The existing one-time identity authentication technology cannot continuously guarantee the legitimacy of user identity during the whole human-computer interaction session, and often requires active cooperation of users, which seriously limits the availability. This study proposes a new non-contact identity recognition technology based on cardiac micro-motion detection using ultra wideband (UWB) bio-radar. After the multi-point micro-motion echoes in the range dimension of the human heart surface area were continuously detected by ultra wideband bio-radar, the two-dimensional principal component analysis (2D-PCA) was exploited to extract the compressed features of the two-dimensional image matrix, namely the distance channel-heart beat sampling point (DC-HBP) matrix, in each accurate segmented heart beat cycle for identity recognition. In the practical measurement experiment, based on the proposed multi-range-bin & 2D-PCA feature scheme along with two conventional reference feature schemes, three typical classifiers were selected as representatives to conduct the heart beat identification under two states of normal breathing and breath holding. The results showed that the multi-range-bin & 2D-PCA feature scheme proposed in this paper showed the best recognition effect. Compared with the optimal range-bin & overall heart beat feature scheme, our proposed scheme held an overall average recognition accuracy of 6.16% higher (normal respiration: 6.84%; breath holding: 5.48%). Compared with the multi-distance unit & whole heart beat feature scheme, the overall average accuracy increase was 27.42% (normal respiration: 28.63%; breath holding: 26.21%) for our proposed scheme. This study is expected to provide a new method of undisturbed, all-weather, non-contact and continuous identification for authentication.
现有一次性身份认证技术无法持续保证整个人-机交互会话过程中的用户身份合法性，且往往需要用户主动配合而严重限制可用性。本研究首次提出一种基于超宽谱（UWB）生物雷达检测心脏微动的非接触身份识别新技术，通过生物雷达连续检测心脏体表区域距离维多点微动回波，在心拍分割的基础上利用二维主成分分析（2D-PCA）压缩提取心拍周期内距离通道-采样点二维图像的矩阵特征用于身份识别。实测实验中，以多距离单元& 2D-PCA特征方案为基础结合两种常规的参考特征方案，选取三种典型分类器为代表在正常呼吸和屏息两种状态下进行心拍身份识别。结果表明，本文所提多距离单元& 2D-PCA特征方案表现出最优的识别效果（识别率最高可达90%以上），相对最佳距离单元&整条心拍特征方案识别准确率总体平均提高6.16%（正常呼吸6.84%、屏息5.48%），相对多距离单元&整条心拍特征方案总体平均提高27.42%（正常呼吸28.63%、屏息26.21%）。本研究有望为未来社会用户信息安全防护提供一种无扰式、全天候、非接触、连续性身份识别新方法。.

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.

Skin is an important ecosystem that links the human body and the external environment. Previous studies have shown that the skin microbial community could remain stable, even after long-term exposure to the external environment. In this study, we explore two questions: Do there exist strains or genetic variants in skin microorganisms that are individual-specific, temporally stable, and body site-independent? And if so, whether such microorganismal genetic variants could be used as markers, called \"fingerprints\" in our study, to identify donors? We proposed a framework to capture individual-specific DNA microbial fingerprints from skin metagenomic sequencing data. The fingerprints are identified on the frequency of 31-mers free from reference genomes and sequence alignments. The 616 metagenomic samples from 17 skin sites at 3-time points from 12 healthy individuals from Integrative Human Microbiome Project were adopted. Ultimately, one contig for each individual is assembled as a fingerprint. And results showed that 89.78% of the skin samples despite body sites could identify their donors correctly. It is observed that 10 out of 12 individual-specific fingerprints could be aligned to Cutibacterium acnes. Our study proves that the identified fingerprints are temporally stable, body site-independent, and individual-specific, and can identify their donors with enough accuracy. The source code of the genetic identification framework is freely available at https://github.com/Ying-Lab/skin_fingerprint.

