Search

Human identification can be performed through various available biometric traits such as the face, iris, fingerprint, ECG, gait, and ear. Among them, face is one of the most popular and widely used biometrics. In the security domain, early warnings and the trace of suspects can be accomplished using face recognition. The contemplated augmentation projected an intelligent computational model for human recognition which is an ingenious melding of unsupervised outline and complex domain neurocomputing. The unsupervised framework of our proposal constitutes evolutionary fuzzy computations in complex domain. The supervised schema capitalizes on a complex domain neural network with higher-order neurons and resilient propagation algorithm. Trainable multiple stages are populated in this proposal for the estimation of recognition and classification. This proposal offers an intelligent performance on recognition and classification tasks. Comprehensive experimental analysis on the datasets of AR face, PubFig83, and Indian face evidenced the enhanced precision of the proposed model. Our model achieves an impressive accuracy range of 97% to 99% across all datasets. These results clearly demonstrate the superior performance of our approach, showcasing the dominance of the combined unsupervised and supervised frameworks over other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Palm print identification is a biometric technique that relies on the distinctive characteristics of a person's palm print to distinguish and authenticate their identity. The unique pattern of ridges, lines, and other features present on the palm allows for the identification of an individual. The ridges and lines on the palm are formed during embryonic development and remain relatively unchanged throughout a person's lifetime, making palm prints an ideal candidate for biometric identification. Using deep learning networks, such as GoogLeNet, SqueezeNet, and AlexNet combined with gray wolf optimization, we achieved to extract and analyze the unique features of a person's palm print to create a digital representation that can be used for identification purposes with a high degree of accuracy. To this end, two well-known datasets, the Hong Kong Polytechnic University dataset and the Tongji Contactless dataset, were used for testing and evaluation. The recognition rate of the proposed method was compared with other existing methods such as principal component analysis, including local binary pattern and Laplacian of Gaussian-Gabor transform. The results demonstrate that the proposed method outperforms other methods with a recognition rate of 96.72%. These findings show that the combination of deep learning and gray wolf optimization can effectively improve the accuracy of human identification using palm print images. [ABSTRACT FROM AUTHOR]

Scientific and technological developments experienced by forensic sciences have increased the possibility of human identification. Forensic anthropology has developed worldwide and has made significant progress in Brazil in the last 10 years. This context has allowed forensic medicine institutes to use new techniques to resolve cold cases of human identification. This work aimed to report the methodology, development, and partial results of the LAFOL Identifies Operation, carried out at the Forensic Anthropology and Forensic Dentistry Laboratory (LAFOL) of the Medico-Legal Institute of Porto Velho. We carried out a multidisciplinary expert approach on human skeletal remains archived over the last 20 years to identify these individuals using current scientific methods. Eighty-one cold cases of skeletonized and/or mummified human skeletal remains were reanalyzed; they were archived in the LAFOL Laboratory collection as unidentified. Anthropological analyses showed that the collection is predominantly composed of adult individuals (86.4%), between 21 and 39 years old (55.6%), and males (62.9%). In the human skeletal remains identified, forensic anthropology played a key role in the case screening process. We expected that the results presented in this work will inspire other Medico-Legal Institutes in Brazil and worldwide to establish task forces for the reanalysis of cold cases in their institutes, promoting new forensic dentistry and anthropological comparisons and collecting biological samples to feed the database of genetic profiles of missing persons.

In this study, population data were generated from South Africans using the Investigator® 24plex GO! Kit (QIAGEN, Hilden, Germany). Participants represented the four major population groups in South Africa, with self-reported ancestral origin being African (n = 208), European (n = 213), Indian/Asian (n = 103) or Admixed (n = 209). Allele frequency data and forensic parameters were calculated for each population group using Arlequin (v.3.5.2.2) and FORSTAT (v1.0). TPOX had the lowest discrimination capacity for all population groups, except for the African population group where THO1 was the least informative. SE33 had the highest discrimination capacity for all population groups (>0.98), with 38 different alleles observed in the Admixed population group. Samples exhibiting novel alleles or anomalies underwent massively parallel sequencing using the ForenSeq™ DNA Signature Prep kit, which confirmed the following results: one null Y allele at Amelogenin, ten instances of TPOX tri-allelism and four novel micro-variant alleles. An additional four novel alleles in SE33 were observed but remain unconfirmed, due to SE33 not being included in the ForenSeq™ DNA Signature Prep kit. Moreover, nine individuals had an allele 8 or 9 at D1S1656, where the peaks for these alleles occur before the D1S1656 marker range on the electropherogram and showed as a peak within the DYS391 marker. Although this observation was rare overall (1.2%), these nine individuals were from three of the four population groups, which motivates for the adjustment of the Investigator® 24plex PCR chemistry to avoid allelic overlap of D1S1656 with DYS391. Overall, these findings highlight the diverse genetic makeup of the South Africa population and accentuate the importance of local population studies.

Artificial intelligence (AI) and sensor technology developments have sparked revolutionary shifts in a number of fields, including biometric Identification. In order to improve human identification processes, this research offers a novel method that integrates AI and many biometric image sensors. The accuracy, robustness, and susceptibility to spoofing assaults of conventional single-modal biometric systems are among their many drawbacks. To overcome these challenges, we introduce a secure multi-biometric system that relies on feature-level fusion to identify users. In the preprocessing step, fingerprint images undergo Min-Max normalization to mitigate variations in image quality. In order to extract high-level features from both raw Electrocardiogram (ECG) signals and Min-Max normalized fingerprint images, ResNet50, a deep convolutional neural network, is used. These extracted feature vectors are able to distinguish between the two modalities. We proposed boosted Xgboost as a classifier for authentication in the identification steps to improve performance. The proposed approach is simulated using Python. A comparison study for improved Xgboost is presented using measures for accuracy, precision-recall, and F1-Score. Across all comparative metrics, the technique achieves much better performance. According to experimental findings, the suggested multi-biometric systems are more effective, dependable, and robust than the existing multi-biometric authentication systems.

