AI-Enabled High-Performance Data Analytics Framework: Using Adaboost Regression For Healthcare&Automobile Domains

Abstract

The exponential growth of data in recent years has necessitated a paradigm shift from traditional data processing methods to high-performance data engineering solutions. This study presents an integrated framework that combines artificial intelligence with modern data engineering tools to deal with the difficulties associated with large-scale data analytics, especially in healthcare domains. Using the MIMIC-IV medical dataset with machine learning algorithms including Apache Spark, Delta Lake, and Ada boost Regression, we demonstrate an AI-driven method that automates data cleaning, schema matching, and workflow optimization. The framework addresses critical limitations in conventional ETL processes that struggle with the volume and velocity of healthcare data from electronic health records, sensors, and patient monitors. By eliminating costly data duplication and integrating analytics directly into relevant data warehouses, this approach significantly improves predictive healthcare capabilities, hospital resource management, and real-time diagnostics, while reducing the 70% of project time traditionally spent on data preparation tasks. Keywords: High Performance Data Analytics (HPDA), Artificial Intelligence, Health Data Engineering, Machine Learning, Apache Spark, Ada boost Regression, ETL (Extract, Transform, and Load)

Ähnliche Arbeiten