Author Login IJIRT Partner Network (IPN) Login

Optimized Ensemble Models for Predicting Diseases from Metagenomic Data

  • Unique Paper ID: 167263
  • Volume: 11
  • Issue: 3
  • PageNo: 702-707
  • Abstract:
  • This study introduces an innovative ensemble deep learning approach, EnsDeepDP, for disease prediction using human metagenomics data. The method employs a combination of unsupervised and supervised learning techniques to effectively handle the high-dimensional features and limited sample sizes inherent in microbiome data. Various deep learning architectures including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), CNN-LSTM, and CNN-GRU are utilized alongside traditional machine learning models such as Multilayer Perceptron (MLP), Random Forest, Bagging Classifier with Random Forest, and a Voting Classifier combining Bagging Classifier with Random Forest and Decision Trees. Through extensive experimentation on six public datasets, our framework consistently outperforms existing algorithms in disease prediction tasks. Notably, the ensemble approach incorporating Bagging Classifier and Voting Classifier achieves superior performance, surpassing the 90% accuracy threshold. This comprehensive ensemble strategy showcases promising potential for advancing disease prediction accuracy in human microbiome studies.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 3
  • PageNo: 702-707

Optimized Ensemble Models for Predicting Diseases from Metagenomic Data

Related Articles

Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry