| CmpE WEB

Boun NLP: A Morphological Analysis System for Turkish

Morphological analysis is a very important sub-task of natural language processing. It is used for tokenization, stemming, lemmatization and normalization. For the NLP task in which machine learning approach plays a crucial role, pre-processing the data is vital and the success rate is highly dependent on the pre-processing methodologies. This project proposes a tool for morphologically analyzing words in Turkish which is an agglutinative language in order to constitute a baseline for the further NLP projects.

Recommendation System with Apache Spark

The aim of this project is to implement a movie recommendation system using apache spark. In the first phase of the project we learned how to use spark and installed it to our local machines. Then coded a recommendation algorithm using python. In the second phase, we hired 4 machines from Google Cloud and installed our application to cluster and run it in parallel to reach better time performance. And we focused on validating our test results.

Facial Age Estimation for Elderly

Age estimation is one research field of face analysis. Image-based age estimation can be defined as determination of a person's age from facial images. Estimating the age of the elderly from the images attempt came up from the interesting approach of the doctors of Alzheimer’s patients. It seems like most of the Alzheimer’s patients look younger than their actual age according to doctors’ observations. Until today, video data has been gathered from up to 20 people, each one older than the age of 65.

Product Validation and Verification using Raspberry Pi

In this project, we build a system for identifying and counting beverage cans inside commercial fridges by placing a hidden camera into the fridge. Camera is connected to a Raspberry Pi
located at the top of the fridge. The idea is that if an undesired product is detected or the arrangement does not fit a planogram, Raspberry Pi will notify the irregularity to a server. We
use Bag-of-Words algorithm with SVM classifier. Our training data consists of Coca Cola, Sprite, Nestea, Redbull cans. We test the system with different arrangements of cans in a fridge and

An interactive tool to visualize Nazım Hikmet's poetry

Digital Humanities is an area where computing and humanistic disciplines intersect. In this project, we intersect literature with computing by visualizing Nazım Hikmet’s poetry. We developed a visualization tool to explore the distinctive style of Nazım Hikmet, to examine the changes in his style over the years, and to enable scholars to query aspects of his oeuvre selectively. We combined text-mining methodologies and interactive visualizations for this purpose. A database is created from Nazım’s entire work to store and query both content and structure. We parsed the content,

An Augmented Reality Campus Tour iOS Application

We implemented an augmented reality campus tour application for iPhone. Also, we use some tools to design an 3D view of the campus. First of all we get 2D model of the campus from the “openstreetmap.org”. We get the gps location of each length of buildings and the campus itself in 2D view. By using them, we design the 3D model in CityEngine. In CityEngine, we design each building model one by one. To design more realistic buildings, we use real photos of the building to show walls of buildings in campus. Then, we create shapes of all buildings and pyramid in the

Learning by doing

Project is about creating a Virtual Reality work environment, in which player can enhance their abilities. With today’s technology it is possible to make realistic virtual worlds, so using this we can improve people’s abilities and decision making mechanisms in various situations. Starting a job without any experience can lead to psychological pressure, with this project we are aiming to reduce this anxiety and stress by creating a similar environment where user will work.

Sleep Quality Monitoring with the Smart Watch

Our objective for the project is to detect physical and biological changes occurred during the sleep and their relation with the sleep quality. There are different parameters and biological characteristics that affect the sleep quality such as body movements, heart rate, snoring, breathing rate and so on. Hence, for our project, we have used an off-the-shelf smart watch for data collection with its built-in sensors. Using linear regression, we can classify a person’s sleep with up to 80% accuracy.

Smart Watch Smoking Cessation Assistant

Over the past few years, there has been considerable research effort on the active research area directed towards the prevention of smoking, which has been called the single biggest preventable cause of death in the world.

Stress Detection with Smart Watch

In this project, we found correlation between heart rate, physical activity and stress level. We collect sensor data for stress level from the user. In addition, user gives us input from the watch about the instant stress he or she experiences, arousal and valence values. We process the raw data and come up with statistics and graphs for each user. Then, with knn algorithm on Matlab, we find accuracy percentages for each individual subject. By analyzing all inputs we get from the user with the heart rate data, we create groups of subjects as classification. We checked each group

Search form

Main Menu