Paper Info
Title
Spread Control for Huge Data Fuzzy Learning.
Abstract
The control of Growing Self Organizing Maps (GSOM) algorithms presents a serious issue with huge data learning. In conjunction with the growing threshold (GT), the spread factor (SF) is used as a controlling measure of the map size during the growing process. The effect of the spread factor in fuzzy learning with Fuzzy Multilevel Interior GSOMs (FMIG) algorithm is investigated. Further analysis is conducted on very large data in order to demonstrate the spread control of data distribution with FMIG learning in comparison with Multilevel Interior Growing SOM (MIGSOM), GSOM, Fuzzy Kohonen Clustering Network (FKCN) and fuzzy GSOM. Therefore, the aim of this paper is to study the effect of the spread factor values on the map structure in term of quantization error, topology preservation and dead units. Experimental studies with huge synthetic and real datasets are fulfilled at different spread factor values for the advertised algorithms.
Year
DOI
Venue
2016
10.1007/978-3-319-52941-7_58
PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON HYBRID INTELLIGENT SYSTEMS (HIS 2016)
Keywords
Field
DocType
Fuzzy learning,Spread factor,Threshold growing,Multilevel interior growing self-organizing maps,Quantization,Topology
Data mining,Computer science,Fuzzy logic,Self-organizing map,Artificial intelligence,Cluster analysis,Quantization (signal processing),Machine learning,Fuzzy learning
Conference
Volume
ISSN
Citations 
552
2194-5357
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Monia Tlili111.02
Tarek M. Hamdani214316.16
Mohamed Adel Alimi31947217.16