Method For Individual Identification Research Articles

Automatic location and recognition of horse freezing brand using rotational YOLOv5 deep learning network

Individual livestock identification is of great importance to precision livestock farming. Liquid nitrogen freezing labeled horse brand is an effective way for livestock individual identification. Along with various technological developments, deep-learning-based methods have been applied in such individual marking recognition. In this research, a deep learning method for oriented horse brand location and recognition was proposed. Firstly, Rotational YOLOv5 (R-YOLOv5) was adopted to locate the oriented horse brand, then the cropped images of the brand area were trained by YOLOv5 for number recognition. In the first step, unlike classical detection methods, R-YOLOv5 introduced the orientation into the YOLO framework by integrating Circle Smooth Label (CSL). Besides, Coordinate Attention (CA) was added to raise the attention to positional information in the network. These improvements enhanced the accuracy of detecting oriented brands. In the second step, number recognition was considered as a target detection task because of the requirement of accurate recognition. Finally, the whole brand number was obtained according to the sequences of each detection box position. The experiment results showed that R-YOLOv5 outperformed other rotating target detection algorithms, and the AP (Average Accuracy) was 95.6 %, the FLOPs were 17.4 G, the detection speed was 14.3 fps. As for the results of number recognition, the mAP (mean Average Accuracy) was 95.77 %, the weight size was 13.71 MB, and the detection speed was 68.6 fps. The two-step method can accurately identify brand numbers with complex backgrounds. It also provides a stable and lightweight method for livestock individual identification.

A radar emitter individual identification method based on maximum entropy spectrum estimation

A radar emitter individual identification method based on maximum entropy spectrum estimation

Health determinants among participants in targeted health dialogues offered to all 40-year-old individuals in a metropolitan region of 1.4 million people

Objective To examine cardiovascular risk factors in 40-year-old participants in the health screening program targeted health dialogues (THDs). Design Cross-sectional study. Setting 99 Swedish healthcare centers. Intervention Metabolic risk factors and health behaviors were assessed. THDs were provided. Subjects 1831 (62.3%) THD participants that consented to take part in the research project. Main outcome measures (1) Prevalence of metabolic risk factors (blood pressure, LDL cholesterol, fasting plasma glucose, BMI, waist-hip ratio) and unhealthy behaviors (tobacco, alcohol, diet, physical activity) by sex, education, and place of birth. (2) Associations between different health behaviors and between the number of unhealthy behaviors and prevalence of metabolic risk factors. (3) THD participation by sociodemographics compared to age-matched controls. Results Men had a higher prevalence of all metabolic risk factors, excessive alcohol use and tobacco use than women. Lower educated individuals had a higher prevalence of metabolic risk factors (except for LDL cholesterol) and tobacco use than highly educated. Participants born outside Sweden had a higher prevalence of obesity, high waist-hip ratio, and tobacco use. Participants with 3–4 unhealthy behaviors had significantly higher prevalence of each of the metabolic risk factors except BMI. Women, highly educated and Swedish-born participants were slightly over-represented in the THDs. Conclusion Considering the associations between unhealthy behaviors and metabolic risk factors, the THD method, covering lifestyle as well as objective health measures, may be an appropriate method for early identification of individuals at risk for future non-communicable diseases in the whole population with a specific focus on certain groups. ClinicalTrials.gov NCT04912739

Data Augmentation and Individual Identification Method for Emitters Using Contour Stella Image Mapping

Data Augmentation and Individual Identification Method for Emitters Using Contour Stella Image Mapping

A novel and convenient lying cow identification method based on YOLOX and CowbodyNet: A study with applications in a barn

