Automatically Selecting Parameters for Graph-Based Clustering
MetadataShow full item record
Data streams present a number of challenges, caused by change in stream concepts over time. In this thesis we present a novel method for detection of concept drift within data streams by analysing geometric features of the clustering algorithm, RepStream. Further, we present novel methods for automatically adjusting critical input parameters over time, and generating self-organising nearest-neighbour graphs, improving robustness and decreasing the need to domain-specific knowledge in the face of stream evolution.
Showing items related by title, author, creator and subject.
Student Perceptions of Classroom Environments in Streamed Middle Secondary Mathematics Classes in Australian Christian SchoolsKilgour, Peter; Rickards, Anthony (2008)This paper reports on a study into the perceptions students have of the learning environment in Year 9 and 10 mathematics classrooms when the classes are streamed. The sample consisted of 581 students in Years 9 and 10 ...
Gender, grade-level and stream differences in learning environment and student attitudes in primary science classrooms in SingaporePeer, Jarina (2011)A major focus of this research was the validity and reliability of a learning environment and attitude questionnaire in primary school classrooms in Singapore. The learning environment scales were chosen from Constructivist ...
Techniques for improving clustering and association rules mining from very large transactional databasesLi, Yanrong (2009)Clustering and association rules mining are two core data mining tasks that have been actively studied by data mining community for nearly two decades. Though many clustering and association rules mining algorithms have ...