This study proposes a passive human identification system based on wireless signals. The proposed system comprises three phases; preprocessing and standardization of recorded channel state information (CSI) signals and the extraction of relevant data using principal component analysis (PCA), transformation of the signals into feature vectors, and finally construction of classification models. To evaluate the proposed approach, we collected data from ten subjects in an indoor environment while performing a set of activities. The proposed approach was tested using three different activities: walking, sitting/standing, and picking up a pen, achieving subject identification accuracy of 97.3%, 99.75%, and 65.5%, respectively. The results suggest that activity-based identification systems can serve as an effective alternative to traditional methods such as passwords and smart cards.

In this paper, we discuss our proposed unified approach to iris recognition called the SwinIris. This approach works efficiently when combing a tuned version of the original Swin Transformer with a set of iris recognition processes. While the original Swin Transformer has recently been used on different biometric modalities due to its competitive advantage over other architectures, it has not been used for iris recognition. Thus, in our work, our proposed deep learning architecture is using a pre-trained Swin Transformer model that is fine-tuned with a set of linear layers. This model is a set of algorithmic aspects that achieve competitive iris-matching accuracy when using any of the selected iris databases selected to test our approach. Specifically, our proposed SwinIris Transformer-based iris recognition system is composed of four modules, namely, the eye detection, iris detection, iris segmentation, and iris classification modules. The proposed system commences with a detection process that aims to identify eyes within the camera-captured original iris images. Subsequently, the iris detection process identifies the iris patterns within the detected iris images to ensure that they are present and can be segmented. The third module involves iris segmentation, which extracts iris features utilized by the fourth and final module that matches iris images using the SwinIris-based Transformer model. The performance of the proposed system is evaluated on small- and large-scale iris datasets, including the CASIA-Iris- Thousand, CASIA-Iris-Lamp, CASIA-IntervalV4, and CASIA- IntervalV3. Our proposed model has a competitive iris classification accuracy when compared to various academic state-of-the-art methodologies, resulting in a classification performance ranging from 95.14% to 99.56%.

In the modern world of human–computer interaction, notable advancements in human identification have been achieved across fields like healthcare, academia, security, etc. Despite these advancements, challenges remain, particularly in scenarios with poor lighting, occlusion, or non-line-of-sight. To overcome these limitations, the utilization of radio frequency (RF) wireless signals, particularly wireless fidelity (WiFi), has been considered an innovative solution in recent research studies. By analyzing WiFi signal fluctuations caused by human presence, researchers have developed machine learning (ML) models that significantly improve identification accuracy. This paper conducts a comprehensive survey of recent advances and practical implementations of WiFi-based human identification. Furthermore, it covers the ML models used for human identification, system overviews, and detailed WiFi-based human identification methods. It also includes system evaluation, discussion, and future trends related to human identification. Finally, we conclude by examining the limitations of the research and discussing how researchers can shift their attention toward shaping the future trajectory of human identification through wireless signals.

Background: Intraoral scans (IOS) provide precise 3D data of dental crowns and gingival structures. This paper explores an application of IOS in human identification. Methods: We propose a dental biometrics framework for human identification using 3D dental point clouds based on machine learning-related algorithms, encompassing three stages: data preprocessing, feature extraction, and registration-based identification. In the data preprocessing stage, we use the curvature principle to extract distinguishable tooth crown contours from the original point clouds as the holistic feature identification samples. Based on these samples, we construct four types of local feature identification samples to evaluate identification performance with severe teeth loss. In the feature extraction stage, we conduct voxel downsampling, then extract the geometric and structural features of the point cloud. In the registration-based identification stage, we construct a coarse-to-fine registration scheme in order to realize the identification task. Results: Experimental results on a dataset of 160 individuals demonstrate that our method achieves a Rank-1 recognition rate of 100% using complete tooth crown contours samples. Utilizing the remaining four types of local feature samples yields a Rank-1 recognition rate exceeding 96.05%. Conclusions: The proposed framework proves effective for human identification, maintaining high identification performance even in extreme cases of partial tooth loss.

Radar signal has been shown as a promising source for human identification. In daily home sleep-monitoring scenarios, large-scale motion features may not always be practical, and the heart motion or respiration data may not be as ideal as they are in a controlled laboratory setting. Human identification from radar sequences is still a challenging task. Furthermore, there is a need to address the open-set recognition problem for radar sequences, which has not been sufficiently studied. In this paper, we propose a deep learning-based approach for human identification using radar sequences captured during sleep in a daily home-monitoring setup. To enhance robustness, we preprocess the sequences to mitigate environmental interference before employing a deep convolution neural network for human identification. We introduce a Principal Component Space feature representation to detect unknown sequences. Our method is rigorously evaluated using both a public data set and a set of experimentally acquired radar sequences. We report a labeling accuracy of 98.2% and 96.8% on average for the two data sets, respectively, which outperforms the state-of-the-art techniques. Our method excels at accurately distinguishing unknown sequences from labeled ones, with nearly 100% detection of unknown samples and minimal misclassification of labeled samples as unknown. [ABSTRACT FROM AUTHOR]

Introduction: The uniqueness of the human dentition serves its wide acceptance in the identification of individual in forensic science. Aim and Objectives: To estimate the accuracy of age by using modified Kvaal’s formula and coronal pulp cavity index (CPCI) and compare the standard error and establish the technique among the Pune population. Materials and Methods: Four hundred cone‑beam computed tomography (CBCT) scans were randomly selected with satisfying the established criteria. The second premolar was included in the study and the maximum length of tooth, root, and pulp was measured using modified Kvaal’s method and CPCI by using Planmeca CBCT machine with Romexis‑three‑dimensional imaging software. Results: The results were analyzed using the Chi‑square test and ANOVA. Modified Kvaal’s formula was found to be the better followed by CPCI in the estimation of age among Indians with lesser error in prior. Conclusion: Modified Kvaal’s formula is precise, noninvasive, and most reliable biomarker for age estimation than tooth‑coronal index. [ABSTRACT FROM AUTHOR]

