BROWSE
Detail
Conference Paper
A Practical Data Preparation Approach for Machine Learning over Heterogeneous Data Sources
Cited - time in 
Share 
Share
- Authors
- Taewhi Lee, Jang-Ho Choi, Miyoung Jang, Jongho Won, Jiyong Kim
- Issue Date
- 2020-12
- Citation
- International Conference on Internet (ICONI) 2020, pp.1-2
- Language
- English
- Type
- Conference Paper
- Abstract
- Machine learning applications often involve various kinds of data from heterogeneous data sources. It is tedious, time-consuming, and error-prone to integrate such heterogeneous data, so we need an easy-to-use solution. This paper presents a practical approach to prepare data for machine learning that uses heterogeneous data from multiple sources. This approach can support federated queries over heterogeneous data sources and multi-dimensional array operations for data transformation. Such queries can be defined as views for user convenience. Users can therefore query the integrated data with some arbitrary conditions in a convenient manner.
- KSP Keywords
- Array operations, Federated Queries, Heterogeneous Data Sources, Integrated data, Multi-dimensional array, Multiple sources, Practical approach, data preparation, data transformation, machine learning applications