Department of Information Technology

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/161

Browse

Now showing 1 - 16 of 16

ANALYZING HUMAN SKIN TEXTURE USING MACHINE LEARNING APPROACHES
(International Journal of Computer Applications, 2016-02) M, Preethi; K, Sathiyakumari
Analysis of skin texture is very useful for creation and development of cosmetic products, skin texture modeling, and face recognition in security applications and also computer assisted diagnosis in dermatology. Several types of skin diseases are increasing human begins daily life; to deal with an effective and also very important manner the disease must be diagnosed properly. Skin texture analysis is one of the major problems in the field of medical diagnosis for finding skin diseases. Hence, the texture of skin is analyzed based on various features and characteristics so that the inconsistencies can be avoided during the treatment. The main goal of this study was to examine the texture of the human skin by image processing method. The skin properties like skin oiliness, dryness, pigmentation, fungus, infection, allergic symptoms and itching kind of problems association with skin texture profile is debated in the proposed work. Skin images are preprocessed using various pre-processing techniques and the Texture Filtering method is used for segment the skin textures so it can easy to identifying the skin properties accurately. Finally machine learning techniques are used to analyze and categorize the skin textures based on the texture and shape features. The experimental result shows that Decision Tree algorithm outperforms well in categorizing skin textures.
BACKLINK ANALYSIS USING MOZRANK ALGORITHM OF BLOGS
(The International Journal of Computer Science & Applications, 2012-11) S, Geetha; K, Sathiyakumari
Social networking has become very popular during the past few years, but it can still very difficult to understand for someone new to social networking. Social networking is based on a certain structure that allow people to both express their individuality and meet people with similar interests. This structure includes having profiles, friends, blog posts, widgets, and usually something unique to that particular social networking website such as the ability to ‘poke’ people on facebook or hi5. Blogs is another feature of some social networks is the ability to create own blog entries. While not as feature rich as blog hosts like wordpress or blogger, blogging through a social network is perfect for keeping people informed on own information. This paper represents a web page ranking algorithm using mozrank algorithm for blog searching and the ranking web sites. In this algorithm can be using online tool. The majesticseo and open site explorer using blog page ranking with the mozrank algorithm. Blog search engine uses the page rank algorithm to assign quantitatively authority values to blog web pages in a network.
BRAIN STROKE SEGMENTATION USING FUZZY C-MEANS CLUSTERING
(Foundation of Computer Science, 2016-11) S, Keerthana; K, Sathiyakumari
Image processing technique plays an important role in medical science for envisage various phenomenal structure of human body. Even though it helps more, sometimes it’s very difficult to detect abnormal structures of human body by using simple images. Magnetic Resonance Imaging (MRI) is the one of the most significant technique to analyze human body and helpful for distinguishing and expounding the neural architecture of human brain effectively. This proposed strategy focus on detection and extraction of brain stroke from different patient’s MRI images. In this work some preprocessing techniques like noise removal, filtering and segmentation is used for extract brain stroke partition accurately. The segmentation of brain stroke is implemented by using Fuzzy C-Means (FCM) clustering with two different levels of extraction. Edge detection is used for finding segmented portion of brain stroke edges accurately. Finally the stroke size is calculated for help doctors to make effective decisions about brain stroke. The experimental result proven that the proposed method is successful in detecting and extraction brain stroke efficiently with less time.
A BRIEF STUDY OF IMAGE PROCESSING AND TECHNIQUES
(CiiT International Journal of Digital Image Processing, 2017-02) S, Keerthana; K, Sathiyakumari
The development of digital image processing is closely tied to the development of the digital computers. Because of its nature, digital image requires lot of storage space and their processing needs so much computational power that progress in the field of digital image processing had been highly dependent on the development of modern digital computer which came only in 1940s. This paper is a complete review of various image processing techniques and large number of related application in diverse disciplines, including medical, biometrics, moving object tracking, vehicle detection & monitoring, document analysis and retrieval, outdoor surveillance, remote sensing and Traffic queue detection algorithm for processing various real time image processing challenges. Techniques discussed segmentation, edge detection and corner detection also application areas and their future scope are explained. The intension of this paper is useful to researchers and practitioners interested in real time image processing.
