Abstract | ||
---|---|---|
This paper proposes an approach of the spatio-temporal data mining in order to predict next learning steps (next ubiquitous learning logs to be learned) in accordance with their situations or context from past learners' experiences in their daily lives accumulated in the ubiquitous learning system called SCROLL (System for Capturing and Reminding of Learning Log). Ubiquitous learning log (ULL) is defined as a digital record of what learners have learned in their daily life using ubiquitous technologies. It allows learners to log their learning experiences with photos, audios, videos, location, RFID tag and sensor data, and to share and reuse ULL with others. This paper describes some data mining methods using the association analysis in order to detect effective and efficient learning logs for learner from relationships among ubiquitous learning logs collected by a number of the research studies for a long period of the SCROLL project (2011~2014). |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICALT.2015.66 | International Conference on Advanced Learning Technologies |
Keywords | Field | DocType |
component, ubiquitous learning, data mining, association analysis | Ubiquitous learning,World Wide Web,Reuse,Computer science,Association rule learning,Temporal data mining,Multimedia,Market research | Conference |
ISSN | Citations | PageRank |
2161-3761 | 2 | 0.44 |
References | Authors | |
4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kousuke Mouri | 1 | 55 | 14.67 |
Hiroaki Ogata | 2 | 796 | 96.69 |
Noriko Uosaki | 3 | 73 | 17.34 |