Author(s):
1. ANUPAMA N:
DGitam School of Technology, Department of CSE, Hyderabad, Telangana, India
2. RAVI SANKAR V:
Gitam School of Technology, Department of CSE,Hyderabad, Telangana, India
3. SUDARSON JENA:
SUIIT, Department of Computer Science Engineering & Application,Sambalpur, Odissa, India
Abstract:
Data mining is the process of discovering hidden knowledge from the existing datasets. The process of knowledge discovery is a complex task when the data source is in the form of data streams and more tough when the data source is of class imbalance in nature. To find an optimal solution for these problems many research proposals are formulated by researchers. Some of the unsolved problems in the literature for the above said problem are for very large data sources of data streams with class imbalance nature. In this paper, a novel proposal for class imbalance large data streams is presented with novel techniques of oversampling and a unique multi modal filtering technique known as Multimodal Increment over Sampling for Data Streams (MIOSDS). The experimental simulations are conducted on three large datasets with different domains with high class imbalance ratio. The results generated are very impressive in terms of accuracy, AUC, precision, recall and F-measure validation metrics.
Page(s):
5675-5687
DOI:
DOI not available
Published:
Journal: Journal of Theoretical and Applied Information Technology, Volume: 100, Issue: 19, Year: 2022
Keywords:
Knowledge discovery
,
Imbalanced data
,
Multimodal Increment Over Sampling for Data Streams MIOSDS
,
Data Streams
,
oversampling
References:
References are not available for this document.
Citations
Citations are not available for this document.