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

Search research articles

Related Experiment Video

Updated: May 21, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

An explainable multimodal temporal deep learning framework for intrusion detection (EMT-IDNet) in IoT environments.

Anurag Jain¹, Abhirup Khanna², Amit Pimpalkar³

¹School of Computer Science & Engineering, IILM University, Gurugram, Haryana, India.

Scientific Reports

|May 19, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Influenza Vaccine Effectiveness Against Pediatric Death in the United States: 2016-2025.

Pediatrics·2026

Same author

A blockchain-enabled multi-objective reinforcement learning framework for secure energy- and time-efficient smart path planning in cloud environments.

Scientific reports·2026

Same author

SmartGridDrive: an integrated adaptive Q-learning framework for precision self-parking and reverse navigation in dynamic grid environments-a proof-of-concept study.

Scientific reports·2026

Same author

A multi-domain graph-integrated neural framework for robust acoustic anomaly detection under adverse environmental conditions.

Scientific reports·2026

Same author

Multi-Objective AI Optimization of Plastic Waste Pyrolysis Integrating Energy Return on Investment for Circular Polymer Recycling.

Polymers·2026

Same author

SPHTRLM: secure and privacy-preserving hyperparameter-tuned reinforcement learning method for robot path finding in dynamic environments.

Scientific reports·2026

This summary is machine-generated.

This study introduces EMT-IDNet, a deep learning framework for Internet of Things (IoT) security. It enhances intrusion detection by analyzing multimodal data and temporal patterns, improving accuracy and interpretability.

Area of Science:

Cybersecurity
Artificial Intelligence
Internet of Things (IoT)

Background:

The rapid expansion of Internet of Things (IoT) ecosystems poses significant security challenges due to device heterogeneity, dynamic network behavior, and inherent security limitations.
Traditional intrusion detection systems (IDS) struggle with multi-stage attacks in IoT environments, primarily due to reliance on single data sources and inadequate temporal analysis.
Existing methods lack the ability to effectively model complex, time-dependent attack sequences common in IoT networks.

Purpose of the Study:

To develop an explainable multimodal temporal deep learning framework for enhanced intrusion detection in IoT systems (EMT-IDNet).
To address the limitations of traditional IDS by integrating diverse data sources and improving temporal modeling capabilities.
To provide interpretable insights into detected threats, increasing the practical utility of IoT security solutions.

Keywords:

Cyberattacks Explainable AI Internet of Things Intrusion detection system Multi-modal threat detection

Related Experiment Videos

Last Updated: May 21, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Main Methods:

The proposed EMT-IDNet framework integrates network traffic, host operating system logs, and IoT telemetry data.
It employs modality-specific encoders and a cross-modal attention-based fusion block for comprehensive data analysis.
A temporal attention module identifies critical attack sequences and time moments, coupled with an attention-based hierarchical multi-layered perceptron (TA-MLP) for classification.

Main Results:

EMT-IDNet achieved exceptional performance on the TON-IoT dataset, with 99.98% accuracy, 99.99% precision, 99.97% recall, and 99.98% F1-score for binary classification.
The Area Under the Curve (AUC) value reached 0.9999, indicating highly reliable detection capabilities.
The framework demonstrated significant temporal and modality-level explanations, validated through attention weight visualization.

Conclusions:

EMT-IDNet effectively overcomes the limitations of traditional IDS in IoT security by leveraging multimodal data and temporal deep learning.
The framework provides high accuracy and efficiency in detecting both binary and multi-class intrusions.
The explainability features enhance trust and practical applicability for real-world IoT security deployments.