Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies

Morphological classification is the gold standard for identifying necrophilous flies, but its complexity and the scarcity of experts make accurate classification challenging. The development of artificial intelligence for autonomous recognition holds promise as a new approach to improve the efficien...

Full description

Saved in:
Bibliographic Details
Main Authors: Yixin Ma, Lin Niu, Bo Wang, Dianxin Li, Yanzhu Gao, Shan Ha, Boqing Fan, Yixin Xiong, Bin Cong, Jianhua Chen, Jianqiang Deng
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Insects
Subjects:
Online Access:https://www.mdpi.com/2075-4450/16/5/529
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327228437921792
author Yixin Ma
Lin Niu
Bo Wang
Dianxin Li
Yanzhu Gao
Shan Ha
Boqing Fan
Yixin Xiong
Bin Cong
Jianhua Chen
Jianqiang Deng
author_facet Yixin Ma
Lin Niu
Bo Wang
Dianxin Li
Yanzhu Gao
Shan Ha
Boqing Fan
Yixin Xiong
Bin Cong
Jianhua Chen
Jianqiang Deng
author_sort Yixin Ma
collection DOAJ
description Morphological classification is the gold standard for identifying necrophilous flies, but its complexity and the scarcity of experts make accurate classification challenging. The development of artificial intelligence for autonomous recognition holds promise as a new approach to improve the efficiency and accuracy of fly morphology identification. In our previous study, we developed a GLB-ViT (Global–Local Balanced Vision Transformer)-based deep learning model for fly species identification, which demonstrated improved identification capabilities. To expand the model’s application scope to meet the practical needs of forensic science, we extended the model based on the forensic science practice scenarios, increased the database of identifiable sarcosaphagous fly species, and successfully developed a WeChat Mini Program based on the model. The results show that the model can achieve fast and effective identification of ten common sarcosaphagous flies in Hainan, and the overall correct rate reaches 94.00%. For the few cases of identification difficulties and suspicious results, we have also constructed a rapid molecular species identification system based on DNA Barcoding technology to achieve accurate species identification of the flies under study. As the local fly database continues to be improved, the model is expected to be applicable to local forensic practice.
format Article
id doaj-art-2f6bf6fa51a04c37b09fb29d3278ce19
institution Kabale University
issn 2075-4450
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Insects
spelling doaj-art-2f6bf6fa51a04c37b09fb29d3278ce192025-08-20T03:47:57ZengMDPI AGInsects2075-44502025-05-0116552910.3390/insects16050529Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous FliesYixin Ma0Lin Niu1Bo Wang2Dianxin Li3Yanzhu Gao4Shan Ha5Boqing Fan6Yixin Xiong7Bin Cong8Jianhua Chen9Jianqiang Deng10Hainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaSchool of Biomedical Informatics and Engineering, Hainan Medical University, Haikou 571199, ChinaHainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaHainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaSchool of Biomedical Informatics and Engineering, Hainan Medical University, Haikou 571199, ChinaSchool of Public Health, Hainan Medical University, Haikou 571199, ChinaHainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaHainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaDepartment of Forensic Medicine, Hebei Medical University, Shijiazhuang 050011, ChinaHainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaHainan Provincial Tropical Forensic Engineering Research Center & Hainan Provincial Academician Workstation (Tropical Forensic Medicine), Key Laboratory of Tropical Translational Medicine of Ministry of Education, School of Basic Medicine and Life Sciences, Hainan Medical University, Haikou 571199, ChinaMorphological classification is the gold standard for identifying necrophilous flies, but its complexity and the scarcity of experts make accurate classification challenging. The development of artificial intelligence for autonomous recognition holds promise as a new approach to improve the efficiency and accuracy of fly morphology identification. In our previous study, we developed a GLB-ViT (Global–Local Balanced Vision Transformer)-based deep learning model for fly species identification, which demonstrated improved identification capabilities. To expand the model’s application scope to meet the practical needs of forensic science, we extended the model based on the forensic science practice scenarios, increased the database of identifiable sarcosaphagous fly species, and successfully developed a WeChat Mini Program based on the model. The results show that the model can achieve fast and effective identification of ten common sarcosaphagous flies in Hainan, and the overall correct rate reaches 94.00%. For the few cases of identification difficulties and suspicious results, we have also constructed a rapid molecular species identification system based on DNA Barcoding technology to achieve accurate species identification of the flies under study. As the local fly database continues to be improved, the model is expected to be applicable to local forensic practice.https://www.mdpi.com/2075-4450/16/5/529forensic entomologyArtificial Intelligencesarcosaphagous fliesspecies identificationfine-grained image classification
spellingShingle Yixin Ma
Lin Niu
Bo Wang
Dianxin Li
Yanzhu Gao
Shan Ha
Boqing Fan
Yixin Xiong
Bin Cong
Jianhua Chen
Jianqiang Deng
Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies
Insects
forensic entomology
Artificial Intelligence
sarcosaphagous flies
species identification
fine-grained image classification
title Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies
title_full Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies
title_fullStr Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies
title_full_unstemmed Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies
title_short Preliminary Development of Global–Local Balanced Vision Transformer Deep Learning with DNA Barcoding for Automated Identification and Validation of Forensic Sarcosaphagous Flies
title_sort preliminary development of global local balanced vision transformer deep learning with dna barcoding for automated identification and validation of forensic sarcosaphagous flies
topic forensic entomology
Artificial Intelligence
sarcosaphagous flies
species identification
fine-grained image classification
url https://www.mdpi.com/2075-4450/16/5/529
work_keys_str_mv AT yixinma preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT linniu preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT bowang preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT dianxinli preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT yanzhugao preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT shanha preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT boqingfan preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT yixinxiong preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT bincong preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT jianhuachen preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies
AT jianqiangdeng preliminarydevelopmentofgloballocalbalancedvisiontransformerdeeplearningwithdnabarcodingforautomatedidentificationandvalidationofforensicsarcosaphagousflies