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

Aggregates Classification01:29

Aggregates Classification

1.1K
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
1.1K
Force Classification01:22

Force Classification

2.5K
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,...
2.5K
Classification of Systems-II01:31

Classification of Systems-II

540
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,
540
Classification of Systems-I01:26

Classification of Systems-I

640
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:
640
Correlation and Regression00:53

Correlation and Regression

3.7K
In statistics, correlation describes the degree of association between two variables. In the subfield of linear regression, correlation is mathematically expressed by the correlation coefficient, which describes the strength and direction of the relationship between two variables. The coefficient is symbolically represented by 'r' and ranges from -1 to +1. A positive value indicates a positive correlation where the two variables move in the same direction. A negative value suggests a...
3.7K
Classification of Signals01:30

Classification of Signals

1.5K
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...
1.5K

You might also read

Related Articles

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

Sort by
Same author

Repurposed ethoxzolamide reprograms antitumor immunity through β-TrCP-dependent PD-L1 ubiquitination.

Cell reports. Medicine·2026
Same author

Shared genetic regulators and diagnostic biomarkers in gallbladder stone and cholangiocarcinoma: A comprehensive comparative transcriptomic analysis.

Translational oncology·2026
Same author

Pituitary adenylate cyclase-activating polypeptide attenuates coronary microembolization-induced myocardial apoptosis via PAC1 receptor activation in rats.

Tissue & cell·2026
Same author

Dispersion Compensation and Multi-Beam Interference Correction Algorithm for Thickness Measurement of SiC Epitaxial Layer.

Sensors (Basel, Switzerland)·2026
Same author

Perceived message effectiveness and readiness to quit among youth in Guangdong: The mediating role of self-efficacy and the moderating effect of nicotine dependence.

Medicine·2026
Same author

Structure and druggable conformation of the homodimeric lipoprotein transporter of Acinetobacter baumannii.

Nature communications·2026

Related Experiment Video

Updated: Feb 28, 2026

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

1.1K

Training DCNN by Combining Max-Margin, Max-Correlation Objectives, and Correntropy Loss for Multilabel Image

Weiwei Shi, Yihong Gong, Xiaoyu Tao

    IEEE Transactions on Neural Networks and Learning Systems
    |June 17, 2017
    PubMed
    Summary

    This study introduces a new objective function for deep convolutional neural networks (DCNNs) to improve multilabel image classification. The novel approach enhances accuracy and simplifies thresholding for better image analysis.

    Related Experiment Videos

    Last Updated: Feb 28, 2026

    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

    1.1K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Multilabel image classification assigns multiple labels to an image.
    • Deep Convolutional Neural Networks (DCNNs) are effective but require optimized objective functions for complex tasks.
    • Existing methods face challenges in accuracy and threshold determination.

    Purpose of the Study:

    • To develop a novel objective function for DCNNs to enhance multilabel image classification performance.
    • To improve the accuracy and ease threshold determination in image classifiers.
    • To create an end-to-end trainable framework for advanced image analysis.

    Main Methods:

    • Proposed a novel objective function comprising max-margin, max-correlation, and correntropy loss.
    • Implemented the objective function within general DCNN architectures (AlexNet, VGG-16, GoogLeNet, ResNet).
    • Utilized Pascal VOC 2007 and MIR Flickr 25K datasets for comprehensive evaluation.

    Main Results:

    • The proposed objective function significantly improved performance accuracies across various DCNN models.
    • Max-margin objective enhanced classifier accuracy and simplified threshold setting.
    • Max-correlation objective facilitated learning of a robust latent semantic space.
    • Correntropy loss effectively minimized training errors compared to traditional softmax loss.

    Conclusions:

    • The novel objective function offers a significant advancement in DCNN-based multilabel image classification.
    • The framework demonstrates superior performance and robustness on benchmark datasets.
    • This approach provides a more effective tool for complex image recognition tasks.