Akademik Veri Yönetim Sistemi
Journal of the Faculty of Engineering and Architecture of Gazi University, cilt.38, sa.3, ss.1919-1929, 2023 (SCI-Expanded)
© 2023 Gazi Universitesi Muhendislik-Mimarlik. All rights reserved.It is a necessity to use machine learning model in client server systems. However, collecting data from the clients, transferring them to the server, training the machine learning model and integrating this model into the devices running on the clients bring along many problems. The transfer of data from the clients to the server causes network traffic, requires a lot of energy, and data privacy can be abused. Within the scope of the study, federated learning architecture is used to solve the mentioned problems. According to the architecture, the machine learning model is trained on each client from the client's own data. Models trained on each client are sent to the server and a new model is created by merging these models on the server. The final model created is distributed to the clients again. In this study, a relational classification algorithm called Data Unaware Classification Based on Association (du-CBA) was developed. In order to compare federated learning and classical learning architectures and measure their success, a simulation environment was created within the scope of the study. Models were trained using du-CBA and CBA algorithms in the simulation environment and the results were compared. Five data sets from the University of California Irvine (UCI) repository were used to train the models. Experimental results showed that for each dataset, the models trained with federated learning achieved almost the same accuracy as the models trained with classical learning, but the training times were decreased by about 70%. The results show that the developed algorithm has been successful.