Search research articles

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

[A seroepidemiologic analysis of hepatitis B in Sichuan province].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2009

Same author

[Efficacy and safety of drospirenone-ethinylestradiol on contraception in healthy Chinese women: a multicenter randomized controlled trial].

Zhonghua fu chan ke za zhi·2009

Same author

RGS5, a hypoxia-inducible apoptotic stimulator in endothelial cells.

The Journal of biological chemistry·2009

Same author

Theory and experiment of a fiber loop mirror filter of two-stage polarization-maintaining fibers and polarization controllers for multiwavelength fiber ring laser.

Optics express·2009

Same author

Selective binding and highly sensitive fluorescent sensor of palmatine and dehydrocorydaline alkaloids by cucurbit[7]uril.

Organic & biomolecular chemistry·2009

Same author

Abatement of toluene from gas streams via ferro-electric packed bed dielectric barrier discharge plasma.

Journal of hazardous materials·2009

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: Jan 8, 2026

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

Semi-supervised learning with dynamic classifier selection for PMI estimation: An animal study.

Jian Li¹, Yan-Juan Wu¹, Xing-Yu Lu¹

¹School of Forensic Medicine, Shanxi Medical University, No. 98, University Street, Wujinshan Town, Yuci District, Jinzhong City, Shanxi Province, 030604, China; Shanxi Key Laboratory of Forensic Medicine, Jinzhong, 030600, Shanxi, China.

Journal of Forensic and Legal Medicine

|December 17, 2025

Summary

Semi-supervised learning with dynamic classifier selection (SSL-DCS) improves machine learning models for estimating the postmortem interval (PMI). This approach effectively utilizes limited samples, enhancing accuracy in forensic science applications.

Keywords:

DCS Forensic Postmortem interval Semi-supervised learning

More Related Videos

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jan 8, 2026

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

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Forensic Science
Machine Learning
Molecular Biology

Background:

Machine learning for postmortem interval (PMI) estimation faces challenges due to limited labeled samples.
Undetermined PMI samples reduce model efficacy and exacerbate sample scarcity in forensic investigations.

Purpose of the Study:

To evaluate supervised learning (SL) and semi-supervised learning (SSL) models for PMI estimation using skeletal muscle samples.
To enhance SL and SSL models with dynamic classifier selection (DCS) for improved performance.

Main Methods:

Utilized rat skeletal muscle samples with known and unknown PMI.
Compared the efficacy of SL and SSL models, both with and without DCS.
Assessed model performance using metrics like AUC and R-squared.

Main Results:

SSL-DCS significantly outperformed SL-DCS in PMI prediction.
SSL-DCS achieved an AUC of 0.89 and an R-squared of 0.93 for estimating time to death within 0-9 days.
The study demonstrated enhanced predictive efficacy and improved utilization of scarce samples.

Conclusions:

SSL-DCS offers a superior approach for machine learning-based PMI estimation.
This method effectively addresses the challenge of limited data in forensic science.
The SSL-DCS paradigm shows potential for application in other biomedical fields.