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 Concept Videos

Classification of Signals01:30

Classification of Signals

1.6K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.6K
State Space Representation01:27

State Space Representation

785
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
785

You might also read

Related Articles

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

Sort by
Same author

Gated recurrent unit model for forecasting greenhouse gas concentrations with uncertainty quantification.

Frontiers in artificial intelligence·2026
Same author

Agent-based simulation of seasonal malaria chemoprevention strategy in Southern Tanzania: comparing dihydroartemisinin-piperaquine with or without primaquine.

Malaria journal·2026
See all related articles

Related Experiment Video

Updated: Apr 30, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

605

Efficient spatio-temporal modeling for sign language recognition using CNN and RNN architectures.

Kasian Myagila1,2, Devotha Godfrey Nyambo1, Mussa Ally Dida1

  • 1School of Computation and Communication Science and Engineering, The Nelson Mandela African Institution of Science and Technology, Arusha, Tanzania.

Frontiers in Artificial Intelligence
|September 10, 2025
PubMed
Summary

This study introduces a deep learning model for recognizing Tanzania Sign Language, achieving 94% accuracy. The model shows promise but requires further development for signer-independent recognition.

Keywords:
CNN-GRUCNN-LSTMELU activation functionTanzania sign languagedeep learningsign language

Related Experiment Videos

Last Updated: Apr 30, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

605

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Bridging communication gaps for speech-impaired individuals is crucial.
  • Sign language recognition faces challenges with dynamic word signs.
  • Mobile phone data presents opportunities for sign language research.

Purpose of the Study:

  • To investigate deep learning algorithms for Tanzania Sign Language recognition.
  • To evaluate CNN-LSTM and CNN-GRU architectures using mobile phone selfie data.
  • To propose an enhanced CNN-GRU model with ELU activation for improved performance.

Main Methods:

  • Utilized Tanzania Sign Language datasets captured via mobile phone selfie cameras.
  • Implemented and compared Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) architectures.
  • Proposed a novel CNN-GRU model incorporating an Exponential Linear Unit (ELU) activation function.

Main Results:

  • The proposed CNN-GRU with ELU activation achieved 94% accuracy.
  • This performance surpassed the standard CNN-GRU (93%) and CNN-LSTM models.
  • Signer-independent recognition yielded variable results, with a maximum accuracy of 66%.

Conclusions:

  • The developed CNN-GRU model with ELU activation demonstrates high accuracy for sign language recognition.
  • Further research is needed to enhance signer independence and address challenges like hand dominance.
  • Optimizing spatial features is key for improving generalization in sign language recognition systems.