Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 4;14(1):12851.
doi: 10.1038/s41598-024-63630-7.

Enhanced analysis of tabular data through Multi-representation DeepInsight

Alok Sharma  1   2   3 , Yosvany López  4 , Shangru Jia  5 , Artem Lysenko  6   7 , Keith A Boroevich  6 , Tatsuhiko Tsunoda  8   9   10
Affiliations

Enhanced analysis of tabular data through Multi-representation DeepInsight

Alok Sharma et al. Sci Rep. .

Abstract

Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods can be used for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (MRep-DeepInsight), a novel extension of the DeepInsight method designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach is able to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimer's data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest, XGBoost, LightGBM, FT-Transformer and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By leveraging the power of diverse representations, MRep-DeepInsight offers a promising new avenue for advancing decision-making and scientific discovery across a wide range of fields.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Schematic overview of the MRep-DeepInsight method. (a) Demonstrates the transformation difference between the original DeepInsight and MRep-DeepInsight, showcasing the shift from a single representation to multiple representation for each feature vector. (b) Depicts the MRep-DeepInsight pipeline, illustrating the steps involved in converting tabular data into a set of image samples with varied representations, from manifold to the final image conversion.
Figure 2
Figure 2
Image samples converted by MRep-DeepInsight are processed by deep learning model.
Figure 3
Figure 3
Model analysis phase: a novel test sample is analyzed to one of the defined classes.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Sharma, A. & Paliwal, K. K. Linear discriminant analysis for the small sample size problem: an overview. Int. J. Mach. Learn. Cybern.6, 443–454 (2015).
    1. Fukushima, K. Neocognitron. Scholarpedia2(1), 1717 (2007).
    1. Ho, T. K. Random Decision Forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition 278–282 (1995).
    1. Duda, R. O. & Hart, P. E. Pattern classification and scene analysis. (Wiley, 1973).
    1. Bishop, C. M. Pattern recognition and machine learning. (Springer, 2006).

LinkOut - more resources