Technology environment
Fraunhofer INT
Many national and international governments establish organizations for applied science research funding.
For this, several organizations have defined procedures for identifying relevant projects that based on prioritized technologies.
Even for applied science research projects, which combine several technologies it is difficult to identify all corresponding technologies
of all research-funding organizations.
We present an approach that classifies applied science research projects according to corresponding technologies and applications of research-funding organizations. This supports researchers and research-funding planners. For this multi-label classification problem, machine learning techniques as supervised learning methods are used together with centroid-based text classification algorithm, Jaccard's coefficient and fuzzy alpha cut method.
This approach is evaluated using the example of defense and security based technological research. This is because the growing importance of this application field leads to an increasing number of research projects and the appearance of many new technologies and applications. Thus, security and defence based taxonomies are integrated in the application that can be replaced by own taxonomies.
Here we demonstrate our first prototype application based on this text mining approach.
Mining Technologies
We present an approach that classifies applied science research projects according to corresponding technologies and applications of research-funding organizations. This supports researchers and research-funding planners. For this multi-label classification problem, machine learning techniques as supervised learning methods are used together with centroid-based text classification algorithm, Jaccard's coefficient and fuzzy alpha cut method.
This approach is evaluated using the example of defense and security based technological research. This is because the growing importance of this application field leads to an increasing number of research projects and the appearance of many new technologies and applications. Thus, security and defence based taxonomies are integrated in the application that can be replaced by own taxonomies.
Here we demonstrate our first prototype application based on this text mining approach.
Mining Technologies
Set Bookmark