• Forensic application of IRMS is dependent on the quality isotope data. • We discuss ways to assess isotopic data reliability for human identification work. • We also discuss accreditation of isotope testing for forensic identification. Application of isotope ratio mass spectrometry (IRMS) to skeletal remains has become an important tool to investigate human behavior and history. Isotopic variations in collagen, enamel, and keratin reflect variations in an individual's diet and drinking water. Since food and water sources typically are geographically linked, isotope testing can assist in forensic identification by classifying remains to a likely geographic or population origin. If remains are commingled, differences in diet or geographic origin also can support their separation. The usefulness of IRMS in forensic science is dependent on the underlying quality and surety of the isotope test results; in other words, we need to understand their reliability in interpretations. To take ownership of isotopic data quality, we recommend asking a series of questions: 1. How well are the mass spectrometer and associated peripheral(s) operating? 2. Are test results reproducible (over time and between locations)? 3. Can we differentiate between populations that we would like to? 4. How variable are the populations of interest? 5. Have the samples been isotopically altered? 6. How variable are the samples? Here, we use data collected during the buildout and accreditation of an isotope testing program at the Defense POW/MIA Accounting Agency (DPAA) to answer the above questions for the forensic application of IRMS for human identification. While our primary focus is on the preparation and analysis of bone collagen, the questions above should be considered whenever isotope testing is used in forensic casework. Whether the populations of interest are drugs or humans, olives or explosives, users need to evaluate their isotopic data and interpretations to ensure they are scientifically sound and legally defensible. [ABSTRACT FROM AUTHOR]

This study aims to establish the significance and impact of using DNA data in forensics. The study employed the anamnestic method, descriptive analysis, and forecasting. The conducted research identified the key problems of creating and using DNA databases, including insufficient logistical and laboratory support, understaffing, lack of special legislation, low level of security, slow filling of databases, disregard of the public position, and the need to establish international cooperation. It was established that DNA analysis enables identifying the identity of the deceased or a person who cannot identify himself; determining the number of persons at the crime scene; establishing whether DNA traces belong to a suspect; establishing a connection between several crimes by matching DNA samples taken from the scene; establishing those accused of crimes. It is proposed to increase the effectiveness of law enforcement activities through the development of an International Strategy for the Influence of the Use of DNA Databases and ensure international cooperation on the exchange of DNA information in forensics. [ABSTRACT FROM AUTHOR]

BACKGROUND Adipose tissue is often overlooked in DNA testing due to misconceptions about its DNA content. However, its shock-absorbing qualities may be useful for high-pressure scenarios like bomb blasts. This study aimed to evaluate DNA quality and quantity in adipose tissue affected by blasts compared to that in unaffected tissue. METHODS 10 adipose tissue samples were taken from regions near and far from the blast, representing the blast-exposed and non-blast-exposed groups. The adipose tissue was stored at a low temperature for 5 days, after which an organic extraction method was applied. The purity of the DNA extract was assessed using a NanoDrop spectrophotometer, and its integrity was evaluated using 0.8% concentration gel electrophoresis at 60 V for 90 min. DNA typing was conducted using the GlobalFiler™ kit, and DNA quantity was determined with the Quantifiler™ Trio DNA Quantification kit. RESULTS Of 20 DNA extracts from adipose tissue, all samples demonstrated purity, integrity, and complete typing results. Adequate integrity was found in 90% of samples in both groups. A 50% incidence of allele shifting was observed at the D7S820 locus within the blast-exposed group. CONCLUSIONS DNA from blast-exposed adipose tissue exhibited no significant quality or quantity differences from non-blast-exposed tissue. This suggested adipose tissue's potential as an alternative DNA source in a bomb explosion. [ABSTRACT FROM AUTHOR]

Human identification using unobtrusive visual features is a daunting task in smart environments. Gait is among adequate biometric features when the camera cannot correctly capture the human face due to environmental factors. In recent years, gait-based human identification using skeleton data has been intensively studied using a variety of feature extractors and more sophisticated deep learning models. Although skeleton data is susceptible to changes in covariate variables, resulting in noisy data, most existing algorithms employ a single feature extraction technique for all frames to generate frame-level feature maps. This results in degraded performance and additional features, necessitating increased computing power. This paper proposes a robust feature extractor that extracts a quantitative summary of gait event-specific information, thereby reducing the total number of features throughout the gait cycle. In addition, a novel Attention-guided LSTM-based deep learning model with residual connections is proposed to learn the extracted features for gait recognition. The proposed approach outperforms the state-of-the-art works on five publicly available datasets on various benchmark evaluation protocols and metrics. Further, the CMC test revealed that the proposed model obtained higher than 97% Accuracy in lower-level ranks on these datasets. [ABSTRACT FROM AUTHOR]

Recognizing human activities non-intrusively has prevailed as a challenging and active area of research. In real life, it is a major requirement for human-centric applications like assisted living for elderly care, health-care and creating a smart home environment etc. Considering that people spend more than 90% (Klepeis et al. in J Exposure Sci Environ Epidemiol 11(3):231, 2001) of their time indoors, a proper indoor activity monitoring system will be helpful to monitor the abnormal behavior of the occupants. Existing approaches have implemented intrusive or invasive methods such as a camera or wearable devices. In this work, we present a non-invasive, non-intrusive sensing technique using an array of heterogeneous ultrasonic sensors for human activity monitoring. The ultrasonic sensors are placed in two separate deployments as sensor grids and in different positions of the door-frame. The proposed system senses a stream of events as the occupants perform different activities categorized as primary, postural and group activities. The primary activities considered are sitting, standing and fall. The postural activities are intermediate transitional states in the primary activities. These activities when performed in groups, are considered as a group activity. Other than activities it can identify different indoor movements, count room occupancy and identify occupants. Based on the collected data, the results show that the proposed system achieves an accuracy of more than 90% for detection of different activities and shows improvement over existing works. The final outcome of this work can be seen as developing the current prototype into smart ceiling panels that can be easily used in the indoor environment for human activity monitoring. [ABSTRACT FROM AUTHOR]

Colombia faces the complex humanitarian challenges of locating approximately 100,000 missing persons and identifying thousands who are deceased. Identification is a difficult task in many cases, because the skeletonized bodies are deteriorated, missing person data are unavailable for comparison, and the provenance of the remains is often totally unknown. Isotopic analysis of human tissues (e.g., bone, hair, nails, and teeth) aid in the identification process of unknown individuals because they can provide valuable information on possible geographic origin. This project evaluated the isotopic variability of carbon (C), oxygen (O), strontium (Sr), and lead (Pb) in modern Colombian teeth according to city, department (a political designation similar to "state" in the US or Mexico), and one of four geographically determined regions of origin; and assessed its utility for human identification in Colombia. Isotopic data (O‐C‐Sr‐Pb) were analyzed from modern Colombians originating from the cities of Bogotá, Cali, and Neiva (n = 95); and these data were compiled with published Colombian data of individuals mainly from the city of Medellín (n = 61). Results indicate a wide range and overlap of O‐C‐Sr‐Pb isotopic distribution according to the defined categories. However, differences between coastal and lowland individuals are observed when using δ18O values, and differences between mountainous regions are observed when using 87Sr/86Sr values. In addition, this study suggests that the usefulness of isotopic analysis for unidentified individuals in Colombia would be with assigning them geographically using the designations of North, Central Andes, Eastern Andes, or Southwest Andes versus making classifications at a city or department level. [ABSTRACT FROM AUTHOR]

This technical note aims to characterize and contextualize the creation of a new collection of identified skeletons stored in the University Institute of Health Sciences—CESPU. This project presents unique and innovative pedagogical opportunities, with students actively involved in the cleaning and processing of the bones and antemortem/postmortem information gathering, as well as in anthropology research projects. This XXI Century Identified Skeletal Collection is composed of 98 complete adult skeletons of both sexes and is still expanding, being the 10th contemporary collection available in Portugal. The skeletons consist exclusively of Portuguese nationals who died between 1946 and 2007, and the 42% that have been processed so far are in good preservation. Comparative learning outcomes after implementing this active learning strategy are not yet available. Improvements are expected since more participation and enthusiasm in classes and research were perceived.

Accurate human identification using radar has a variety of potential applications, such as surveillance, access control and security checkpoints. Nevertheless, radar-based human identification has been limited to a few motion-based biometrics that are solely reliant on micro-Doppler signatures. This paper proposes for the first time the use of combined radar-based heart sound and gait signals as biometrics for human identification. The proposed methodology starts by converting the extracted biometric signatures collected from 18 subjects to images, and then an image augmentation technique is applied and the deep transfer learning is used to classify each subject. A validation accuracy of 58.7% and 96% is reported for the heart sound and gait biometrics, respectively. Next, the identification results of the two biometrics are combined using the joint probability mass function (PMF) method to report a 98% identification accuracy. To the best of our knowledge, this is the highest reported in the literature to date. Lastly, the trained networks are tested in an actual scenario while being used in an office access control platform to identify different human subjects. We report an accuracy of 76.25%.

Three-dimensional technology using personal data records has been explored for human identification. The present study aimed to explore two methodologies, photography and orofacial scanning, for assessing orofacial records in forensic scenarios, highlighting their impact on human identification. A pilot and quasi-experimental study was performed using Canon 5D-Full Frame equipment (Tokyo, Japan) and an i700 scanner (Medit, Lusobionic, Portugal) (Seoul, Republic of Korea) with Medit Scan for Clinics (MSC) and Smile Design software (V3.3.2). The sample included living patients (n = 10) and individuals in forensic cases (n = 10). The study was divided into two complementary phases: (i) data collection using 2D and 3D technologies and (ii) visual comparison by superimposition procedures, 3D dental images with 3D facial records (3D–3D), and 2D photography with screen printing of 3D facial records (2D-3S). Statistical analyses were performed using descriptive procedures (Likert scale) and the Mann–Whitney U test. The Mann–Whitney U test comparing the data (n = 220 records) from living individuals and those in forensic cases identified statistically significant differences in the performance of the photographic methods for evaluating intraoral mineralisation (p = 0.004), intraoral soft tissues (p = 0.016), intraoral distortion (p = 0.005) and the scan methods for intraoral extra devices (p = 0.003) and extraoral soft tissues (p = 0.005). A visual comparison (n = 40) allowed 3D–3D superimposition. Additionally, 2D-3S superimposition qualitatively identified the middle third of the face as the corporal area within the anatomical features required for successful surgery. In conclusion, the present study presented evidence-based data suggesting that the IO scan method, as an emergent technology, should be explored as a valuable tool in forensic facial identification in real-world scenarios.

