Application of Convolutional Neural Network for Fingerprint-Based Prediction of Gender, Finger Position, and Height.

Fingerprints are the most common personal identification feature and key evidence for crime scene investigators. The prediction of fingerprints features include gender, height range (tall or short), left or right hand, and finger position can effectively narrow down the list of suspects, increase the speed of comparison, and greatly improve the effectiveness of criminal investigations. In this study, we used three commonly used CNNs (VGG16, Inception-v3, and Resnet50) to perform biometric prediction on 1000 samples, and the results showed that VGG16 achieved the highest accuracy in identifying gender (79.

Establishing a DNA identification system for pigs (Sus scrofa) using a multiplex STR amplification.

In this study we establish a novel STR multiplex using 13 tetra-nucleotide STRs and the amelogenin marker for the forensic identification of pigs. The genotypes and allele frequency were generated based on 341 samples from 11 pig breeds in Taiwan. Genetic variation was tested including Na, Ne, Ho, He, F-statistics, PIC, Pm and PE for each STR locus and for each breed.

Species identification of Kachuga tecta using the cytochrome b gene.

A DNA technique has been established for the identification to species level of tortoises. The test on the shell of the animal was used to identify samples from the species Kachuga tecta. A total of 100 tortoise shell specimens collected from the National Council of Agriculture (COA), Taiwan, were used in this study.