CLASSIFICATION OF UNWANTED MESSAGES IN ONLINE SOCIAL NETWORK USING MACHINE LEARNING ALGORITHMS
(International Journal of Computer Trends and Technology, 2013-08) B, Padma Priya; K, Sathiyakumari
This One major fact in today's technical world, people are very active users of Online Social Networks. They share every details of their day to day life and are in touch with their loved ones no matter in which part of the world they live. The main issue is the ability to control the messages that are posted in the user's private message or walls to detect and negotiate unwanted messages. This work focus on predicting the emotions of a particular message or post in various OSN like twitter, blogs etc for emotion analysis so as to filter the messages which are inappropriate. This paper focuses on collecting corpus for sentimental analysis and performs linguistic analysis and machine learning techniques for predicting emotions accurately. Using the corpus we define distinct emotions and filter unwanted messages.
A COMPARATIVE STUDY OF FUZZY MODELS IN DOCUMENT CLUSTERING
(International Journal on Computer Science and Engineering, 2012-11) G, Manimekalai; K, Sathiyakumari; V, Preamsudha
The availability of large quantity of text documents from the World Wide Web and business document management systems has made the dynamic separation of texts into new categories as a very important task for every business intelligence systems. Text document clustering is one of the emerging and most needed clustering techniques used to cluster documents with regard to similarity among documents. It is used widely in digital library management system in the modern context. Document clustering is widely applicable in areas such as search engines, web mining, information retrieval, and topological analysis. There are several clustering approaches available in the literature to cluster the document. But most of the existing clustering techniques suffer from a wide range of limitations. The existing clustering approaches face the issues like practical applicability, very less accuracy, more classification time etc. Thus a novel approach is needed for providing significant accuracy with less classification time. In recent times, inclusion of fuzzy logic in clustering provides better clustering results. One of the widely used fuzzy logic based clustering is Fuzzy C-Means (FCM) Clustering. In order to further improve the performance of clustering, this thesis uses Modified Fuzzy C-Means (MFCM) Clustering. The documents are ranked using Term Frequency–Inverse Document Frequency (TF–IDF) technique. From the experimental results, it can be observed that the proposed technique results in better clustering when compared to the FCM clustering technique.
A COMPARATIVE STUDY OF MACHINE LEARNING ALGORITHMS APPLIED TO PREDICTIVE DIABETES DATA
(CiiT International Journal of Data Mining Knowledge Engineering, 2009-11) C, Deepa; K, Sathiyakumari; V, Preamsudha
Healthcare industry encompasses abundant data, which is increasing everyday. Conversely, tools for analyzing these records are incredibly less. Machine learning provides a lot of techniques for solving diagnostic problems in a variety of medical domains. Intelligent systems are able to learn from machine learning methods, when they are provided with a set of clinical cases as training set. This paper aims at a comparative study of widely used supervised classification algorithms – Naïve Bayes, Multi Layer Perceptrons, Logistic Model Trees, and Nearest Neighbor with Generalized Exemplars applied to predictive diabetes dataset. The machine learning algorithms used in this study are chosen for their representability and diversity. They are evaluated on the basis of their accuracy, learning time and error rates.
ENSEMBLE LEARNING TECHNIQUES FOR APPENDICITIS PREDICTION
(International Journal of Computer Applications, 2017-04) K, Sathiyakumari
Appendicitis leftovers the most common cause of decrease belly ache. It retains a common look at all ages. The appendix is an attachment or adjunct like shape. it's miles a wormlike stomach diverticulum extending from the blind cease of the cecum; it varies in period and leads to a blin extremity. Early and correct analysis of appendicitis can lower the contamination and clinic cost by using lowering the put off in prognosis of appendicitis and its related headaches. accurate prognosis of appendicitis is a tough trouble in exercise especially if the patient is just too young or pregnant girls in that radiological check have excessive risk. thus, ultrasonography image evaluation is a good way to reduce the problem. This work affords an attempt to diagnose the appendicitis with the aid of extracting appendix of different levels from the stomach ultrasound picture. Diverse filtering techniques like LEE and FROST strategies are used for noise removal and Marker-controlled Watershed method is used for segmentation of appendicitis. The vicinity of interest (ROI) approach is used to extract the accurate portion of appendix photograph. The feel functions of the segmented ROI are Gary degree Co-prevalence Matrix (GLCM) and form capabilities are extracted for the future cause of classifying appendicitis. In the end, the ensemble gaining knowledge of set of rules is used to classify appendicitis appropriately via the use of an AdaBoost technique. The AdaBoost technique is evaluated the usage of various measures like Resubstitution Loss mistakes, Generalization mistakes, cross-Validation errors, and schooling errors. It gives very low loss errors rate.
