SDNB Vaishnav College for Women

Chennai, India

SDNB Vaishnav College for Women

Chennai, India
SEARCH FILTERS
Time filter
Source Type

Suganya P.,Bharthiar University | Sumathi C.P.,Sdnb Vaishnav College For Women
International Journal of Control Theory and Applications | Year: 2016

Data Mining is basically forecasting various decisions based on the information provided to predict future trends and behavior. Data Mining is highly accurate to knowledge driven decision in the field of scientific, physiology, sociology and business decision. The features of the datasets are important which decide the performance of the classification algorithms. The feature selection algorithm is an optimization technique which is used to remove the irrelevant features from the data set to improve the efficacy of various models. The categories of feature selection algorithm fall into filter, hybrid and wrapper to produce useful subsets of prediction. In feature selection the features are discriminated using various measures and they can be deployed in medical data. Breast cancer is the second leading cause of cancer deaths especially for women. The basic aim of this article is to predict the Breast cancer data set using different classifier models. The breast cancer occurs when a cell in the breast undergoes a change and solid masses can be non-cancerous tumor or they may be Breast cancer. There are nine attributes in the data set which represent cytological characteristics of breast fine aspirates with two classes with one being malignant and other being benign. The Wisconsin Breast Cancer Data (WBCD) set is an imbalanced data set with 694 samples out of which 250 samples are benign and 44 samples are malignant. The data set is balanced with class balancer to undergo feature extraction using FScore method and to classify them. The classification results have indicated that the network gave the good diagnostics performance of 99.27%. © International Science Press.


Pushkala K.,Sdnb Vaishnav College For Women | Gupta P.D.,Manipal University India
Journal of Analytical Oncology | Year: 2016

The disturbed circadian rhythm due to long exposure to varied photo periods or to artificial light during night time (LAN) results in hormonal imbalance. The epidemiological survey indicates a clear difference in the incidence of breast cancer (BC) in countries closer to the poles and to the equator. Long-term exposure to LAN during sleep cycle is found to be the root cause of many health problems. Light dependent conversion of melatonin from serotonin plays a major role in cancer development. In rat model it is shown that levels of melatonin are always inversely proportional to oestradiol in the blood. Melatonin decreases the formation of oestrogens (mitogenic hormone) from androgens via aromatise inhibition. In a pilot study we have shown that in menopausal blind (risk age for BC) women the prevalence of BC is very low (1:169; Risk Rate (RR); Cumulative Risk (CR)35-64 age), compared to sighted women (1:78; CR, 35 - 64 age). Data was collected from a total of 2060 blind subjects (18.8% being < 40 years of age and 81.2% above 40 years). Partially blind subjects have 11% greater risk of developing BC than those who are totally blind (RR=1.106; 95% CI=.352 to 3.472). Other established risk factors for BC are ineffective in blind. The blind women model (proposed in this study) suggests that dark hours are essential in our daily routine. By management of proper circadian rhythms better management of various endocrine diseases including hormone dependent cancers can be achieved. © 2016 Lifescience Global.


Gayathri B.M.,Sdnb Vaishnav College For Women | Sumathi C.P.,Sdnb Vaishnav College For Women
2016 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2016 | Year: 2017

Now-A-days breast cancer has become one of the leading cause of cancer death among women. This cancer is caused mostly due to the lifestyle changes, avoiding breast feeding etc. Detecting breast cancer takes long time due to manual diagnosis. Even though there are many diagnostic systems are available still, it takes more time for proper classification. For detecting breast cancer, mostly machine learning techniques are used. This work deals with the comparative study of Relevance vector machine(RVM) which provides Low computational cost while comparing with other machine learning techniques which are used for breast cancer detection. The aim of this work is to compare and explain how RVM is better than other machine learning algorithms for diagnosing breast cancer even the variables are reduced. © 2016 IEEE.


Dhanalakshmi C.P.,University of Madras | Vijayalakshmi L.,Sdnb Vaishnav College For Women | Narayanan V.,University of Madras
Journal of Biomaterials and Tissue Engineering | Year: 2012

Carbonated hydroxyapatite/Poly(4-vinyl pyridine-co-styrene) nano composites of varying composition for biomaterial applications have been synthesized. The Carbonated hydroxyapatite/Poly(4-vinyl pyridine-co-styrene) nano composite materials were characterized by XRD, FTIR, 31P NMR, TGA, DTA, FESEM and TEM. Carbonated Hydroxyapatite nano rod embedded composite was prepared using Poly(4-vinyl pyridine-co-styrene) as a matrix with different weight percentages (wt%). The results indicated that the size and crystallinity of Carbonated hydroxyapatite nano particles decreases with increase in Poly(4-vinyl pyridine-co-styrene) concentration in the composite. SEM confirms the presence of carbonated hydroxyapatite nano rod crystals in Poly (4-vinyl pyridine-co-styrene) matrix. Carbonated hydroxyapatite/Poly(4-vinyl pyridine-co-styrene) nano composites were screened for antimicrobial activity and anti inflammatory activity. © 2012 American Scientific Publishers. All rights reserved.


