Individual Identification of Dairy Cows Based on Deep Feature Extrac-tion and Matching

Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional neural network had the disadvantages in prolonged training at the additions of new cows samples.Therefore,a cow individual identification framework was proposed based on deep feature extraction and matching,and the individual identification of dairy cows based on this framework could avoid repeated training.Firstly,the trained convolutional neural network model was used as the feature extractor;secondly,the feature extraction was used to extract features and stored the features into the template feature library to complete the enrollment;finally,the identifies of dairy cows were identified.Based on this framework,when new cows joined the herd,enrollment could be completed quickly.In order to evaluate the application performance of this method in closed-set and open-set individual identification of dairy cows,back images of 524 cows were collected,among which the back images of 150 cows were selected as the training data to train feature extractor.The data of the remaining 374 cows were used to generate the template data set and the data to be identified.The experiment results showed that in the closed-set individual identification of dairy cows,the highest identification accuracy of top-1 was 99.73%,the highest identification accuracy from top-2 to top-5 was 100%,and the identification time of a single cow was 0.601 s,this method was verified to be effective.In the open-set individual identification of dairy cows,the recall was 90.38%,and the accuracy was 89.46%.When false accept rate(FAR)=0.05,true accept rate(TAR)=84.07%,this method was verified that the application had certain research value in open-set individual identification of dairy cows,which provided a certain idea for the application of individual identification in the field of intelligent animal husbandry.

Amur tiger stripes:individual identification based on deep convolutional neural network

The automatic individual identification of Amur tigers(Panthera tigris altaica)is important for population monitoring and making effective conservation strategies.Most existing research primarily relies on manual identifi-cation,which does not scale well to large datasets.In this paper,the deep convolution neural networks algorithm is constructed to implement the automatic individual identification for large numbers of Amur tiger images.The experimental data were obtained from 40 Amur tigers in Tieling Guaipo Tiger Park,China.The number of images collected from each tiger was approximately 200,and a total of 8277 images were obtained.The experiments were carried out on both the left and right side of body.Our results suggested that the recognition accuracy rate of left and right sides are 90.48%and 93.5%,respectively.The accuracy of our network has achieved the similar level compared to other state of the art networks like LeNet,ResNet34,and ZF_Net.The running time is much shorter than that of other networks.Consequently,this study can provide a new approach on automatic individual identification technology in the case of the Amur tiger.

Digital Barcode Development for Single Nuclotide Polymorphism (SNP) Identification of Suzhong Swine Individuals

Suzhong swine is a hybrid breed derived from Taihu sows and Landraee boars. To identify Suzhong swine individuals and trace the source of pork products, single nucleotide polymorphisms （SNPs） identification of Suzhong swine individuals was studied. A total of 29 pairs of primers were designed and sev- en pairs of primers were used for identification of Suzhong swine individuals. The products amplified by seven pairs of primers could be directly sequenced, with clean sequencing map background and no ambiguity in sequence read. Totally 52 SNPs loci were amplified by seven pairs of primers, and 41 SNPs loci were reserved for identification of Suzhong swine individuals through correlation analysis and heterezygosity filtration （ H ≥0.1 ）. Meantime, the digital barcodes for SNP identification of 96 individuals of Suzhong swine derived from seven boars and 12 sows were developed, which well distinguished 96 individuals of Suzhong swine. Theoretically, 41SNPs amplified by seven pairs of primers could be used for identification of 5.0 × 10^6 pig individuals. Therefore, digital barcode devel- opment method for SNP identification of Suzbong swine individuals can be used for individual identification of Suzhong swine in scale pig farm and meat product traceability.

Population and genetic diversity of Tibetan red deer based on fecal DNA

The Tibet Shannan Red Deer Nature Reserve is the center of the geographic distribution of Tibetan red deer. This paper presents the results of DNA analysis of 199 red deer fecal pellet groups collected during 2013 and 2014 during the green-plant period. We successfully extracted DNA from 87 DNA pellet groups and determined individual identification with 12 microsatellite loci. We evaluated the genetic diversity of the population and various population estimates with Capwire in R software. The87 successfully extracted pellet groups were from 50 individuals. In the population, the average number of alleles was 7.58 ± 0.18, the average effective number of alleles was 4.58 ± 0.15, and average polymorphism information content was 0.67 ± 0.01. Among the 12 loci,only T123 was moderately polymorphic; the other 11 loci were highly polymorphic. Expected heterozygosity ranged from 0.45 to 0.91, with an average of 0.72 ± 0.01, and average observed heterozygosity was 0.52 ± 0.11.Although Tibetan red deer remains endangered, the high genetic diversity indicates that this population has a good chance of recovery. This study provided insight that could be used by the local forestry department to develop programs to protect Tibetan red deer.

