Since the so-called Web 2.0 has arrived, user-generated content has become an expected behavior on the Web. Commenting, rating and other types of contributions are widespread. While users are able to provide content (unlike in Web 1.0), they still can not introduce user-generated behavior. In other words, their contributions are limited to the designs of the application builders.
This is a project which evolves Turkish text classification of two different classes (Financial texts or Random Wikipedia texts) and their prediction results. As a classifier, Logistic regression is used. The intention of this project is to successfully identify the texts which contain financial news or data about companies from the other texts which are in random topics. The importance of the financial news documents can be understood if we look at the correlation between the stock price of a company, and the publicly published news about this company.
With the widespread of Internet and social media, the information flow growth unboundedly and without control . So there are much more disinformation today than a copule years ago . One of the most common widespread wrong information type is poems that actually do not belong to the author specified in the social media post or anywhere else on the Internet. Our application uses machine learning to detect author of the Turkish poems.
Facial Age Estimation for Elderly mainly aims to analyze whether the Alzheimer’s patients look younger than their age or not using the data set gathered from Çapa Hospital. As a start, this 491 project develops methodology of feature extraction and regression using another data set to have an insight on the study beforehand. Using ELM with LBP and HOG visual descriptors.
Digital Humanities is an area where computing and humanistic diciplines intersect. In this project, we intersect literature with computing by visualizing Nazım Hikmet’s poetry. The project is intended to notice the distinctive parameters of style of Nazım Hikmet, examine the change of his style among his works by applying text-mining methodologies to analyze and show the results of our analysis by using an interactive visualizations. Our goal is developing an interactive tool where users can see various visualization reated using Nazım’s works.
Beta lactamase antibiotics are one of the widely used antibiotics in the world. They constitute over 50% of the worldwide antibiotic usage and used for bacterial infections. So to find and develop better solutions to bacterial infections, we need to study on Beta lactamase and collect all the information. In this project we aim to create a database that has all the information from worldwide about beta lactamases.
Time series analysis is used to estimate and predict behaviour of time dependent processes. In this project we have made use of two stochastic volatility models: Univariate Stochastic Volatility Model, and Multivariate Stochastic Volatility via Wishart Distribution. We estimated their parameters using combinations of MCMC methods, which are mainly Metropolis-Hastings Algorithm and Gibbs sampler. The work done gave us tools to estimate time dependent variance structure of the time series.
