Conference proceedings

Permanent URI for this collection

https://ir.avinuty.ac.in/handle/avu/922

Browse

Browsing Conference proceedings by Issue Date

Filter results by year or month
Now showing 1 - 20 of 380
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    குறுந்தொகை
    (2010) கலாவதி, க
  • No Thumbnail Available
    Item
    Towards Learner Autonomy
    (2010) Kalamani, S
  • No Thumbnail Available
    Item
    Neural Network Approaches and MSPCA in Vehicle Acoustic Signal Classification using Wireless Sensor Networks
    (2010) Shanumugapriya, D
    Acoustic communication has been widely used in wireless sensor networks. Vehicle acoustic signals have long been considered as unwanted traffic noise. In this research acoustic signals generated by each vehicle will be used to detect its presence and classify the type. The goal of multiscale : PCA (MSPCA) is to reconstruct a simplified multivariate signal, starting from a multivariate signal and using a simple representation at each resolution level. Multiscale principal components analysis generalizes the PCA of a multivariate signal represented as a matrix by simultaneously performing a PCA on the matrices of details at different levels. By selecting the numbers of retained principal components, simplified signals can be reconstructed. These simplified signals are used for extracting the features. Six different features of the vehicle acoustic signals are calculated for the pre-processed acoustic vehicle signals and then further utilized as input to the classification system. These features include Signal Energy, Energy Entropy, Zero-Crossing Rate, Spectral Roll-Off, Spectral Centroid and Spectral Flux. Acoustic signal classification consists of extracting the features from a sound, and of using these features to identify classes the sound is liable to fit. Neural network approaches used here are KNN, PNN and BPN and these three approaches are combined with the MSPCA to obtain better accuracy.
  • No Thumbnail Available
    Item
    A Study on Decision Tree Classifier Methodology
    (2010) Vasantha Kalyani David
    Decision Tree Classifiers (DTC’s) are used successfully in many diverse areas such as radar signal classification, character recognition, remote sensing, medical diagnosis, expert systems and speech recognition, to name only a few. Perhaps, the most important feature of DTC’s is their capability to break down a complex decision-making process into a collection of simpler decisions, thus providing a solution which is often easier to interpret. This paper presents a study on current methods for DTC designs and the various existing issues. After considering potential advantages of DTC’s over single stage classifiers, the subjects of tree structure design, feature selection at each internal node and decision and search strategies are discussed. Some remarks concerning the relation between decision trees and Neural Networks (NN) are also made.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Digital Image Processing: Methods and Applications
    (2010) Geethalakshmi, S N
    In electrical engineering and computer science, image processing is any form of signal processing that converts the raw form of an input image into a usable and often meaningful output image. There are several standard techniques available for image processing and these techniques are broadly classified as image ^enhancement and image analyzing techniques. This paper discusses some of the most frequently used methods under this category.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    ESTIMATION OF BLOOD GLUCOSE AND INSULIN LEVELS OF SELECTED ADOLESCENTS AND YOUNG ADULT
    (2010) Sridevi Sivakami, P L
    Diabetes mellitus is now emerging as a pandemic among the adolescents and young adults, which is a tender, impressionable and transient age. Every silver lining has a cloud , thus the shift with development from food scarcity to food surplus is accompanied by rise in diabetes, obesity and all its associated health consequences. The objective of the study is to estimate the life style, dietary pattern, blood glucose and insulin levels of adolescents and young adults of both diabetic and non diabetic parents. A total of 300 subjects (150- adolescents and 150 - young adults) in the age group of 14^0 years consisting of both males and females, of diabetic and non-diabetic parents were selected. Socioeconomic status, lifestyle pattern and dietary pattern were obtained using a pre structured questionnaire and anthropometiic measurements were measured. Biochemical estimation such as fasting blood glucose (Enzymatic GOD-POD method) and insulin levels (immuno radiometric assay) was done for the selected 100 sub-samples, consisting of 50 adolescents and 50 young adults. The results of blood glucose and insulin level were normal for the majority of the adolescents and young adults, except one male and two females whose blood glucose and insulin level were elevated and were diabetic. Consumption of aerated drinks, fast foods, fiied foods and processed foods were found to be high. Snaking habit in-between meals and intake of coffee/ tea was also found high. Physical activity was found to be low. Individual diet counselling was given on dietary practices and lifestyle pattern to be followed in order to prevent and control diabetes in future and to have a healthy lifestyle for all the selected subjects like adopting proper meal timing with balanced diet, regular exercise, etc., were emphasized. Myths and facts on diabetes and obesity were discussed and changes in eating patterns were also suggested to the selected sample.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Prospects for Assessing Inclusiveness among Women through Social Capital and Social Support
    (2010) Visalakshi Rajeswari, S
    Well-being as an outcome o f inclusiveness has two personal dimensions- people's satisfaction and a sens o f their social well-being. Measuring their sk ill improvement, health sta tu s and their behaviour through persona improvement can be taken as indicators. Such indicators can he (pialitative or quantitative and exhibit the presence o or change in subjective things a n d /o r objective culture. This p a p e r concentrates on the use o f the acronym o f AIM. b y authorities in arriving a t certain criteria in terms o f social capital and social support, for assessing the ex ten t o identification and internalization b y women g roups regarding their own status o f being 'included' in a social setting.