Characterization of 12 polymorphic microsatellite markers in the Chinese tree shrew(Tupaia belangeri chinensis)

The Chinese tree shrew(Tupaia belangeri chinensis)is a small experimental animal with a close affinity to primates.This species has long been proposed to be an alternative experimental animal to primates in biomedical research.Despite decades of study,there is no pure breed for this animal,and the overall genetic diversity of wild tree shrews remains largely unknown.In order to obtain a set of genetic markers for evaluating the genetic diversity of tree shrew wild populations and tracing the lineages in inbreeding populations,we developed 12 polymorphic microsatellite markers from the genomic DNA of the tree shrew.An analysis of a wild population of 117 individuals collected from the suburb of Kunming,China,showed that these loci exhibited a highly expected heterozygosity(0.616).These 12 microsatellites were sufficient for individual identification and parentage analysis.The microsatellite markers developed in this study will be of use in evaluating genetic diversity and lineage tracing for the tree shrew.

Near-infrared studies of nova V5584 Sgr in the pre-maximum and early decline phase

We present near-infrared spectroscopic and photometric observations of nova V5584 Sgr taken during the first 12 d following its discovery on Oct. 26.439 UT2009. The evolution of the spectra is shown from the initial P Cygni phase to an emission line phase. The prominent carbon lines seen in the JHK spectra closely match those observed in an Fe II class nova outburst. The spectra show first-overtone CO bands in emission between 2.29-2.40 μm. By examining WISE and other publicly available data, we show that the nova underwent a pronounced dust formation phase between February- April 2010.

Hierarchical auditory perception for species discrimination and individual recognition in the music frog

The ability to discriminate species and recognize individuals is crucial for reproductive success and/or survival in most animals.However,the temporal order and neural localization of these decision-making processes has remained unclear.In this study,event-related potentials(ERPs)were measured in the telencephalon,diencephalon,and mesencephalon of the music frog Nidirana daunchina.These ERPs were elicited by calls from 1 group of heterospecifics(recorded from a sympatric anuran species)and 2 groups of conspecifics that differed in their fundamental frequencies.In terms of the polarity and position within the ERP waveform,auditory ERPs generally consist of 4 main components that link to selective attention(N1),stimulus evaluation(P2),identification(N2),and classification(P3).These occur around 100,200,250,and 300 ms after stimulus onset,respectively.Our results show that the N1 amplitudes differed significantly between the heterospecific and conspecific calls,but not between the 2 groups of conspecific calls that differed in fundamental frequency.On the other hand,the N2 amplitudes were significantly different between the 2 groups of conspecific calls,suggesting that the music frogs discriminated the species first,followed by individual identification,since N1 and N2 relate to selective attention and stimuli identification,respectively.Moreover,the P2 amplitudes evoked in females were significantly greater than those in males,indicating the existence of sexual dimorphism in auditory discrimination.In addition,both the N1 amplitudes in the left diencephalon and the P2 amplitudes in the left telencephalon were greater than in other brain areas,suggesting left hemispheric dominance in auditory perception.Taken together,our results support the hypothesis that species discrimination and identification of individual characteristics are accomplished sequentially,and that auditory perception exhibits differences between sexes and in spatial dominance.

A Review of Animal Individual Recognition Based on Computer Vision

With the improvement of modernization,China’s animal husbandry and fishery enterprise has ushered in a new vogue of informationization,factorization,and precision farming,and the demand for unique identification of individual animals is growing.Traditional individual animal identification methods,such as footprint identification,molecular biology,and different techniques,have low accuracy,excessive cost,and different risks.RFID technological know-how and implants put on monitoring units and different techniques additionally face invasiveinvasiveness,excessive labor costs,slender application scopes and challenges in promoting a massive place and different issues.Deep learning is enjoying an increasing number of essential positions in the discipline of animal individual identification,which has made it possible for the noninvasive recognition of individual animals.This paper discusses the progress of individual animal recognition using computer vision techniques and its application popularity in different species fields,focuses on the issues and challenges of individual animal recognition,and suggests that future lookup instructions for animal identification are foreseen.

