Dharm Singh

STG-NoC: A Tool for Generating Energy Optimized Custom Built NoC Topology

on Chip (NoC) has emerged as a viable solution to the complex communication requirements of constantly evolving System on Chip (SoC). The communication centric architecture of NoC can be optimized across a variety of parameters as per the design requirements. With the development of customized application the inclination has shifted from regular architectures to irregular topology which leaves researchers with larger spectrum of optimization parameters. Many heuristic methods have been explored as the optimization problems encountered are NP-hard. This paper presents a customized topology generator STG-NoC which implements a heuristic technique based on simulated annealing for achieving the objective of energy optimization.

Scrambled hybrid wavelet-singular domain digital image watermarking

Digital watermarking has attracted substantial attention as it is the most commonly applied method for the copyright protection of the intellectual property rights of digital media. In conformity with the characters of human vision, the objective of the paper is to be focused on the performance of proposed algorithm on the basis of invisibility, interference and robustness to attacks using scrambled hybrid wavelet-singular domain watermarking system. By the use of MATLAB 7.7.0, the efficiency of the watermarking scheme has been demonstrated via the experimental results. The results show the proposed algorithm can embed and distill digital watermark more effectively in comparison.

Dynamic Adaptive Cross layer mapping mechanism for video transmission over wireless networks

The increase of IEEE 802.11s bandwidth led to a deployment of many multimedia applications over wireless networks. Nevertheless, these applications impose rigorous discipline constraints in QoS. To support the varying Quality-of-Service (QoS) requirements of emerging applications, the QoS-capable standard IEEE 802.11e [1] has been specified. Digital video delivered over wired-to-wireless networks is expected to suffer quality degradation from packet loss. Video traffic is widely expected to account for a large portion of the traffic in future hybrid network, as multimedia applications are becoming increasingly popular. Initially this paper attempted to discover optimal parameters such as bandwidth utilization and packet size in order to enhance video stream quality and proposed New Adaptive Crosslayer Algorithm, a novel scheme for QoS enhancement for IEEE 802.11 wireless networks.

Multimedia based fitness function optimization through evolutionary game learning

One of the areas of Artificial intelligence is Board Game Playing. Game-playing programs are often described as being a combination of search and knowledge. The board games are very popular. Board Games provide dynamic environments that make them ideal area of computational intelligence theories, architectures, and algorithms. Building a quality evaluation function is usually a lot of manual hard work and luck. The goodness of the evaluation function is determined by its accuracy, relevance, cost and outcome. All of these parameters must be addressed and the weighed results are added to an evaluation function experimentally. Evolutionary algorithms such as Genetic algorithm are applied to the game playing because of the very large state space of the problem. In natural evolution, the fitness of an individual is defined with respect to its competitors and collaborators, as well as to the environment. Evolutionary algorithms follow the same path to evolve game playing programs. Among all computer board games, Go-moku (Five-inLine), which is a variant of a Game of GO. This paper mainly highlights how genetic algorithm can be applied to game of Go-moku, where fitness values can be used by applying genetic operators through linear evaluation function.

Video Traffic in Wireless Sensor Networks

The primary goal of clustering in wireless sensor networks is to efficiently manage the energy consumption of among the sensory nodes using multi-hop communication with particular cluster. This proposed approach will reconsider the concept of leveling, sectoring and adaptive clustering for video traffic. Partitioning the entire network into clusters would manage the video traffic required for the data dissemination to the base station using multi-hop communication. Making both the cluster head selection and cluster size dynamic has been the central idea of this routing protocol. In this paper the simulation for transmission of videos over wireless networks is performed in MATLAB and the results are analyzed on the basis evaluation of configuring parameters such as PSNR, Network Life time, and Average Power Consumption. The Proposed mechanism improved the PSNR, Network Life time, and Average Power Consumption.

An Efficient Secure Routing Protocol in MANET Security - Enhanced AODV (SE-AODV)

+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+| | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-++-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

Performance improvement in game playing using evolutionary computation by large search space exploration

Soft Computing branch of intelligence research is primarily focused on the path of achieving high performance by mimicking the human approach. The central idea is to capture and encode human knowledge in artificial learning form. Applying AI technology to develop efficient game-playing programs is through realization of search-intensive approach in very large and complex search intensive areas. Many researchers have developed very powerful search techniques over the past two decades and successfully applied these search algorithms to problems domains of optimization, machine learning and soft computing paradigms. This paper extends this approach, by developing a program which is almost completely reliant on search optimization through evolutionary computation. Very efficient evolutionary algorithms and advancement of “intelligent” search along with improved hardware resources like faster processors, larger memories, and larger disks makes it possible to push the limits to solve problem of type and size of Checkers which has search space as high as 5 × 1020 representing a daunting challenge. The collected checkers result pushes the boundary of evolutionary algorithms based problem domains.

Quality of state improvisation through evaluation function optimization in genetic application learning

Artificial intelligence algorithms have been applied on computer board games since 1950s. Board Games provide competitive, cognitive learning and dynamic environments that make them ideal area of computational intelligence theories, architectures, and algorithms. Natural Evolution can also be considered to be a game play in which the rewards for a test organism that plays a good game of life are the propagation of its genetic material to its successors and its continued survival. In natural evolution, the fitness of an individual is defined with respect to its competitors and collaborators, as well as to the environment. Evolutionary algorithms follow the same path to evolve game playing programs. Among all computer board games, because of its low branching property, Reversi (Game of Othello) playing program can easily defeat humans by designing with strategies based game moves. Here on, the goal of computer Reversi game is no longer to challenge or defeat human players but to compete and evolve against other computer programs. This paper mainly highlights optimization of Reversi program fitness values by applying genetic operators through linear evaluation function.