Related Experiment Video
Updated: Jul 30, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.7K
Age estimation of bloodstains based on convolutional neural network algorithm and hyperspectral imaging technology
Yang Qifu1, Zhang Xinyu1, Qi Yueying2
1College of Science, Kunming University of Science and Technology, Kunming, 650500, China. 453937936@qq.com.
Analytical Methods : Advancing Methods and Applications
|September 25, 2023
Summary
This study introduces a new method using hyperspectral imaging and a Convolutional Neural Network (CNN) algorithm to accurately estimate bloodstain age. The CNN model significantly outperforms traditional methods for forensic bloodstain analysis.
Area of Science:
- Forensic Science
- Spectroscopy
- Machine Learning
Background:
- Bloodstains are crucial evidence in forensic investigations.
- Determining the age of bloodstains is vital for reconstructing crime events.
- Current methods for age estimation have limitations.
Purpose of the Study:
- To develop and evaluate a novel method for estimating bloodstain age.
- To compare the performance of a Convolutional Neural Network (CNN) model with traditional algorithms.
- To leverage hyperspectral imaging for enhanced forensic analysis.
Main Methods:
- Collected spectral data from bloodstains of varying ages using hyperspectral imaging (400-1000 nm).
- Developed a blood aging model utilizing a CNN algorithm.
- Compared CNN performance against Partial Least Squares (PLS) and Extreme Learning Machine (ELM) models.
Main Results:
- The CNN model demonstrated superior performance with a high coefficient of determination (R² = 0.987).
- CNN achieved the lowest Root Mean Square Error of Prediction (RMSEP = 6.949 hours) and Mean Absolute Percentage Error (MAPE = 0.49%).
- CNN significantly outperformed PLS (R² = 0.883, RMSEP = 18.752) and ELM (R² = 0.936, RMSEP = 13.717).
Conclusions:
- The proposed hyperspectral imaging and CNN method accurately estimates bloodstain age.
- This approach offers a reliable new technology for forensic bloodstain detection.
- The findings provide a valuable reference for advancing forensic science techniques.