Estimating abundance and density of Amur tigers along the Sino- Russian border

As an apex predator the Amur tiger(Panthera tigris altaica)could play a pivotal role in maintaining the integ­rity of forest ecosystems in Northeast Asia.Due to habitat loss and harvest over the past century,tigers rapidly declined in China and are now restricted to the Russian Far East and bordering habitat in nearby China.To fa­cilitate restoration of the tiger in its historical range,reliable estimates of population size are essential to assess effectiveness of conservation interventions.Here we used camera trap data collected in Hunchun National Na­ture Reserve from April to June 2013 and 2014 to estimate tiger density and abundance using both maximum likelihood and Bayesian spatially explicit capture-recapture(SECR)methods.A minimum of 8 individuals were detected in both sample periods and the documentation of marking behavior and reproduction suggests the presence of a resident population.Using Bayesian SECR modeling within the 11400 km2 state space,den­sity estimates were 0.33 and 0.40 individuals/100 km^(2) in 2013 and 2014,respectively,corresponding to an es­timated abundance of 38 and 45 animals for this transboundary Sino-Russian population.In a maximum likeli­hood framework,we estimated densities of 0.30 and 0.24 individuals/100 km^(2) corresponding to abundances of 34 and 27,in 2013 and 2014,respectively.These density estimates are comparable to other published estimates for resident Amur tiger populations in the Russian Far East.This study reveals promising signs of tiger recovery in Northeast China,and demonstrates the importance of connectivity between the Russian and Chinese popula­tions for recovering tigers in Northeast China.

DNA recovery and analysis from skeletal material in modern forensic contexts

The generation of a DNA profile from skeletal remains is an important part of the identifica-tion process in both mass disaster and unidentified person cases. Since bones and teeth are often the only biological materials remaining after exposure to environmental conditions, intense heat, certain traumatic events and in cases where a significant amount of time has passed since the death of the individual, the ability to purify large quantities of informative DNA from these hard tissues would be beneficial. Since sampling the hard tissues for gen-etic analysis is a destructive process, it is important to understand those environmental and intrinsic factors that contribute to DNA preservation. This will serve as a brief introduction to these topics, since skeletal sampling strategies and molecular taphonomy have been dis-cussed in depth elsewhere. Additionally advances in skeletal DNA extraction and analysis will be discussed. Currently there is great variation in the DNA isolation methods used by laboratories to purify DNA from the hard tissues;however, a standardized set of short tan-dem repeat (STR) loci is analyzed by many US laboratories to allow for comparisons across samples and jurisdictions. Recent advances have allowed for the generation of DNA profiles from smaller quantities of template DNA and have expanded the number of loci analyzed for greater discriminatory power and predictions regarding the geographic ancestry and phenotype of the individual. Finally, utilizing databases and expanding the number of com-parison samples will be discussed in light of their role in the identification process.

An inter-laboratory study of DNA-based identity,parentage and species testing in animal forensic genetics

The probative value of animal forensic genetic evidence relies on laboratory accuracy and reliability.Inter-laboratory comparisons allow laboratories to evaluate their performance on specific tests and analyses and to continue to monitor their output.The International Society for Animal Genetics(ISAG)administered animal forensic comparison tests(AFCTs)in 2016 and 2018 to assess the limitations and capabilities of laboratories offering forensic identification,parentage and species determination services.The AFCTs revealed that analyses of low DNA template concentrations(≤300 pg/μL)constitute a significant challenge that has prevented many laboratories from reporting correct identification and parentage results.Moreover,a lack of familiarity with species testing protocols,interpretation guidelines and representative databases prevented over a quarter of the participating laboratories from submitting correct species determination results.Several laboratories showed improvement in their genotyping accuracy over time.However,the use of forensically validated standards,such as a standard forensic short tandem repeat(STR)kit,preferably with an allelic ladder,and stricter guidelines for STR typing,may have prevented some common issues from occurring,such as genotyping inaccuracies,missing data,elevated stutter products and loading errors.The AFCTs underscore the importance of conducting routine forensic comparison tests to allow laboratories to compare results from each other.Laboratories should keep improving their scientific and technical capabilities and continuously evaluate their personnel’s proficiency in critical techniques such as low copy number(LCN)analysis and species testing.Although this is the first time that the ISAG has conducted comparison tests for forensic testing,findings from these AFCTs may serve as the foundation for continuous improvements of the overall quality of animal forensic genetic testing.