DNA analysis plays a crucial role in forensic investigations, helping in criminal cases, missing persons inquiries, and archaeological research. This study focuses on the DNA concentration in different skeletal elements to improve human identification efforts. Ten cases of unidentified skeletal remains brought to the Institute of Forensic Medicine in Timisoara, Romania, underwent DNA analysis between 2019 and 2023. The results showed that teeth are the best source for DNA extraction as they contain the highest concentration of genetic material, at 3.68 ng/µL, compared to the petrous temporal bone (0.936 ng/µL) and femur bone (0.633 ng/µL). These findings highlight the significance of teeth in forensic contexts due to their abundant genetic material. Combining anthropological examination with DNA analysis enhances the understanding and precision of identifying human skeletal remains, thus advancing forensic science. Selecting specific skeletal elements, such as the cochlea or teeth, emerges as crucial for reliable genetic analyses, emphasizing the importance of careful consideration in forensic identification procedures. Our study concludes that automated DNA extraction protocols without liquid nitrogen represent a significant advancement in DNA extraction technology, providing a faster, more efficient, and less labor-intensive method for extracting high-quality DNA from damaged bone and tooth samples.

The present study aimed to establish human earwax as a potential source of DNA evidence that could be effectively used in human identification. Sixty earwax samples were obtained from 15 healthy male and female Saudi volunteers living in Riyadh, Saudi Arabia. Four consecutive earwax swab samples were obtained from each volunteer and stored for 1, 15, 30 and 60 days. Earwax samples were stored at room temperature (20–22 °C). Reference oral swab was also taken from each volunteer. DNA was extracted by QIAamp DNA Mini kit and quantified by real-time polymerase chain reaction (RT-PCR) on 7500 Thermal Cycler. Autosomal STR loci were amplified using AmpFLSTR™ Identifiler™ Plus PCR Amplification Kit (Thermo Fisher Scientific, Carlsbad, CA, USA). Amplified fragments were size separated and analyzed on a 3500 Genetic Analyzer. Complete autosomal STR profiles were obtained from the earwax swabs of all the volunteers stored up to 30 days after the collection. Some STR profiles were partially obtained 60 days after the earwax collection. Allelic drop-out, allelic drop-in, and stutters were seen in earwax samples analyzed 60 days after the collection. The results have shown that human earwax can be a potential source of DNA evidence for human identification up to 30 days after the earwax collection. It is recommended to quickly analyze earwax samples or store them at room temperature or at −10 °C after their recovery from the crime scene.

AI-empowered sweat metabolite analysis is an emerging and open research area with great potential to add a third category to biometrics: chemical. Current biometrics use two types of information to identify humans: physical (e.g., face, eyes) and behavioral (i.e., gait, typing). Sweat offers a promising solution for enriching human identity with more discerning characteristics to overcome the limitations of current technologies (e.g., demographic differential and vulnerability to spoof attacks). The analysis of a biometric trait’s chemical properties holds potential for providing a meticulous perspective on an individual. This not only changes the taxonomy for biometrics, but also lays a foundation for more accurate and secure next-generation biometric systems. This paper discusses existing evidence about the potential held by sweat components in representing the identity of a person. We also highlight emerging methodologies and applications pertaining to sweat analysis and guide the scientific community towards transformative future research directions to design AI-empowered systems of the next generation.

This study aimed to evaluate the reliability of an age estimation method based on the pulp⁄tooth area ratio by assessing intra- and inter-examiner agreement across five observers at different intervals. Using the same X-ray device and technical parameters, 96 digital periapical X-ray images of upper and lower canines were obtained from 28 deceased people in Central America, whose age at death ranged from 19 to 49 years. Excellent and good agreement of results were achieved, and there were no statistically significant differences. The R2 value for upper teeth (54.0%) was higher than the R2 value for lower teeth (45.7%). The highest intraclass correlation coefficient value was 0.995 (0.993–0.997) and the lowest 0.798 (0.545–0.895). Inter-examiner agreement was high with values of 0.975 (0.965–0.983) and 0.927 (0.879–0.955). This method is adequate for assessing age in missing and unidentified people, including victims of mass disasters.

Within anatomical willed body programs and skeletal collections, whole bodies and their disassociated limbs and organs are identified and tracked. However, if these tracking mechanisms fail, DNA recovered from the formalin‐fixed tissues/organs could provide an additional layer of quality assurance. Embalming fluids preserve biological tissues; however, they also damage, fragment, and cross‐link DNA and protein molecules. This project investigated the success of STR‐typing from various soft tissue and bone samples that were fixed with embalming solutions with a range of formaldehyde concentrations. Formalin‐fixed samples dissected from five cadavers, including skin, muscle, bone, heart, and kidney were used in Phase 1 of this study. In Phase 2, an additional 57 tissue samples from various embalmed organs and body parts were collected to demonstrate long‐term fixation and direct applicability within a body donor program. DNA was extracted from the samples using the QIAamp® FFPE Tissue Kit (QIAGEN), quantified with the Investigator® QuantiPlex® Pro RGQ qPCR Kit (QIAGEN), and amplified using the Investigator® 24plex and 26plex QS Kits and the Investigator® DIPplex Kit (QIAGEN). The results show the DNA was severely damaged, degraded, and often in low amounts (after one year post‐embalming). Sampling from skin and muscle tissues embalmed with ~2.5%–5% formaldehyde solutions appears to be the best strategy for identification, while also maintaining the preservation of the tissues. The results of this project can provide informative data when determining which genotyping strategy may be best suited for the identification, re‐association, and establishment of a database for the provenance of formalin‐fixed human remains. [ABSTRACT FROM AUTHOR]

