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 Video

Updated: Jan 10, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.2K

A tiny inertial transformer for human activity recognition via multimodal knowledge distillation and explainable AI.

Ismail Lamaakal1, Chaymae Yahyati1, Yassine Maleh2

  • 1Multidisciplinary Faculty of Nador, Mohammed Premier University, Oujda, Morocco.

Scientific Reports
|November 27, 2025
PubMed
Summary

Related Concept Videos

Inertia Tensor01:24

Inertia Tensor

1.1K
The concept of the inertia tensor is employed to depict the mass distribution and rotational inertia of a solid or rigid object. This tensor is expressed through a three-by-three matrix. Each component within this matrix corresponds to varying moments of inertia about specific axes.
The diagonal components of the inertia tensor matrix represent the moments of inertia concerning the principal axes of the object. These primary axes are defined as the axes where the object experiences the least...
1.1K

You might also read

Related Articles

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

Sort by
Same author

Resilient federated intrusion detection with explainable AI: a robust CNN-LSTM architecture for extreme non-IID data distributions.

Scientific reports·2026
Same author

Efficient uncertainty aware human activity recognition on microcontrollers using hyperdimensional computing and conformal prediction.

Scientific reports·2026
Same author

An explainable hybrid CNN-transformer model for sign language recognition on edge devices using adaptive fusion and knowledge distillation.

Scientific reports·2026
Same author

Correction: FastKAN-DDD: A novel fast Kolmogorov-Arnold network-based approach for driver drowsiness detection optimized for TinyML deployment.

PloS one·2026
Same author

Proactive identification of cybersecurity compromises via the PROID compromise assessment framework.

Scientific reports·2025
Same author

FastKAN-DDD: A novel fast Kolmogorov-Arnold network-based approach for driver drowsiness detection optimized for TinyML deployment.

PloS one·2025

XTinyHAR offers a lightweight, transformer-based solution for human activity recognition (HAR) on edge devices. This interpretable model achieves high accuracy and fast inference, making real-time HAR more accessible.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Accurate and interpretable human activity recognition (HAR) is crucial for healthcare, fitness, and smart environments.
  • Deploying HAR models on resource-constrained edge devices presents significant challenges due to computational limitations.

Purpose of the Study:

  • To introduce XTinyHAR, a novel, lightweight, transformer-based unimodal framework for human activity recognition.
  • To enable efficient and interpretable HAR on edge devices through cross-modal knowledge distillation.

Main Methods:

  • Developed XTinyHAR, a unimodal transformer framework utilizing temporal positional embeddings and attention rollout.
  • Employed cross-modal knowledge distillation from a multimodal teacher model for training.

Related Experiment Videos

Last Updated: Jan 10, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.2K
  • Evaluated performance on UTD-MHAD and MM-Fit datasets.

    • Main Results:

    • Achieved high test accuracies of 98.71% (UTD-MHAD) and 98.55% (MM-Fit) with matching F1-scores.
    • Demonstrated excellent interpretability with Cohen's Kappa above 0.98.
    • Model size is 2.45 MB, with fast inference (3.1 ms CPU, 1.2 ms GPU) and low computational cost (11.3M FLOPs).

    Conclusions:

    • XTinyHAR provides a high-performance, interpretable, and deployable solution for real-time HAR on edge devices.
    • Ablation studies validated the effectiveness of individual model components.
    • Subject-wise evaluations confirmed strong generalization capabilities across different users.