Completed

In this project, relation extraction in Turkish text will be implemented using pattern matching and supervised machine learning techniques. First, the existing literature will be reviewed. Then, a corpus will be collected and the relation types that will be extracted will be identified. This will be followed by developing different types of algorithms for extracting the relations.

As a consensus mechanism the system should deter the denial of service attacks by requiring some work from the client processing time. The work must be based on the network bandwidth pricing function.

Video: https://drive.google.com/file/d/1XAhWZMK7HrnbJ-p_MRn4QB4zkv02E-pL/view?u...

We have developed a system which integrates IoT data market with Blockchain. The system allows IoT data producers to sell their IoT data such as pressure and light sensor data from Android devices in the Blockchain network and ML service providers will be able to access the IoT data in a decentralized way. We have used solidity language for our my smart contract and React for the development of front-end service.

Building models that can generalize and reproduce desired tasks will  enable the robots to learn and do more, which will make our lives  easier. The aim of this project is to build such a model, able to  learn and reproduce different tasks. We chose Learning from  Demonstration as the way of teaching and we used Hidden Markov Models  (HMM) with a modified version of Gaussian Mixture Regression (GMR) in  order to teach a robot multiple types of trajectories together, with a  small number of demonstrations for each.

Morning routines of people differ from each other and include some similarities. On this topic, various practices and studies have been performed. We studied on sleep quality of users and connected it with morning schedule. On one hand, we measured sleep actions of users. Our experiment provided us useful data to analyze and comment sleep quality of users. We defined sleep cycles for users and calculated an appropriate alarm clock. User should define a gap time before alarm clock for early wake up.