F-KCW-Department Publications

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/1

Browse

Now showing 1 - 11 of 11

DATA WAREHOUSE AUTOMATION- A REVIEW
(CIIT International Journal of Data Mining and Knowledge Engineering, 2010-10) A S, Kavitha; R, Kavitha
Business enterprises invest lots of money to develop data warehouse that gives them real, constant and up to date data for decision making. To keep data warehouse update, traditionally, data warehouses are updated periodically. Periodic updates make a delay between operational data and warehouse data. These updates are triggered on time set; some may set it to evening time when there is no load of work on systems. This fixing of time does not work in every case. Many companies run day and night without any break, then in these situations periodic updates stale warehouse. This delay depends upon the periodic interval, as interval time increase the difference between operational and warehouse data also increase. The most recent data is unavailable for the analysis because it resides in operational data sources. For timely and effective decision making warehouse should be updated as soon as possible. Extraction, Transformation and Loading (ETL) are designed tools for the updating of warehouse. When warehouse is refreshed for the update purpose, it often gets stuck due to overloading on resources. Perfect time should be chosen for the updating of warehouse, so that utilize our resources can be utilized efficiently. Warehouse is not updated once, this is cyclic process. Here this paper is introducing automation for ETL, the proposed framework will select best time to complete the process, so that warehouse gets updated automatically as soon as resources are available without compromising on data warehouse usage.
DATA WAREHOUSE AUTOMATION-A REVIEW
(CIIT JOURNALS, 2010) A S, Kavitha; R, Kavitha
Business enterprises invest lots of money to develop data warehouse that gives them real, constant and up to date data for decision making. To keep data warehouse update, traditionally, data warehouses are updated periodically. Periodic updates make a delay between operational data and warehouse data. These updates are triggered on time set; some may set it to evening time when there is no load of work on systems. This fixing of time does not work in every case. Many companies run day and night without any break, then in these situations periodic updates stale warehouse. This delay depends upon the periodic interval, as interval time increase the difference between operational and warehouse data also increase. The most recent data is unavailable for the analysis because it resides in operational data sources. For timely and effective decision making warehouse should be updated as soon as possible. Extraction, Transformation and Loading (ETL) are designed tools for the updating of warehouse. When warehouse is refreshed for the update purpose, it often gets stuck due to overloading on resources. Perfect time should be chosen for the updating of warehouse, so that utilize our resources can be utilized efficiently. Warehouse is not updated once, this is cyclic process. Here this paper is introducing automation for ETL , the proposed framework will select best time to complete the process, so that warehouse gets updated automatically as soon as resources are available without compromising on data warehouse usage.
EMPIRICAL EVALUATION OF FEATURE SELECTION TECHNIQUE IN EDUCATIONAL DATA MINING
(ARPN Journal of Science and Technology, 2012-12) A S, Kavitha; R, Kavitha; J, Viji Gripsy
In machine learning the classification task is commonly referred to as supervised learning. In supervised learning there is a specified set of classes and objects are labeled with the appropriate class. The goal is to generalize from the training objects that will enable novel objects to be identified as belonging to one of the classes. Evaluating the performance of learning algorithms is a fundamental aspect of machine learning. The primary objective of this thesis is to study the classification accuracy using feature selection with machine learning algorithms. Feature selection is considered successful if the dimensionality of the data is reduced and accuracy of a learning algorithm improves or remains the same. Hence our contribution in this research is to prepare an educational dataset with real time feedback from students and try to apply the same with weka tool to measure the classification accuracy. Some part of implementation is compiled with weka, which is written in java and experiment with weka explorer.
EMPIRICAL EVALUATION OF FEATURE SELECTION TECHNIQUE IN EDUCATIONAL DATA MINING
(ARPN Journal of Science and Technology, 2012) A S, Kavitha; J, VijiGrpisy; R, Kavitha
In machine learning the classification task is commonly referred to as supervised learning. In supervised learning there is a specified set of classes and objects are labeled with the appropriate class. The goal is to generalize from the training objects that will enable novel objects to be identified as belonging to one of the classes. Evaluating the performance of learning algorithms is a fundamental aspect of machine learning. The primary objective of this thesis is to study the classification accuracy using feature selection with machine learning algorithms. Feature selection is considered successful if the dimensionality of the data is reduced and accuracy of a learning algorithm improves or remains the same. Hence our contribution in this research is to prepare an educational dataset with real time feedback from students and try to apply the same with weka tool to measure the classification accuracy. Some part of implementation is compiled with weka, which is written in java and experiment with weka explorer.
IMPROVEMENT OF CLOUD PERFORMANCE USING LOAD BALANCING TECHNIQUES
(International Journal of Innovations & Advancement in Computer Science, 2018-01) A S, Kavitha; J, Shalini
Cloud computing is a promising and very popular technology nowadays. Because this contains huge attractive features, which allows the cloud users to save, distribute their data either privately or publically. The cloud computing paradigm provides numerous applications and services. Due to its wide range of utility, the maintaining the performance of the cloud is very challenging. The performance of the cloud can be degraded by several factors such as flash crowd, low resource availability, multimedia data sharing etc. To improve the performance of the cloud applications, there are several techniques and methods have widely deployed. This survey provides a summary about the cloud computing and the performance issues along with its recent approaches to overcome that. The comprehensive study on existing performance improvement techniques are discussed in this paper. Finally the outline of the problem is suggested to improve the current load balancing and performance improvement techniques.