Keystroke dynamics is a soft biometric based on the assumption that humans always type in uniquely characteristic manners. Previous works mainly focused on analyzing the key press or release events. Unlike these methods, we explored a novel visual modality of keystroke dynamics for human identification using a single RGB-D sensor. In order to verify this idea, we created a dataset dubbed KD-MultiModal, which contains 243.2 K frames of RGB images and depth images, obtained by recording a video of hand typing with a single RGB-D sensor. The dataset comprises RGB-D image sequences of 20 subjects (10 males and 10 females) typing sentences, and each subject typed around 20 sentences. In the task, only the hand and keyboard region contributed to the person identification, so we also propose methods of extracting Regions of Interest (RoIs) for each type of data. Unlike the data of the key press or release, our dataset not only captures the velocity of pressing and releasing different keys and the typing style of specific keys or combinations of keys, but also contains rich information on the hand shape and posture. To verify the validity of our proposed data, we adopted deep neural networks to learn distinguishing features from different data representations, including RGB-KD-Net, D-KD-Net, and RGBD-KD-Net. Simultaneously, the sequence of point clouds also can be obtained from depth images given the intrinsic parameters of the RGB-D sensor, so we also studied the performance of human identification based on the point clouds. Extensive experimental results showed that our idea works and the performance of the proposed method based on RGB-D images is the best, which achieved 99.44 % accuracy based on the unseen real-world data. To inspire more researchers and facilitate relevant studies, the proposed dataset will be publicly accessible together with the publication of this paper. [ABSTRACT FROM AUTHOR]

Background: A difficulty associated with forensic applications is the detection of degraded biological materials. Due to the large amplicon sizes of short tandem repeat alleles, valid genotyping results cannot be obtained from degraded biological materials. Recently, insertion/deletion (InDel) polymorphisms have been used in forensic applications for their widespread distributions in the human genome, short amplicon sizes, and low mutation rates. Purpose: Human identification InDel panels have mostly been designed for European populations. Therefore, our laboratory independently developed a multiplex polymerase chain reaction (PCR) system with 35 polymorphic InDel loci to be used for human identification in China. Forensic validation studies were conducted on this novel 35-InDel multiplex PCR system. Methods: The 35 InDel loci were screened in the database, and then used with the traditional PCR amplification and capillary electrophoresis platform combined with five-color fluorescence parallel detection technology. Validation studies were performed on this novel panel, including accuracy, repeatability and reproducibility, species specificity, sensitivity, stability, forensic case sample detection, and mixture studies. In addition, forensic efficiency assessments were conducted in populations from different continents. Results: The data of validated studies indicated that the novel 35-InDel panel was accurate, stable, and efficient for forensic purposes. For human identification, the cumulative power of discrimination values for the these 35 InDel loci in East Asian, South Asian, European, American, and African populations were 0.999999999999995, 0.999999999999995, 0.999999999999971, 0.9999999999999960, and 0.999999999998166, respectively. Conclusions: In this study, a set of 35 InDel loci were conducted in a multiplex amplification system for human identification of degraded DNA sample, and this new assay was efficient and stable. The present results suggested that the 35-InDel panel was a reliable tool for forensic use and could be efficiently used for human identification in the East Asian populations. [ABSTRACT FROM AUTHOR]

Our research addresses the critical challenge of identifying and locating survivors during natural disasters, focusing on the innovative application of body odor analysis. Natural disasters, like earthquakes, demand rapid rescue efforts. Traditionally, canine teams have played a pivotal role, but our study proposes a novel approach using volatile organic compounds (VOCs) found in body odor as biometric markers. We created a comprehensive simulation model based on existing scientific literature, utilizing advanced data resampling techniques and Principal Component Analysis (PCA) alongside clustering methods. Our findings demonstrate convincingly that VOC analysis effectively distinguishes and pinpoints individuals in disaster scenarios. This research opens a new avenue for practical implementation. In summary, our study highlights the promise of VOC-based body odor analysis as a groundbreaking solution for identifying and locating human survivors during natural disasters. This innovation holds significant potential for enhancing disaster response strategies and ultimately saving lives. [ABSTRACT FROM AUTHOR]

The establishment of anthropometric measurements is of fundamental importance for the correct identification of human bodies. The objective of this study was to evaluate the accuracy and reliability of two-dimensional craniometric landmarks obtained from three-dimensional cone beam computed tomography reconstructions for forensic identification of humans. Computed tomography images with voxel sizes of 0.25, 0.3, and 0.4 mm were obtained using i-CAT® three-dimensional equipment. Ten landmarks were randomly selected, and 10 measurements were demarcated in the three-dimensional reconstruction to evaluate the mandibular condyle, ramus, and body. This study demonstrated that protocols with voxels of 0.3 mm should be preferentially indicated for the evaluation of linear and angular measurements. Implementing our methodology using prototypes for clinical and forensic simulations allows comparisons with human databases in identification issues. [ABSTRACT FROM AUTHOR]

This technical note aims to characterize and contextualize the creation of a new collection of identified skeletons stored in the University Institute of Health Sciences—CESPU. This project presents unique and innovative pedagogical opportunities, with students actively involved in the cleaning and processing of the bones and antemortem/postmortem information gathering, as well as in anthropology research projects. This XXI Century Identified Skeletal Collection is composed of 98 complete adult skeletons of both sexes and is still expanding, being the 10th contemporary collection available in Portugal. The skeletons consist exclusively of Portuguese nationals who died between 1946 and 2007, and the 42% that have been processed so far are in good preservation. Comparative learning outcomes after implementing this active learning strategy are not yet available. Improvements are expected since more participation and enthusiasm in classes and research were perceived. [ABSTRACT FROM AUTHOR]

Dental biometrics is a type of biometrics that uses dental information to identify individuals. Well-known biometric features such as fingerprints and gait images have been successfully used to identify individuals. However, these features can be easily damaged. Teeth are more durable than other biometric features. Therefore, dental biometrics are used when other biometric features are not available. There are several types of dental radiographs. Panoramic radiographs are a type of x-ray that show the entire jaw. In these x-rays, all the teeth are viewed together. Panoramic x-rays contain more information about the tooth and jaw structures. However, they also contain unwanted elements such as the bite disc, mandible, nasal bone, etc. This makes them more difficult to process. All types of dental radiographs have difficulties in processing due to slight differences in brightness, overlapping or differently aligned teeth. Identifying individuals from dental radiographs often involves the following main steps: jaw separation, tooth segmentation, feature extraction, and feature matching. The accuracy of jaw and tooth segmentation influences the next steps. In this study, a new fully automatic method for separating mandible, maxilla, and teeth in panoramic radiographs is proposed. The proposed method achieved high accuracy in jaw separation. It also achieved better jaw separation performance than comparable studies. Although the proposed method is a fully automatic method, its performance in tooth separation is close to that of the compared semi-automatic method. In the proposed study, a jaw separation ratio of 0.99, based on the number of correctly aligned teeth, was achieved. The detection rate of the separators for the teeth in the mandibular jaw is 0.90 and the accuracy is 0.86. For maxillary teeth, these values are 0.92 and 0.90, respectively. The results are promising for the automatic segmentation of panoramic radiographs for human identification. [ABSTRACT FROM AUTHOR]

