Volume 9, Issue 7, December 2018

Multimodal Image Fusion Technique MIFT-DWNRT for Improvement of Medical Diagnosis Abilities
Pages: 1-6 (6) | [Full Text] PDF (425K)
Manvi and Ashish Oberoi
RIMT University, Mandi-Gobindgarh – 147301, Punjab, India

Abstract -
In this article, a novel multimodal Medical Image Fusion Technique (MIFT) in light of MIFT-HDWRT, Non-sub sampled Contourlet Transform (NSCT) and Pulse-Coupled Neural Network (PCNN) is displayed. The MIFT-DWNRT plot tells the advantages of both the NSCT and PCNN to acquire better combination results. The source medical images are first decayed by NSCT. The low-recurrence sub bands (LFSs) are intertwined utilizing the MIFT-HDWRT run the show. For melding the high-recurrence sub bands (HFSs) a NSCT-PCNN show is used. Altered Spatial Frequency (MSF) in NSCT space is contribution to propel the PCNN, and coefficients in NSCT area with expansive terminating times are chosen as coefficients of the intertwined image. At long last, opposite of NSCT i.e., INSCT is connected to get the intertwined image. Abstract and target examination of the outcomes and correlations with cutting edge MIF technique demonstrate the effectiveness of the MIFTDWNRT plot in melding multimodal therapeutic images.
 Index Terms - Image Fusion, Pulse-Coupled Neural Network, Multiscale Geometric Analysis, Medical Imaging and NSCT
Image Crypto-Compression Based on Elliptic Curves and Linear Feedback Shift Register (LFSR)
Pages: 7-13 (7) | [Full Text] PDF (581K)
Cidjeu Djeuthie Diderot and Tieudjo Daniel
University of Ngaoundere, P.O.box 455, Ngaoundere
Department of Mathematics and Computer Science, University of Ngaoundere, P.O.box 455, Ngaoundere

Abstract -
Images are represented in several forms to facilitate their processing and security. These last years, elliptic curves have demonstrated remarkable performances in Cryptography. For Elliptic Curve Cryptography (ECC) to be applied on images, they should be represented as points on elliptic curves. in this paper, we present a formalism to transform an image into a sequence of points of an elliptic curve. A stream encryption based on the Linear Feedback Shift Register (LFSR) is proposed and used to encrypt images seen as sequences of points on elliptic curves. The JPEG compression is combined to this encryption to produce a new crypto-compression scheme. This scheme is implemented on sample images. The obtained results, compared to existing works, offer better satisfaction in terms of integrity.
 Index Terms - Crypto-Compression, Image, LFSR and Elliptic Curves.
Security Threat and Challenges Analysis of Cloud Computing with some Solutions
Pages: 14-23 (10) | [Full Text] PDF (785K)
Jihad Qaddour
School of Information Technology, Illinois State University Normal, USA

Abstract -
Cloud Computing extends shared services to the businesses worldwide. It provides access to software and hardware resources to individuals and business without having to know the actual underlying infrastructure. It has evolved greatly as an industry inviting more and more users using services available from within their realm. Cloud computing has enormous benefits like Multi-tenancy, Massive scalability, Elasticity, pay as you go, Self-provisioning of resources. While there are so many benefits there are always risks involved with sharing resources, which leads to privacy and security concerns. In this paper we are going to investigate some of the security challenges faced in Cloud Computing and propose measures to overcome these. This paper focuses on various technical security issues like data security, authenticating users, host security and many more arising from the usage of Web Service in the Cloud Environment. Using AES encryption technique, we can encrypt the already modified data and store on cloud, as well as decrypt the data in a similar fashion on the receiving end.
 Index Terms - Cloud Computing, Service Models, scalability, Elasticity, Security, Encryption and Decryption
Performance Evaluation of Bayesian Classifier on Filter-Based Feature Selection Techniques
Pages: 24-30 (7) | [Full Text] PDF (509K)
Federal Polytechnic, Ile Oluji, Ondo State, Nigeria
Federal University of Technology, Akure, Ondo State, Nigeria

Abstract -
Feature selection (FS) is a Machine Learning technique and a preprocessing stage in building intrusion detection system which can be independent of the choice of the learning algorithm or not, it plays important role in eliminating irrelevant and redundant feature in intrusion detection system (IDS); thereby increases the classification accuracy and reduces computational overhead cost of the IDS. it is an efficient way to reduce the dimensionality of an intrusion detection problem. This research examined the features of UNSW-NB15 dataset; a recently published intrusion detection dataset and applied three (3) filtered based feature selection techniques; information gain based, consistency based and correlation based on it to obtained a reduce dataset of attributes to build an intrusion detection system models that reduce the overhead computational cost and increases classification performance accuracy models. The result of the performance evaluations of the IDS model built on the reduced and whole datasets with Naive bayes machine learning algorithm shows that the reduced dataset accuracy and overhead processing cost outperformed the original whole dataset, model built with the consistency based reduced features has highest classification accuracy improvement of 14.16% over the classification accuracy of the whole test dataset, followed by information gain and correlation reduced test dataset with classification accuracy improvement of 13.55% and 10.7% respectively
 Index Terms - Attack Categories, Dimensionality, Computational Overhead and Filtered Based Features Selection
Ubiquitous, Modular Epistemologies for Multicast Frameworks
Pages: 31-35 (5) | [Full Text] PDF (343K)
Jimmy Rustler

Abstract -
E-commerce must work. Given the current status of decentralized configurations, analysts shockingly desire the improvement of consistent hashing, which embodies the intuitive principles of fuzzy robotics. We investigate how interrupts can be applied to the visualization of expert systems.
 Index Terms - --