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

Deconvolution01:20

Deconvolution

511
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...
511
Masking and Demasking Agents01:19

Masking and Demasking Agents

3.4K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
3.4K
Sampling Continuous Time Signal01:11

Sampling Continuous Time Signal

626
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
626
Downsampling01:20

Downsampling

552
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
552
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

348
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
348
Generator Voltage Control01:21

Generator Voltage Control

581
Generator voltage control is crucial for maintaining the stable operation of synchronous generators and wind turbines. In older models, a DC generator driven by the rotor delivers DC power to the rotor's field winding, and the power is transferred through slip rings and brushes. In the latest models, static or brushless exciters are used. Static exciters rectify AC power from the generator terminals and then transfer the DC power directly to the rotor. Brushless exciters, on the other hand, use...
581

You might also read

Related Articles

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

Sort by
Same author

eHealth4U: A pathway from the Cyprus eHealth law to a citizen-centred national EHR prototype interoperable with myHealth@EU and international patient summary.

Digital health·2026
Same author

Bridging language barriers in healthcare: a patient-centric mobile app for multilingual health record access and sharing.

Frontiers in digital health·2025
Same author

Integrating Chatbot Functionality in a Patient Summary Based Healthcare System.

Studies in health technology and informatics·2024
Same author

Empowering Citizens Through Translated Patient Summary Access and Sharing in Digital Health Ecosystems.

Studies in health technology and informatics·2024
Same author

A Prototype of the National EHR system for Cyprus<sup></sup>.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2021
Same author

Integration of Biobanks in National eHealth Ecosystems Facilitating Long-Term Longitudinal Clinical-Omics Studies and Citizens' Engagement in Research Through eHealthBioR.

Frontiers in digital health·2021

Related Experiment Video

Updated: Jan 2, 2026

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

1.6K

Conditional Generative Denoising Autoencoder.

Savvas Karatsiolis, Christos N Schizas

    IEEE Transactions on Neural Networks and Learning Systems
    |December 12, 2019
    PubMed
    Summary

    This study introduces a novel generative denoising autoencoder with an embedded classifier. This model uses class-based features to generate improved data samples, offering a new direction for deep learning research.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Deep Learning

    Background:

    • Generative models are crucial for data synthesis but often lack control over generated features.
    • Existing methods like Variational Autoencoders (VAEs) impose priors on latent distributions, limiting flexibility.
    • Research on supervised and unsupervised learning interaction primarily focuses on unsupervised methods aiding supervised tasks.

    Purpose of the Study:

    • To propose a generative denoising autoencoder with an integrated classifier for enhanced data sample generation.
    • To explore the conditional generation of data samples by incorporating class-based information.
    • To investigate the interaction between supervised and unsupervised learning in the opposite direction of prior research.

    Main Methods:

    Related Experiment Videos

    Last Updated: Jan 2, 2026

    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

    1.6K
  • Developed a conditional generative model using a denoising autoencoder architecture with an embedded classifier.
  • Employed a Markov chain Monte Carlo (MCMC) sampling process guided by labels for desired or undesired classes.
  • Incorporated discriminative information directly into the latent representation of the autoencoder.

    • Main Results:

    • The model successfully generates data samples influenced by predefined class characteristics, allowing for control over feature presence or absence.
    • The embedded classifier aids in leveraging class-based discriminating features for improved sample quality.
    • Demonstrated the benefit of integrating discriminative information within the autoencoder's latent space.

    Conclusions:

    • The proposed model offers a viable alternative to VAEs by allowing direct control over generation through class labels.
    • Integrating supervised learning signals (via the classifier) into unsupervised generative models can enhance performance.
    • This work highlights the potential of using supervised learning to benefit unsupervised learning, reversing the common research trend.