Browsing by Author "Incereis,N."

Now showing 1 - 2 of 2

Citation Count: 1
Comparison of Sampling Methods Using Machine Learning and Deep Learning Algorithms with an Imbalanced Data Set for the Prevention of Violence Against Physicians
(Institute of Electrical and Electronics Engineers Inc., 2021) Cakir,H.; Incereis,N.; Akgun,B.T.; Tastemir,A.S.Y.
The aim of this study is to compare sampling methods using machine and deep learning algorithms with a small and imbalanced data set for the prevention of violence against physicians. In this data set, it is determined whether there is violence against physicians by using various demographic information of physicians. In addition, in this study, it is tried find effective solutions to improve the working conditions of physicians in order to reduce violence against physicians. As a solution to the imbalanced data problem, Synthetic Minority Oversampling (SMOTE), Random Oversampling (ROS) and Random Undersampling (RUS) methods were used to balance the data in this study. Then, Random Forest Classifier (RFC), Extra Tree Classifier (ETC) and Multi-Layer Perceptron (MLP) algorithms were applied. Among all sampling techniques and classification algorithms, the ETC algorithm applied with the ROS method shows the best performance with 82% accuracy and 0.81 F1-Score. © 2021 IEEE.
Citation Count: 0
A Remote Program Loading Service Design and Implementation;
(Institute of Electrical and Electronics Engineers Inc., 2020) Incereis,N.; Akgun,B.T.
Internet of Things (IoT) technology, which is one of the new technologies, is a network that holds the objects that can exchange information via the internet and the formation of a software supported system which contributes to the management of these objects. This study aims to design and implement a remote program installation service called OTA service. For the system design of this study, general IoT systems, local system, local administration/remote access system, remote management system and distributed management system are examined. A recommendation has been made and implemented for the remote program installation service system. Scenario conditions have been created to improve the system. These are in the form the installation of users to the system or device according to their registration status, decision-making structure of devices according to their dependence on the system, monitoring of the devices at certain intervals according to the condition of being active or passive in the system, security measures for updating. In the proposed system, NodeMcu devices are used as IoT units. © 2020 IEEE.