Abstract :

Vehicle Performance Evaluation And Condition Monitoring Are Essential For Improving Efficiency, Safety, And Maintenance Planning In The Automotive Domain. Traditionally, These Tasks Were Performed Using Manual Inspection Methods And Basic Statistical Analysis, Which Required Significant Human Effort, Consumed Time, And Lacked Scalability For Handling Large Datasets. These Conventional Approaches Also Failed To Provide Accurate Predictive Insights And Real-time Decision Support. The Proposed System Presents An Intelligent Web-based Solution Developed Using The Django Framework, Integrating Advanced Machine Learning (ML) Techniques For Automated Vehicle Analysis And Prediction. The System Supports Both Classification And Regression Tasks Based On The Classification And Regression Trees (CART) Methodology, Including Vehicle Condition And Performance Optimization (classification), As Well As Engine Performance And Fuel Efficiency (regression). Multiple ML Algorithms Such As Ridge, Huber, SLIM, And A Novel PCN-FIGS (Polynomial Convolution Network With Fast Interpretable Greedy-Tree Sums) Model Are Implemented. The PCN-FIGS Model Enhances Feature Representation Through Polynomial Expansion And Convolution-based Smoothing, Resulting In Improved Predictive Performance. Experimental Results Demonstrate That The Proposed Model Achieves High Accuracy In Classification Tasks And Strong R² Scores In Regression Analysis. The System Incorporates Exploratory Data Analysis (EDA), Model Comparison, And Both Single And Batch Prediction Functionalities. Role-based Access Control Enables Corporate Users To Perform Advanced Analytics, While General Users Utilize Prediction Features. The Research Is Completed By Integrating Data Preprocessing, Model Training, Evaluation, And Deployment Into A Unified And User-friendly Platform, Providing A Scalable And Efficient Solution For Real-time Vehicle Performance Prediction.

Published:

22-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

752-762

Section:

Articles

License:

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

How to Cite