Publications & Conferences

DESIGN AND APPLICATION OF IoT BASED WEATHER STATION FOR HIGH VOLTAGE LABORATORIES
_{Kumru, C.F., Vural, M.S (2023). Design and Application of Iot Based Weather Station for High Voltage
Measurements, Journal of Engineering Sciences and Design, 11(3), 1190-1201.}

_{This study presents the design and implementation of an internet of things (IoT) based weather station for high voltage laboratories using the Raspberry Pi 4 Model B and two BME680 sensors. The weather station calculates the relative air density and humidity correction coefficients using the temperature, pressure, and relative humidity data obtained from the sensors. The study investigates the effect of the constant and real-time calculation of these coefficients on the measurement of AC, DC and lightning breakdown voltage using spherical electrodes. Measurements were performed within a laboratory setting for a period of 12 hours, and the obtained results were subsequently compared. The findings reveal that the real time calculation of the correction coefficients leads to a reduction in measurement errors. The study also includes the development of a web-based user interface using HTML and CSS, which is hosted on the Raspberry Pi 4 using the Flask web framework. This interface allows users to access the weather station data from any device with a web browser and provides real-time monitoring of the current coefficients, as well as the capability to calculate actual parameters online.}

CLASSIFICATION OF THE HEARTBEATS IN ELECTROCARDIOGRAMS WITH K-NEAREST NEIGHBORS ALGORITHM, RANDOM FORESTS, AND SUPPORT VECTOR MACHINES – A PILOT STUDY
_{Muzaffer Samed Vural, Katarzyna Heryan, Szymon Sieciński, Paweł Biłko, Marcin Grzegorzek. Classification of the Heartbeats in Electrocardiograms with K-Nearest Neighbors Algorithm, Random Forests, and Support Vector Machines – A Pilot Study. In: HealthTech Innovations Conference 2023, Lecture Notes in Networks and Systems, 2024}

_{This study aimed to compare the performance of three classifiers (K-Nearest Neighbors (KNN), Random Forests (RF), and Support Vector Machine (SVM)) in classifying heartbeats using heartbeat and ECG signal features. The performance of classifiers was assessed by evaluating their accuracy, positive predictive value, and sensitivity.}