Jove
Visualize
Contact Us

Related Concept Videos

Distributed Loads: Problem Solving01:21

Distributed Loads: Problem Solving

1.1K
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
1.1K
Energy and Power Signals01:17

Energy and Power Signals

1.0K
In an electrical system with a resistor, voltage and current signals facilitate the measurement of power and energy across the resistor. For a continuous-time signal, the total energy over a time interval is defined as the integral of the square of the signal's magnitude over that interval. Mathematically, this is expressed as:
1.0K

You might also read

Related Articles

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

Sort by
Same author

Prevalence of mental health symptoms and its effect on insomnia among healthcare workers who attended hospitals during COVID-19 pandemic: A survey in Dhaka city.

Heliyon·2021
See all related articles
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 7, 2026

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

1.1K

Advancing Machine Learning Strategies for Power Consumption-Based IoT Botnet Detection.

Almustapha A Wakili1, Saugat Guni1, Sabbir Ahmed Khan1

  • 1Department of Computer and Information Sciences, Towson University, Towson, MD 21252, USA.

Sensors (Basel, Switzerland)
|December 31, 2025
PubMed
Summary
This summary is machine-generated.

This study benchmarks intrusion detection models for Internet of Things (IoT) botnets using power consumption. Random Forest excels on single devices, while CNN + Transformer offers a balance of accuracy and efficiency across devices.

Keywords:
CHASE’19 datasetInternet of Things (IoT)botnet detectiondeep learninghybrid modelsmachine learningpower consumption

Related Experiment Videos

Last Updated: Jan 7, 2026

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

1.1K

Area of Science:

  • Cybersecurity
  • Machine Learning
  • Internet of Things (IoT)

Background:

  • Traditional Intrusion Detection Systems (IDSs) face challenges with encrypted and sparse IoT traffic.
  • Power consumption analysis presents a viable side-channel for device-level botnet detection.
  • Existing research often lacks cross-device generalization and broad model class comparisons.

Purpose of the Study:

  • To conduct a unified benchmarking and comparison of various machine learning models for IoT botnet detection.
  • To evaluate model performance across single-device and cross-device scenarios.
  • To assess both accuracy and efficiency (latency, throughput) of different detection models.

Main Methods:

  • Benchmarking classical (SVM, RF), deep (CNN, LSTM, 1D Transformer), and hybrid models.
  • Utilizing the CHASE'19 dataset and a new three-class botnet dataset.
  • Consistent preprocessing and evaluation across single- and cross-device settings.

Main Results:

  • Random Forest achieved the highest single-device accuracy (99.43%).
  • CNN + Transformer demonstrated a strong accuracy-efficiency trade-off in cross-device detection (94.02% accuracy at ~60,000 samples/s).
  • Performance varied based on the specific device and model configuration.

Conclusions:

  • Provides practical guidance for selecting IoT botnet detection models based on accuracy, latency, and throughput constraints.
  • Establishes a reproducible baseline for power-side-channel Intrusion Detection Systems.
  • Highlights the importance of considering cross-device generalization in model selection.