The lying time of cows is a key indicator of their health and comfort. The ability to automatically recognize the lying posture of cows while simultaneously realizing individual cow identification can play an important role in improving cow welfare, increasing milk yield, detecting cow diseases in a timely manner and enabling precision dairy farming management. In this paper, a method of individual identification for lying dairy cows in a barn based on YOLOX and a feature extraction network named CowbodyNet is proposed. When new cows join the herd, there is no need to collect a large number of images to retrain the model. It is very convenient to collect several images of newly added cows lying and store them in the database. First, the low-light images collected at night are enhanced by the multiscale retinex with chromaticity preservation (MSRCP) algorithm to improve the image quality. Then, the YOLOX target detection algorithm is applied to detect and segment cows in the lying posture. Following this, the segmented images of lying cows are input into CowbodyNet to generate feature vectors, which are used to construct a feature vector database. Subsequently, the Euclidean distances between the feature vector of a cow to be identified and the feature vectors in the database are calculated to determine the identification result. The proposed method achieves 94.43% lying cow identification accuracy on a data set containing top-view images of 72 cows. Finally, the individual cow detection and identification model is successfully deployed on the Jetson Xavier NX embedded platform. The results demonstrate the effectiveness and practicability of the proposed cow identification method. This study provides effective technical support for the application of identifying individual lying cows.

Particle Size-Tunable Polydopamine Nanoparticles for Optical and Electrochemical Imaging of Latent Fingerprints on Various Surfaces.

Powder dusting method is the most widely used approach due to its low cost, simplicity, minimal instrument dependence, and extensive applicability for developing latent fingerprints (LFPs). Herein, a novel optical and electrochemical dual-mode method for high-resolution LFP enhancement has been explored based on size-tunable polydopamine (PDA) nanoparticles (NPs) and scanning electrochemical microscopy (SECM). Dark PDAs rich in functional groups and negative charges can combine with the residues of LFPs on various surfaces with high sensitivity and selectivity to realize high-resolution visual fingerprint physical patterns on various porous and nonporous substrates with light color. However, optical visualization is not feasible for LFPs on dark or multicolored surfaces. Fortunately, based on the differences in electrochemical reactivity between ridges and furrows caused by the conductivity and reducibility of PDA powders, SECM can serve as a powerful supplement to optical methods to effectively overcome background color interference and distinctly display fingerprint patterns. Intriguingly, it is noteworthy that the binding amount and particle size of PDA powder significantly affected the optical and electrochemical visualization of LFPs: more powder binding amounts provided darker ridges in optical, and more surface reaction sites (larger powder binding mass at the same particle size or smaller particle size at the same mass) provided higher currents of ridges in electrochemical imaging. It demonstrates that the PDA powder as a dual-mode developer for LFPs offers a promising method for individual identification in forensics.

Evaluation of individual visual implant elastomer tag marking of Japanese eel (Anguilla japonica) larvae

Visual implant elastomer (VIE) marking was evaluated as a tool for individual tagging of larval Japanese eels, Anguilla japonica, during rearing conditions. Combinations of eight colors of VIE tag were used to individually mark leptocephalus larvae (104–110 days post hatched) by injecting them with either a mixture of a silicone color material and a curing agent, or only color material. Injections were at three locations on the dorso-lateral body surface for individual identification, and a sham-operated control group was also prepared. Tag retention was 100% with or without curing agent, and individuals could be tracked until larvae completely metamorphosed into glass eels. After some initial mortality, the survival and growth rates were not different between each treatment group. These results suggested that VIE tagging could provide good individual larva identification method for research during rearing conditions.

SEX DETERMINATION USING ANTHROPHOMETRIC MEASUREMENTS OF THE HUMAN EXTERNAL EAR IN CHENNAI POPULATION

The human external ear, including the auricle (pinna) and the external auditory canal, is valuable in forensics. External ear: Its unique parameters can be used for identification through ear measurements. These features make the external ear useful for identifying individuals and collecting forensic evidence. OBJECTIVE: This current study, objective is to find out that with the help of the ruler (in cm) is possible to differentiate the person by measuring their outer ear’s parameter variations, also to determine their sex with the these measurements. METHODOLOGY: The present study consists of 100 participant of 50 male and 50 female. The external ear measured using the ruler in cm. The sample universe for this study is Chennai population age group of 20-25 years. For statistical analysis SPSS software were used. RESULT: According to the current study, there is a significant variation of parameters among both the sexes of participant. Additionally as expected, the uniqueness in the variations of parameters from each participant. CONCLUSION: The study has successfully demonstrated that the variations in outer ear parameters offer a reliable and effective additional method of individual identification. In future and with reference to the articles these findings in this field suggests that ear biometrics could be integrated into existing security systems to enhance identification processes, confirming the potential of outer ear measurements as a valuable tool in the field of forensic science and personal security technologies. KEYWORDS: Ear measurements, Anthropometric measurements, Ear evidence

Individual identification method using samples associated with doping tests: A comparison of mitochondrial and nuclear genetic data.

