Network Anomaly Activity Detection Model Based on Feature Correlation Analysis
Bibliographic record
Abstract
Anomalous activity in computer networks can disrupt communication services between computers and potentially lead to attacks.Several previous studies have introduced machine learning-based anomaly detection models and have optimized them using feature selection methods.However, the feature selection process requires a correlation analysis to assess the strength of feature correlations, thereby improving the performance of the detection model.This paper proposes a new approach to detecting anomalous activity that potentially indicates malicious activity in computer networks.It aims to analyze improvements in the classification model's detection performance using correlation intersection analysis with the Pearson and Kendall correlation methods.The contribution lies in the approach of selecting correlated features using both correlation approaches, yielding the best results with eight features.In the experiment, the model uses the UNSW NB-15 public dataset and is limited to three classification methods.The Decision Tree classification method achieved optimal performance, with a detection accuracy of 96.63%, an F1-score of 94.51%, a recall of 97.96%, and a precision of 91.29%.Network administrators can utilize the proposed model to expedite the analysis of anomalous activity and integrate it with intrusion detection systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".