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 13, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

A hybrid CNN-transformer model with adaptive activation function for potato leaf disease classification.

Ayan Mondal1, Ayan Chatterjee2, Nurilla Avazov3

  • 1School of Electrical Engineering, Aalto University, Otakaari 1B, 02150, Espoo, Finland.

Scientific Reports
|January 6, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Light Acquisition02:16

Light Acquisition

9.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
9.4K

You might also read

Related Articles

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

Sort by
Same author

Cr(III)-Salen-Catalyzed Enantioselective C3-Aryloxylation of Spiroepoxy Oxindoles.

The Journal of organic chemistry·2026
Same author

Gastrointestinal image classification with GIDNet CNN model and non-linear Tansh activation function.

Computers in biology and medicine·2026
Same author

Evidence of spin-phonon-charge coupling and spin-orbit excitations in quasi-one-dimensional Ising spin chain system<i>α</i>-CoV<sub>2</sub>O<sub>6</sub>.

Journal of physics. Condensed matter : an Institute of Physics journal·2026
Same author

Integrative Lifestyle Strategies for Osteoarthritis Management in Post-Menopausal Women: Insights on Exercise and Diet.

Current rheumatology reviews·2026
Same author

Flatbands, Landau levels, Hall conductivity and Hofstadter butterfly in large-angle twisted bilayer graphene: a high pressure study.

Journal of physics. Condensed matter : an Institute of Physics journal·2025
Same author

Systems-Integrated Thermostable Vaccine Delivery: Converging Cold-Chain-Free Design, AI-Augmented Formulation, and Climate-Resilient Infrastructure.

Molecular pharmaceutics·2025

This study introduces potato leaf diseases DenseNet (PLDNet), a hybrid deep learning model for accurate potato disease classification. PLDNet achieves high accuracy, offering an efficient solution for automated plant disease identification.

Area of Science:

  • Agricultural Science
  • Computer Science
  • Artificial Intelligence

Background:

  • Potato cultivation faces significant yield and quality losses due to various diseases.
  • Current disease detection methods are often inefficient, inaccurate, and labor-intensive.
  • Automated disease identification is crucial for sustainable agriculture.

Purpose of the Study:

  • To develop a novel hybrid deep learning architecture for accurate potato leaf disease classification.
  • To introduce an adaptive parametric activation function to enhance model performance.
  • To provide an efficient and scalable solution for automated plant disease identification.

Main Methods:

  • A hybrid deep learning architecture, potato leaf diseases DenseNet (PLDNet), was developed, integrating DenseNet with a Transformer-based attention module.
Keywords:
AFpMActivation functionCNNClassificationPFpMPLDNetPotato plant disease

Related Experiment Videos

Last Updated: Jan 13, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
  • An Adaptive Flatten p-Mish (AFpM) activation function was proposed to improve learning flexibility and representational capacity.
  • The PLDNet model was evaluated on the PlantVillage and Mendeley datasets.

    • Main Results:

    • PLDNet achieved classification accuracies of 99.54% on the PlantVillage dataset and 87.50% on the Mendeley dataset.
    • The proposed AFpM activation function demonstrated superior performance compared to Mish, Swish, and PFpM activation functions.
    • AFpM improved accuracy by 2.52% on Mendeley and 1.93% on PlantVillage compared to PFpM, and by over 3% compared to Swish and Mish.

    Conclusions:

    • The PLDNet framework offers a highly accurate and efficient approach for automated potato leaf disease identification.
    • The novel AFpM activation function enhances deep learning model performance through adaptive nonlinearity and dynamic gradient control.
    • The study demonstrates strong generalization capabilities, paving the way for improved crop disease management strategies.