| CmpE WEB

Log Analysis of Boğaziçi University Dining Halls

This project is about visualizing the log data of Boğaziçi University’s dining halls. Eating habits of the individuals change with many reasons. Several researches have been done to investigate these habits and results show that the decisions on eating can be stereotyped. People tend to eat healthy and tasty meals and for some reasons the time that they spend on eating changes time to time.

A System for Social Text Normalization

Social media along with the Web is growing and extending. Text in social media has its own grammatical rules and way of using words. For example a social media user can use a sentence like “I like u w you smiiiile”. This kind of text is hard to process with natural language processing tools and use in analyses. Therefore a normalization task for this social media text is essential to be able to process this huge data generated by social media users all around the world.

Stress Detection with Smart Watch

The project is about stress detection using the data gathered by the smartwatch, focusing on the students and the stress they have been living through, especially when they are about to face examinations, mainly midterms and finals

Processing Data ow Graphs of SQL Queries

As SQL queries can be represented as data ow graphs, performance gain can be achieved in a multiprocessor architecture by taking advantage of the parallelism inherent in the graph structure. The aim of the project is to extend upon the work of Can Guler's Data ow Graph Generation From an SQL Query [1] to develop tools necessary for automatic scheduling.

Analysis and Visualization of Time Series

Data visualization and data analysis have become such important topics in our age with the huge boom in produced data. In our project, we wanted to develop an interactive visualization platform for time series data. We used multi-way arrays (also called as tensors) to store time series data in different entities and we used D3.js library to visualize those arrays. We filled missing data in the dataset with cubic spline interpolation. In the responsive platform we built, users can upload their own datasets and choose different tensor combinations for different visualizations.

Analysis of Graduate Studies Application Data

Free formatted and non-standardized data can be a problem when it comes to process and extract information. Free format can contain misspellings, different representation of same attribute, non-comparable and heterogeneous data. This paper mainly focuses on analysis of graduate studies data which requires cleaning and correcting using “keyword detection” and standardization. Analysis is done by grouping candidates according to some criteria which can be dynamically decided by user. Pattern recognition; instance matching, translation and conversion and clustering methods are used.

Baxter the Robot Helper: Inferring and Achieving Others' Goals in Altrustic Robots

Altruism (n): (Merriam-Webster Dictionary)
1. unselfish regard for or devotion to the welfare of others,
2. 2. behavior by an animal that is not beneficial to or may be harmful to itself but that benefits others of its species.

Parallel Simulation Framework for Nanonetworking

Nanonetworking is a new communication paradigm in computer networks, which gained interest in last decade. Nanonetworks differ from traditional computer networks in terms of communication characteristics. Therefore, new approaches are presented which needs testing and simulation. Current simulators are of course capable of simulating molecular world but they are not in the context of nanonetworking. Hence in this area, a need for a simulation toolbox has arisen.

Financial Analysis Using Machine Learning Methods

Machine Learning methods have long been applied to financial data. We explore the correlation (or the lack thereof) of financial data, such as the BIST 100 index or individual stock prices, to features extracted from financial news and past data. We intend to use the advancements in text classification and Natural Language Processing capabilities in general, and machine learning models to extract the features of Turkish news documents and stock price series using statistical methods and to analyze the correlation of the extracted features with the financial data.

Chrome Extension for Spam Detection

Nowadays, spam contents in the internet could be really annoying and harmful while surfing the internet. There are some approaches to find a solution for that problem. However, those does not focus on natural language processing approach and does not give much credit for the machine learning techniques.

Arama formu

Main Menu