Abstract :

The Rapid Growth Of Wireless Communication Technologies Such As WiFi, 4G, And 5G Has Significantly Increased The Demand For Intelligent Systems Capable Of Analysing Network Performance And Predicting Signal Behaviour. Network Signal Quality Plays A Crucial Role In Determining Data Transmission Efficiency, Connection Stability, And Overall User Experience. This Research Focuses On The Development Of A Web-based Machine Learning System For Network Signal Analysis And Prediction Using Python, Flask, And Various Machine Learning Algorithms. The Primary Challenge Addressed Is The Difficulty In Accurately Analysing Network Signal Metrics And Predicting Key Parameters, Such As Network Type And Signal Strength, Using Conventional Methods. Traditional Network Monitoring Systems Primarily Rely On Graphical Dashboards To Observe Parameters Like Latency, Throughput, And Signal Strength. However, These Approaches Lack Automated Data Preprocessing Techniques, Including Feature Encoding, Normalization, And Handling Of Missing Values. To Address These Limitations, The Proposed System Introduces A Machine Learning-based Web Application For Advanced Network Signal Analytics. The System Is Developed Using The Flask Framework And Integrates Multiple Machine Learning Models To Process And Analyse Network Datasets. Specifically, The Solution Employs Ridge Classifier (RC), Ridge Regressor (RR), Decision Tree Classifier (DTC), Decision Tree Regressor (DTR), Along With Hybrid Classifier (HC) And Hybrid Regressor (HR) Models Combined With Multi-Layer Perceptron (MLP) And Categorical Boosting (CB). Network Type Prediction Is Treated As A Classification Task, While Signal Strength Prediction Is Handled As A Regression Task. Model Performance Is Evaluated Using Accuracy, Precision, Recall, F1-score, MAE, MSE, RMSE, And R² Score, Ensuring Effective Comparison And Optimal Model Selection Within An Interactive Web-based Platform

Published:

10-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2221-2232

Section:

Articles

License:

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

How to Cite