Chithra Devi M.,Bharathiar University |
Audithan S.,UniversityTamil Nadu
Biomedical Research (India) | Year: 2017
Breast cancer is a serious problem and common form of cancer diagnosed in the woman. Computer Aided Diagnosis (CAD) is a tool which can assist the radiologists in the detection of abnormalities in medical images. In this study, a CAD system for breast cancer using X-ray mammography is presented with a high level of sensitivity by wavelet entropy features. Discrete Wavelet Transform (DWT) of a digital mammogram provides a multi-resolution representation of it. The characteristics of a mammogram at different resolution levels are represented by computing wavelet entropy and used as features for the corresponding mammogram. Then, ensemble classification using K-Nearest Neighbors (KNN), Bayes, and Support Vector Machine (SVM) is employed to classify the abnormalities as benign/ malignant. The experiments show promising results with the high level of sensitivity and hence it is feasible for mammogram classification. © 2017, Scientific Publishers of India. All rights reserved.
Bhanu Sree Reddy D.,UniversityTamil Nadu |
Uma Pricilda J.,UniversityTamil Nadu
IIOAB Journal | Year: 2016
Sentiment Analysis is considered as a critical research technique for collecting and analyzing textual data that is available on social websites. SA is also used as research method that systematically evaluates the consumer opinions in real sense in an efficient and effective manner. Marketing experts can collect rich data on attitudes and opinions about the products and services which help them in taking a relook at features which are positive and negative and use this as feedback system to rectify anything. By identifying the polarity of opinion either positive or negative will help businesses to identify right strategies to make their brands appreciated better by consumers. This review paper focuses on evolution of sentiment analysis, synonyms and why it is used and how research has happened related to how SA could be used in e- commerce. © 2016, Institute of Integrative Omics and Applied Biotechnology. All rights reserved.
Shanmugasundaram N.,UniversityTamil Nadu |
Thangavel S.,KS Rangasamy College of Technology
Journal of Computational and Theoretical Nanoscience | Year: 2017
This paper presents simulation, mathematical model and analysis of power cable for a three-level inverter fed Induction Motor drive system. A three level inverter provides smooth output voltage when compared to a two level inverter in different switching conditions. An improved high-frequency cable equivalent circuit model is developed to represent the high-frequency behavior of power cable. This model will help us to calculate the cable parameters of long power cable for different pulse width modulation techniques. A three level inverter is significant in the analysis of transient overshoot voltages and cable Screen voltages in both common and differential mode. In this paper, the simulation results and the same are analyzed with and without suitable capacitive filter circuit which added near the motor input terminals so that the overshoot voltage is minimized. The cable behavior is also estimated in frequency domain as well as time domain for a developed new power cable. It has been implemented and the results are in good agreement with MATLAB/SIMULINK model. Copyright © 2017 American Scientific Publishers.
Kumar D.S.,UniversityTamil Nadu |
Reddy D.M.,UniversityTamil Nadu |
Bharanidharan R.,UniversityTamil Nadu
International Journal of Mechanical and Production Engineering Research and Development | Year: 2017
This paper addresses about the condition monitoring and damage detection of structural beams by using model based techniques. In this work, a technique for programmed crack recognition as well as localization is exhibited. The structure is thought to be placed with actuators as well as sensors to vibrate and captures its dynamic reaction, includes impacts of vibration. In vibrational appeal, the information incorporates the modal reactions of the structure actuator previously, also after the crack. In order to locate the structure based damage, an element of the structure is taken for simulation, the damage in the structure is simulated by varying the stiffness of the element accordingly. The severity and location of unknown defects are judged closely using damage index (DI) which is calculated from the Frequency Response Function (FRF) is used to indicate the severity and location of the crack by judging closely by Damage Index (DI). The contrasts between dynamical properties in the damaged and undamaged structures give the estimation of Damage Index (DI). This methodology is applied to simple beam and plate with reduced local stiffness. The potential techniques for practical application condition monitoring problems are discussed. © TJPRC Pvt. Ltd.
Kamalakannan J.,Vellore Institute of Technology |
Rajasekhara Babu M.,UniversityTamil Nadu
IIOAB Journal | Year: 2016
Breast cancer is the one of the most common invasive cancer type among women. Early detection and diagnosis of breast cancer can be facilitating the chance of better treatment for the cancer affected people with mammography image analysis, since mammograms are cost effective and the world standard for screening of breast. Extracting the features from mammograms will help in identifying and classifying the breast abnormalities. There are many ways to extract the features; in this paper we have used GLCM to extract features from the mammographic images. GLCM is a statistical method of examining texture that uses the spatial relationship of pixels . the features which are extracted can be given to a classifier to classify the abnormalities as benign and malignant. The mammograms from mini MIAS database is used for extracting the features. The radiologist uses the CAD system for differentiating benign and malignant abnormalities from the mammograms in a better way. The technique which is adapted in this paper can be helpful in improving the performance of the CAD system which can assist the radiologist for better diagnosis of breast cancer. © 2016, Institute of Integrative Omics and Applied Biotechnology. All rights reserved.
