| CmpE WEB

Sentiment Analysis

Opinions in natural language are mostly expressed in very complex manner. This makes very difficult for computer to completely understand a document written in a language. Sentiment analysis(opinion mining) refers to use of natural language processing to systematically identify, extract, quantify, and study these opinions. Since huge amount of information is available in on-line documents, obtaining some valuable information from these documents such as sentiments or opinions people express about a specific object is a task that attracts attention.

Scheduling for graduate applications

Scheduling is a fundamental issue that comes up in many different application areas and needs to be solved in the most optimal way possible given the problem parameters. MS and PhD application process in universities is no
exception. This study focuses on interview scheduling with a group of applicant students and university instructors based on a custom algorithm that avoids any conflict and makes exceptions for each instructor availabilities. It

A recommendation engine for cafés

The aim of the project is to develop a recommendation system for customers in a cafe with mobile devices. QR code activates the menu and meanwhile the recommendation algorithm executes. The menu comes with recommendation labels. The customer orders from the menu and rate the items ordered while leaving. Collaborative filtering is popular among recommendation systems. However, it has some problems like dependency on human ratings, sparsity and cold start problem.

Constructing Risk Map of Cyber Entities Belonging to Boğaziçi University in terms of Security

The object of my dissertation is identifying the ways to exploit vulnerabilities to defeat the security features of system components used in Boğaziçi University. The goal of penetration testing will be determining whether and how a malicious user can gain unauthorized access to assets that affect the fundamental security of the systems.

The scope of the project is:

Stochastic Volatility and Options Pricing

Option is a crucial phenomenon for investors to make profitable moves in their trades. They need to know at which price they should trade stocks, i.e underlying securities. Options are derivative contracts giving the holder the right of buying or selling shares of a stock at a price (strike or exercise) upon which both parties(writer and holder) agree. Depending on the strategy, option trading can provide a variety of benefits, including the security of limited risk and the advantage of leverage.

A web-based database for protein-ligand interactions

This project is related to protein-ligand interactions which are important for drug design studies. In this project, the team has coded different scripts which can be used for data extraction, network construction of protein-protein interactions. For these scripts, a user-friendly website has to be created for data extraction and network construction of protein-protein interactions by using protein-ligand interactions for a selected protein family. Designing such a website is so beneficial for the users who do not have any programming skills.

Object Classification with Deep Learning on Theano

Machine Learning is a trend topic that aims to solve problems about future by learning the past. Everyday we generate data about our actions and mostof it is stored in some storages. Evidently, tendency of human actions are the similar for ages. People try to act according to what they have learned until now. We can expand the term by examining the usage on computers. With Machine Learning, we are able to use past data to find out a meaning.

Topic Modeling for Twitter Accounts

Makers, scientists, influencers and many other people share their ideas, products and innovations via the most intellectual social network Twitter. It is hard to find the information about a topic in the giant network of Twitter. Our aim is to find users who are tweeting about the same topic. With this aim we want to bring people interested in the same community together. In this project, we focused on maker communities and influencers in the context of computer science, such as ML, Robotics, 3D Printing, Arduino.

Emre Erdoğan YL tez savunması

Infant Cry Classification

Recently, researches have been invested into developing automated methods to recognize baby's need using a short audio recording of its live cry. In this project, we report the initial results those we obtained by applying machine learning methods that were successfull in language recognition domain to the task of infant cry classification.

Arama formu

Main Menu