EEG-based human identification has gained a wide range of attention due to the further increase in demand for security. How to improve the accuracy of the human identification system is an issue worthy of attention. Using more features in the human identification system is a potential solution. However, too many features may cause overfitting, resulting in the decline of system accuracy. In this work, the graph convolutional neural network (GCN) was adopted for classification. Multiple features were combined and utilized as the structure matrix of the GCN. Because of the constant signal matrix, the training parameters would not increase as the structure matrix grows. We evaluated the classification accuracy on a classic public dataset. The results showed that utilizing multiple features of functional connectivity (FC) can improve the accuracy of the identity authentication system, the best results of which are at 98.56%. In addition, our methods showed less sensitivity to channel reduction. The method proposed in this paper combines different FCs and reaches high classification accuracy for unpreprocessed data, which inspires reducing the system cost in the actual human identification system.

When accidents occur, panoramic dental images play a significant role in identifying unknown bodies. In recent years, deep neural networks have been applied to address this task. However, while tooth contours are significant in classical methods, few studies using deep learning methods devise an architecture specifically to introduce tooth contours into their models. Since fine-grained image identification aims to distinguish subordinate categories by specific parts, we devise a fine-grained human identification model that leverages the distribution of tooth masks to distinguish different individuals with local and subtle differences in their teeth. First, a bilateral branched architecture is designed, of which one branch was designed as the image feature extractor, while the other was the mask feature extractor. In this step, the mask feature interacts with the extracted image feature to perform elementwise reweighting. Additionally, an improved attention mechanism was used to make our model concentrate more on informative positions. Furthermore, we improved the ArcFace loss by adding a learnable parameter to increase the loss of those hard samples, thereby exploiting the potential of our loss function. Our model was tested on a large dataset consisting of 23,715 panoramic X-ray dental images with tooth masks from 10,113 patients, achieving an average rank-1 accuracy of 88.62% and rank-10 accuracy of 96.16%.

Due to the virtues of no stutter peaks, low rates of mutation, and short amplicon sizes, insertion/deletion (InDel) polymorphism is an indispensable tool for analyzing degraded DNA samples from crime scenes for human identifications (Wang et al., 2021). Herein, a self-developed panel of 43 InDel loci constructed previously by our group was utilized to evaluate the genetic diversities and explore the genetic background of the Han Chinese from Beijing (HCB) including 301 random healthy individuals. The lengths of amplicons at 43 InDel loci in this panel ranged from 87 to 199 bp, which indicated that the panel could be used as an effective tool to utilize highly degraded DNA samples for human identity testing. The loci in this panel were validated and performed well for forensic degraded DNA samples (Jin et al., 2021). The combined discrimination power (PD) and combined probability of exclusion (PE) values in this panel indicated that the 43 InDel loci could be used as the candidate markers in personal identification and parentage testing of HCB. In addition, population genetic relationships between the HCB and 26 reference populations from five continents based on 19 overlapped InDel loci were displayed by constructing a phylogenetic tree, principal component analysis (PCA), and population genetic structure analysis. The results illustrated that the HCB had closer genetic relationships with the Han populations from Chinese different regions.

Insertion/deletion (InDel) polymorphisms, combined desirable characteristics of both short tandem repeats (STRs) and single nucleotide polymorphisms (SNPs), are considerable potential in the fields of forensic practices and population genetics. However, most commercial InDel kits designed based on non-Asians limited extensive forensic applications in East Asian (EAS) populations. Recently, a novel 6-dye direct and multiplex PCR-CE-based typing system was designed on the basis of genome-wide EAS population data, which could amplify 60 molecular genetic markers, consisting of 57 autosomal InDels (A-InDels), 2 Y-chromosomal InDels (Y-InDels), and Amelogenin in a single PCR reaction and detect by capillary electrophoresis, simultaneously. In the present study, the DNA profiles of 279 unrelated individuals from the Hainan Li group were generated by the novel typing system. In addition, we collected two A-InDel sets to evaluate the forensic performances of the novel system in the 1,000 Genomes Project (1KG) populations and Hainan Li group. For the Universal A-InDel set (UAIS, containing 44 A-InDels) the cumulative power of discrimination (CPD) ranged from 1-1.03 × 10-14 to 1-1.27 × 10-18, and the cumulative power of exclusion (CPE) varied from 0.993634 to 0.999908 in the 1KG populations. For the East Asia-based A-InDel set (EAIS, containing 57 A-InDels) the CPD spanned from 1-1.32 × 10-23 to 1-9.42 × 10-24, and the CPE ranged from 0.999965 to 0.999997. In the Hainan Li group, the average heterozygote (He) was 0.4666 (0.2366-0.5448), and the polymorphism information content (PIC) spanned from 0.2116 to 0.3750 (mean PIC: 0.3563 ± 0.0291). In total, the CPD and CPE of 57 A-InDels were 1-1.32 × 10-23 and 0.999965, respectively. Consequently, the novel 6-dye direct and multiplex PCR-CE-based typing system could be considered as the reliable and robust tool for human identification and intercontinental population differentiation, and supplied additional information for kinship analysis in the 1KG populations and Hainan Li group.

