Department of Information Technology

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/161

Browse

Author: search.filters.author.T, Hashni

Search Results

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    ARTIFICIAL INTELLIGENCE IN MILITARY
    (Coimbatore Institute of Technology, 2019-08-29) T, Hashni; G M, Kavyasre; M, Mohana
    In this paper we are going toreview about how Artificial Intelligence is useful inMilitary. Artificial intelligence (AI) is a hastily growingfield of science with doubtlessly significant implicationsfor country wide security. As such, the U.S. Departmentof Défense (DOD) and other nations are developing AIapplications for a vary of navy functions. AI lookup isunderway in the fields of Genius series and analysis,logistics, cyber operations, information operations,command and control, and in a variety of semi-autonomous and self-sustaining vehicles. Already, AI hasbeen integrated into military operations in Iraq and Syria.Congressional action has the manageable to structure thetechnology’s improvement further, with budgetary andlegislative decisions influencing the growth of navypurposes as nicely as the tempo of their adoption.AI applied sciences present unique challenges for navyintegration, mainly because the bulk of AI improvementis happening in the business sector. Although AI is notspecial in this regard, the protection acquisition processmay also want to be tailored for acquiring emergingtechnologies like AI. In addition, many commercial AIpurposes ought to endure significant modification priorto being practical for the military. A wide variety ofcultural issues additionally challenge AI acquisition, assome commercial AI businesses are averse to partneringwith DOD due to ethical concerns, and even inside thedepartment, there can be resistance to incorporating AItechnology into current weapons structures andprocesses.
  • No Thumbnail Available
    Item
    A VERSATILE APPROACH FORSCHEDULING USING BEE COLONYOPTIMIZATION (BCO) ALGORITHMS
    (Allied Publishers Pvt.Ltd, 2011-07-29) T, Hashni
    Swarm Intelligence (SI) is a branch of ArtificialIntelligence (AI), it is collective behavior ofsocial insect colonies and other animal societies.It designs algorithms for distributed problem-solving devices by using behavior of insects. BeeColony Optimization (BCO) is one of the recenttrends in the swarm Intelligence, has beensuccessfully applied to many combinatorialoptimization problems, mostly in transportation,location and scheduling fields. This paperdiscusses various types of scheduling, BeeColony Optimization (BCO) algorithms and itfocuses on scheduling using BCO algorithms.
  • No Thumbnail Available
    Item
    SOFTWARE AGENT BASED SCHEDULING IN GRID COMPUTING-A BRIEF STUDY
    (Department of Statistics, Bharathiar University, 2010-12-21) T, Amudha; T, Hashni; P, Deepan Babu
    Grid computing is the combination of computer resources multiple administrative domains to achieve a common goal. Gird computing (or the use of a computational grid) is applying the resources of many computers in a network to a single problem at the same time- usually to a scientific or technical problem that requires a great number of computer processing cycles or access to large amounts of data. A computational grid is a hardware and software infrastructure that provides dependable, consistent, pervasive and inexpensive access to high-end computational capabilities. A software agent is a piece of software that acts for user or other program in a relationship of agency. Such “action on behalf of “implies the authority to which action is appropriate. Schedulers are types of applications responsible for management of jobs, such as allocating resources needed for any specificjob, partitioning of jobs to schedule parallel execution of tasks. A Software agent is a scheduler, evaluates the services level requirements of jobs and allocate to the respective resources. This paper presents an introduction to agent-based scheduling in grid computing for resources allocation.
  • No Thumbnail Available
    Item
    A SUPERLATIVE APPROACH FOR CLUSTERING TECHNIQUES-BRIEF STUDY
    (MIT International Journal of Computer Science & Information Technology, 2013-08) T, Hashni; M, Divyavani
