| CmpE WEB

Blockchain Based Geostamping

A geostamp is a record of a geographic location with a timestamp. An Ethereum blockchain based data market will be developed where observers will be able to submit geostamps of moving entities and get paid for their usage by others.

Phenotype Prediction using Machine Learning based on Genomic Data

The human genome contains valuable information about the person and its hand analysis is cumbersome since it consists of billions of nucleotides. This work computationally analyses the mutations in the human genome which are the main source of differences and diseases. It utilizes ensembling of various feature selection models on an ALS dataset that is obtained from MinE Project and labels the genomes as ALS or non-ALS. The experiments display that the dataset is too small to derive solid rules with computational approaches.

Visualization of Time Series Data

In this project, I implemented a visualizing tool for time-series data. The data is read from the csv file and stored as a 3d tensor. This results in application being very memory efficient and fast compared to most other applications. Some of the most recent technologies were used for implementation such as electron, react and chartjs library.

Machine Learning Methods for Music Transcription

Music transcription is the transformation of a musical signal into either a human-readable, or a machine-readable form. Some trained people could achieve this task, with the help of their education and the human intuition. But it is very challenging to develop an automated transcriber, because we need to teach a machine to. We do not realize it often, but there is great mathematical harmony in music. So if we could figure out the aspects of this mathematics, it would be help us develop new technologies for the

Management Tool For Software Laboratories

Dealing with large number of computers sequentially in software laboratories (in terms of maintenance and performing other tasks) is time and energy consuming. Administrator accounts of central computers in laboratories has to be used by everyone to make or change states of computers if any mechanism for role differentiation does not exist. With this tool, computers can be suspended, shutdown, rebooted, and some programs can be enabled/disabled with just one-click concurrently. User roles are adjusted and users cannot go beyond their roles. Classroom addition is also possible.

Path Finding with AR Drone and Mobile Robot in the Campus

Unmanned aerial vehicles (UAV), known as drones, first arose from military purposes but through the last years it became very popular among the people. Now, drones are being used for commercial, scientific, agricultural, and other applications in many countries. We are using AR Drone Parrot 2.0 for our project. It can be controlled via a smart phone or a tablet and the footage can be seen at the screen simultaneously. We implemented a program for drone to follow a specific tag called "ar_marker".

Machine Learning Algorithms Used in Recommendation Systems

Recommendation systems help people by recommending items which suit their preferences. In collaborative filtering approach, methods recommend items to the users from other users whose past activities are similar to the recommendee users.In this project a review of collaborative filtering (cf) area on recommendation systems are given. After the review three models named SVD, Biased SVD and NNMF that are categorized under dimensionality reduction topic of model-based collaborative filtering models are implemented along with a simple naive bayes probabilistic model.

Applications of Hidden Markov Models

Predictive maintenance is one of many applications of HMMs and it has become an increasingly popular topic with the increase in the use of IIoT devices as they lets us get knowledge about the conditions of the systems. Besides detecting the current health and performance of the system, predicting the expected failure of a system is also possible with HMMs. Making these predictions accurately is extremely beneficial for industry since it decreases the maintenance costs significantly and lets the production continue without any interruption.

Proposing players for basketball teams

Each year thousands of transfers are happening in the sports industry and most of them are happening under the influence of managers who are not the part of the actual community. In other words who are not from the kitchen. This project aims to remove this influence and tries to offer coaches players depending on their tastes.

Turkish Sentiment Analysis on Twitter

My project is about analyzing current status of a person or institution or organization on society by using Twitter. What do people think about an institution? Is the general judiciary positive or negative? Or neutral? Twitter is a platform where people can instantly share their thoughts. Users around the world post around 350,000 new tweets every minute. This may create a big data about related person or institution or organization. When this data is analyzed emotionally, the result represents the general thought about that subject.

Arama formu

Main Menu