Research
Research themes
- Mixed metrics(Bibliometrics)
- Technology landscaping
- Emerging technology discovery
- Technology opportunity discovery
- Health technology acceptance
Research directions
Initial exploration of extensive data sets: Our first objective is to delve into comprehensive data sets encompassing bibliographies, economic data, and patent information. By applying machine learning techniques, we aim to precisely identify promising research topics and emerging technologies within this vast information landscape.
Enhancing technology acceptance through causal relationship identification: Our second goal is to improve technology acceptance. To achieve this, we will analyze survey data employing structural equation modeling. By identifying causal relationships, we seek to uncover key factors influencing the acceptance of technological innovations.
Technology prediction using machine learning: Our third aim involves utilizing a machine learning-based technique to predict technology outcomes. By leveraging the data and outcomes mentioned earlier, we aim to develop predictive models that can accurately anticipate the trajectory and potential of emerging technologies.
Research methods
Exploring big data
- Multi-metrics(Bibliometrics, Econometrics, Patentmetrics)
- Latent class analysis (LCA)
- Word embedding and Topic modeling (BERTopic)
- Social network analysis
Examining casual relationship
- Structural equation modeling (SEM)
Building prediction model
- Machine learning via scikit-learn
- Deep learning via PyTorch, Tensorflow/Keras