A Method for Reducing Training Time of ML-Based Cascade Scheme for Large-Volume Data Analysis.

Area of Science:

• Biomedical Data Analysis
• Machine Learning
• Data Science

Background:

• Large datasets are crucial for insights, but training machine learning (ML) models is resource-intensive.
• Existing ML cascade schemes face challenges in processing large biomedical datasets due to iterative training and complex feature extraction.

Purpose of the Study:

• To propose a modified ML-based cascade scheme for efficient analysis of large biomedical datasets.
• To reduce computational resources and training time for ML models in cascade schemes.

Main Methods:

• Incorporated Principal Component Analysis (PCA) at each level of the ML cascade.
• Selected principal components to retain 95% of data variance.
• Enhanced ML training and application algorithms.

Main Results:

• Demonstrated significant reduction in training time compared to existing methods.
• Showcased improved generalization properties and accuracy in large data analysis.
• PCA integration reduced non-significant attributes, enhancing overall performance.

Conclusions:

• The modified cascade scheme with PCA offers a more efficient and accurate approach for large biomedical data analysis.
• This method addresses the computational challenges of ML model training in cascade schemes.
• The enhanced generalization properties make it suitable for intelligent large data analysis.