Home > Research > Publications & Outputs > Applications of Autonomous Data Partitioning


Text available via DOI:

View graph of relations

Applications of Autonomous Data Partitioning

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNChapter (peer-reviewed)peer-review

Publication date2019
Host publicationEmpirical Approach to Machine Learning
EditorsPlamen Angelov, Xiaowei Gu
Number of pages16
ISBN (print)9783030023836)
<mark>Original language</mark>English

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X


In this chapter, the algorithm summaries of both, the offline and evolving versions of the proposed autonomous data partitioning (ADP) algorithm described in chapter 7 are provided. Numerical examples based on well-known benchmark datasets are presented for evaluating the performance of the ADP algorithm on data partitioning. Furthermore, numerical examples on semi-supervised classification are also conducted as a potential application of the ADP algorithm. The state-of-the-art approaches are used for comparison. Numerical experiments demonstrate that the ADP algorithm is able to perform high quality data partitioning results in a highly efficient, objective manner. The ADP algorithm can also be used for classification even when there is very little supervision available. The pseudo-code of the main procedure of the ADP algorithm and the MATLAB implementations can be found in appendices B.2 and C.2, respectively. © 2019, Springer Nature Switzerland AG.