LINK PREDICTION MODEL FOR PAGE RANKING OF BLOGS
(International Journal on Computer Science and Engineering, 2012-11) S, Geetha; K, Sathiyakumari
Social Network Analysis is mapping and measuring of relationships and flows of information between people, organizations, computers, or other information or knowledge processing entities. Social media systems such as blogs, LinkedIn, you tube are allows users to share content media, etc. Blog is a social network notepad service with consider on user interactions. In this paper study the link prediction and page ranking using MozRank algorithm using blog websites. It finds out how all the websites on the internet link to each other with the largest Link Intelligence database. As link data is also a component of search engine ranking, understanding the link profile of Search Engine positioning. Here the MozRank algorithm is using backlinks from blog websites and linking websites quality. Good websites with many backlinks which linking the corresponding WebPage give highly value of MozRank. MozRank can be improved a web page's by getting lots of links from semi-popular pages or a few links from very popular pages. The algorithm for page ranking must work differently and MozRank is more comprehensive and accurate than Goggle’s page rank. Another tool is Open Site Explorer that is ability to compare five URL's against each other. Open Site Explorer’s Compare Link Metrics option is how one measures page level metrics, the other domain. This result can help to generate a chart form for the comparative URLs. A comparison chart of the important metrics for these pages is shown which makes it very clear and easy to compare the data between the five URL's.
PREDICTING LINK STRENGTH IN ONLINE SOCIAL NETWORKS
(International Journal of Engineering Research and Applications, 2012-12) R, Hema Latha; K, Sathiyakumari
Social Media is a term that encompasses the platforms of New Media, but also implies the inclusion of systems like Facebook, and other things typically thought of as social networking. The idea is that they are media platforms with social components and public communication channels. Social media are primarily Internetbased tools for sharing and discussing information among human beings. Data mining (the analysis step of the “Knowledge Discovery in Databases” process, or KDD), is the process that attempts to discover patterns in large data sets. The overall goal of the data mining process is to extract information from a data set and transform it into an understandable structure for further use. It involves database and data management aspects, data preprocessing, model and inference considerations, interestingness metrics, complexity considerations, postprocessing of discovered structures, visualization, and online updating. Link prediction in Facebook and Twitter can be done at a familiar class of graph generation model, where the nodes are united with locations in a latent metric space and connections are more likely between closer nodes. In this paper, Gephi tool is used to predict the link of Facebook.
PREDICTION OF THE COMPRESSIVE STRENGTH OF HIGH PERFORMANCE CONCRETE MIX USING TREE BASED MODELING
(International Journal of Computer Applications, 2010-09) C, Deepa; K, Sathiyakumari
Concrete is the safest and sustainable construction material which is most widely used in the world as it provides superior fire resistance, gains strength over time and gives an extremely long service life. Its annual consumption is estimated between 21 and 31 billion tones. Designing a concrete mix involves the process of selecting suitable ingredients of concrete and determining their relative amounts with the objective of producing a concrete of the required, strength, durability, and workability as economically as possible. According to the National Council for Cement and Building Materials (NCBM), New Delhi, the compressive strength of concrete is governed generally, by the water-cement ratio. The mineral admixtures like fly ash, ground granulated blast furnace, silica fume and fine aggregates also influence it. The main purpose of this paper is to predict the compressive strength of the high performance concrete by using classification algorithms like Multilayer Perceptron, M5P Tree models and Linear Regression. The result from this study suggests that tree based models perform remarkably well in predicting the compressive strength of the concrete mix.
SUPERVISED LEARNING APPROACH FOR BRAIN STROKE CLASSIFICATION USING DEEP LEARNING TECHNIQUES
(International Journal of Research in Engineering and Technology, 2016-10) S, Keerthana; K, Sathiyakumari
This research present the detection and segmentation of brain stroke using fuzzy c-means clustering and H2O deep learning algorithms. Brain stroke segmentation in magnetic resonance imaging (MRI) has become an evolving research area in the field of a medical imaging system. Brain stroke detection helps in finding the exact size, shape, extraction and location of the stroke. The system is consisting of three stages to detect and segment a brain stroke. An efficient algorithm is proposed for stroke detection based on segmentation and preprocessing techniques. The firstly quality of a scanned image is enhanced and then preprocessing techniques are applied to detect the stroke in the scanned image. In this system film artifacts removal, skull extraction and filtering methods are used to enhance the image. The second stage preprocessed image is segmented using fuzzy c-means clustering to obtain stroke region and edges are detected for accurate prediction of stroke location. After that edge detection operator is applied for boundary extraction and to find the size of the stroke, which helps doctors to make a decision about stroke location, size and etc. Finally, H2O deep learning method is used to classify stroke based on texture features and statistical features. The experimental result shows that the proposed work is performed well in detecting brain stroke efficiently.
