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

You might also read

Related Articles

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

Sort by
Same author

Preventing Post-induction Hypotension During General Anaesthesia: A Dose-Response Study of Ringer's Lactate Guided by the Inferior Vena Cava Collapsibility Index.

Cureus·2026
Same author

A novel role of circCPSF6 regulating antiviral innate immunity via miR-665 and PCBP2-IPS-1 axis in IAV infection.

Molecular therapy. Nucleic acids·2026
Same author

Progress and perspectives on recycling spent electrolytes in lithium-ion batteries: A review.

Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA·2026
Same author

Nitrogen-Doped Carbon Quantum Dots for FRET-Assisted and Smartphone-Enabled Fluorescent Detection of Melatonin in Biological Samples.

Journal of fluorescence·2026
Same author

Profiling of bacterial community associated with sugarcane rhizosphere.

Journal, genetic engineering & biotechnology·2026
Same author

Fluorescent boron and phosphorus Co-doped graphene quantum dots for bovine serum albumin sensing in cow's milk with smartphone-enabled real-time readout.

Journal of materials chemistry. B·2026

Related Experiment Video

Updated: Nov 15, 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

4.7K

Emotion Recognition Using Electrodermal Activity Signals and Multiscale Deep Convolutional Neural Network.

Nagarajan Ganapathy1, Yedukondala Rao Veeranki2, Himanshu Kumar2

  • 1Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India. info.nagarajan@gmail.com.

Journal of Medical Systems
|March 4, 2021
PubMed
Summary

This study classifies emotional states using electrodermal activity (EDA) signals and a Multiscale Convolutional Neural Network (MSCNN). The MSCNN approach achieved high accuracy, demonstrating its effectiveness for automated emotion analysis.

Keywords:
ClassificationConvolutional neural networkDeep learningElectrodermal activityEmotionMultiscale features

More Related Videos

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.1K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.8K

Related Experiment Videos

Last Updated: Nov 15, 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

4.7K
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

34.1K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.8K

Area of Science:

  • Physiological computing
  • Machine learning for affective computing
  • Signal processing for emotion recognition

Background:

  • Electrodermal activity (EDA) signals are valuable physiological indicators of emotional states.
  • Traditional methods often require extensive manual feature engineering for emotion classification.
  • Multiscale analysis can capture complex patterns in physiological signals.

Purpose of the Study:

  • To classify emotional states using electrodermal activity (EDA) signals.
  • To evaluate the effectiveness of a Multiscale Convolutional Neural Network (MSCNN) for this task.
  • To investigate whether multiscale learning captures robust complementary features at different scales.

Main Methods:

  • Utilized EDA signals from the publicly available DEAP dataset.
  • Decomposed EDA signals into multiple scales using the coarse-grained method.
  • Applied a Multiscale Convolutional Neural Network (MSCNN) for end-to-end feature learning and classification.

Main Results:

  • The MSCNN approach achieved classification accuracies of 69.33% for valence and 71.43% for arousal.
  • Performance was influenced by the number of network layers and signal length.
  • The MSCNN outperformed single-layer convolutional neural networks.

Conclusions:

  • The proposed MSCNN method effectively classifies emotional states using EDA signals.
  • Multiscale learning captures complementary features, enhancing classification robustness.
  • This approach offers an automated, signal-processing-free tool for emotion assessment.