Search results

The sustainable transition towards the circular economy requires the effective use of artificial intelligence (AI) and information technology (IT) techniques. As the sustainability targets for 2030–2050 increasingly become a tougher challenge, society, company managers and policymakers require more support from AI and IT in general. How can the AI-based and IT-based smart decision-support tools help implementation of circular economy principles from micro to macro scales?

This chapter provides a conceptual framework about the current status and future development of smart decision-support tools for facilitating the circular transition of smart industry, focussing on the implementation of the industrial symbiosis (IS) practice. IS, which is aimed at replacing production inputs of one company with wastes generated by a different company, is considered as a promising strategy towards closing the material, energy and waste loops. Based on the principles of a circular economy, the utility of such practices to close resource loops is analyzed from a functional and operational perspective. For each life cycle phase of IS businesses – e.g., opportunity identification for symbiotic business, assessment of the symbiotic business and sustainable operations of the business – the role played by decision-support tools is described and embedding smartness in these tools is discussed.

Based on the review of available tools and theoretical contributions in the field of IS, the characteristics, functionalities and utilities of smart decision-support tools are discussed within a circular economy transition framework. Tools based on recommender algorithms, machine learning techniques, multi-agent systems and life cycle analysis are critically assessed. Potential improvements are suggested for the resilience and sustainability of a smart circular transition.

This study aims to initiate an investigation into the drop-out rate from building information modelling (BIM) courses.

During 2017-2018, BIM courses (16 weeks) have been developed as active learning modules. Peer instruction was used to engage students and improve the overall student’s performance. Students’ activity data were captured and analysed based on study groups and suggested study module completion dates.

By mapping students’ activity data against suggested completion date at various assessment milestones revealed a possible degradation of motivation throughout the course which, in turn, may have been a possible cause of drop-out.

This paper presents ongoing research and a preliminary understanding about peer instruction effectiveness in BIM-related subjects as high intensity courses. It investigates whether a student’s active participation can improve their motivation to acquire a subject’s learning outcomes and reduce the drop-out.

The peer instruction methodology that is used here is quite universal and can be successfully applied to various other subjects to increase the student’s involvement in the course.

Results are drawn based on students’ involvement at the high intensity course and show the gradual increase of a learner’s motivation once they get continuous support from fellow learners and a teacher.