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 Systems-I01:26

Classification of Systems-I

366
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:
366
Classification of Systems-II01:31

Classification of Systems-II

259
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,
259
Classification of Signals01:30

Classification of Signals

1.0K
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...
1.0K
Force Classification01:22

Force Classification

1.8K
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,...
1.8K
Methods of Classification and Identification01:28

Methods of Classification and Identification

340
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
340

You might also read

Related Articles

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

Sort by
Same author

Stability analysis of stochastic networked control systems under deception attacks: A novel self-triggered impulsive framework.

ISA transactions·2025
Same author

Sliding Flexible Prescribed Performance Boundary-Guided Reinforcement Learning Control for Input-Constrained Nonlinear Systems.

IEEE transactions on cybernetics·2025
Same author

Dual Flexible Prescribed Performance Control of Input Saturated High-Order Nonlinear Systems.

IEEE transactions on cybernetics·2025
Same author

DoS attacks resilience of heterogeneous complex networks via dynamic event-triggered impulsive scheme for secure quasi-synchronization.

ISA transactions·2024
Same author

Prescribed-Time Output Feedback Control for Cyber-Physical Systems Under Output Constraints and Malicious Attacks.

IEEE transactions on cybernetics·2024
Same author

Unified Fuzzy Control of High-Order Nonlinear Systems With Multitype State Constraints.

IEEE transactions on cybernetics·2023

Related Experiment Video

Updated: Oct 18, 2025

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

4.4K

A Novel Handwritten Digit Classification System Based on Convolutional Neural Network Approach.

Ali Abdullah Yahya1, Jieqing Tan2, Min Hu2

  • 1School of Computer and Information, Anqing Normal University, Anqing 246011, China.

Sensors (Basel, Switzerland)
|September 28, 2021
PubMed
Summary
This summary is machine-generated.

This study enhances Convolutional Neural Network (CNN) classification by optimizing filter size using effective receptive field (ERF) calculation, improving data preparation, and employing data augmentation. The proposed CNN achieves state-of-the-art handwritten digit recognition accuracy, even with added noise.

Keywords:
MNIST handwritten digit databaseRoot Mean Square Propagation (RMSprop)batch normalizationdata augmentationreceptive field

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

999
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K

Related Experiment Videos

Last Updated: Oct 18, 2025

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

4.4K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

999
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Existing Convolutional Neural Network (CNN) classification algorithms often overlook critical factors like filter size, data quality, and noise, hindering accuracy.
  • Inadequate data preparation and dataset limitations can lead to misleading results and reduced classification performance.
  • Real-world image degradation necessitates robust algorithms capable of handling noise.

Purpose of the Study:

  • To introduce a refined CNN classification approach that addresses the limitations of existing algorithms.
  • To enhance classification accuracy by incorporating domain knowledge for optimal filter size selection.
  • To improve the robustness and generalization of CNNs through advanced data handling techniques.

Main Methods:

  • Calculated the effective receptive field (ERF) to determine optimal filter sizes for CNNs.
  • Implemented rigorous data preparation to remove redundant variables and ensure data relevance.
  • Utilized data augmentation techniques to mitigate dataset limitations and reduce training/validation errors.
  • Introduced additive white Gaussian noise (σ = 0.5) to the MNIST dataset to simulate real-world conditions.

Main Results:

  • Achieved state-of-the-art performance in handwritten digit recognition with 99.98% accuracy on the clean MNIST dataset.
  • Demonstrated high robustness with 99.40% accuracy on the MNIST dataset even with 50% added noise.
  • The proposed methods significantly improved classification accuracy compared to conventional CNN algorithms.

Conclusions:

  • The integration of ERF-based filter size selection, meticulous data preparation, and data augmentation substantially boosts CNN classification accuracy.
  • The developed CNN algorithm exhibits superior performance and robustness in handwritten digit recognition tasks, outperforming existing methods.
  • Addressing data quality and noise is crucial for advancing CNN performance in practical applications.