Navaneethan C.,UniversityTamil Nadu
International Journal of Pharmacy and Technology | Year: 2016
The wireless detector network is wide employed in totally different areas of application like military applications etc. Wireless detector network is nothing however the cluster of detector nodes those area unit human action to every alternative mistreatment radio frequencies through the bottom station. Every detector node in network has the battery that is important and crucial to outline the lifetime of detector node. Due to distributed nature of these networks and their deployment in remote areas,these networks are vulnerable to numerous security threats that can adversely affect their proper functioning. This problem is more critical if the network is deployed for some mission-critical applications such as in a tactical battlefield. Random failure of nodes is also very likely in real-life deployment scenarios. Due to resource constraints in the sensornodes,traditional security mechanisms with large overhead of computation and communication are infeasible in WSNs. Security and energy efficient in sensor networks is,therefore,a particularly challenging tasks. This paper discusses the current state of the art in security mechanisms and energy saving techniques for WSNs. © 2016,International Journal of Pharmacy and Technology. All rights reserved.
Nivash J.P.,UniversityTamil Nadu |
Dhinesh Babu L.D.,UniversityTamil Nadu
International Journal of Pharmacy and Technology | Year: 2016
In order to prevent air quality deterioration and human health consequences,globally the pollution makes up most important emergency. For theses causes,in a local and on a regional scale mobile monitoring has increased in the last decade. By describing vital issues and effects,we have summed up the present condition in this area. Recent research says that massive data collected from various devices have to be processed efficiently. Many researchers have proposed ideas for data collection in a distributed way. Efficient data processing architecture is needed for massive data collected through IOT environment. Three-layer architecture was designed to deal the data processing in IOT. The data received from devices are initially stored in Data Assembly Layer (DAL). It is then passed to Data Separation Layer (DSL) for assuring the data efficiency. If the data is static,it is directly stored in the database by DSL else the Data Examining Layer (DEL) prepares the data to neighborhood structure. ODP (Optimal Data processing) model distributes the stress of data storage which reduces the workload of remote air pollution monitor. © 2016,International Journal of Pharmacy and Technology. All rights reserved.
Marappan R.,UniversityTamil Nadu |
Sethumadhavan G.,UniversityTamil Nadu
International Journal of Applied Engineering Research | Year: 2015
Graph coloring is a classical NP-Complete combinatorial optimization problem and it is widely applied in different engineering applications. This paper explores the effectiveness of applying heuristics and recursive backtracking strategy to solve the coloring assignment of a graph G. The proposed method applies heuristics through recursive backtracking to obtain the approximate solution to χ(G), the minimum number of colors needed to color the vertices of G. The proposed heuristics splits V(G) into higher degree and lower degree vertices such that the search space is reduced when calling the recursive backtracking algorithm for higher degree vertices first. The performance of this approximation method is evaluated using some well known benchmark graphs, and the results are found to be proficient. © Research India Publications.
Banudevi S.,UniversityTamil Nadu |
Swaminathan S.,UniversityTamil Nadu |
Maheswari K.U.,UniversityTamil Nadu
Nutrition and Cancer | Year: 2015
Cancer is considered a complicated health issue worldwide. The mean cancer survival through standard therapeutic strategies has not been significantly improved over the past few decades. Hence, alternate remedies are needed to treat or prevent this dreadful disease being explored. Currently, it has been recognized that repeated treatment with chemotherapeutic agents has been largely ineffective due to multidrug resistance and further conventional treatment possesses limited drug accessibility to cancerous tissues, which in turn necessitates a higher dose resulting in increased cytotoxicity. Drug combinations have been practiced to address the problems associated with conventional single drug treatment. Recently, natural dietary agents have attracted much attention in cancer therapy because of their synergistic effects with anticancer drugs against different types of cancer. Natural phytochemicals may execute their anticancer activity through targeting diverse cancer cell signaling pathways, promoting cell cycle arrest and apoptosis, regulating antioxidant status and detoxification. This review focuses mainly on the anticancer efficacy of dietary phytochemicals in combination with standard therapeutic drugs reported from various in vitro and in vivo experimental studies apart from clinical trials. This review adds knowledge to the field of intervention studies using combinational modalities that opens a new window for cancer treatment/chemoprevention. Copyright © 2015 Taylor & Francis Group, LLC.
Arunma M.,UniversityTamil Nadu |
Ezhilmaran D.,UniversityTamil Nadu
International Journal of Applied Engineering Research | Year: 2016
In this paper, we propose a new key-agreement protocol using near polynomial ring over a near-ring. We concretely generate the near polynomial ring f (x)ЄN(x) such that (formula presented) It is proved that the proposed protocol meets several security attributes under the assumption that the near polynomial ring over the near-ring defined below. © Research India Publications.