Doping offenses involve the use or attempted use of any prohibited method or substance as well as substituting samples. Consequently, it has been recommended that short tandem repeat (STR) analysis be used to determine if the doping control samples are from the same athlete. However, it has been recognized that it may be difficult to obtain full STR analysis using negligible amounts of DNA samples. Mitochondrial DNA (mtDNA) is characterized by its stability and high cellular copy number. Therefore, mtDNA testing in urine is expected to be used to analyze samples that cannot be analyzed using STR analysis. The objective of this study was to compare mtDNA testing with STR analysis by conducting sensitivity, concordance (whole blood, dried blood spot, and urine), and case-type studies. In sensitivity studies, mtDNA testing exhibited greater sensitivity compared with STR analysis. Concordance studies indicated that all samples were consistent with the mtDNA sequences and STR profiles. Allelic dropout occurred in some urine samples that were examined for STR analysis. Case-type sample studies demonstrated that mtDNA testing could be used to obtain DNA profiles of all the samples tested, including blood, dried blood spots, urine, blood residues on needles, and blood stains. In conclusion, mtDNA testing is valuable for analyzing highly degraded DNA samples, such as urine samples, compared with STR analysis. Urine testing should be performed for the initial testing procedure, because mtDNA is inherited maternally. In situations where the DNA match is detrimental to the athlete, additional blood STR analysis may be required.

Mitochondrial DNA Analysis of Teeth for Identification of Natural Disaster Victims in Manila, Philippines

Introduction: Natural disasters such as earthquakes, tsunamis and hurricanes often cause significant loss of life and damage to infrastructure. Identification of victims of natural disasters is an important aspect in the recovery process and forensic investigation. Mitochondrial DNA (mtDNA) has been proven to be an effective tool for individual identification due to its stable and maternally inherited nature. Teeth are an ideal source of DNA material for mtDNA analysis because they are durable against environmental degradation. This study aims to evaluate the effectiveness of mtDNA analysis of teeth for identifying victims of natural disasters in Manila, Philippines. Methods: Dental samples were collected from identified natural disaster victims and their family members. Mitochondrial DNA was extracted from teeth and analyzed using PCR and DNA sequencing techniques. The results of the mtDNA analysis were compared with mtDNA data obtained from family members to confirm the victim's identity. Results: Analysis of mtDNA on teeth succeeded in identifying all victims of natural disasters identified in this study. The mtDNA analysis results were consistent with mtDNA data obtained from family members, indicating the effectiveness of this method for individual identification. Conclusion: Analysis of mtDNA in teeth is a valuable tool for the identification of victims of natural disasters. This method can help in the recovery process and forensic investigations after natural disasters.

Specific emitter identification based on ensemble domain adversarial neural network in multi-domain environments

Specific emitter identification is pivotal in both military and civilian sectors for discerning the unique hardware distinctions inherent to various launchers, it can be used to implement security in wireless communications. Recently, a large number of deep learning-based methods for specific emitter identification have been proposed, achieving good performance. However, these methods are trained based on a large amount of data and the data are independently and identically distributed. In actual complex environments, it is very difficult to obtain reliable labeled data. Aiming at the problems of difficulty in data collection and annotation, and the large difference in distribution between training data and test data, a method for individual radiation source identification based on ensemble domain adversarial neural network was proposed. Specifically, a domain adversarial neural network is designed and a Transformer encoder module is added to make the features obey Gaussian distribution and achieve better feature alignment. Ensemble classifiers are then used to enhance the generalization and reliability of the model. In addition, three real and complex migration environments, Alpine–Montane Channel, Plain-Hillock Channel, and Urban-Dense Channel, were constructed, and experiments were conducted on WiFi dataset. The simulation results show that the proposed method exhibits superior performance compared to the other six methods, with an accuracy improvement of about 3%.

