Kousik Dasgupta

Genetic algorithm and gravitational emulation based hybrid load balancing strategy in cloud computing

Cloud computing enables a new supplement of consumption and delivery model for internet based services and protocol. It helps to provide software, hardware and data in form of collaborative services on the demand of the end user. To meet the QoS and ensure high interoperability and scalability is one of the most challenging tasks for cloud service provider. However, there are also several technical challenges that need to be tackled before the benefits can be fully realized. Among them reliability, resource provisioning, and efficient resources consuming etc are major concern. Load balancing also one of them. It includes selecting a proper node that must be full filled end user demand and also distribution of dynamic workload evenly into the multiple nodes. So load balancing can be described as an optimization problem and should be adapting nature due to the changing needs. In this paper we suggest a novel load balancing strategy to search under loaded node to balance load from overwhelmed node. CloudAnalyst used as a simulation tool for the proposed load balancing strategy. Experimental results of the sample application are really very encouraging. Significantly the results of the proposed algorithm are compared and outperformed the traditional strategy like First Come First Serve(FCFS), local search algorithm like Stochastic Hill Climbing(SHC) and soft computing approaches like Genetic Algorithm (GA) and Ant Colony Optimization(ACO).

An Ant Colony Based Load Balancing Strategy in Cloud Computing

Cloud computing thrives a new supplement of consumption and delivery model for internet based services and protocol. It provides large scale computing infrastructure defined on usage and also provides infrastructure services in a very flexible manner which may scales up and down according to user demand. To meet the QoS and satisfy the end users demands for resources in time is one of the main goals for cloud service provider. For this reason selecting a proper node that can complete end users task with QoS is really challenging job. Thus in Cloud distributing dynamic workload across multiple nodes in a distributed environment evenly, is called load balancing. Load balancing can be an optimization problem and should be adapting its strategy to the changing needs. This paper proposes a novel ant colony based algorithm to balance the load by searching under loaded node. Proposed load balancing strategy has been simulated using the CloudAnalyst. Experimental result for a typical sample application outperformed the traditional approaches like First Come First Serve (FCFS), local search algorithm like Stochastic Hill Climbing (SHC),another soft computing approach Genetic Algorithm (GA) and some existing Ant Colony Based strategy.

A Novel Visual Cryptographic Technique through Grey Level Inversion (VCTGLI)

In this paper a new (2, 2) visual cryptographic technique has been proposed, where the aspect ratio and the dimension of the secrete image/share with respect to source image remains constant during the process. In the VCTGLI technique grey level of some pixels of the input image has been inverted using random function to generate shares, instead of generating new pixels for shares. The scheme may be more secured and easy to implement like other techniques of visual cryptography.

A three-dimensional self-organizing neural network architecture for three-dimensional object extraction from a noisy perspective

Processing of three-dimensional image data for quality enhancement, segmentation and analysis is a challenging proposition due to the enormity of the underlying data content as well due to the inadequacy of data description standards. Extraction of objects from 3-dimensional image information is no exception. In this article, a novel three-dimensional neural network architecture is presented for faithful extraction of 3-dimensional objects from a noisy perspective. The proposed network architecture operates in a self-supervised mode assisted by fuzzy measures. Results of application of the proposed architecture are demonstrated on several synthetic and real life three-dimensional binary voxelized images. The efficacy of the architecture in different types of noises indicates encouraging avenues.

A Framework of Secured and Bio-Inspired Image Steganography Using Chaotic Encryption with Genetic Algorithm Optimization (CEGAO)

The two key issues related to steganography techniques are, statistical undetectability and picture quality. Image steganography takes the advantage of limited power of Human Visual System (HVS). The proposed framework offers an approach of secure data hiding technique in digital images. Novel scheme, presented encrypts meaningful secret data using nonlinear dynamics (chaos theory) before embedding into host or cover image. A basic LSB embedding method is used for encrypting data into cover image. Genetic Algorithm based pixel adjustment process is used to reduce the difference of error between the host image and its stego version with low distortions. The results of proposed scheme are compared with other steganographic algorithm using Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) index, color frequency test and StirMark analysis.

A Three Dimensional Bi-directional Self-Organizing Neural Network (3-DBDSONN) Architecture for Three Dimensional Object Extraction from a Noisy Perspective

A novel three dimensional bi-directional self-organizing neural network (3-DBDSONN) architecture with fuzzy context sensitive thresholding suitable for three-dimensional (3D) image processing applications, is proposed in this article. The proposed architecture comprises three interconnected three-dimensional fuzzy layers of neurons. It is devoid of any back-propagation algorithms for weight adjustments. An application of extraction of three-dimensional binary objects from various degrees of noisy background is demonstrated on one synthetic and two real life three-dimensional binary voxelized images. The efficiency of the proposed network as regards to immunity to different types of noise indicates encouraging avenues.