ABSTRACT
With the growing popularity of design thinking capacity building initiatives for entrepreneurship education, educators are striving to explore technology-supported learning environments and pedagogy to achieve the inter-disciplinary, easily accessible, and student-oriented entrepreneurship education innovation. The lingering effects of unfinished learning amid the COVID-19 and mixed-mode learning have become part of a new normal, we designed and implemented a novel learning framework to put co-design pedagogical structures in place that allow educators, students, and stakeholders to form new learning experiences and create innovation together. Through the case study we designed and implemented in three universities across different regions, we propose and investigate an approach that enables micro-level analysis of knowledge creation model for student's design thinking capacity building as well as macro-level understanding of learning dynamics for entrepreneurship education. This study presents a pedagogy-based template, and the findings have implications for the design of technology-empowered educational interventions and pedagogical innovation. © ISLS.
ABSTRACT
In this paper, we present a hybrid deep learning framework named CTNet which combines convolutional neural network (CNN) and transformer together for the detection of COVID-19 via 3D chest CT images. It consists of a CNN feature extractor module with SE attention to extract sufficient features from CT scans, together with a transformer model to model the discriminative features of the 3D CT scans. Compared to previous works, CTNet provides an effective and efficient method to perform COVID-19 diagnosis via 3D CT scans with data resampling strategy. Advanced results on a large and public benchmarks, COV19-CT-DB database, was achieved by the proposed CTNet with a macro F1 score of 88.21% on the validation set, which lead ten percentage over the state-of-the-art baseline approach proposed together with the dataset. Notably, the inference speed of the proposed framework is about ten times faster than that of the typical CNN frameworks which make it more promising in actual applications.