Recently, based on Internet and mobile environments, the Fintech industry that fuses finance and IT together has been rapidly growing and Fintech services armed with simplicity and convenience have been leading the conversion of all financial services into online and mobile services. However, despite the rapid growth of the Fintech industry, few studies have classified Fintech technologies into detailed technologies, analyzed the technology development trends of major market countries, and supported technology planning. In this respect, using Fintech technological data in the form of unstructured data, the present study extracts and defines detailed Fintech technologies through the topic modeling technique. Thereafter, hot and cold topics of the derived detailed Fintech technologies are identified to determine the trend of Fintech technologies. In addition, the trends of technology development in the USA, South Korea, and China, which are major market countries for major Fintech industrial technologies, are analyzed. Finally, through the analyses of networks between detailed Fintech technologies, linkages between the technologies are examined. The trends of Fintech industrial technologies identified in the present study are expected to be effectively utilized for the establishment of policies in the area of the Fintech industry and Fintech related enterprises' establishment of technology strategies.
To respond the climate change and environmental pollution, the studies on renewable energy policies are increasing. The renewable energy is a new growth engine technology represented by the green industry and green technology. At present, the investments for the renewable energy supply and technology development projects of three main strategy sectors such as sunlight, wind power and hydrogen fuel cell are implemented in our country, while they are still in the early stage, accordingly reducing those uncertainty for the research direction and investment fields is the most urgent issue among others. Thus, this study applied text mining method and multinominal topic model among the big data analysis methods on our country's newspaper articles concerning the renewable energy over the last 10 years, and then analyzed the core issues and global research trend, forecasting the renewable energy fields with the growth potential. It is predicted that these results of the study based on information and communication technology will be actively applied on the renewable energy fields.
As the number of end-of-life vehicles (ELVs) has kept increasing, the management of ELV has also become one of the academic research focuses and European Union recently adopted the directive on ELVs. For the stakeholders has become a principle agent of dealing with all about ELVs, it is relevant investment decision to set up and to decide high-cost ELVs entity locations and to forecast future ELVs' amount in advance. In this paper, transition probability matrixes between months are made by using Markov Chain and the number of ELVs is predicted with them. This study will perform a great role as a fundamental material in Korea where just started having interests about recycling resources and studies related to the topic. Moreover, the forecasting method developed for this research can be adopted for other enhancements in different but comparable situations. †
The Bidirectional LSTM CRF model used for Named Entity Recognition takes much time to train Named Entity. The hyper-parameters of Word Embedding used as input data in this model affect performance and training time. However, there is very little research on the number of dimensions, which is one of the parameters of Word Embedding. In this paper, we obtain proper number of 4-Word Embeddings (fastText, GloVe, skipgram, CBOW) considering performance and training time in Bidirectional LSTM CRF which can input large amount of data. Next, apply the PCA to the word vector in Word Embedding to reduce the dimension to small dimensional (10 dimensions) intervals. Therefore, applying PCA to conventional Word Embedding and training Word Embedding with small dimensional intervals shows that the model can be trained by maintaining or improving performance based on stable training time in fewer dimensions than conventional Word Embedding. †
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.