Time filter

Source Type

Rangarajan R.,VSB Engineering College | Bindhu V.,Coimbatore Institute of Technology
Applied Soft Computing Journal | Year: 2012

This paper presents the evaluation of mental stress assesment using heart-rate variability (HRV). The activity of the autonomic nervous system (ANS) is studied by means of time-frequency analysis (TFA) of the heart-rate variability signal. Spectral decomposition of the heart-rate variability before smoking and after smoking was obtained. Mental stress is accompanied by dynamic changes in ANS activity. HRV analysis is a popular tool for assessing the activities of autonomic nervous system. The approach consists of (1) monitoring of heart rate signals, (2) signal processing using wavelet transform (WT) (different wavelets), (3) neuro fuzzy evaluation techniques to provide robustness in HRV analysis, (4) monitoring the function of ANS under different stress conditions. Our experiment involves 20 physically fit persons under different times (before smoking and after smoking). Nero fuzzy technique have been used to model the experimental data. © 2012 Elsevier B.V.

Ghosh D.K.,Vsb Engineering College
International Review on Computers and Software | Year: 2013

The search engine produces numerous result for a single query, but the question is how relevant the result towards the query. The results provided by the search engines are not that much relevant to the query submitted, due to the ranking measures adopted by the search engines. The search engines used now a day return results based on the contextual information not by the content of the document. The ranking measure adapted by the familiar search engine also based on number of visits and time spent on the web page. For a personalized search the search engine has to produce some personalized results according to the user interest. We propose a new ranking algorithm using the semantic measures, which shows the semantic relevancy of the web document towards the query submitted. The query categorization is performed by computing same semantic link measure for the query towards set of domain ontology O. Given a web document set Ds of n documents, the category of each document Di is identified by the semantic link measure between each document term set Ts and set of concept or classes from domain ontology O. The document which comes under the category of query are identified and ranked based on the semantic link measure. Based on semantic link measure and depthness we compute a cumulative semantic measure which represents the document closure about a domain. We used domain ontology and word net to compute these measures for efficient ranking. © 2013 Praise Worthy Prize S.r.l. - All rights reserved.

Padma A.,Vsb Engineering College | Giridharan N.,Dal Housie University
International Journal of Imaging Systems and Technology | Year: 2016

A computer software system is designed for the segmentation and classification of benign and malignant tumor slices in brain computed tomography images. In this paper, we present a texture analysis methods to find and select the texture features of the tumor region of each slice to be segmented by support vector machine (SVM). The images considered for this study belongs to 208 benign and malignant tumor slices. The features are extracted and selected using Student's t-test. The reduced optimal features are used to model and train the probabilistic neural network (PNN) classifier and the classification accuracy is evaluated using k fold cross validation method. The segmentation results are also compared with the experienced radiologist ground truth. Quantitative analysis between ground truth and segmented tumor is presented in terms of quantitative measure of segmentation accuracy and the overlap similarity measure of Jaccard index. The proposed system provides some newly found texture features have important contribution in segmenting and classifying benign and malignant tumor slices efficiently and accurately. The experimental results show that the proposed hybrid texture feature analysis method using Probabilistic Neural Network (PNN) based classifier is able to achieve high segmentation and classification accuracy effectiveness as measured by Jaccard index, sensitivity, and specificity. © 2016 Wiley Periodicals, Inc.

Baranidharan T.,KS Rangasamy College of Technology | Ghosh D.K.,Vsb Engineering College
European Journal of Scientific Research | Year: 2012

The digital medical image recordings of the patient's condition, clinical care form part of database. The database are used for diagnostic, research and educational purposes. With the amount of digital medical images generated, the medical database is huge and multi-varied. Retrieving the required medical image from the database is a major challenge. Most of the time, the focus is within the image that is relevant to the clinical or research query. Content based image retrieval (CBIR) which helps retrieve images from the database similar to the query image are now widely used for medical image retrieval. There are many researches in literature dealing with CBIR for medical images based on various feature extraction, and classification methods. The major drawback being, each retrieval system handles either a specific type of medical image like mammography, brain tumour or some specific disease. In this paper, we address the problem of retrieving medical images from a multi-varied database. We propose an algorithm based on energy information gained from Hilbert Transform for classification of medical images according to imaging modalities and body parts. Neural networks have been widely used in image classification. In this paper, we exploited the spatial information of the image to decide the classification result and propose a novel medical image classification method 2D-I Neural Networks using Fuzzy Logic for data pre processing. © 2012 EuroJournals Publishing, Inc.

