Study on Trends and Predictions of Convergence in Cybersecurity Technology Using Machine Learning

Abstract

The indiscriminate convergence of technologies makes prediction difficult and can cause many difficulties in technology investment. This makes it difficult to choose capital investment and can induce excessive investment in inefficient technologies. Therefore, analyzing the trend of convergence technology and predicting a highly influential convergence area in the future can induce effective investment, and lead the highly influential technology to achieve great technological development. The purpose of this paper is to analyze technologies that are expected to have high influence in the future through prediction of major fusion areas and to present fusion areas that can be used as indicators of investment. The proposed mechanism selected four prominent journals in the security area and collected metadata to generate a dataset in terms of technological excellence and a dataset in terms of commercialization through patent metadata collection. Thereafter, a process of extracting a main keyword according to a topic from a metadata set by applying a Latent Dirichlet Allocation (LDA) is performed. The extracted topics and keywords are not related to topics and keywords of other years. Therefore, a dynamic topic model (DTM) is applied to analyze the trend of the extracted topics and perform prediction. DTM analyzes the topics in the fusion area classified by LDA and the trend of changing topics linked by year for each topic keyword. Finally, the association of the fusion region is analyzed to derive a fusion region with high influence. These results are believed to be used as an indicator of effective technology investment by providing a high impact area in the convergence area of cybersecurity.