An ultra-lightweight method for individual identification of cow-back pattern images in an open image set

Cow recognition forms the foundation of smart livestock management. Current closed-set cow recognition models can exclusively identify cows within their training set and are ill-equipped to recognize other subjects in the open world. Additionally, there is a dearth of comprehensive research on open-set cow recognition. Existing open-set recognition models not only exhibit suboptimal accuracy but also impose a substantial burden on hardware resources due to their extensive parameterization. These challenges hinder the practical deployment of cow recognition models. This study introduces an innovative open-set metric learning-based recognition framework for cow-back patterns, aiming to rectify a significant limitation of individual cow recognition models, which is their inability to identify cows not included in the training set. The proposed framework combines various loss functions, metric methods, and backbone networks. This integration enables the open-set recognition of cow back pattern images, thereby facilitating the identification of cows previously unrecognized by the model. To mitigate hardware resource consumption, we have devised a novel ultra-lightweight backbone network known as LightCowsNet. This network draws inspiration from existing lightweight backbone networks such as MobileFaceNet, MobileViT, and EfficientNetV2. Its purpose is to extract features from cow back pattern images efficiently. LightCowsNet employs attention mechanisms, inverted residual structures, and depthwise separable convolutions. LightCowsNet first uses attention mechanisms, inverted residual structures, and depthwise separable convolutions to design multiple new feature extraction modules. These modules, which have different structures, are subsequently placed to extract different levels of image information, which enables complete extraction of the textural information of the cows’ back patterns. The present study reorganized the Cows2021 dataset to render it suitable for open-set recognition of cow-back patterns, with the test set comprising image pairs. The results revealed that using A-SoftMax as the loss function and Euclidean distance as the metric method enabled LightCowsNet to achieve the highest accuracy of 94.26 %, with a model weight space occupation of only 4.06 MB. Compared to MobileFaceNet, MobileViT, and EfficientNetV2, LightCowsNet achieved 6.24 %, 8.82 %, and 2.3 % greater accuracy on the test set, respectively. Its weight also decreased by 0.71 MB, 0.24 MB, and 4.3 MB, respectively. These results demonstrate that the proposed model achieved both accuracy improvement and model lightweightness, and these findings could serve as reference solutions for intelligent farming on cow farms.

Paint marking using CO2 anaesthetization does not affect exploratory and recruitment behaviours in the rock ant, Temnothorax rugatulus

The study of animal behaviour sometimes requires unique identification of individuals, especially in the study of social behaviours involving the interactions of multiple individuals. To this end, researchers have developed many different methods of marking individuals. For small animals like insects, paint marks are often applied to their bodies by anaesthetizing them using low temperature or carbon dioxide. Despite this procedure being ubiquitous when studying social insects, the effect of paint and anaesthetics on their behaviour has not been well investigated, especially their effect on performance during a collective task. In our study, we investigate how paint marks and anaesthetics affect the movement and recruitment behaviours of the ant Temnothorax rugatulus in a house hunting context. We painted two thirds of colony members, half of them using CO2 and the other half using low temperature as methods of anaesthetization, and left the one third unpainted as a control group. We then measured their exploratory behaviour prior to house hunting and their recruitment behaviours during house hunting. We found that neither paint marks nor anaesthetics reduce activity levels of these behaviours. However, low-temperature anaesthetized ants performed a higher number of recruitment behaviours than control ants. Because CO2 anaesthetized ants performed all tasks at the same level as control ants, our data suggest that this is a good technique for paint marking ants, especially T. rugatulus. This is the first study empirically testing negative effects of paint marking on individual and collective outcomes in social insects. Our study represents an important step towards routine validation of individual identification methods used in the study of animal behaviour.

Species-specific SNP arrays for non-invasive genetic monitoring of a vulnerable bat