Shanmugasundaram O.L.,Anna University | Gowda R.V.M.,Anna University | Gowda R.V.M.,VSB Engineering College
Fibers and Polymers | Year: 2011

The bamboo yarn of Ne 40 s was used for the preparation of the Gauze fabric. The physical properties such as areal density and stiffness of fabrics were measured. The fabric was then scoured and bleached as per the standard procedure using distilled water. Chitosan-sodium alginate, Calcium-sodium alginate polymer and their mixture were coated separately on the gauze structure to improve the antibacterial and wound healing property of the bandage. Scanning electron microscope (SEM) analysis was carried out to observe the uniform distribution of polymers in the samples. The antibiotic drugs were selected based on the antibiotic sensitivity test. The drugs such as Tetracycline hydrochloride (250 mg), Chloramphenicol (250 mg) and Rifampicin (250 mg) were immobilized on the polymer coated fabrics to increase the rate of wound healing and antibacterial activity. The drug loaded samples were subjected to drug release study for about four days in a static condition. The results show that good amount of drug was released during all the four days. Further, the antibacterial activity of the drug loaded and polymer coated samples were evaluated against S. aureus and Proteus bacteria. The results show excellent antibacterial activity. © 2011 The Korean Fiber Society and Springer Netherlands.

Shanmugasundaram O.L.,Anna University | Mahendra Gowda R.V.,VSB Engineering College
Journal of Industrial Textiles | Year: 2012

This article deals with development and characterization of cotton and organic cotton flat knit bandages for wound healing. Bioploymers such as chitosan-sodium alginate, sodium-calcium alginate, and their mixtures were coated on the bandage and subjected to Fourier transform-infrared and scanning electron microscope analysis. Bacteria present in infected wound samples were identified using different bio-chemical methods. Three antibiotic drugs were selected based on the antibiotic sensitivity test and incorporated into the polymer-coated samples to improve the antibacterial and wound healing properties. Further, the antibacterial activities of the samples were evaluated against the identified bacteria in the wound for about 4 days. The strongest antibacterial activity was found in chitosan-sodium alginate-calcium alginate coated with chloramphenicol and tetracycline hydrochloride drug-loaded cotton and organic cotton samples. Hence, these bandages are suitable for quick wound healing process. © The Author(s) 2011 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.

Rajathi G.M.,Sri Ramakrishna Engineering College Coimbatore | Rangarajan R.,VSB Engineering College
European Journal of Scientific Research | Year: 2012

The major objective of the image enhancement techniques is to emphasize and sharpen the features of image for better display and investigation. It is the process of enhancing the quality of the image by applying the enhancement techniques to assist for the improvement of a solution to a computer imaging setback. As a result, the enhancement technique depends on the application and in practice it is developed empirically. It is the fundamental step which is used as a preprocessing step in computer vision applications, medical imaging, satellite imaging, and fingerprint identification, to ease the vision task. In this paper, proposed an enhanced adaptive wiener filter based on fast lifting wavelet transform by applying the thresholding. First step is to convert the noisy image into the wavelet domain with the use of Fast Lifting Wavelet Transform. Then the thresholding is applied in wavelet domain using VisuShrink and BayesShrink thresholding. After that, Lifting-based adaptive Wiener filter is applied to all the sub-band images. Finally, these sub-band images are inversely transformed to reconstruct the final improved image. From the simulation results, it is conformed that the performance of the adaptive Wiener filter with BayesShrink thresholding performs better in terms of peak-signal-to-noise-ratio (PSNR), execution time (ET) and Mean squared error (MSE) than the Wiener Filter, Adaptive Wiener Filter and adaptive Wiener filter with VisuShrink threshold. © 2012 EuroJournals Publishing, Inc.

