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

1.0K
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
Deconvolution01:20

Deconvolution

290
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
290
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

482
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...
482
Classification of Systems-I01:26

Classification of Systems-I

357
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:
357
Classification of Systems-II01:31

Classification of Systems-II

255
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,
255
Aggregates Classification01:29

Aggregates Classification

413
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...
413

You might also read

Related Articles

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

Sort by
Same author

GeNeX: Genetic Network eXperts Framework for Addressing Validation Overfitting.

IEEE transactions on neural networks and learning systems·2026
Same author

Explainable Image Similarity: Integrating Siamese Networks and Grad-CAM.

Journal of imaging·2023
Same author

Special Issue on Machine Learning and AI for Sensors.

Sensors (Basel, Switzerland)·2023
Same author

Explainable Machine Learning Framework for Image Classification Problems: Case Study on Glioma Cancer Prediction.

Journal of imaging·2021
Same author

Smoothing and stationarity enforcement framework for deep learning time-series forecasting.

Neural computing & applications·2021
Same author

An Improved Self-Labeled Algorithm for Cancer Prediction.

Advances in experimental medicine and biology·2020
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: Oct 12, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets.

Emmanuel Pintelas1, Ioannis E Livieris2, Panagiotis E Pintelas1

  • 1Department of Mathematics, University of Patras, 26500 Patras, Greece.

Sensors (Basel, Switzerland)
|November 27, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a convolutional autoencoder to reduce noise and redundant data in images, improving the stability and reliability of deep learning models for image classification. The new method enhances prediction accuracy by creating robust feature representations.

Keywords:
computer visionconvolutional autoencodersconvolutional neural networksdeep learningdimensionality reductionimage classification

More Related Videos

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

682

Related Experiment Videos

Last Updated: Oct 12, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K
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

682

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Deep convolutional neural networks excel in image classification but are susceptible to noise and high-dimensional data.
  • Vulnerability to noisy inputs leads to unstable and unreliable predictions in deep learning models.
  • Autoencoders offer unsupervised dimensionality reduction for filtering noise and creating stable feature representations.

Purpose of the Study:

  • To address the vulnerability of deep learning models to noisy image data.
  • To propose a novel convolutional autoencoder topological model for data compression and noise filtering.
  • To enhance the performance and reliability of image classification using deep learning.

Main Methods:

  • A convolutional autoencoder was designed for compressing and filtering high-dimensional input images.
  • The filtered and compressed image data was then used to train convolutional neural networks.
  • The approach focused on unsupervised dimensionality reduction to create robust feature representations.

Main Results:

  • The proposed convolutional autoencoder effectively filtered out noise and redundant information.
  • The compressed image representations led to more stable and reliable predictions.
  • Significant performance improvements were observed in deep learning models trained with the processed data.

Conclusions:

  • The integration of a convolutional autoencoder significantly enhances the performance of deep learning models for image classification.
  • This method provides a robust solution for mitigating the impact of noise and high dimensionality in image data.
  • The findings demonstrate the efficacy of unsupervised feature learning for improving deep neural network reliability.