Abstract :

Internet Of Things (IoT) Data Is Growing At An Exponential Rate, Which Means That Scalable And Efficient Big Data Analysis Frameworks Are Needed. This Is Because Standard Machine Learning Methods Can T Handle Huge Datasets With Real-time Needs. The Earthquake Detection Dataset Includes Details About Events Like Size, Location, Alerts, And The Chance Of A Tsunami. These Are Important Details For Predictive Models. The Dataset Helps Create Automatic Big Data Analysis Services That Are In Line With The Goals Of Industry 4.0 And Society 5.0. This Makes Sure That Accurate And Timely Information About Environmental Risks Is Shared. The AutoBDA Framework Combines Hadoop And Spark To Allow Distributed Processing, Which Makes Machine Learning Jobs More Scalable. For Predicting The Size Of An Earthquake, Logistic Regression Is Used As The Main Method. The Performance Of The Model Is Shown By An RMSE Of 0.10 And An MAE Of 0.07. This Shows How Well The Distributed Analysis Approach Works. A Flask-based Deployment Allows Seamless User Interaction, Where Test Input Values Are Analyzed And Predictions Are Generated In Real Time Using Spark S In-memory Processing, Reducing Communication And Computation Costs. Ensemble Algorithms, Like Random Forest And Gradient Boosted Trees, Can Be Used To Improve Speed Even More. These Algorithms Are More Accurate Than Others. Random Forest Has An RMSE Of 0.08 And An MAE Of 0.04. Gradient Boosted Trees Has The Best Results, With An RMSE Of 0.03 And An MAE Of 0.006. Adding Healthcare And Resource Management To AutoBDA S List Of Services Can Make It More Inclusive And Flexible Across Many Fields.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1697-1706

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite