Search research articles

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

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

Sort by

Same author

WTAP-mediated m6A methylation of SOX2 affects lung adenocarcinoma malignancy via Wnt/β-catenin pathway.

Frontiers in genetics·2026

Same author

MND1 regulates PANoptosis and stemness of lung adenocarcinoma cells by stabilizing RCOR2 mRNA.

Cell death & disease·2026

Same author

High-quality phage assembly from metagenomes with PALACE.

Nature biotechnology·2026

Same author

Erythrocytapheresis Improves Health-Related Quality of Life in High-Altitude Migrants with Chronic Mountain Sickness: A Single-Arm Before-After Trial at 4,000-4,500 m.

High altitude medicine & biology·2026

Same author

Oleanolic Acid Ameliorates Metabolic Dysfunction-Associated Steatotic Liver Disease by Inhibiting Ferroptosis through Targeting PTGS2 as a Key Molecular Node and Activating the AMPK/ACC Signaling Pathway.

Journal of agricultural and food chemistry·2026

Same author

Saikosaponin A restores the IDO1-driven gut-testis kynurenine axis to alleviate oligozoospermia.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

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

Search research articles

Related Experiment Video

Updated: Jul 1, 2025

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

A novel machine learning-based imputation strategy for missing data in step-stress accelerated degradation test.

Yaqiu Li^1,2, Qijie Zhou^1,2, Ye Fan³

¹China Electronic Product Reliability and Environmental Testing Research Institute, No. 76, West Zhucun Avenue, Guangzhou, China.

|March 4, 2024

Summary

This study introduces a new hybrid imputation method combining LSSVM and RBF models to effectively handle missing data in accelerated degradation tests. The method improves data reliability for step-stress tests, even with high missing rates.

Keywords:

Accelerated degradation test Missing data imputation Radial basis function Support vector machine

More Related Videos

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Related Experiment Videos

Last Updated: Jul 1, 2025

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Area of Science:

Data Science
Materials Science
Engineering

Background:

Missing data significantly compromises data quality, impacting analysis accuracy and reliability.
Accelerated tests, especially step-stress accelerated degradation tests, are prone to missing data due to conversion processes, leading to unequal measurement intervals.
Existing imputation methods are often inadequate for handling the high missing rates characteristic of accelerated test data.

Purpose of the Study:

To develop and validate a novel hybrid imputation method for addressing missing data in accelerated degradation tests.
To compare the proposed method against traditional and machine learning imputation techniques.
To demonstrate the method's effectiveness on real-world super-luminescent diode (SLD) degradation data.

Main Methods:

A hybrid imputation model combining the Least Squares Support Vector Machine (LSSVM) and Radial Basis Function (RBF) models was developed.
Simulation data was used to compare the proposed hybrid model with existing imputation methods.
The model was applied to real degradation datasets from super-luminescent diode (SLD) accelerated tests.

Main Results:

The proposed hybrid imputation method demonstrated superior performance compared to traditional and other machine learning imputation methods in simulation studies.
Validation on real SLD degradation data confirmed the model's effectiveness in handling missing data within step-stress accelerated degradation tests.
The method successfully addressed issues of unequal measuring intervals caused by high missing data rates.

Conclusions:

The novel hybrid LSSVM-RBF imputation method is effective for handling missing data in step-stress accelerated degradation tests.
The proposed method offers a significant improvement over existing techniques, particularly in scenarios with high missing data rates.
The generalizability of the method suggests its applicability to other fields experiencing similar data quality challenges.