Abstract :

The Growing Need For Accurate And Efficient Classification Systems Has Led To The Integration Of ML Algorithms And DL Into Different Areas. This Work Uses Structured CSV Data With Unstructured Image Data To Create A Hybrid Classification Framework That Improves The Overall Accuracy And Durability Of Classification Models. Pre -processing Processes For A Structured Data File Include Deprivation Of Duplicate Attributes And Coding Labels. Ten ML Techniques Are Used: Decision-making Classifier, Random Forest Regressor, Linear Discriminatory Analysis, Vector “Support Vector Classifier (SVC), Gradient Boost, Logistic Regression, Gaussian Naive Bayes, K-Nearest Neighbors (KNN)” The Image Data Generator Is Used For Preliminary Processing Of Unstructured Image Data By Changing, Zooming, Editing, Overturning And Transformation. A “convolutional Neural Network (CNN)” Is Used To Select Functions And Sorting Processed Images. “To See How Well The Model Works, The Used Measurement Measures Include Accuracy, Download And F1-skore. The XGBOOST Classifier Has The Highest Accuracy Of 94.27%on Tabular Data, While The CNN Has 96.85%accuracy” On The Image Data File. This Shows That The CNN Model Is Better When Classifying Images. Index Terms - Machine Learning, Deep Learning, Classification, CNN, XGBoost, Preprocessing, Image Augmentation, Accuracy.

Published:

18-8-2025

Issue:

Vol. 25 No. 8 (2025)

Page Nos:

207-216

Section:

Articles

License:

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

How to Cite