Knowledge Graph Embedding (KGE) for Semantic Representation of Big Data

This work presents a new approach to logically represent big data in rapidly expanding large data sets, namely medical visualization, using Knowledge Graph Embedding (KGE) Knowledge graphs are a great tool for capturing data communication complex due to structure and depth comprehension skills. These grids can be effectively transformed into continuous vector spaces, preserving the logical relationships between the data. The basis of this approach is to build an optimal knowledge map for medical image data, which is then subjected to sophisticated embedding techniques and then evaluate the efficiency of the resulting vector representation in many applications such as anomaly detection, . semantic similarity analysis and image classification. Furthermore, the use of embedded knowledge facilitates the interpretation of results, which is important for medical research. This work extends the application of KGE to other big data applications in addition to new opportunities for complex data representation in medical imaging