Dhanalakshmi C.P.,University of Madras | Vijayalakshmi L.,Sdnb Vaishnav College For Women | Narayanan V.,University of Madras
Journal of Bionanoscience | Year: 2012

Nano carbonated hydroxyapatite/Poly(vinyl alcohol) composites of varying composition for biomaterial applications have been synthesized. The nano Carbonated hydroxyapatite/Poly(vinyl alcohol) composite materials were characterized by XRD, FTIR, HRTEM, TGA, DTA and FESEM. Carbonated Hydroxyapatite nano rod embedded composite was prepared using poly(vinyl alcohol) as a matrix with different weight percentages (wt%). The results indicated that the size and crystallinity of Carbonated hydroxyapatite nano particles decreases with increase in poly(vinyl alcohol) concentration in the composite. SEM confirms the presence of carbonated hydroxyapatite nano rod crystals in poly(vinyl alcohol) matrix. Nano Carbonated hydroxyapatite/Poly(vinyl alcohol) composites were screened for antimicrobial activity and anti inflammatory activity. Copyright © 2012 American Scientific Publishers All rights reserved.


Sumathi C.P.,SDNB Vaishnav College For Women | Santhanam T.,DG Vaishnav College For Men | Priya N.,SDNB Vaishnav College For Women
Journal of Theoretical and Applied Information Technology | Year: 2012

Text extraction in images and video has been developing rapidly since 1990s and is an important research field in content-based information indexing and retrieval, automatic annotation and structuring of images. Extraction of this information involves detection, localization, tracking, extraction, enhancement, and recognition of the text from a given image. However, variations of text due to differences in size, style, orientation, and alignment, as well as low image contrast and complex background make the problem of automatic text extraction extremely difficult and challenging job. A large number of techniques have been proposed to address this problem and the purpose of this paper is to classify and review these techniques, discuss the applications and performance evaluation, and to identify promising directions for future research. © 2005 - 2012 JATIT & LLS. All rights reserved.


Hemalatha G.,Mononmaniam Sundaranar University | Sumathi C.P.,Sdnb Vaishnav College For Women
2016 International Conference on Information Communication and Embedded Systems, ICICES 2016 | Year: 2016

Image Preprocessing is an essential factor for any Face image, when processing it for research purpose, The need for Preprocessing is due to its variation in Lightening condition, differences in Pose, Head orientation and Expressions because the quality of an Image depend on the effectiveness of capture device like CCTV, Webcams etc. The common Preprocessing involves Color Normalization, Noise Reduction, Edge Detection and Histogram Equalization. The aim of Preprocessing is to improve the quality of the Image and to enhance the Image features for further processing. In this paper Median filter is used for Color Normalization and Noise Reduction. Gabor filter is used for Edge enhancement and Histogram Equalization for Image contrast illumination. Hence an improved quality of Image is produced by using Hybrid filters this helps for the efficiency of producing result for any research processing. © 2016 IEEE.


Sumathi C.P.,Sdnb Vaishnav College For Women | Gayathri Devi G.,Sdnb Vaishnav College For Women
Journal of Computer Science | Year: 2014

The aim of this study is to propose a new methodology for text region extraction and non text region removal from complex background colored images. This study presents a new approach based on Gamma correction by determining a gamma value for enhancing the foreground details in an image. The approach also uses gray level co-occurrence matrices, texture measures, threshold concepts. The proposed method is a useful preprocessing technique to remove non text region and to show the text region in the image. Experiments were on various images from the datasets collected and tagged by the ICDAR robust reading dataset collection team. Experimental results show that the proposed method has a good performance on extracting text regions in an image. © 2014 Science Publications.


Sumathi C.P.,SDNB Vaishnav College for Women | Priya S.N.,SDNB Vaishnav College for Women
2013 International Conference on Information Communication and Embedded Systems, ICICES 2013 | Year: 2013

Text embedded in image provides high-level semantic information for automatic annotation, indexing and retrieval. Extraction of text is difficult due to the complex background in image, font size, shape, orientation, as well as color variance, and these make it a challenging task. In recent years many methods have been proposed for text extraction in different images. In this paper the comparative evaluation analysis of various text extraction techniques is presented. It has been shown that the Morphological - Region combined algorithm is computationally more expensive and performs better than the texture based and multi-scale edge based text extraction methods under almost all scenarios. © 2013 IEEE.


Sumathi C.P.,SDNB Vaishnav College for Women | Mahadevi M.,SDNB Vaishnav College for Women
Proceedings - 2014 International Symposium on Biometrics and Security Technologies, ISBAST 2014 | Year: 2015

Skin color detection plays an important phase in identifying the face in images. Detecting face has become difficult because of the complexity in facial features and the similarity between those features. To identify a face, one of the basic step is to segment the image based on skin color. The main objective of the paper is to find a color model which is more suitable and shows a good performance in detecting a face. This paper compares each of the skin color models namely HSV, YCBCR, Lab for better accuracy. On such comparison, a hybrid skin color model is derived by combining the suitable color component from the three skin color models. After Morphological operations and using connected components a face is detected. After experiments it is observed that the Hybrid color model based skin detection is more suitable with an accuracy of 93%. © 2014 IEEE.

Loading SDNB Vaishnav College for Women collaborators
Loading SDNB Vaishnav College for Women collaborators