Kayalvizhi P.,Vsb Engineering College | Selvi C.A.,Vsb Engineering College
Proceedings of 2015 IEEE 9th International Conference on Intelligent Systems and Control, ISCO 2015 | Year: 2015

Sharing of information with their friends on social networks has become an integral part in everyone's life. The post made by the social network user may have text, image and video. The previous approaches, [1] link anomaly detection method and [2] text-based anomaly detection method may not discover the dynamic post immediately as it concentrates on either links or text respectively, but the posts contain not only text or only links it may have images, videos or the combinations of links, text and image. The proposed model is to identify the new dynamic topics by analyzing the content of the message by extracting features of text, using [6] WordNet tool, this tool takes the words as synsets and the synonym, homonyms are identified The user may share the post by forwarding the post to their friends that may create a forward link. The normal behavior of user such as frequent forwarding friends list and the number of people on the list is considered for training model, future forwarding behavior is predicted and the anomalous behavior is detected using the training data set, from that the anomaly score is calculated. Aggregate the anomaly score from hundred users for each post, with that aggregated score and analyze the aggregated result with Sequentially Discounting Normalized Maximum-Likelihood (SDNML) coding [3] and Moving Average Convergence Divergence (MACD) burst-detection method [5] and pinpoint which post is about the dynamic topic that is discussed in a social network. In this approach, the change-point score is compared with the dynamically optimized threshold, if the score exceeds the threshold value that particular post will be pinpointed. © 2015 IEEE.

Sivakumar L.,Sri Krishna College of Engineering And Technology | Devi S.,Vsb Engineering College
Applied Soft Computing Journal | Year: 2014

There is a global challenge in demand and need of electricity. Whenever a serious fault occurs, it affects the productivity of any power plant. So many indicators have been identified in real-time fault diagnosis of steam turbine which is extremely important in a functioning power plant. Detection of fault and early rectification requires a real time intelligent fault diagnostic system. This paper considers seven types of very slowly happening and accumulating physical phenomena which will ultimately lead to deterioration in turbine performance. Based on the acquired domain knowledge, an online intelligent diagnostic analyzer for turbine performance degradation is designed in this paper by using a VLSI based methodology written in Verilog code and simulated using a simulator (Modelsim Altera 6.4a). This system can be easily implemented on to FPGA which enables the identification of the root causes for turbine performance degradation. The simulation results show that the developed real-time fault diagnostic system is accurate, high percentile with less time consuming, cost effective, and easy to apply and user friendly. © 2014 Elsevier B.V. All rights reserved.

Umamaheswari E.,Vsb Engineering College | Ghosh D.K.,Vsb Engineering College
International Journal of Engineering and Technology | Year: 2014

The software reliability is the significant factor to find out software failures in software development Life Cycle. The one more factor considered is the quality of software measurement process. These two factors are mostly considered for the possibility of execution of the software without failures in a software development life cycle. The software reliability and software quality cannot be predicted accurately because of its unsuccessful detection of failures in certain scenarios. This paper mainly focuses on improving the software engineering metrics using an expert opinion and in order to resolve the software failures. On choosing the software engineering measures there are different types of problem that are been occurred in that in this paper we have taken two main issues. The first issue is number of measures that are utilized in estimating software quality and these software measures are chosen with the help of expert opinion. However, the experts are humans so they may have less adequate knowledge about different software evaluations. The Problem is resolved by taking consideration with first level and second level of experts' opinion for selecting the best measures for software quality. The second issue is of data aggregation function which is not suitable for large number of data aggregations, here in this paper we select a prioritized opinion for data aggregation. The prioritization is based on number of experts involved in each life-cycle phase of software development with time duration to give the opinion. Finally the experiments results are shown for the software quality improvisation by the proposed framework.

Loading VSB Engineering College collaborators
Loading VSB Engineering College collaborators