Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

You might also read

Related Articles

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

Sort by

Same author

A promising approach using Fibonacci sequence-based optimization algorithms and advanced computing.

Scientific reports·2023

Same author

Damage assessment of suspension footbridge using vibration measurement data combined with a hybrid bee-genetic algorithm.

Scientific reports·2022

Same author

Model Updating for Nam O Bridge Using Particle Swarm Optimization Algorithm and Genetic Algorithm.

Sensors (Basel, Switzerland)·2018

Same author

Outcome of right hepatectomy for living liver donors: a single Egyptian center experience.

Journal of gastrointestinal surgery : official journal of the Society for Surgery of the Alimentary Tract·2012

Same author

Raman scattering boson peak and differential scanning calorimetry studies of the glass transition in tellurium-zinc oxide glasses.

Journal of physics. Condensed matter : an Institute of Physics journal·2011

Same author

Incidence of perioperative adverse events in obese children undergoing elective general surgery.

British journal of anaesthesia·2010

Search research articles

Related Experiment Video

Updated: Sep 29, 2025

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

Damage assessment in structures using artificial neural network working and a hybrid stochastic optimization.

H Tran-Ngoc^1,2, S Khatir³, T Le-Xuan²

¹Laboratory Soete, Department of Electrical Energy, Metals, Mechanical Constructions, and Systems, Faculty of Engineering and Architecture, Ghent University, 9000, Gent, Belgium.

Scientific Reports

|March 24, 2022

Summary

This study introduces a novel Artificial Neural Network (ANN) training method combining gradient descent with metaheuristic algorithms (MAs) to avoid local minima and improve accuracy. The hybrid approach, ANNPSOGA, demonstrates superior performance and reduced computational cost compared to traditional methods.

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Related Experiment Videos

Last Updated: Sep 29, 2025

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Data Acquisition Protocol for Determining Embedded Sensitivity Functions

Published on: April 20, 2016

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Area of Science:

Artificial Intelligence
Machine Learning
Computational Science

Background:

Artificial Neural Networks (ANNs) commonly use gradient descent (GD) for training.
GD-based training risks entrapment in local minima, hindering optimal solutions.
Existing ANNs may struggle with complex optimization problems.

Purpose of the Study:

To propose a novel ANN training method overcoming local minima limitations.
To enhance ANN performance by integrating metaheuristic algorithms (MAs).
To improve convergence speed and solution accuracy.

Main Methods:

A hybrid approach combining gradient descent (GD) with metaheuristic algorithms (MAs) for ANN training.
Utilizing GD for initial convergence, MAs for escaping local minima, and GD again for refinement.
Employing a hybrid of particle swarm optimization and genetic algorithm (PSOGA) for enhanced global search capacity.

Main Results:

The proposed ANNPSOGA achieved higher accuracy than traditional ANNs and PSO.
The method demonstrated effectiveness even with high levels of noise.
ANNPSOGA significantly reduced computational cost compared to Particle Swarm Optimization (PSO).

Conclusions:

The novel ANNPSOGA effectively overcomes the local minima problem in ANN training.
This hybrid approach offers superior accuracy and efficiency for complex problems.
ANNPSOGA presents a promising advancement in neural network optimization.