Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Fissios and postoperative complications (FPoC trial): a multicentre, randomised, controlled clinical trial.

BMJ open respiratory research·2026

Same author

Adrenal metastasis of hepatocellular carcinoma after liver transplantation: Case report and systematic review of literature.

World journal of transplantation·2026

Same author

Widespread antimicrobial resistance in the middle Tagus River Basin: Environmental drivers and seasonal dynamics.

Environmental research·2026

Same author

Diagnostic Role and Clinical Impact of Zr-Girentuximab PET-CT for the Diagnosis and Treatment of Clear-Cell Renal Cell Carcinoma.

Diagnostics (Basel, Switzerland)·2026

Same author

Reply regarding the European Respiratory Society and European Society of Thoracic Surgeons clinical practice guideline on fitness for curative intent treatment of lung cancer.

The European respiratory journal·2026

Same author

REACT Score, a Novel Scoring System, Improves the Prediction of Non-Elective Readmissions in Patients With Decompensated Cirrhosis.

Liver international : official journal of the International Association for the Study of the Liver·2026

Search research articles

Related Experiment Video

Updated: Aug 17, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Evaluation of Machine Learning Techniques for Traffic Flow-Based Intrusion Detection.

María Rodríguez¹, Álvaro Alesanco¹, Lorena Mehavilla¹

¹Aragón Institute of Engineering Research (I3A), University of Zaragoza, 50018 Zaragoza, Spain.

Sensors (Basel, Switzerland)

|December 11, 2022

Summary

Machine learning intrusion detection systems (IDS) are crucial for identifying new cyber threats. Tree-based machine learning techniques, particularly PART and J48, demonstrate superior efficiency and speed for real-time network traffic classification.

Keywords:

CICIDS2017 Weka Zeek datasets intrusion detection machine learning traffic flows

More Related Videos

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Published on: February 1, 2020

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Related Experiment Videos

Last Updated: Aug 17, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Published on: February 1, 2020

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Area of Science:

Cybersecurity
Machine Learning
Network Intrusion Detection

Background:

Modern society's increasing reliance on technology necessitates robust cybersecurity measures.
Traditional signature-based threat detection methods are insufficient against novel and frequent cyberattacks.
Machine learning (ML) techniques offer a promising alternative for developing advanced intrusion detection systems (IDS).

Purpose of the Study:

To evaluate various machine learning techniques for network traffic classification.
To determine the most effective ML methods for intrusion detection based on performance and execution time.
To assess the impact of feature selection on classification accuracy and efficiency.

Main Methods:

Utilized the CICIDS2017 dataset, containing benign and malicious network traffic flows.
Evaluated multiple classification algorithms including naive Bayes, logistic regression, multilayer perceptron, and tree-based methods (J48, PART, Random Forest) using Weka software.
Assessed multiclass and binary classification, and applied Correlation-based Feature Selection (CFS) for attribute reduction.
Processed raw traffic captures using Zeek to extract flow-based attributes.

Main Results:

Tree-based methods (PART, J48, Random Forest) achieved high F1 scores (>0.999) on the complete dataset.
Feature reduction using CFS with tree-based techniques maintained high performance (F1 >0.990) while reducing testing time by over 30%.
Zeek-processed data with tree-based classifiers yielded excellent results (F1 >0.997) with low execution times, supporting hundreds of thousands of flows per second.

Conclusions:

Tree-based machine learning techniques are highly suitable for flow-based intrusion detection.
Algorithms like PART and J48 present efficient and faster alternatives to Random Forest for intrusion detection.
Optimized attribute selection significantly enhances the real-time applicability of ML-based IDS.