtmlclip1\01\clip_image001.gif"/></figure></td></tr></tbody></table></figure>  <figure class="image"><img src="file:///C:\Users\Admin\AppData\Local\Temp\msohtmlclip1\01\clip_image002.gif"/></figure>An efficient image system-based grey wolf optimiser method for multimedia image security using reduced entropy-based 3D chaotic map

The patient's health record is sensitive and confidential information. The sharing of health information is a first venture to make health services more productive and improve the quality of healthcare services. Decentralized online ledgers with blockchain-based platforms were already proposed and in use to address the interoperability and privacy issues. However, other challenges remain, in particular, scalability, usability, and accessibility as core technical challenges. The paper focuses on ensuring the integrity of the health record with context-based Merkle tree (CBMT) through temporal shadow. In this system, two ledgers were used to ensure the integrity of eHealth records like general public ledger (GPL) and personalized micro ledger (PML). The context-based Merkle tree (CBMT) is used to aggregates all the transactions at a particular time. The context means it depends on time, location, and identity. This is ensured without the help of a third party. © 2020 IGI Global.

International Journal of Information Technology and Web Engineering

Integrity of e-health record ensured with context-based merkle tree through temporal shadow in blockchain

The herpesvirus, polyomavirus, papillomavirus, and retrovirus families are associated with breast cancer. More effort is needed to assess the role of these viruses in the detection and diagnosis of breast cancer cases in women. The aim of this paper is to propose an efficient segmentation and classification system in the Mammography Image Analysis Society (MIAS) images of medical images. Segmentation became challenging for medical images because they are not illuminated in the correct way. The role of segmentation is essential in concern with detecting syndromes in human. This research work is on the segmentation of medical images based on intuitionistic possibilistic fuzzy c-mean (IPFCM) clustering. Intuitionist fuzzy c-mean (IFCM) and possibilistic fuzzy c-mean (PFCM) algorithms are hybridised to deal with problems of fuzzy c-mean. The introduced clustering methodology, in this article, retains the positive points of PFCM which helps to overcome the problem of the coincident clusters, thus the noise and less sensitivity to the outlier. The IPFCM improves the fundamentals of fuzzy c-mean by using intuitionist fuzzy sets. For the clustering of mammogram images for breast cancer detector of abnormal images, IPFCM technique has been applied. The proposed method has been compared with other available fuzzy clustering methods to prove the efficacy of the proposed approach. We compared support vector machine (SVM), decision tree (DT), rough set data analysis (RSDA) and Fuzzy-SVM classification algorithms for achieving an optimal classification result. The outcomes of the studies show that the proposed approach is highly effective with clustering and also with classification of breast cancer. The performance average segmentation accuracy for MIAS images with different noise level 5%, 7% and 9% of IPFCM is 91.25%, 87.50% and 85.30% accordingly. The average classification accuracy rates of the methods (Otsu, Fuzzy c-mean, IFCM, PFCM and IPFCM) for Fuzzy-SVM are 79.69%, 92.19%, 93.13%, 95.00%, and 98.85%, respectively. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

Department of Software and Systems Engineering

World University root node

Fulltext

Sensors (Switzerland)

An efficient segmentation and classification system in medical images using intuitionist possibilistic fuzzy C-mean clustering and fuzzy SVM algorithm

It has been highly prescribed that our network needs to be locked as the use of storing data on the network has increased the number of snoopers. When an unauthorized or an unwanted activity occurs in a computer system then we refer it as network intrusion. It may allow a third party network to peek into our data, steal the data as well as change it. Therefore, the need to secure our network is highly recommended. To achieve this level of security, different machine learning algorithms are used and compared. The several algorithms which are compared are Naïve Bayes, Decision Table, K-Nearest Neighbor, Random Forest and Ad boost. The motive of this comparison is to identify the best performance algorithm. The following best algorithm will provide the high network attack accuracy. The dataset is produced which may contain a variety of intrusions. Our system will provide detection of the vicious network and establish the type of attack that has occurred in the system. Likewise, we can protect break off spiteful connection and provide security to our system. © 2020 IEEE.