Automatic detection of teeth and dental treatment patterns on dental panoramic radiographs using deep neural networks

Disaster victim identification issues are especially critical and urgent after a large-scale disaster.The aim of this study was to suggest an automatic detection of natural teeth and dental treatment patterns based on dental panoramic radiographs(DPRs)using deep learning to promote its applicability as human identifiers.A total of 1638 DPRs,of which the chronological age ranged from 20 to 49 years old,were collected from January 2000 to November 2020.This dataset consisted of natural teeth,prostheses,teeth with root canal treatment,and implants.The detection of natural teeth and dental treatment patterns including the identification of teeth number was done with a pre-trained object detection network which was a convolutional neural network modified by EfficientDet-D3.The objective metrics for the average precision were 99.1%for natural teeth,80.6%for prostheses,81.2%for treated root canals,and 96.8%for implants,respectively.The values for the average recall were 99.6%,84.3%,89.2%,and 98.1%,in the same order,respectively.This study showed outstanding performance of convolutional neural network using dental panoramic radiographs in automatically identifying teeth number and detecting natural teeth,prostheses,treated root canals,and implants.

Anthropological analyses of 30 insertion/deletion autosomal markers in five major ethnic groups of Pakistan

We investigated the forensic efficacy of the 30 insertion/deletion(Indel)markers included in the Qiagen Investigator■DIPplex kit in 529 Pakistani individuals from five major subpopulations in Pakistan(Punjabi,Pashtun,Sindhi,Saraiki,and Baloch).In the Sindhi population,the distribution of HLD81 and HLD97 alleles deviated from Hardy-Weinberg equilibrium after Bonferroni correction.The combined match probability ranged from 2.0E-12(Pashtun and Baloch)to 1.0E-12(Sindhi),and the mean paternity exclusion power varied from 0.995(Punjabi,Sindhi,and Saraiki)to 0.996(Pashtun and Baloch).The high combined power of discrimination(0.99999999999997)and low combined match probability(1.7E-12)for all subpopulations studied support the utility of the 30 Indel markers for forensic identification in the studied subpopulations.The allele frequencies of the Indel markers in the Pakistani subpopulations were compared with those from 18 other populations.The results show that the populations clustered according to geography.The subpopulations investigated in this work showed a close genetic relationship with others from Pakistan,as well as with South Central Asian and Middle Eastern populations.The results suggest that the Investigator■DIPplex kit can be useful as a supplementary tool for human identification in the five Pakistani subpopulations investigated in this study.

A tree counting algorithm for precision agriculture tasks

This study proposes an automatic procedure for individual fruit tree identification using GeoEye-1 sensor data.Depending on site-specific pruning practices,the morphologic characteristics of tree crowns may generate one or more brightness peaks(tree top)on the imagery.To optimize tree counting and to minimize typical background noises from orchards(i.e.bare soil,weeds,and man-made objects),a four-step algorithm was implemented with spatial transforms and functions suitable for spaced stands(asymmetrical smoothing filter,local minimum filter,mask layer,and spatial aggregation operator).System perfor-mance was evaluated through objective criteria,showing consistent results in fast capturing tree position for precision agriculture tasks.

Recent Developments in Forensic DNA Typing

The field of forensic DNA typing,often referred to as“DNA fingerprinting,”has evolved and expanded considerably since its beginnings in the mid-1980s.Originally,forensic DNA typing was primarily used for individual identification and criminal investigations,but it has evolved into a versatile discipline with a wide range of applications.This article addresses the growing scope of forensic genetics,which includes advances in DNA sequencing technologies,mixture analysis,body fluid identification,phenotypic profiling,forensic genealogy,microbiological analysis,exploration of novel markers,and ethical and legal considerations.These developments have enabled the analysis of difficult samples and provided comprehensive insights into the origins of biological evidence.In an ever-evolving landscape,forensic genetics continues to shape the future of forensic science by providing new tools and techniques that help deliver justice in an increasingly complex world.