Selecting Datasets for Evaluating an Enhanced Deep Learning Framework
This work addresses dataset selection for researchers developing deep learning frameworks for sequential data analysis, but it appears incremental as it focuses on adapting existing methods for dataset evaluation rather than proposing a new framework.
The researchers tackled the problem of selecting appropriate datasets for evaluating a deep learning framework designed for analyzing sequences with discrete irregular patterns, concluding that financial market daily currency exchange data is the most suitable due to its high levels of such patterns.
A framework was developed to address limitations associated with existing techniques for analysing sequences. This work deals with the steps followed to select suitable datasets characterised by discrete irregular sequential patterns. To identify, select, explore and evaluate which datasets from various sources extracted from more than 400 research articles, an interquartile range method for outlier calculation and a qualitative Billauer's algorithm was adapted to provide periodical peak detection in such datasets. The developed framework was then tested using the most appropriate datasets. The research concluded that the financial market-daily currency exchange domain is the most suitable kind of data set for the evaluation of the designed deep learning framework, as it provides high levels of discrete irregular patterns.