LINK STABILITY BASED ENERGY AWARE BACKBONE FORMATION IN MOBILE WIRELESS SENSOR NETWORKS
(International Journal of Computer Science and Mobile Computing, 2016-01) A S, Kavitha; J, Viji Gripsy; N, Deepa
Mobile Wireless Sensor Networks (MWSNs) are newly evolving smaller field of research area which needs to be given more importance. In MWSNs, nodes can self-propel via springs, wheels, or they might be connected to transporters, for example vehicles. Sensors have restricted energy supply and the sensor network is required to be functional for a long time, so enhancing the energy utilization to extend the network lifetime becomes a significant issue. An important property that distinguishes mobile wireless sensor networks from other distributed systems is their requirement for energy efficiency because sensors have limited energy saves. Since there is no static organization or centralized control in WSN, a connected dominating set (CDS) has been proposed as a virtual backbone. The CDS performs a main role in routing, broadcasting, coverage and movement planning. To decrease the activity during communication and extend the network lifetime, it is desirable to build a minimum CDS (MCDS). The main challenges faced by the mobile sensor network are link breakage, due to mobility or the energy depletion of the nodes. In this paper, we propose a new backbone formation algorithm based on link stability and energy.
A REVIEW PAPER ON BRAIN TUMOR
(International Research Journal of Engineering and Technology, 2019-07) A S, Kavitha; S, Keerthana
Brain controls all the necessary functions of body. The most complex organ in human body is brain and it is part of the central nervous system (CNS).A brain tumor is a mass or growth of abnormal cells within the brain or spinal cord. Brain tumor can be dangerous as it will disrupt the proper function of the brain. On may9 2016, the world health organization officially reclassifies all of the types of brain tumor. There are 120 types of brain tumors. American took a survey and declared that there were more than 79,000 new cases of brain tumors diagnosed in the United States in 2017.ABTA also estimated that there are 7,00,000 people who was suffering from brain tumors in the U.S. According to ABTA, an estimated 16,700 people died from brain and spinal cord tumors in 2017. Doctors may also refer to a tumor based on where the tumor cell originates. It can be referred to as a primary brain tumor, if the tumor began in the brain. If it began it’ll spread to another part of the body and affect the brain and that can be referred to as secondary or metastatic, brain tumors. In case of young age, cells divided comparatively faster, which helps in the growth of child. The uncontrolled growth of cells is known as tumor.
A REVIEW PAPER ON CANCER BIOLOGY USING BIOTECNOLOGY AND NANOTECHNOLOGY
(International Research Journal of Engineering and Technology, 2019-07) A S, Kavitha; G, Lakshana
This project mainly aims about using of NANOTECNOLOGY to analyze molecular mechanisms of different kinds of cancers. Nanotechnology which includes biotechnology has recently been applied to study various cellular processes, such as cell cycles and cell migration, providing rich spatial and temporal phenotype information. Many opportunities and challenges exist in combining nanotechnology with genomics signal processing techniques to develop more accurate and sensitive biomedical devices for cancer genomics and proteomics to obtain a better understanding of the cellular and molecular mechanisms of different kinds of cancers. In this article, we present the applications of new nanotechnology treatments using nanoscale that include nanoparticles and devices for genomic signal processing (GSP) in cancer research.
SURVEY ON ENVIRONMENTAL ISSUES OF GREEN COMPUTING
(INDIAN JOURNAL OF APPLIED RESEARCH, 2014-02) A S, Kavitha; J, Viji Gripsy
Computer equipment recycling and refurbishing is an important part of an organization’s sustainable waste strategy. Businesses are encouraged to dispose of their IT equipment in an environmentally responsible way, and there are government regulations, such as the WEEE directive, designed to deal with hazardous waste. Computer equipment recycling reduces the volume of waste which ends up in landfill sites, or gets dumped illegally. It cuts down on the amount of raw materials needed for the manufacture of new products, and it also means more users. In addition, if computing equipment is refurbished, this can benefit people and organizations that cannot afford to buy new IT equipment.
SURVEY ON FUTURISTIC ALIGNMENT OF IT PROCESSES REFERENCE TO INDIA
(International Journal of Emerging Trends & Technology in Computer Science (IJETTCS), 2013-01) A S, Kavitha; J, Viji Gripsy; N, Deepa
Today environmental sustainability is a global issue. Main attention of Environmental sustainability is to preserve the capability of environment to support human life. It not only involves reduction of waste but also make waste as useful resource. In India green IT sustainability initiatives will double within 5 years. In 2010 it was $35 billion but in 2015 it will increase to $70 billion. Recently Indian IT companies such as HP, Dell, Acer, Wipro, HCL, Infosys and a few others are adopting green computing. And they are also encouraging their customers and employees to adopt green computing. We mainly focus on the minimization of power consumption and heat reduction.
A SURVEY ON ROUTING PROTOCOL IN WIRELESS AD-HOC AND SENSOR NETWORKS
(International Journal of Pure and Applied Mathematics, 2018-02) A S, Kavitha; J, Viji Gripsy
Remote sensor systems are normally sent in ungracious conditions keeping in mind the end goal to achieve a particular mission. Therefore, these systems are liable to different quantities of assaults and dangers. In this way, security ought to be a noteworthy viewpoint that must be considered when outlining directing conventions for remote sensor systems. Furthermore, sensor hubs have constrained assets. In this manner, complex steering and security conventions can't be utilized. In this paper we give an overview of secure steering conventions that can be utilized as a part of remote sensor systems since it is imperative to give a grouping of the accessible conventions. Thus, a few conventions were checked on in this paper. The steering conventions can be arranged into two primary classifications in particular topology based and convention activity based. The principle objective of the work proposed in this paper is to give specialists an unmistakable thought regarding the accessible security based steering conventions and their properties. This review paper explains the certainties and investigation of the past and most despise examine did in "Specially appointed system's directing security".