  • No Thumbnail Available
    Item
    Enhanced Actionable Knowledge Mining for Effective Customer Relationship Management using Neural Networks
    (2010) Vasantha Kalyani David
    Most Data Mining algorithms and tools stop at discovered customer models, producing distribution information on customer profiles. Such techniques when applied to industrial problems such as CRM (Customer Relationship Management) are useful in pointing out customers who are likely attrittors and customers who are loyal, but they require human experts to post process the discovered knowledge manually. Most of the post processing techniques did not directly suggest actions that will lead to increase in the objective function such as profit .A novel algorithm is proposed in this paper that suggest actions to change the customers from undesired status to desired ones. This approach combines data mining with decision trees using neural networks to realistic insurance application domain and UCI benchmark data.
  • No Thumbnail Available
    Item
    Synthesis of Eco- Friendly Plant mediated Nanoparticles from Leucas aspera (Thumbai) and its Antimicrobial Properties in Food Packaging during Disaster Risk Management
    (2010) Sylvia Subapriya, M
    Silver nanoparticles due to their unique properties, find use in day-to-day applications in human life. The major advantage of using plant extracts for silver nanoparticle synthesis are easily available, safe, and nontoxic. The main mechanism of the process is plant-assisted reduction due to phytochemicals and are quicker than microbes in synthesis. In this present work, we have worked on environment friendly technique on green synthesis of silver nanoparticles from ImM AgNO^ solution through the extract of Leucas aspera which jxtssess both the reducing as well as capping agent. The particle size, Zeta potential and Antimicrobial property showed an average size of 23 nm with stability solution fifty percentage. Further, these green synthesized nanoparticles were found to be highly toxic against different human pathogens which could be an added advantage as an antimicrobial agent in food packaging.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Cluster pre-existence probability from WKH integral
    (2010) Rajeswari, N S; Balasubramaniam, M
  • No Thumbnail Available
    Item
    Big Data Framework for Healthcare using Hadoop
    (2010) Sarojini, B
    The technological advancements prevailing today make it possible to sense, collect, transmit, store and analyze the voluminous, heterogeneous medical data. This data could be mined to provide valuable and interesting patterns. However, extracting knowledge from big data poses a number of challenges that need to be addressed. In this paper we propose big data architecture for processing medical data. To handle this large volume of data. Big Data’s Hadoop tool can be used. The Apache Hadoop Framework for processing distributed healthcare database is also discussed.
  • No Thumbnail Available
    Item
    A Study on Associative Classification Mining
    (2010) Kalpana, B
    Traditional classification techniques such as ID3, C4.5, CART and RIPPER use heuristic search methods to find a small subset of patterns. In recent years, an emerging new approach in data mining that mainly uses association rules to discover patterns in classification called as associative classification which focuses on large subset of data. Algorithms like CPAR, CMAR, MCAR and MM AC are used widely in this field. Many studies show that Associative Classifiers give better accuracy than other traditional classifiers. Associative classification system is more robust and makes predictions based on entire dataset. In this paper, we aim to discuss an associative classification method by surveying and reviewing the current state-of-the-art called Incremental Learning and Mining Low Quality Data sets. This improves the overall accuracy of the associative classifier. Additionally, the classifiers produced are highly competitive with regards to error rate and efficiency.
  • No Thumbnail Available
    Item
    Dual Nutrition Burden in Women
    (2010) Sridevi Sivakami, P L
    Too early, too close, too many and too late"pregnancies adversely affect nutrition and health status of the mother child dyad; timely contraceptive care has become an indirect effective intervention to prevent deterioration in maternal and child nutrition. Epidemiological studies from India documented the magnitude and adverse consequences o f Chronic Energy Deficiency (CED) on the mother child dyad and paved way for intervention programmes to address under nutrition during pregnancy and lactation. Yet another important indirect cause of under nutrition continues to be infection s, under nutrition increases the susceptibility to infections; infections aggravate under nutrition. Over the last decade there will be increase in under nutrition in women is due to HIV infection. While under nutrition continues to be a major problem as in the earlier decades, the current decades has witnessed the progressive rise in over nutrition in women during reproductive age especially among the affluent segments o f population both in urban and in rural areas and associated steep increases in the prevalence o f non communicable diseases. In this an attempt had been made to find data on the factors responsible for emerging problem o f dual burden o f mai nutrition and associated health hazards in women.
  • No Thumbnail Available
    Item
    Satellite Image Mining
    (2010) Vasantha Kalyani David
    Advances in image acquisition and storage technology have led to tremendous growth in very large and detailed image databases. These images if analyzed can reveal useful information to human users. Image mining is more than just an extension of data mining to image domain. It is an interdisciplinary endeavor that draws expertise in computer vision, image processing, image retrieval, data mining, machine learning and artificial intelligence. In this paper we are reviewingThe trends and developments in image mining.