International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2020

Forecasting of Network Intrusion by means of Efficient Machine Learning Algorithm

Devices of cognitive Radio (CR) help Secondary Users (SU) to locate a vacant channel licensed to Primary Users (PU). SU vacates the channel by doing a handoff on condition when PU enters that channel. Now SU seeks a different channel to proceed further. This paper narrates an algorithm of an evolutionary type called Invasive Weed Optimization (IWO) that solves the issue of Spectrum Handoff (SHO). The fixed and Probabilistic method of hybrid spectrum handoff utilizes the algorithm of IWO. The prime limitation of SUs’ prolonging the time in data delivery gets minimal by optimizing the period in the network of CR. The centralized Cognitive Device (CCD) is minimizing delay in handoff, monitoring the balancing of the load as well as improving efficiency. The proposed method is verified and validated with the existing Genetic algorithm (GA) and Particle Swarm Optimization (PSO) methods. Apart from that the pre-emptive resume priority MG/1 model for queuing too is employed. This leads the IWO method’s accuracy of channel selection to an improvement of 97.6%. There is a greater reduction in handoff delay. This excels in the schemes of traditional type in practice now. © 2020, World Academy of Research in Science and Engineering. All rights reserved.

International Journal of Advanced Trends in Computer Science and Engineering

Probabilistic approach for channel selection in centralized cognitive scheme utilizing invasive weed optimization

A model for providing solutions to the security issue of the cloud computing environment is addressed in this article by proposing a distributed collaborative trust service recommender (DTSR) system. DTSRs are kept in a distributed manner spread over the clouds, and they are used to extract raw trust from different sources. This trust information is based on the feedback by cloud service user's observation about the adherence of a cloud service provider (CSP) to a service level agreement for the cloud-based service provided. Using this trust data, the overall trust of CSPs is computed by using collaborative computation. The trust values are propagated among the distributed DTSRs in the network so that the trust values are available to everyone in the cloud environment. Experiments were conducted, which clearly shows that our proposed system is useful in providing a secure multicloud environment. © 2020 John Wiley &amp; Sons, Ltd.

Transactions on Emerging Telecommunications Technologies

A distributed collaborative trust service recommender system for secure cloud computing

Novice counselors are far more likely to maintain their own therapy interests and tend to use the closed issue effectively to test interpretation with instructor. While experienced therapists teach counseling skills to newbie counselors, they don't forget that a consumer's reaction to the problem of a novice therapist is essential to imagine in a suitable method. To answer the question, we've built a computer to imagine the go with the therapy communiqué flow. Nevertheless, the professional psychiatrist, as the gadget person demands a manual adjustment of the original category outcome and the painting pressure is immense, since the precision of the description of verbal communication results may be very low from the inside of the current system. To improve this issue, we have applied the class approach of text records with SVM (Support Vector System) as a system gaining knowledge of method to visualize the flow of interaction in therapy. However, we contrasted and tested the cutting-edge gadget's initial classification system with consequences. As these consequences indicate, the SVM model's the accuracy rating is below the existing device performance. © 2020 IEEE.

Department of Information Technology

Department of Embedded Technology

School of Electronics Engineering

Automated category Text identification using Machine Learning

Big data refers to the huge torrent of large-scale datasets that are being generated at an exponential growth. Since we live in this digital world, the era of big data has emerged in part and parcel of our lives. The emergence of big data has reached in almost several domains like healthcare industry, telecom industry, molecular biology, biochemistry, physics, astronomy, computer science, business and others. In this paper, we have termed the types of big data by the form SMSS data which is simply meaning social, mobile, spatial and sensor data. This paper aims to provide the importance of big data analytics brought over the different types of big data extracted from heterogeneous data sources. To achieve this objective, we have made an intensive study of several literatures and considered a variety of big data applications which are being discussed to showcase its value. Also, a generic framework is proposed that can be applicable to any kind of big data types extracted from such a diverse heterogeneous data sources. Finally, a few open source tools that can be used for processing the big data are presented.

VIT Unitversity

International Journal of Intelligent Enterprise

SMSS: does social, mobile, spatial and sensor data have high impact on big data analytics

Electronic health information is an efficient technique for providing health care services to society. Patient health information is stored in the cloud, to allow access of eHealth information from anywhere, and at any time, but the technical problems are security, privacy, etc. Sharing the medical data in a trustless environment is overcome by the proposed framework SeFra. The proposed work provides a secure framework to manage the eHealth record by using blockchain (SeFra). For authentication purposes, a temporal shadow is used and the integrity of health records is ensured by blockchain technology. Copyright © 2020, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.