Genetic tagging from scats is one of the minimally invasive sampling (MIS) monitoring approaches commonly used to guide management decisions and evaluate conservation efforts. Microsatellite markers have traditionally been used but are prone to genotyping errors. Here, we present a novel method for individual identification in the Threatened ghost bat Macroderma gigas using custom-designed Single Nucleotide Polymorphism (SNP) arrays on the MassARRAY system. We identified 611 informative SNPs from DArTseq data from which three SNP panels (44–50 SNPs per panel) were designed. We applied SNP genotyping and molecular sexing to 209 M. gigas scats collected from seven caves in the Pilbara, Western Australia, employing a two-step genotyping protocol and identifying unique genotypes using a custom-made R package, ScatMatch. Following data cleaning, the average amplification rate was 0.90 ± 0.01 and SNP genotyping errors were low (allelic dropout 0.003 ± 0.000) allowing clustering of scats based on one or fewer allelic mismatches. We identified 19 unique bats (9 confirmed/likely males and 10 confirmed/likely females) from a maternity and multiple transitory roosts, with two male bats detected using roosts, 9 km and 47 m apart. The accuracy of our SNP panels enabled a high level of confidence in the identification of individual bats. Targeted SNP genotyping is a valuable tool for monitoring and tracking of non-model species through a minimally invasive sampling approach.

MLDA: Multi-Loss Domain Adaptor for Cross-Session and Cross-Emotion EEG-Based Individual Identification.

Traditional individual identification methods, such as face and fingerprint recognition, carry the risk of personal information leakage. The uniqueness and privacy of electroencephalograms (EEG) and the popularization of EEG acquisition devices have intensified research on EEG-based individual identification in recent years. However, most existing work uses EEG signals from a single session or emotion, ignoring large differences between domains. As EEG signals do not satisfy the traditional deep learning assumption that training and test sets are independently and identically distributed, it is difficult for trained models to maintain good classification performance for new sessions or new emotions. In this article, an individual identification method, called Multi-Loss Domain Adaptor (MLDA), is proposed to deal with the differences between marginal and conditional distributions elicited by different domains. The proposed method consists of four parts: a) Feature extractor, which uses deep neural networks to extract deep features from EEG data; b) Label predictor, which uses full-layer networks to predict subject labels; c) Marginal distribution adaptation, which uses maximum mean discrepancy (MMD) to reduce marginal distribution differences; d) Associative domain adaptation, which adapts to conditional distribution differences. Using the MLDA method, the cross-session and cross-emotion EEG-based individual identification problem is addressed by reducing the influence of time and emotion. Experimental results confirmed that the method outperforms other state-of-the-art approaches.

An attentional residual feature fusion mechanism for sheep face recognition

In the era of globalization and digitization of livestock markets, sheep are considered an essential source of food production worldwide. However, sheep behavior monitoring, disease prevention, and precise management pose urgent challenges in the development of smart ranches. To address these problems, individual identification of sheep has become an increasingly viable solution. Despite the benefits of traditional sheep individual identification methods, such as accurate tracking and record-keeping, they are labor-intensive and inefficient. Popular convolutional neural networks (CNNs) are unable to extract features for specific problems, further complicating the issue. To overcome these limitations, an Attention Residual Module (ARM) is proposed to aggregate the feature mapping between different layers of the CNN. This approach enables the general model of the CNN to be more adaptable to task-specific feature extraction. Additionally, a targeted sheep face recognition dataset containing 4490 images of 38 individual sheep has been constructed. Furthermore, the experimental data was expanded using image enhancement techniques such as rotation and panning. The results of the experiments indicate that the accuracy of the VGG16, GoogLeNet, and ResNet50 networks with the ARM improved by 10.2%, 6.65%, and 4.38%, respectively, compared to these recognition networks without the ARM. Therefore, the proposed method for specific sheep face recognition tasks has been proven effective.

Fusion of RetinaFace and improved FaceNet for individual cow identification in natural scenes