Tattoos are secondary identifiers that can be used to provide a presumptive identity and provide information about a deceased individual to a case. Additional information may be available through the analysis of the visual presentation of tattoos. The aim of this study was to examine the morphological changes of tattoos during the decomposition of a human donor in an Australian environment. Using time-lapse cameras recording for 16 months, stills were extracted and tattoos were quantified using ImageJ. A full analysis was completed on three tattoos, while a fourth tattoo was partially analysed. The tattoos showed the most change in area during the bloat stage of decomposition, staying relatively constant in size for the remainder of the study. The detailed shape of the outlines showed the morphological effect of desiccation as part of decomposition and continued to change until the tattoo was no longer visible. Of the tattoos fully analysed, two became redundant as secondary identifiers on day 294, the other on day 333, all due to lack of visibility. This information is useful during investigations of unknown deceased persons; in this case, the stage of decomposition influenced the presentation of the tattoo. [ABSTRACT FROM AUTHOR]

Gait recognition is a biometric recognition technology, where the goal is to identify the subject by the subject's walking posture at a distance. However, a lot of redundant information in gait sequence will affect the performance of gait recognition, and the most existing gait recognition models are overly complicated and parameterized, which leads to the low efficiency in model training. Consequently, how to reduce the complexity of the model and eliminate redundant information effectively in gait have become a challenging problem in the field of gait recognition. In this paper, we present a residual structure based gait recognition model, short for ResGait, to learn the most discriminative changes of gait patterns. To eliminate redundant information in gait, the soft thresholding is inserted into the deep architectures as a nonlinear transformation layer to improve gait feature learning capability from the noised gait feature map. Moreover, each sample owns unique set of thresholds, making the proposed model suitable for different gait sequences with different redundant information. Furthermore, residual link is introduced to reduce the learning difficulties and alleviate computational costs in model training. Here, we train the network in terms of various scenarios and walking conditions, and the effectiveness of the method is validated through abundant experiments with various types of redundant information in gait. In comparison to the previous state-of-the-art works, experimental results on the common datasets, CASIA-B and OUMVLP-Pose, show that ResGait has higher recognition accuracy under various walking conditions and scenarios. [ABSTRACT FROM AUTHOR]

(1) Background/Objectives: Accurate determination of chronological age is crucial in legal dental identification. This study aimed to compare the effectiveness of different formulas in estimating the age of a Brazilian subpopulation by analyzing the pulp/tooth ratio of the maxillary canine and mandibular second premolar in panoramic and periapical radiographs. (2) Methods: The sample consisted of panoramic and periapical radiographs of 247 individuals. The file of each radiograph was opened in the Adobe Photoshop CS4® program to outline and obtain values in pixels for calculating the pulp/tooth ratio. Statistical analysis was conducted using the SPSS program, with a significance level set at 5%. (3) Results: The interclass correlation coefficient demonstrated excellent intra-observer agreement (0.990–0.999). The determination coefficients (R2) suggested that only 30–35% of the actual age results could be explained by the pulp/tooth ratio. The smallest differences were observed with Cameriere’s formula for the mandibular second premolar on panoramic radiographs (+4.1 years). The greatest differences were found with the formulas for the mandibular second premolar in panoramic radiographs of the Korean (+12.5 years) and Portuguese (−12.1 years) populations. (4) Conclusions: The equations employed showed little agreement between the actual age and the estimated age.

A common application for intraoral scanners is the digitization of the morphology of teeth and palatal rugae. Palatal scans are most commonly required to fabricate complete dentures and immediate transitional dentures and serve as a reference point for assessing orthodontic results. However, they are also frequently included by accident, even though the main purpose of intraoral scanning is to reconstruct dentition using computer-aided manufacturing (CAM). The literature shows that the identification of disaster victims has frequently involved palatal rugae impressions. As the skull provides sound insulation, the rugae are resistant to heat, chemicals, and stress. Antemortem data might be difficult to find during a forensic inquiry, particularly in disaster victim identification cases. In contrast with DNA and fingerprints, there is a greater likelihood of having a dental record that contains palatal scans. With specialized software, the scans can be exported as open stereolithography (STL) files. Considering that a full case consumes up to about 100 MB of hard drive space, long-term storage should not be an issue compared to a plaster model. Additionally, dentists widely use online databases to exchange data for smile design, implant registration, and orthodontic purposes. This will produce a digital database that grows quickly and is readily usable for forensic investigations. The uniqueness of forensic features is frequently challenged; however, palatal morphology’s unique trait could make it possible as it is characteristic of individuals as well as the most distinguishing factor. This review will highlight how rugae, palatal morphology, mirroring, superimposition, and geometrics can serve in forensic identification.

