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

DRDarkNet: a hybrid deep feature engineering model for accurate autopsy image classification.

International journal of legal medicine·2026
Same author

SEPoolConvNeXt: A Deep Learning Framework for Automated Classification of Neonatal Brain Development Using T1- and T2-Weighted MRI.

Journal of clinical medicine·2025
Same author

KidneyNeXt: A Lightweight Convolutional Neural Network for Multi-Class Renal Tumor Classification in Computed Tomography Imaging.

Journal of clinical medicine·2025
Same author

Tendon regeneration deserves better: focused review on <i>In vivo</i> models, artificial intelligence and 3D bioprinting approaches.

Frontiers in bioengineering and biotechnology·2025
Same author

A Pyramid Deep Feature Extraction Model for the Automatic Classification of Upper Extremity Fractures.

Diagnostics (Basel, Switzerland)·2023
Same author

Exemplar MobileNetV2-Based Artificial Intelligence for Robust and Accurate Diagnosis of Multiple Sclerosis.

Diagnostics (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jun 17, 2025

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.2K

Multilevel hybrid handcrafted feature extraction based depression recognition method using speech.

Burak Taşcı1

  • 1Vocational School of Technical Sciences, Firat University, Elazig 23119, Turkey.

Journal of Affective Disorders
|August 10, 2024
PubMed
Summary
This summary is machine-generated.

This study presents an efficient machine learning model for depression detection using speech audio signals. The Hybrid Handcrafted Feature (HHF) model achieved 94.63% accuracy, offering a computationally efficient approach.

Keywords:
Depression classificationLocal binary patternSpeech audio signal processingStatistical feature extraction

More Related Videos

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method
07:12

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Published on: August 2, 2021

3.5K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

Related Experiment Videos

Last Updated: Jun 17, 2025

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.2K
Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method
07:12

Individualized rTMS Treatment for Depression using an fMRI-Based Targeting Method

Published on: August 2, 2021

3.5K
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

Area of Science:

  • Machine Learning
  • Computational Psychiatry
  • Speech Signal Processing

Background:

  • Depression diagnosis relies on clinical assessments and patient/relative input.
  • Machine learning (ML) models analyze speech audio for automated depression detection.
  • Deep learning models offer high accuracy but are resource-intensive.

Purpose of the Study:

  • Introduce an innovative, multilevel hybrid feature extraction classification model for depression detection.
  • Develop a computationally efficient model with reduced time complexity.
  • Improve automated depression detection using speech analysis.

Main Methods:

  • Utilized the MODMA dataset (29 healthy, 23 Major Depressive Disorder audio signals).
  • Integrated multilevel hybrid feature extraction (Hybrid Handcrafted Feature - HHF) and iterative feature selection (Iterative Neighborhood Component Analysis - INCA).
  • Employed Multilevel Discrete Wavelet Transform (MDWT) for high-level feature extraction and a 1D nearest neighbor classifier with 10-fold cross-validation.

Main Results:

  • The HHF-based model achieved 94.63% classification accuracy for depression detection.
  • Demonstrated excellent performance in classifying speech audio signals for depression.

Conclusions:

  • The HHF-based model shows significant proficiency in depression classification.
  • The model is computationally efficient, making it a practical tool for depression detection.