Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm
This study highlights the urgent need for effective real-time network security solutions in the face of increasing cyber threats. It examines the performance of a logistic regression model enhanced by Bayesian optimization for detecting TOR traffic using the UNB-CIC TOR-NonTOR datasets and a Bayesia...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Journal of Engineering |
| Online Access: | http://dx.doi.org/10.1155/je/5430763 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849236616749514752 |
|---|---|
| author | Manisankar Sannigrahi R. Thandeeswaran |
| author_facet | Manisankar Sannigrahi R. Thandeeswaran |
| author_sort | Manisankar Sannigrahi |
| collection | DOAJ |
| description | This study highlights the urgent need for effective real-time network security solutions in the face of increasing cyber threats. It examines the performance of a logistic regression model enhanced by Bayesian optimization for detecting TOR traffic using the UNB-CIC TOR-NonTOR datasets and a Bayesian-optimized random forest model for the CIC-Darknet2020 dataset. The research evaluates four key machine learning algorithms: Random forest, logistic regression, support vector machine (SVM), and K-nearest neighbors (K-NN). Bayesian optimization is employed to systematically fine-tune the model’s hyperparameters, thereby improving accuracy and efficiency by concentrating on promising areas of the hyperparameter space and avoiding unnecessary evaluations. The findings indicate that the proposed models effectively detect TOR traffic with higher accuracy and fewer false positives, essential for real-time threat mitigation. Compared to other machine learning algorithms, the proposed models demonstrate superior performance in balancing accuracy, computational efficiency, and detection speed, making them ideal for real-time network security applications. This approach’s flexibility to adapt to various network conditions and datasets ensures consistent optimal performance as traffic patterns change. |
| format | Article |
| id | doaj-art-b8d1d6f37c10458b9948179fc6db4ea7 |
| institution | Kabale University |
| issn | 2314-4912 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Engineering |
| spelling | doaj-art-b8d1d6f37c10458b9948179fc6db4ea72025-08-20T04:02:12ZengWileyJournal of Engineering2314-49122025-01-01202510.1155/je/5430763Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest AlgorithmManisankar Sannigrahi0R. Thandeeswaran1Vellore Institute of TechnologyVellore Institute of TechnologyThis study highlights the urgent need for effective real-time network security solutions in the face of increasing cyber threats. It examines the performance of a logistic regression model enhanced by Bayesian optimization for detecting TOR traffic using the UNB-CIC TOR-NonTOR datasets and a Bayesian-optimized random forest model for the CIC-Darknet2020 dataset. The research evaluates four key machine learning algorithms: Random forest, logistic regression, support vector machine (SVM), and K-nearest neighbors (K-NN). Bayesian optimization is employed to systematically fine-tune the model’s hyperparameters, thereby improving accuracy and efficiency by concentrating on promising areas of the hyperparameter space and avoiding unnecessary evaluations. The findings indicate that the proposed models effectively detect TOR traffic with higher accuracy and fewer false positives, essential for real-time threat mitigation. Compared to other machine learning algorithms, the proposed models demonstrate superior performance in balancing accuracy, computational efficiency, and detection speed, making them ideal for real-time network security applications. This approach’s flexibility to adapt to various network conditions and datasets ensures consistent optimal performance as traffic patterns change.http://dx.doi.org/10.1155/je/5430763 |
| spellingShingle | Manisankar Sannigrahi R. Thandeeswaran Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm Journal of Engineering |
| title | Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm |
| title_full | Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm |
| title_fullStr | Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm |
| title_full_unstemmed | Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm |
| title_short | Enhanced Network Traffic Classification Using Bayesian-Optimized Logistic Regression and Random Forest Algorithm |
| title_sort | enhanced network traffic classification using bayesian optimized logistic regression and random forest algorithm |
| url | http://dx.doi.org/10.1155/je/5430763 |
| work_keys_str_mv | AT manisankarsannigrahi enhancednetworktrafficclassificationusingbayesianoptimizedlogisticregressionandrandomforestalgorithm AT rthandeeswaran enhancednetworktrafficclassificationusingbayesianoptimizedlogisticregressionandrandomforestalgorithm |