Author(s)

JingYa Sun^1*, ZiJie Cao²

Affiliation(s)

¹Mathematics and Physics Teaching Department, Hebei GEO University, Shijiazhuang 050030, Hebei, China.

²School of Information Engineering, College of Science & Technology Ningbo University, Ningbo 315300, Zhejiang, China.

Corresponding Author

JingYa Sun

ABSTRACT

With the rapid development of Internet technology, traditional intrusion detection methods have limitations. Although machine learning technology provides new ideas for intrusion detection, its efficiency and accuracy in large-scale data environment still need to be optimized. This study aims to propose an intrusion detection method that combines feature selection with optimized machine learning algorithms to solve the problems of data redundancy and category imbalance, and to reduce the false alarm rate. Based on the UNSW-NB15 dataset, ANOVA, chi-square test and Gini coefficient are used for feature selection, combined with principal component analysis (PCA) dimensionality reduction technique. The model is constructed by algorithms such as logistic regression and random forest, and hyperparameter optimization is carried out using GridSearchCV, and data imbalance and outliers are handled by stratified sampling and RobustScaler. The experiments show that the balanced accuracy of the logistic regression model is 70%, and the accuracy of the random forest model is 67.33%. Feature selection significantly improves the model performance. The method proposed in this study demonstrates high efficiency and reliability in large-scale network data and provides a technical basis for the design of real-time intrusion detection systems.

KEYWORDS

Network intrusion detection; Feature selection; ANOVA; Logistic regression

CITE THIS PAPER

JingYa Sun, ZiJie Cao. Network intrusion detection methods based on machine learning. Journal of Computer Science and Electrical Engineering. 2025, 7(2): 71-77. DOI: https://doi.org/10.61784/jcsee3050.

REFERENCES

[1] Wei Jintai, Gao Qiong. Research on intrusion detection system based on information gain and random forest classifier. Journal of North Central University (Natural Science Edition), 2018, 39(01): 74-79+88.

[2] LJ Zhu, G P Zhao, L H Kang. Intrusion detection method based on the combination of MI feature selection and KNN classifier. Gansu Science and Technology, 2022, 38(15): 33-36.

[3] Hongyan He, Guoyan Huang, Bing Zhang, et al. Anomaly detection model based on recursive elimination of limit tree features and LightGBM. Information Network Security, 2022(1): 64-71.

[4] Samantaray M, Barik C R, Biswal K A. A comparative assessment of machine learning algorithms in the IoT-based network intrusion detection systems. Decision Analytics Journal, 2024: 11100478.

[5] Ali M A, Owais M S Q, Andleeb M S, et al. Robust genetic machine learning ensemble model for intrusion detection in network traffic. Scientific Reports, 2023, 13(1): 17227-17227.

[6] Nabi F, Zhou X. Enhancing intrusion detection systems through dimensionality reduction: a comparative study of machine learning techniques for cyber security. Cyber Security and Applications, 2024: 2100033.

[7] Arco M G J, Carrión M R, Gómez R A R, et al. Methodology for the Detection of Contaminated Training Datasets for Machine Learning-Based Network Intrusion-Detection Systems. Sensors, 2024, 24(2).

[8] Sarhan M, Layeghy S, Moustafa N, et al. Feature extraction for machine learning-based intrusion detection in IoT networks. Digital Communications and Networks, 2024, 10(01): 205-216.

[9] Ren Jiadong, Zhang Yafei, Zhang Bing, et al. A feature selection-based classification method for industrial internet intrusion detection. Computer Research and Development, 2022, 59(05): 1148-1159.