Seema Kolkur

Followers

Following

Public Views

David Seamon

Kansas State University

Armando Marques-Guedes

UNL - New University of Lisbon

Sebastian Heath

New York University

Roshan Chitrakar

Nepal College of Information Technology

Lev Manovich

Graduate Center of the City University of New York

Hatice ŞİRİN

Ege University

Viacheslav Kuleshov

Stockholm University

Bogdan Gabrys

University of Technology Sydney

PALIMOTE JUSTICE

RIVERS STATE POLYTECHNIC

Bálint Molnár

Eötvös Loránd University

Interests

Uploads

Papers by Seema Kolkur

Web Search Relevance Ranking

SpringerReference

Effective Classroom Monitoring by Facial Expression Recognition and Ensemble Learning

Face Detection and Recognition of facial expressions is crucial to many applications in real time... more Face Detection and Recognition of facial expressions is crucial to many applications in real time. A great deal of improvement is made in these areas due to recent concepts of deep learning and abundant datasets available online. The purpose of this paper is to propose a deep learning model along with ensemble learning to further improve the results of face detection and recognition system .Mere presence of a student in a classroom does not merit his/her attention towards the material taught in it. So, the trained model is further extended to a full-fledged classroom monitoring system which can help both students and teachers for effective teaching learning process. The system can recognize students facial expression and based on that can determine how long each student was focusing in class. Also the system can automatically mark a student present in a class. Our system delivers promising results.

Intelligent Document Parser with Zonal OCR and Text to Speech

Optical character recognition (OCR) is well researched and heavily used technology in the field o... more Optical character recognition (OCR) is well researched and heavily used technology in the field of image processing and computer vision. With the advent of technology, we need to digitize different documents every day and hence OCR is used in many applications in recent years. It is a method of converting a scanned image into text. OCR looks at each line of the image and attempts to determine if the black and white dots represent a particular letter or number. However traditional OCR considers a document as a whole, but in some cases, we may be interested only in the specific part of the document. Zonal OCR is used for this purpose. Our system gives a solution to all document parsing needs. Along extraction of data it provides facilities of data sharing, spell checking and text to speech.

Sentiment Analysis for Product Reviews

International Journal of Advanced Research in Computer Science, 2014

With the rapid expansion of e-commerce over the past years, more products are sold on the Web, an... more With the rapid expansion of e-commerce over the past years, more products are sold on the Web, and more and more people are buying products online. In order to enhance customer shopping experience, it has become a common practice for online merchants to enable their customers to write reviews on products that they have purchased. An increasing number of people are writing reviews. As a result, the number of reviews that a product receives grows rapidly. Manual analysis of customer opinions is very time consuming due to the multitude of contributions. So the sentiment analysis is use to extract, aggregate and analysed the opinions on product from discussion forums. In this paper, Sentiment analysis for product reviews is proposed which uses Advanced Naive Baysian Algorithm technique to find whether the reviews are positive or negative. Keywords: Sentiment Analysis, Naive Baysian algorithm

Data Mining Evolutionary Learning (DMEL) using H base

International Journal of Computer Trends and Technology, 2016

In current market scenarios, telecom companies are quite competitive and look forward to have lio... more In current market scenarios, telecom companies are quite competitive and look forward to have lion’s share in the market by winning new and withholding existing customers. Customers who are lost to competitor are known as Churned customers and can be retain by adopting Churn prevention model. For a given dataset, this model predicts the list of customers to be churned in future enabling the respective authorities to take action accordingly. However in telecom, the results of algorithms suffer due to disproportion nature and vast size of datasets. In this paper, Genetic Programming (GP) based approach for modelling the challenging problem of churn prediction is incorporated in HBASE. A data mining algorithm, Data Mining Evolutionary Learnings (DMEL), handles a classification problem which helps to meet accuracy of prediction. As data in telecom industry is going to increase so to make the classification process fast DMEL algorithm is incorporated in HBase. For competitive telecom ind...

Web Data Extraction Using Tree Structure Algorithms - A Comparison

Nowadays, Web pages provide a large amount of structured data, which is required by many advanced... more Nowadays, Web pages provide a large amount of structured data, which is required by many advanced applications. This data can be searched through their Web query interfaces. The retrieved information is also called 'deep or hidden data'. The deep data is enwrapped in Web pages in the form of data records. These special Web pages are generated dynamically and presented to users in the form of HTML documents along with other content. These webpages can be a virtual gold mine of information for business, if mined effectively. Web Data Extraction systems or web wrappers are software applications for the purpose of extracting information from Web sources like Web pages. A Web Data Extraction system usually interacts with a Web source and extracts data stored in it. The extracted data is converted into the most convenient structured format and stored for further usage. This paper deals with the development of such a wrapper, which takes search engine result pages as input and conv...

Convolution Neural Network Classifier for Skin Disease Detection

Indian journal of applied research, 2018

Skin Diseases are becoming very common now days. Number of people suffering from skin diseases is... more Skin Diseases are becoming very common now days. Number of people suffering from skin diseases is increasing rapidly. Human judgment on diagnosis of skin diseases is sometimes subjective and not reproducible. To achieve more reliable and objective accuracy computer aided diagnosis may be used. Skin disease detection is basically an image classification task. Recently deep learning is used in many image classification tasks. We usedConvolution Neural Network (CNN)as a classifier. The results indicate CNN can be feasibly used for skin disease detection.The main advantage of CNN is that we don’t need to hand craft features from images,but it learns features on its own.

Convolution Neural Network for Feature Extraction in Skin Disease Detection

Skin Diseases are becoming very common now days. Number of people suffering from skin diseases is... more Skin Diseases are becoming very common now days. Number of people suffering from skin diseases is increasing rapidly. Human judgment on diagnosis of skin diseases is sometimes subjective and not reproducible. To achieve more reliable and objective accuracy computer aided diagnosis may be used. With advancement in medical imaging, image based classification is been increasingly used for disease detection in medical field. Feature engineering is very important for any classifier to achieve maximum results. Convolution Neural Networks (CNN) can learn features on its own reducing total time required for development of such systems and at the same time increasing level of accuracy. We acquired more than 850 original images for two skin diseases from department of Skin and VD, KEM Hospital, Mumbai. We have used CNN for feature extraction from input images of two skin diseases. These features are fed to Support Vector Machine (SVM) for classification. The results indicate CNN can be feasib...

Review of Web Spam Detection Techniques

Web spam or search engine spam denotes the manipulation of web pages with the intention of improv... more Web spam or search engine spam denotes the manipulation of web pages with the intention of improving their position in search engine results. Spammers use many techniques such as content spam, link spam or a combination of both. Detecting spam in search engine results has been a challenging task for search engines. This paper presents a review of three different approaches for detecting web spam. The first approach deals with language modeling that involves building a language model from different sources of information extracted from web pages. The second approach deals with checking the reliability of links, that is, the ability of a search engine to find, using information provided by the page for a given link, the page that the link actually points at. The third approach deals with the topology of a web graph by exploiting the link dependencies among the Web pages.

Seema Kolkur

Related Authors

Uploads

Papers by Seema Kolkur

Log In