Browsing by Author "Dogdu, E."

Now showing 1 - 2 of 2

Citation - Scopus: 3
Link Prediction in Knowledge Graphs With Numeric Triples Using Clustering
(Institute of Electrical and Electronics Engineers Inc., 2020) Choupani, R.; Dogdu, E.; Bayrak, B.; 06.01. Bilgisayar Mühendisliği; 06. Mühendislik Fakültesi; 01. Çankaya Üniversitesi
Knowledge graphs (KG) include large amounts of structured data in many different domains. Knowledge or information is captured by entities and relationships between them in KG. One of the open problems in knowledge graphs area is "link prediction", that is predicting new relationships or links between the given existing entities in KG. A recent approach in graph-based learning problems is "graph embedding", in which graphs are represented as low-dimensional vectors. Then, it is easier to make link predictions using these vector representations. We also use graph embedding for graph representations. A sub-problem of link prediction in KG is the link prediction in the presence of literal values, and specifically numeric values, on the receiving end of links. This is a harder problem because of the numeric literal values taking arbitrary values. For such entries link prediction models cannot work, because numeric entities are not embedded in the vector space. There are several studies in this area, but they are all complex approaches. In this study, we propose a novel approach for link prediction in KG in the presence of numerical values. To overcome the embedding problem of numeric values, we used a clustering approach for clustering these numerical values in a knowledge graph and then used the clusters for performing link prediction. Then we clustered the numerical values to enhance the prediction rates and evaluated our method on a part of Freebase knowledge graph, which includes entities, relations, and numerical literals. Test results show that a considerable increase in link prediction rate can be achieved in comparison to previous studies. © 2020 IEEE.
Citation - Scopus: 3
A Robust Watermarking Scheme Over Quadrant Medical Image in Discrete Wavelet Transform Domain
(Institute of Electrical and Electronics Engineers Inc., 2018) Goker, O.; Nazli, N.; Erol, M.M.; Choupani, R.; Dogdu, E.; 21259; 06.01. Bilgisayar Mühendisliği; 06. Mühendislik Fakültesi; 01. Çankaya Üniversitesi
The diffusion of digital content is very fast in today's technology. The velocity of gathering data might cause unlawful distribution of content. The major problem in content authorization is the robustness of methodology. Since frangible methodologies result unauthorized content access quicker, more robust solutions are essential for copyright protection. Watermarking technology is considered as a robust solution for copyright protection and authentication. In watermarking, quality of the image is a challenge. Applying a watermark on a medical image might cause corruption in original image, which leads to misleading content. The proposed copyright protection mechanism includes Quadtree algorithm which finds a region of non-interest to apply watermark on medical image in Discrete Wavelet Domain to provide authentication of the content without altering region of interest. Furthermore, in this paper, the visual quality of watermark implemented medical images and sample values are also discussed with the experimental results as well. © 2018 IEEE.