Yazar "Soylu, Mucahit" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    A Hybrid Graph Neural Network Model for Predicting Cyber Attacks From Heterogeneous and Dynamic Network Data
    (Ieee-Inst Electrical Electronics Engineers Inc, 2025) Soylu, Mucahit; Das, Resul
    With valuable data constantly under attack, reactive security measures are no longer sufficient. Predicting cyber threats before they emerge is crucial. Cyberattacks do not occur randomly; they have a systematic underlying pattern. By discovering these patterns, it is possible to predict cyberattacks in advance. Unraveling the mysteries of these evolutionary patterns is quite challenging. Considering the potential of Graph Neural Networks to strengthen cybersecurity defenses, this paper proposes a new hybrid model, DyMHAG (Dynamic Meta-Path Heterogeneous Attention Graph). We propose a novel hybrid GNN model that integrates meta-path-based graph attention networks with the Gated Recurrent Unit (GRU) mechanism for temporal data processing. Our method consists of three layers: node-level attention-based graph embedding, meta-path-level attention-based graph embedding, and evolutionary pattern learning. This model aims to effectively capture complex relational structures and temporal dependencies in heterogeneous and temporally dynamic network data and provide a proactive solution for cyberthreat prediction. Preliminary evaluations indicate that our hybrid model not only improves prediction accuracy but also reduces the false positive rate, providing a more reliable defense against emerging cyber threats.
  • Küçük Resim Yok
    Öğe
    A key review on graph data science: The power of graphs in scientific studies
    (Elsevier, 2023) Das, Resul; Soylu, Mucahit
    This comprehensive review provides an in-depth analysis of graph theory, various graph types, and the role of graph visualization in scientific studies. Graphs serve as powerful tools for modeling and analyzing complex systems in diverse disciplines. The introduction highlights the importance of graphs as a visual representation in scientific research, enabling a better understanding of complex data. Infographics and knowledge graphs have gained significant popularity in recent years due to their effectiveness in conveying information. The review starts by exploring the foundations of graph theory, covering key concepts, algorithms, and applications. It discusses the different types of graphs, including directed, undirected, weighted, and bipartite graphs, and their specific use cases in scientific studies. Special attention is given to special graphs, such as complete graphs, trees, and social networks, which have unique properties and play a significant role in various scientific domains. The review showcases their applications and contributions in fields like biology, social sciences, network analysis, and data mining. Graph visualization emerges as a crucial aspect of understanding and interpreting complex data structures. The review emphasizes the challenges and advancements in graph visualization techniques, enabling researchers to effectively communicate and analyze graph-based information. In conclusion, this comprehensive review serves as a valuable resource for researchers in understanding the principles and applications of graph theory in scientific studies. The exploration of graph types, special graphs, and graph visualization techniques provides insights into the diverse uses and potential of graphs in various scientific disciplines.
  • Küçük Resim Yok
    Öğe
    Knowledge Graph Visualization: Methods, Interactivity and Practical Considerations
    (Institute of Electrical and Electronics Engineers Inc., 2025) Soylu, Mucahit; Das, Resul
    While knowledge graphs are invaluable to fields such as artificial intelligence and data analysis, their size and complexity make them difficult to understand. This study examines how we can make large and complex knowledge graphs more understandable, that is, how we can effectively 'visualize' them. First, we cover basic visualization methods such as node-link diagrams and force-oriented layouts. We compare which method works best when, as well as their advantages and disadvantages. We then focus on interactive techniques that enable users to explore the data independently, beyond simply viewing a static image. We show how features such as filtering, clustering, and zooming simplify and enrich the analysis process with examples. Finally, we discuss today's challenging problems, such as reducing visual clutter and displaying constantly changing (dynamic) data. We conclude by offering a perspective on what opportunities new technologies, such as augmented and virtual reality, can offer in this area. This paper aims to provide both a theoretical foundation and a practical roadmap for anyone interested in knowledge graph visualization. © 2025 IEEE.
  • Küçük Resim Yok
    Öğe
    A new approach to recognizing the use of attitude markers by authors of academic journal articles
    (Pergamon-Elsevier Science Ltd, 2023) Soylu, Mucahit; Soylu, Ayfer; Das, Resul
    This study investigates the use of Attitude Markers(AMs) by native academic authors of English (NAAEs) and Turkish-speaking academic authors of English (TAAEs) in 100 academic articles on Teacher Education. The primary objectives are to examine the forms and functions of AMs used by both groups to indicate their stance in articles and to compare the frequency and variety of AMs used by each group. The study employs a corpus -based approach and adopts a graph visualization method to present the findings. The data were cleaned using a software-supported approach to improve the efficiency of corpus compilation. The data were analyzed using the Antconc text analysis tool (Anthony, 2011) and Log-likelihood statistics. The reliability of the analysis was tested by calculating the inter-rater reliability. To do this, the content coded by one of the researchers and an independent rater was compared using Cohen's Kappa coefficient. The results ranged from 0.81 to 0.92, indicating a high level of reliability. Later, the findings were visualized using a radial knowledge graph. The statistical analysis showed significant differences in the use of certain AMs between the two groups, including AMs related to assessment(-13,20 LL; p<.01) and significance(-82,64 LL; p<.01). The findings indicate that both NAAEs and TAAEs commonly use AMs to convey their stance, with 'significance' and 'assessment' being the most frequent functional categories, and 'adjective' being the most commonly used form of AMs in both corpora. The findings provide valuable insights into the use of AMs in academic writing and can inform the development of English for academic purposes (EAP) course materials to enhance the academic writing skills of novice writers. The results of the study suggest that future research could use graph visualization to carry our corpus studies and could explore the effectiveness of using Artificial Intelligence (AI) technologies to minimize human bias in qualitative analyses.
  • Küçük Resim Yok
    Öğe
    Prediction and graph visualization of cyber attacks using graph attention networks
    (Elsevier Advanced Technology, 2025) Soylu, Mucahit; Das, Resul
    This study proposes a hybrid approach for visualizing cyberattacks by combining the deep learning-based GAT model with JavaScript-based graph visualization tools. The model processes large, heterogeneous data from the UNSW-NB15 dataset to generate dynamic and meaningful graphs. In the data cleaning phase, missing and erroneous data were removed, unnecessary columns were discarded, and the data was transformed format suitable for modeling. Then, the data was converted into homogeneous graphs, and heterogeneous structures were created for analysis using the GAT model. GAT prioritizes relationships between nodes the graph with an attention mechanism, effectively detecting attack patterns. The analyzed data was then converted into interactive graphs using tools like SigmaJS, with attacks between the same nodes grouped reduce graph complexity. Users can explore these dynamic graphs in detail, examine attack types, and track events over time. This approach significantly benefits cybersecurity professionals, allowing them to better understand, track, and develop defense strategies against cyberattacks.