Wireless sensing can be used for human identification by mining and quantifying individual behavior effects on wireless signal propagation. This work proposes a novel device-free biometric (DFB) system, WirelessID, that explores the joint human fine-grained behavior and body physical signatures embedded in channel state information (CSI) by extracting spatiotemporal features. In addition, the signal fluctuations corresponding to different parts of the body contribute differently to the identification performance. Inspired by the success of the attention mechanism in computer vision (CV), thus, to extract more robust features, we introduce the spatiotemporal attention function into our system. To evaluate the performance, commercial WiFi devices are used for prototyping WirelessID in a real laboratory environment with an average accuracy of 93.14% and a best accuracy of 97.72% for five individuals.

Massively parallel sequencing (MPS), or next generation sequencing (NGS), is a promising methodology for the detection of short tandem repeats (STRs) and single nucleotide polymorphisms (SNPs) in forensic genetics. Here, the prototype SifaMPS Panel is designed to simultaneously target 87 STRs and 294 SNPs with forensic interest in a single multiplex in conjunction with the TruSeq™ Custom Amplicon workflow and MiSeq FGx™ System. Two in-house python scripts are adopted for the fastq-to-genotype interpretation of MPS data concerning STR and SNP, respectively. In the present study, by sequencing 50 Chinese Hans and many other DNA samples involved in validation studies, system parameters including the depth of coverage (DoC), heterozygote balance (Hb) and sequence coverage ratios (SCRs), as well as different forensic parameters of STRs and SNPs in a population study, were calculated to evaluate the overall performance of this new panel and its practicality in forensic application. In general, except for two STRs (DYS505 and DYS449) and one SNP (rs4288409) that performed poorly, the other 85 STRs and 293 SNPs in our panel had good performance that could strengthen efficiency for human identification and paternity testing. In addition, discordant STR genotype results between those generated from capillary electrophoresis (CE) and from the MPS platform were clearly illustrated, and these results could be a useful reference for applying these particular non-CODIS STRs in forensic practice.

Radiographically assisted dental identification is an important means for individual identification. Specific identifiers help to quickly filter some of the possible corresponding AM and PM images at the beginning. The study seeks specific oral and maxillofacial identifiers in panoramic radiographs. A total of 920 panoramic radiographs from 460 live patients were used. The most recent radiograph served as the surrogate post-mortem (PM) record of an unidentified person, and the earliest radiograph served as the ante-mortem (AM) record of the same person. We evaluated the following four groups of identifiers of the images: (1) dental morphology, tooth number, and position; (2) dental treatment and pathology; (3) morphological identifiers of the jaw; and (4) pathological identifiers of the jaw. The ratio of each identifier being identified simultaneously in the AM and PM databases was determined. Specific identifiers were defined as those that appeared at low frequency (ratio: 0%-0.250%). A total of 18 specific oral and maxillofacial identifiers were determined. The specific identifiers were a retained deciduous tooth (0.011%), S-shaped deflection of a tooth root (0.012%), distal deflection of tooth root (0.017%), inverted impaction (0.018%), malposition (0.038%), supernumerary teeth (0.061%), mesial deflection of tooth root (0.092%), microdontia (0.136%), buccal/lingual impaction (0.188%), cementoma (0.002%), hypercementosis (0.002%), continuous crown (0.004%), pulp calcification (0.023%), attrition (0.030%), residual root (0.106%), root resorption (0.137%), implant (0.156%), and osteomyelitis (0.002%). Identifiers of the teeth and jaw can be used for human identification, and dental identifiers are more specific than identifiers of jaw.