A Novel Multi-View Partitioning and Ensembled-Based Cancer Classification Using Gene Expression Data

Kavitha K R, Kashyap G, Anjima K S

2025

Abstract

In this research, we propose an ensemble-based multi-view classification framework to analyze high-dimensional gene expression data, targeting the specific application of colon tumor classification. We proposed to incorporate state-of-the-art techniques that tackle the problem of heterogeneity, dimensionality, and classification performance in medical datasets. The methodology starts with clustering the gene expression data into distinct feature subsets (views). Using a Feature Selection and Projection (FSP) algorithm called attribute bagging, these subsets are spread out over several views: V1, V2, V3, V4, and V5, thereby capturing a very broad range of data representations. Each view is independently classified with a specialized classifier-again, one that was especially designed to take full advantage of the particular properties inherent in that view-that could be Random Forest, XGBoost, SVM, Multi-Layer Perceptron (MLP), and LSTM networks. The predictions from these classifiers (Yp1, Yp2, Yp3, Yp4, Yp5) are combined using a weighted ensemble approach based on majority voting, producing a unified prediction (Ypred). This strategy ensures robustness and minimizes the impact of individual model biases. Finally, the accuracy of the ensemble is evaluated, demonstrating the effectiveness of the proposed approach in achieving reliable and precise tumor classification. By using this architecture, we are able to achieve enhanced classification performance with the strengths of ensemble methods and multi-view learning. This scalable and accurate framework is highly pertinent for biomedical data analysis and supports diagnostic decision-making processes.

Paper Citation

in Harvard Style

K R K., G K. and K S A. (2025). A Novel Multi-View Partitioning and Ensembled-Based Cancer Classification Using Gene Expression Data. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 435-443. DOI: 10.5220/0013594100004664

in Bibtex Style

@conference{incoft25,
author={Kavitha K R and Kashyap G and Anjima K S},
title={A Novel Multi-View Partitioning and Ensembled-Based Cancer Classification Using Gene Expression Data},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT},
year={2025},
pages={435-443},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013594100004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT
TI - A Novel Multi-View Partitioning and Ensembled-Based Cancer Classification Using Gene Expression Data
SN - 978-989-758-763-4
AU - K R K.
AU - G K.
AU - K S A.
PY - 2025
SP - 435
EP - 443
DO - 10.5220/0013594100004664
PB - SciTePress