    Clustering is the one of the foremost technique in the data mining and its applied in various areas such as artificial intelligence, bio-informatics, biology, computer vision, city planning, data mining, data compression, earth quake studies, image analysis, image segmentation, information retrieval, machine learning, marketing, medicine, object recognition, pattern recognition, spatial database analysis, statistics and web mining. Clustering means the act of partitioning an unlabelled dataset into groups of similar objects. The goal of clustering is to group sets of objects into classes such that similar objects are placed in the same cluster while dissimilar objects are in separate clusters. Over the past few years, several different types of biologically inspired algorithms have been proposed in the various domains. The ant-based clustering algorithms have received special attention from the community over the past few years for two main reasons. First, they are particularly suitable to perform exploratory data analysis and, second, they still require much investigation to improve performance, stability, convergence, and other key features that would make such algorithms mature tools for diverse applications. Ant-based clustering is a biologically inspired data clustering technique. These algorithms have recently been shown to produce good results in a wide variety of real-world applications. During the last five years, research on and with the ant-based clustering algorithms has reached a very promising state. In this paper, a brief study on ant-based clustering algorithms is described. We also present some applications of ant-based clustering algorithms.
  • No Thumbnail Available
    Item
    A STUDY OF EFFICIENT AND EFFECTIVE APPROACHES IN NATURE-INSPIRED TECHNIQUES FORSOLVING OPTIMIZATION PROBLEMS
    (International Journal of Advanced Research inComputer Science (IJARCS), 2013-01) T, Hashni; M, Divyavani
    Nature-Inspired Techniques has been becoming the focus of research because they achieved the remarkable successes in optimization problems. The power of almost all Nature-inspired techniques comes from the fact that they imitate the best characteristic in nature. Nature-inspired algorithms are characterized by algorithmic operators mimicking computationally useful aspects of various natural phenomena. Nature inspired techniques such as swarm intelligence (SI), Nature Evolution and so on. It has demonstrated strong efficiency technique for solving complex problems and it provides optimum solution. This paper discusses a number of selected nature-inspired algorithms and various types of combinatorial optimization problems and it mainly focused on the unique attitude behind each of the techniques, their applications.
  • No Thumbnail Available
    Item
    RELATIVE STUDY OF CGS WITH ACO AND BCO SWARM INTELLIGENCE TECHNIQUES
    (International Journal of Computer Technology & Applications (IJCTA), 2012-09) T, Hashni; T, Amudha
    Swarm intelligence is the collective-level, problem-solving behavior of groups of relatively simple agents. Local interactions among agents, either direct or indirect through the environment, are fundamental for the emergence of swarm intelligence. Ant Colony Optimization (ACO) is a swarm based meta-heuristic method that is inspired by the behavior of real ant colonies. Bee Colony Optimization (BCO) meta-heuristic belongs to the groupof Swarm Intelligence techniques. Consultant Guided Search (CGS) is a new hybrid meta heuristic, which combinesnew ideas with concepts found in Ant colony Optimization (ACO), Bee Colony Optimization (BCO) technique. Thispaper presents comparative study of CGS, ACO, BCO techniques and the flexibility of CGS.
  • No Thumbnail Available
    Item
    SOLVING QUADRATIC ASSIGNMENT PROBLEMS USING A HYBRID NATURE-INSPIREDTECHNIQUE
    (International Journal of Current Research (IJCR), 2012-02) T, Hashni; T, Amudha
    Nature provides motivation to scientists in many ways. Scientists have started to realize that nature is a great source ofinspiration to develop intelligent systems and techniques. Nature- Inspired algorithms is a kind of algorithms that imitate theproblem-solving behavior from nature. Consultant Guided Search algorithm (CGS) and Genetic algorithm (GA) are some of theNature-Inspired Metaheuristic Algorithms inspired from Nature. In this paper, Consultant Guided Search algorithm (CGS) washybridized with Genetic algorithm (GA) and a new technique was proposed. The proposed Consultant Guided Search – Geneticalgorithm (CGS-GA) was implemented to solve the benchmark instances of Quadratic Assignment Problem (QAP). Theperformance of the proposed CGS-GA was compared with CGS algorithm. Results have shown that the proposed CGS-GA hasoutperformed CGS in arriving at improved optimal solutions for various test instances of Quadratic Assignment Problem