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

719
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...
719
Force Classification01:22

Force Classification

1.4K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.4K
Classification of Systems-I01:26

Classification of Systems-I

272
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
272
Classification of Systems-II01:31

Classification of Systems-II

215
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
215
Reducing Line Loss01:18

Reducing Line Loss

188
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
188
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

349
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
349

You might also read

Related Articles

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

Sort by
Same author

Triple-amplification electrochemiluminescence aptasensor integrating single-atom nanozyme catalysis with CRISPR-Cas12a/HCR cascade for zearalenone detection.

Mikrochimica acta·2026
Same author

Targeting complement and coagulation cascades with Buyang Huanwu Decoction attenuates acute inflammation and enhances neuroprotection in spinal cord injury.

Science China. Life sciences·2026
Same author

Corrigendum to "Confirmation of pain-related neuromodulation mechanism of Bushen Zhuangjin Decoction on knee osteoarthritis" [J. Ethnopharmacol. 324 (2024) 117772].

Journal of ethnopharmacology·2026
Same author

Efficient Extracellular Production of Insulin Glargine in Trichoderma reesei by an Integrative Secretion-Based Strategy.

Microbial biotechnology·2026
Same author

The correlation between left atrial appendage morphology and thromboembolic risk in atrial fibrillation.

Frontiers in stroke·2026
Same author

Injectable Hydrogel Microspheres for Osteoarthritis Therapy via Endogenous Mesenchymal Stem Cells Homing and Chondrogenic Differentiation Enhancement.

Advanced healthcare materials·2025

Related Experiment Video

Updated: Aug 26, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

608

Minimalistic fully convolution networks (MFCN): pixel-level classification for hyperspectral image with few labeled

Buyun Xu, Weijun Hou, Yiwei Wei

    Optics Express
    |October 12, 2022
    PubMed
    Summary

    This study introduces an image-wise deep learning method for hyperspectral image (HSI) classification, utilizing a minimalistic fully convolutional network (MFCN) and a novel semi-supervised loss function for efficient pixel-level classification with minimal labeled data.

    More Related Videos

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
    08:47

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

    Published on: February 9, 2024

    1.6K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.3K

    Related Experiment Videos

    Last Updated: Aug 26, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    608
    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
    08:47

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

    Published on: February 9, 2024

    1.6K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.3K

    Area of Science:

    • Remote Sensing
    • Computer Vision
    • Machine Learning

    Background:

    • Current deep learning methods for hyperspectral image (HSI) classification predominantly rely on pixel-wise or patch-wise approaches.
    • These existing methods often require substantial labeled data for effective training, limiting their applicability in scenarios with limited annotations.

    Purpose of the Study:

    • To propose a novel image-wise classification method for hyperspectral images (HSI).
    • To develop a minimalistic fully convolutional network (MFCN) and a semi-supervised loss function capable of performing pixel-level classification with limited labeled samples.
    • To demonstrate the effectiveness of the proposed method on new benchmark HSI datasets.

    Main Methods:

    • An image-wise classification approach is introduced, using the entire hyperspectral cube as network input.
    • A minimalistic fully convolutional network (MFCN) architecture is designed for efficient processing.
    • A semi-supervised loss function is developed to leverage limited labeled data for pixel-level classification.

    Main Results:

    • The proposed image-wise method, MFCN, and semi-supervised loss achieved effective pixel-level classification on three new benchmark HSI datasets (WHU-Hi-LongKou, WHU-Hi-HanChuan, WHU-Hi-HongHu).
    • The method demonstrated strong performance even with extremely limited labeled data (0.11%-0.16% of total pixels).
    • Ablation studies and theoretical analysis confirmed the effectiveness and superiority of the proposed design choices.

    Conclusions:

    • The developed image-wise classification method offers a significant advancement over traditional pixel-wise and patch-wise approaches for HSI classification.
    • The combination of MFCN and the semi-supervised loss function enables accurate HSI classification with minimal labeled samples, addressing a key challenge in the field.
    • The proposed method shows great potential for practical applications of HSI analysis where labeled data is scarce.