SURVEY ON LINK PREDICTION AND PAGE RANKING IN BLOGS
(International Journal of Engineering Research and Applications, 2012-10) S, Geetha; K, Sathiyakumari
This paper presents a study of the various aspects of link prediction and page ranking in blogs. Social networks have taken on a new eminence from the prospect of the analysis of social networks, which is a recent area of research which grew out of the social sciences as well as the exact sciences, especially with the computing capacity for mathematical calculations and even modelling which was previously impossible. An essential element of social media, particularly blogs, is the hyperlink graph that connects various pieces of content. Link prediction has many applications, including recommending new items in online networks (e.g., products in eBay and Amazon, and friends in Face book), monitoring and preventing criminal activities in a criminal network, predicting the next web page users will visit, and complementing missing links in automatic web data crawlers. Page Rank is the technique used by Google to determine importance of page on the web. It considers all incoming links to a page as votes for Page Rank. Our findings provide an overview of social relations and we address the problem of page ranking and link prediction in networked data, which appears in many applications such as network analysis or recommended systems.
A SURVEY ON VARIOUS APPROACHES IN DOCUMENT CLUSTERING
(International Journal of Computer Technology and Application, 2011-09) K, Sathiyakumari; G, Manimekalai; V, Pream Sudha
Document clustering is the process of segmenting a particular collection of texts into subgroups including content based similar ones. The purpose of document clustering is to meet human interests in information searching and understanding. Nowadays all paper documents are in electronic form, because of quick access and smaller storage. So, it is a major issue to retrieve relevant documents from the larger database. Text mining is not a standalone task that human analysts typically engage in. The goal is to transform text composed of everyday language in a structured, database format. In this way, heterogeneous documents are summarized and presented in a uniform manner. Among others, the challenging problems of document clustering are big volume, high dimensionality and complex semantics.
A TREE BASED MODEL FOR HIGH PERFORMANCE CONCRETE MIX DESIGN
(International Journal of Engineering Science and Technology, 2010-02) C, Deepa; K, Sathiyakumari; V, Pream Sudha
Concrete is the sustainable construction material, which is most widely used in the world as it provides superior fire resistance, gains strength over time and gives an extremely long service life. Its annual consumption is estimated between 21 and 31 billion tones. The paper is aimed at guiding the selection of available materials and proportioning them as to produce the most economical concrete suitable for the desired purpose. According to the National Council for Cement and Building Materials (NCBM), New Delhi, the compressive strength of concrete is governed generally, by the water-cement ratio. The mineral admixtures like fly ash, ground granulated blast furnace, silica fume and fine aggregates also influence it. The main purpose of this paper is to find the accuracy for the compressive strength of high performance concrete by using classification algorithms like Multilayer Perceptron, Rnd tree models and C-RT regression. The result from this study suggests that tree based models perform remarkably well for designing the concrete mix.
UNSUPERVISED APPROACH FOR DOCUMENT CLUSTERING USING MODIFIED FUZZY C MEAN ALGORITHM
(International Journal of Computer& Organization Trends, 2011-11) K, Sathiyakumari; V, Pream Sudha; G, Manimekalai
Clustering is one the main area in data mining literature. There are various algorithms for clustering. There are several clustering approaches available in the literature to cluster the document. But most of the existing cluring techniques suffer from a wide range of limitations. The existing clustering approaches face the issues like practical applicability, very less accuracy, more classification time etc. In recent times, inclusion of fuzzy logic in clustering results in better clustering results. One of the widely used fuzzy logic based clustering is Fuzzy C-Means (FCM) Clustering. In order to further improve the performance of clustering, this thesis uses Modified Fuzzy C-Means (MFCM) Clustering. Before clustering, the documents are ranked using Term Frequency–Inverse Document Frequency (TF–IDF) technique. From the experimental results, it can be observed that the proposed technique results in better clustering results when compared to the existing technique