Sensor-based home Activities of Daily Living (ADLs) monitoring systems have emerged to monitor elderly people’s self-care ability remotely. However, the unobtrusive, privacy-friendly object motion sensor-based systems face challenges such as scarce labeled data and ADL performer confusion in a multi-resident setting. This study adopts the design science paradigm to develop an innovative deep transfer learning framework for human identification (DTL-HID) to address both challenges. A novel convolutional neural network (CNN) is proposed to automatically extract comprehensive temporal and cross-axial motion patterns for the DTL-HID framework. We rigorously evaluate the DTL-HID framework against state-of-the-art benchmarks (e.g., k Nearest Neighbors, Support Vector Machines, and alternative CNN designs). Results demonstrate our proposed DTL-HID framework can identify the ADL performer accurately even on a small amount of labeled data. We demonstrate a case study and discuss how stakeholders can further apply this approach to unobtrusive smart home monitoring for senior citizens. Beyond demonstrating the framework’s practical utility, we discuss two implications of our design principles to mobile analytics and design science research: (1) extracting temporal and axial local dependencies can capture richer information from multi-axial time-series data and (2) transferring knowledge learned on a relevant source domain with sufficient data can improve the performance of the desired task on the target domain with scarce data. [ABSTRACT FROM AUTHOR]

The Korean War claimed approximately 36,500 American service member casualties in its 3 years, of which nearly 7600 are still unaccounted for. The Korea 208 (K208) Project began in 2011 to more strategically address the highly commingled nature of 208 boxes of human remains that were repatriated from North Korea to the United Nations Command in the early 1990s and subsequently turned over to the Central Identification Laboratory, Hawaii (now Defense POW/MIA Accounting Agency [DPAA]) for analysis and identification. The K208 was further expanded by the recovery of remains from Joint Recovery Operations (JROs) in North Korea between 1996 and 2005, which revealed, among other issues, the presence of non-U. S. casualties and crossover of elements between these two assemblages. More recently, 55 boxes of human remains (known as the K55) were repatriated from North Korea in 2018 with many of the same commingling and assemblage crossover issues originally presented by the K208. Additionally, there has been an increased push to disinter more than 800 unknown Korean War service members buried at the National Memorial Cemetery of the Pacific (also known as the Punchbowl) in Honolulu, which represent casualties recovered from both North and South Korea that had undergone prior analysis in the 1950s and 1960s. Subsequent examination has revealed that many Punchbowl remains are commingled despite being thought to have been originally buried as discrete individuals. Because of these developments, the K208 Project has grown in complexity and scope, thus changing its name to the Korean War Identification Project (KWIP) in 2017. Now under its purview are the original accessions from the K208 and JROs as well as the K55 and Punchbowl, representing the largest identification project within the DPAA. A robust and defensible identification process begins with an initial triage of the remains, followed by a systematic process of segregation, consolidation, and corroboration leading to identification. This unique case of highly commingled human remains, involving thousands of missing persons from varied proveniences, highlights the challenges and successes of a multi-disciplinary approach involving historians, anthropologists, odontologists, and DNA and isotope specialists at the forefront, while also working with family members towards resolution. As of December 31, 2020, the KWIP has identified a total of 591 service members and continues to seek ways to innovate and improve both the quantity and quality of its work. This article is categorized under: Forensic Anthropology > Anthropology in Mass Disaster & War Crime Contexts Forensic Biology > Forensic DNA Technologies Forensic Medicine > Historical Perspectives. [ABSTRACT FROM AUTHOR]

The resolution of unidentified human remains (UHR) and long-term missing persons (LTMP) cases is paramount for administrative, legal, and humanitarian reasons. There are various forensic profiling methods for human identification; however, their utility is dependent on several factors. First, UHR can be found in different stages of decomposition, so the availability and diversity of post-mortem (PM) information will differ. Second, the availability and totality of the LTMP's ante-mortem (AM) information will differ. Therefore, the suitability of existing methods will be dependent on the quality and quantity of PM and/or AM data available for comparison. Visual recognition is the simplest and quickest method, but typically not practiced or possible, owing to the altered, fragmented, or skeletonized state of UHR. Primary forensic profiling methods involve the comparison of fingerprint, dental, DNA, and medical data. Secondary forensic profiling methods from anthropology, radiology, geochemistry, and anatomy disciplines can provide supplementary evidence to support comparative identification approaches. Emerging forensic molecular technologies such as genomics, microbiomics, epigenetics, and proteomics, together with individual digital footprints from personal devices, offer new investigative leads for establishing identity. However, despite the success of these individual methods, their limitations must be considered when used in isolation. Through the development of a guiding forensic examination framework, this review endorses an interdisciplinary response to unidentified and missing persons investigations, where various forensic specialists collaboratively examine UHR using a suite of contemporary forensic profiling methods to produce multiple and/or different lines of evidence to link them effectively, efficiently, comprehensively, and systematically to LTMP. This article is categorized under: Forensic Science in Action/Crime Scene Investigation > Special Situations and Investigations Forensic Biology > DNA Testing in Disaster Victim and Missing Persons Identification Forensic Medicine > Medicolegal Death Investigation Systems Jurisprudence and Regulatory Oversight > Interdisciplinary Collaboration. [ABSTRACT FROM AUTHOR]

Hereditary lip prints have been studied by several researchers. However, the literature shows no consensus among the scientific community regarding this topic. Therefore, the aim of this study was to conduct a systematic review to gather evidence to clarify whether the surface structure of lip prints is hereditary and, consequently, if a familial relationship between individuals can be established through the analysis of lip prints. The systematic review was performed following the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines. A bibliographic survey was conducted in PubMed, Scopus, and Web of Science databases, restricted to articles published between 2010 and 2020. Studies were selected according to eligibility criteria, and then the study data were collected. The risk of bias of each study was assessed and applied as additional inclusion or exclusion criteria. The results of the articles eligible for analysis were synthesized by a descriptive approach. In the seven included studies, methodological variations, including the definition of similarity, that contribute to the heterogeneity of results were identified. The data gathered allowed to conclude that there is no strong scientific evidence to support the hypothesis of the existence of heredity in the surface structure of lip prints, since it was not proven that similarities between parents and children occur systematically in all families. [ABSTRACT FROM AUTHOR]