2023 – 2024
PATHFINDER
Detecting Post-Disaster Undamaged Roads by Analysing UAV and Satellite Images with Machine Learning Methods and Finding the Shortest Path to the Target
D’ASAP: DISASTER AUTOMATIC SITUATION ANALYSIS PROJECT
People often use Twitter after a disaster who cannot reach the search and rescue organizations. A project that detects and classifies disaster-related tweets posted on Twitter after a disaster. D'ASAP will use tweets sent after the disaster. First classification is disaster type. Second classification is disaster related requirements. Information can be quickly sent to search and rescue organizations (such as AFAD). Many lives can be saved.
IoT-Based Incubator Monitoring and Machine Learning Powered Alarm Predictions
The system proposed in this work concerns real-time monitoring of changes in the incubator environments using temperature, humidity and gas sensors. The data from these sensors are sent to a mobile application via BLE, and to a cloud server via Wi-Fi using microcontroller hardware. The past and present measurement values are displayed both on mobile device’s display and on the Webpage. Furthermore, predefined alarm conditions and machine learning-powered alarm predictions allow for rapid intervention.
2022 – 2023
VOTEMAT: A Blockchain Based Voting System
The electronic election system that is based on Blockchain is called VOTEMAT. With the help of VOTEMAT, the voters will have the chance to cast their votes with their smartphones or computers without going to the voting center. It is aimed to increase participation in the elections with the realization of the voting with mobile phones. There is no central authority in the VOTEMAT. Because of this, the hacking risk in the electronic elections will be minimized. Voters will vote by installing the mobile application of the VOTEMAT from app store. They will use the National Identification Number (ID Number) or E-Government Password to login to the mobile application. They will confirm the PIN that will be sent to them in the Application after the process of the login. With the registration of the identification of the chain. The electronic vote of the voter will take place at the end of the elections. In the electronic voting of the voter; the vote will be cut by the user and placed into the region of the box to be send.
CCC: Campus Crypto Coin
A Campus Blockchain Framework for Motivating Students to Study More. In the proposed system, on campus virtual currency CCC (Campus Crypto Coin) is defined as a Blockchain created on a Web server. The application on the mobile phone of the student studying in the library communicates with the Web server and the amount of virtual money directly proportional to the student's study time is added to the student's account in the Blockchain. Students can spend the virtual money they earn by studying in the cafeteria and canteens.
PROFILER
Profiling daily living patterns of vulnerable adults and anomaly detection by collecting motion data and using machine learning
2021 – 2022
TELEMEDICINE
Continuous track of heart beats, oxygen saturation in blood, and position/moves of vulnerable adults at home. Emergency situation detection. No need for patients to visit surgeries and hospitals. No need for physicians being in the same room with the patients for diagnosis.
EEG CONTROLLED DRONE
In this project, it is planned to work on brain signals. It is thought to calculate brain signals with EEG and use them in the movement of our drone. When the subjects are connected to the EEG, they will think of vowels and consonants with their mouths closed and will not vocalize them. Later, it is thought to see the difference between these vowels and consonants on the drone. For our plan, the drone will move in a different direction when using audio EEG signals or consonant EEG signals. As a result of our project, it is planned to test that the drone can move in different directions without the need for a command, only with the difference of vowels and consonants.