Jove
Visualize
联系我们

相关实验视频

混合AI入侵检测:平衡准确性和效率

Vandit R Joshi1, Kwame Assa-Agyei1, Tawfik Al-Hadhrami1

  • 1Department of Computer Science, Nottingham Trent University, Nottingham NG1 4FQ, UK.

Sensors (Basel, Switzerland)
|December 31, 2025
PubMed
概括
此摘要是机器生成的。

相关概念视频

Accuracy and Precision01:52

Accuracy and Precision

13.8K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.  Highly accurate...
13.8K
Types of Errors: Detection and Minimization01:12

Types of Errors: Detection and Minimization

9.3K
Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
9.3K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Correction: Almuhaya et al. ZBMG-LoRa: A Novel Zone-Based Multi-Gateway Approach Towards Scalable LoRaWANs for Internet of Things. <i>Sensors</i> 2025, <i>25</i>, 5457.

Sensors (Basel, Switzerland)·2026
Same author

Intelligent reflective surfaces in 5G and beyond: optimizing uplink satellite connectivity for IoT.

PeerJ. Computer science·2025
Same author

ZBMG-LoRa: A Novel Zone-Based Multi-Gateway Approach Towards Scalable LoRaWANs for Internet of Things.

Sensors (Basel, Switzerland)·2025
Same author

Two-stage object detection in low-light environments using deep learning image enhancement.

PeerJ. Computer science·2025
Same author

An Ensemble Machine Learning and Data Mining Approach to Enhance Stroke Prediction.

Bioengineering (Basel, Switzerland)·2024
Same author

SENSES-ASD: a social-emotional nurturing and skill enhancement system for autism spectrum disorder.

PeerJ. Computer science·2024
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

这项研究比较了用于物联网 (IoT) 入侵检测的AI模型. CNN-BiLSTM提供高精度,而XGBoost和随机森林为各种物联网需求提供更快,更具竞争力的检测.

科学领域:

  • 网络安全 网络安全
  • 人工智能的人工智能
  • 物联网 (IoT) 的物联网 (IoT) 的物联网.

背景情况:

  • 物联网 (IoT) 由于资源限制,协议多样性和基础设施异质性而带来了重大安全挑战.
  • 传统的入侵检测系统 (IDS) 与物联网的规模,互操作性,实时需求,数据隐私和不平衡的流量扎,导致虚假阳性.

研究的目的:

  • 系统地评估和比较用于物联网入侵检测的代表性AI模型的性能和延迟.
  • 在异质物联网环境中,根据准确度-延迟权衡选择合适的AI模型,提供实证见解.

主要方法:

  • 对三种AI模型进行比较分析:卷积神经网络-双向长期短期记忆 (CNN-BiLSTM),随机森林和XGBoost.
  • 对两个基准数据集进行评估:NSL-KDD和UNSW-NB15.
  • 对每个模型的检测性能 (例如,F1得分) 和推断延迟的量化.

主要成果:

  • CNN-BiLSTM实现了最高的检测能力,F1得分高达0.986,但产生了更高的计算开销.
  • XGBoost和Random Forest展示了具有竞争力的准确性,其推理延迟显著降低 (在传统硬件上为次毫秒).
  • 在评估的模型中观察到检测准确度和推断延迟之间的明显权衡.
关键词:
这是一个双LSTM.物联网安全物联网安全物联网安全这是NSL-KDD.东南大西洋 - - NB1515卷积神经网络 (CNN) 是一种神经网络.混合型模型 混合型模型 混合型模型侵入检测系统的入侵检测系统绩效指标 绩效指标 是一个指标.

相关实验视频

结论:

  • 选择用于物联网入侵检测的AI模型取决于特定应用程序对准确性和速度的要求.
  • CNN-BiLSTM适用于精度关键的应用,而XGBoost和Random Forest则适用于延迟敏感的场景.
  • 这些发现支持在各种物联网生态系统中提供有效安全的知情部署决策.