Browsing by Author "Karamanlioglu, Alper"

Now showing 1 - 3 of 3

AviBERT: Transformer Tabanlı Hava Aracı Metni Sınıflandırma
(Institute of Electrical and Electronics Engineers Inc., 2025) Unal, Muhammed Cihat; Yurtalan, Gokhan; Karatas, Yahya Bahadir; Karamanlioglu, Alper; Demirel, Berkan
In recent years, transformer-based models pre-trained on extensive corpora have played a critical role in the advancement of Natural Language Processing methodologies. Particularly, methods based on BERT have demonstrated remarkable performance across various tasks by offering robust capabilities in deeply understanding texts semantically. However, despite these advancements, there is a notable scarcity of studies applying these technologies in the aviation sector. This paper develops a multi-class classification model for aviation-specific texts using variants of BERT. The study encompasses the processes of collecting web content related to aircraft, labeling and model training. The details of the dataset are explained and the outcomes of the study are assessed based on the macro F1-score and accuracy of different models. © 2025 Elsevier B.V., All rights reserved.
Citation - WoS: 2
Citation - Scopus: 1
An Experimental Study on Decomposition: Process First or Structure First
(Springer international Publishing Ag, 2019) Suloglu, Selma; Kaya, M. Cagri; Karamanlioglu, Alper; Tokdemir, Gul; Dogru, Ali H.; Cetinkaya, Anil
This article explores the answer to the question of considering the process or the structure dimensions earlier, in software development where decomposition is a preferred technique for top-down model construction. In this research, an experimental study was conducted to observe which software modeling practice is more convenient: process or structural modeling, for the beginning. The study was conducted in different courses that include software modeling where students work within groups to model a system with predefined requirements. The students used Business Process Modeling Notation and Component-Oriented Software Engineering Modeling Language modeling tools. Observations based on the results are analyzed and discussed. The results seem to prioritize the process dimension.
Parallel and Distributed Architecture for Multilingual Open Source Intelligence Systems
(Springer international Publishing Ag, 2024) Karamanlioglu, Alper; Yurtalan, Gokhan; Karatas, Yahya Bahadir
The proliferation of publicly available information across multiple languages presents both unique challenges and opportunities for Open Source Intelligence (OSINT) systems. This paper proposes a novel architecture for multilingual OSINT that is both parallel and distributed. The architecture integrates language identification and translation capabilities, enabling it to handle linguistically diverse data by transforming it into a unified format for efficient analysis. Designed specifically to address the challenges of parallel and distributed processing in OSINT systems, this architecture aims to offer scalability and performance benefits when dealing with massive data volumes. Our primary focus has been on devising strategies and tactics that address these concerns, providing a robust solution for the collection, processing and analysis of data in various languages. This work marks a significant step towards the development of more globally inclusive OSINT systems.