Cows’ posture change is the fatal influencing factor for accurate identification of individual cows. To achieve non-contact, high-precision detection and identification of individual cows in farm environment, a cow individual identification method by the fusion of RetinaFace and improved FaceNet was proposed. MobileNet-enhanced RetinaFace was applied to ameliorate the impact of output channel quantity and convolution kernel dynamics using depthwise convolution combined with pointwise convolution. Regression predictions of bovine facial features and keypoints were generated under varying distances, scales and sizes. FaceNet's core feature network was enhanced through MobileNet integration, and the loss function was jointly optimized with Cross Entropy Loss and Triplet Loss to achieve a quicker and more stable convergence curve. The distances between the generated embedding vectors of cow facial features were corresponding to the similarity between cow faces, enabling accurate matching. RetinaFace exhibited detection false negative rates of 2.67%, 0.66%, 2.67%, and 3.33% under conditions of occlusion, no occlusion, low light, and bright light for cow facial detection. For cow facial pattern detection, the false negative rates for black and white patterns, pure black and pure white were 1.33%, 6.00% and 8.00%, respectively. Regarding cow facial posture changes, the false negative rates for face upward, bowing down, profile, and normal posture were 1.33%, 1.33%, 4.00% and 0.66%, respectively. Improved FaceNet model achieved an accuray of 99.50% on training set and 83.60% on test set. In comparison to YOLOX, the recognition model presented in this research demonstrated increased accuracy in cow facial detection under occlusion, no occlusion and strong lighting conditions by 2.67%, 0.40%, and 0.40%, respectively. Moreover, the accuracy for patterns with pure black and pure white tones surpassed that of YOLOX by 1.06% and 5.71%, correspondingly. Additionally, the accuracy rates for face upward, bowing down, profile and normal posture were higher than YOLOX by 2.00%, 3.34%, 2.66% and 0.40%, respectively. The proposed model demonstrates the proficiency in accurately identifying individual cows in natural scenes.

Review of the Current Research in Animal Individual Recognition

With the development of biological identification for human beings, it also develops such as fingerprint, facial recognition, and iris identification. Scientists and zoologists must be more content with the cumbersome ways of identifying previously existing animals. Old methods such as ear cutting, chip implantation, and nose print recognition harm animals and humans. It has to catch the animals or needed professionals for individual identification (e.g, identify sharks by taking photos of their fins). Therefore, more and more scientists and engineers are trying to develop more efficient methods for individual animal identification. Of course, there are also many very constructive cases. Thus, this literature review will provide information about three regions of the latest recognition technology: radio-frequency identification (RFID), animal facial identification, and iris recognition.

Individual Pig Identification Using Back Surface Point Clouds in 3D Vision.

The individual identification of pigs is the basis for precision livestock farming (PLF), which can provide prerequisites for personalized feeding, disease monitoring, growth condition monitoring and behavior identification. Pig face recognition has the problem that pig face samples are difficult to collect and images are easily affected by the environment and body dirt. Due to this problem, we proposed a method for individual pig identification using three-dimension (3D) point clouds of the pig's back surface. Firstly, a point cloud segmentation model based on the PointNet++ algorithm is established to segment the pig's back point clouds from the complex background and use it as the input for individual recognition. Then, an individual pig recognition model based on the improved PointNet++LGG algorithm was constructed by increasing the adaptive global sampling radius, deepening the network structure and increasing the number of features to extract higher-dimensional features for accurate recognition of different individuals with similar body sizes. In total, 10,574 3D point cloud images of ten pigs were collected to construct the dataset. The experimental results showed that the accuracy of the individual pig identification model based on the PointNet++LGG algorithm reached 95.26%, which was 2.18%, 16.76% and 17.19% higher compared with the PointNet model, PointNet++SSG model and MSG model, respectively. Individual pig identification based on 3D point clouds of the back surface is effective. This approach is easy to integrate with functions such as body condition assessment and behavior recognition, and is conducive to the development of precision livestock farming.

Genetic characterization of the Colombian Creole Horse population via STR markers used in filiation tests and equine certification

Genetic parentage tests have great relevance in breed registration processes in equine specimens. In addition, these tests are used to verify progeny genetic accuracy, using microsatellite molecular markers (STR) as a method for individual identification and kinship between individuals. Specifically, we evaluated a Colombian Creole breed equine population, using blood, saliva, and hair samples as sources of DNA. The samples were extracted using Chelex chelating resins. DNA quantification was performed by NanoDrop and amplified by PCR using the 17 STRs included in the Equine Genotypes panel 1.1 kit. Subsequently, electrophoresis was performed and stained with SYBR safe, and genotypes were determined using capillary electrophoresis. Additionally, the allelic and genotypic frequencies were calculated using the GENEPOP software and the previously obtained genetic profiles. Also, the HWE, heterozygosity per locus, inbreeding, and gametic imbalance were estimated. As a result, some genetic markers such as ASB23, ASB17, and LEX3 were not suitable for executing the tests since they biased the population parameters. However, we recommend expanding the equine population and using more STRs to obtain better results in these genetic tests in future population studies.