Jove
Visualize
Contact Us
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 Videos

IoTDI-ImbS: A Precise Identification Model and Algorithm for IoT Devices from Network Traffic.

Junhao Qian1, Shuang Zhao2, Zhihao Wang2

  • 1School of Automation and Intelligent Science, Jiangnan University, Wuxi 214122, China.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

Related Concept Videos

Rapid Identification of Pathogens01:25

Rapid Identification of Pathogens

MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...
Automated Microbial Diagnostics01:24

Automated Microbial Diagnostics

Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...

You might also read

Related Articles

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

Sort by
Same author

The impact of different immunosuppressants and acute immune rejection on clinical outcomes in diverse solid organ transplant recipients.

Frontiers in immunology·2026
Same author

Generation of multi-μJ few-cycle blue self-compressed soliton pulses in large-core hollow-capillary fibers.

Optics letters·2026
Same author

Association between "Life's Critical 9" health score and the risk of inflammatory bowel disease: a prospective cohort study from the UK biobank.

BMC public health·2026
Same author

Photon-counting CT versus Energy-integrating Detector CT Performance for Various BMI and Tumor Sizes in Lung Cancer.

Radiology·2026
Same author

Gut microbiota-dependent 24-hydroxycholesterol metabolism contributes to capsaicin-induced amelioration of Alzheimer's disease-like pathology in mice.

Nature communications·2026
Same author

Seismic damage evolution and dynamic characteristics of the surrounding rock in tunnel portal anti-dip slopes reinforced with frame beams.

Scientific reports·2026

This study introduces IoTDI-ImbS, a novel method for identifying Internet of Things (IoT) devices by converting network traffic into images and using generative adversarial networks to address data imbalance, significantly improving recognition accuracy.

Area of Science:

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

Background:

  • Accurate identification of Internet of Things (IoT) devices is crucial for security due to increasing cyberattacks.
  • Existing methods using raw, statistical, or deep features have limitations in feature extraction, classifier dependency, and handling traffic sample variations.
  • These limitations result in suboptimal recognition accuracy for certain IoT devices.

Purpose of the Study:

  • To propose a novel method, IoTDI-ImbS, for accurate IoT device identification.
  • To address the challenge of imbalanced datasets in IoT traffic analysis.
  • To enhance the recognition accuracy of IoT end devices through advanced feature extraction and data augmentation techniques.

Main Methods:

  • Network traffic payload information is selected as raw features and converted into grayscale images.
Keywords:
IoT device identificationbidirectional long short-term memory neural network (BiLSTM)network trafficresidual network 18 (ResNet18)

Related Experiment Videos

  • A generative adversarial network-based IoT terminal devices traffic generation (NTGAN) algorithm is employed to generate synthetic traffic samples for underrepresented devices, mitigating sample imbalance.
  • A ResNet18-BiLSTM model is constructed, leveraging ResNet18 for spatial feature mining and BiLSTM for temporal feature extraction to boost recognition accuracy.

    • Main Results:

    • The IoTDI-ImbS method demonstrates superior performance in recognition accuracy compared to existing approaches across various IoT datasets.
    • The method effectively addresses sample imbalance issues, leading to improved identification of minority device classes.
    • Experimental results on UNSW and IoT Sentinel datasets show high accuracy (99.1% on UNSW, 98.7% precision on IoT Sentinel) and an approximate 3.5% improvement for minority classes after integrating NTGAN.

    Conclusions:

    • IoTDI-ImbS offers a more effective solution for IoT device recognition, outperforming baseline methods.
    • The integration of NTGAN significantly enhances the identification of devices with limited data samples.
    • The proposed method proves robust and accurate in diverse IoT environments, contributing to improved IoT security.