Electrocorticography reveals the dynamics of famous voice responses in human fusiform gyrus.

Voice and face processing occur through convergent neural systems that facilitate speaker recognition. Neuroimaging studies suggest that familiar voice processing engages early visual cortex, including the bilateral fusiform gyrus (FG) on the basal temporal lobe. However, what role the FG plays in voice processing and whether it is driven by bottom-up or top-down mechanisms is unresolved. In this study we directly examined neural responses to famous voices and faces in human FG with direct cortical surface recordings (electrocorticography) in epilepsy surgery patients. We tested the hypothesis that neural populations in human FG respond to famous voices and investigated the temporal properties of voice responses in FG. Recordings were acquired from five adult participants during a person identification task using visual and auditory stimuli from famous speakers (U.S. Presidents Barack Obama, George W. Bush, and Bill Clinton). Patients were presented with images of presidents or clips of their voices and asked to identify the portrait/speaker. Our results demonstrate that a subset of face-responsive sites in and near FG also exhibit voice responses that are both lower in magnitude and delayed (300-600 ms) compared with visual responses. The dynamics of voice processing revealed by direct cortical recordings suggests a top-down feedback-mediated response to famous voices in FG that may facilitate speaker identification.NEW & NOTEWORTHY Interactions between auditory and visual cortices play an important role in person identification, but the dynamics of these interactions remain poorly understood. We performed direct brain recordings of fusiform face cortex in human epilepsy patients performing a famous voice naming task, revealing the dynamics of famous voice processing in human fusiform face cortex. The findings support a model of top-down interactions from auditory to visual cortex to facilitate famous voice recognition.

Application of SNPs with low minor allele frequencies in missing person identification (MPI) through kinship analysis of DNA mixtures.

The need to identify a missing person (MP) through kinship analysis of DNA samples found at a crime scene has become increasingly prevalent. DNA samples from MPs can be severely degraded, contain little DNA and mixed with other contributors, which often makes it difficult to apply conventional methods in practice. This study developed a massively parallel sequencing-based panel that contains 1661 single-nucleotide polymorphisms (SNPs) with low minor allele frequencies (MAFs) (averaged at 0.0613) in the Chinese Han population, and the strategy for relationship inference from DNA mixtures comprising different numbers of contributors (NOCs) and of varying allele dropout probabilities. Based on the simulated dataset and genotyping results of 42 artificial DNA mixtures (NOC = 2-4), it was observed that the present SNP panel was sufficient for balanced mixtures when referenced to the closest relatives (parents/offspring and full siblings). When the mixture profiles suffered from dropout, incorrect assignments were markedly associated with relatedness, NOC and the dropout level. We, therefore, indicate that SNPs with low MAFs could be reliably interpreted for MP identification through the kinship analysis of complex DNA mixtures. Further studies should be extended to more possible scenarios to test the feasibility of this present approach.

Easykin: a flexible and user-friendly online tool for forensic kinship testing and missing person identification.

In forensic kinship testing and missing person identification, it is a fundamental question to choose the most informative reference relatives, select appropriate genotyping systems, and evaluate the weight of evidence comprehensively. Despite that several useful tools have been developed, they have not addressed these questions satisfactorily. In this paper, we develop a flexible and user-friendly online tool, Easykin, to address the aforementioned issues. It has some promising features: (i) Pedigrees can be constructed easily and presented intuitively with just a few mouse clicks. (ii) System power can be estimated before testing based on certain set of markers and reference relatives. (iii) The pruning function of EasyKin enables users to choose appropriate subsets of available references. (iv) Parameters at a specific LR for a single case may ease evidence interpretation. (v) The user interface (UI) is an HTML-based dashboard, which is friendly to both professional and non-professional users and can be used anytime and anywhere. Here, we presented three common cases as examples to demonstrate how kinship testing and missing person identification can be improved with EasyKin. In conclusion, this tool provides a one-stop solution for forensic use, that is, instructing users to choose appropriate kits and reference relatives before testing, calculating LR in the testing, and providing parameters for data interpretation after testing. EasyKin is freely available at https://forensicsysu.shinyapps.io/EasyKin/ .

Comparing preservation substrates under field conditions for efficient DNA recovery in bone.

Often bones are the only biological material left for the identification of human remains. As situations may occur where samples need to be stored for an extended period without access to cooling, appropriate storage of the bone samples is necessary for maintaining the integrity of DNA for profiling. To simulate DNA preservation under field conditions, pig rib bones were used to evaluate the effects of bone cleaning, buffer composition, storage temperature, and time on DNA recovery from bone samples. Bones were stored in three different buffers: TENT, solid sodium chloride, and ethanol-EDTA, at 20 °C and 35 °C for 10, 20, and 30 days. Bones were subsequently dried and ground to powder. DNA was extracted and quantified. Results show that temperature and storage time have no significant influence on DNA yield. DNA recovery from bones stored in solid sodium chloride or ethanol-EDTA was significantly higher compared to bones stored in TENT, and grinding of bones was facilitated by the extent of dehydration in solid sodium chloride and ethanol-EDTA compared to TENT. Overall, solid sodium chloride was found to be superior over ethanol-EDTA; when it comes to transportation, dry material such as salt eliminates the risk of leaking; it is non-toxic and in contrast to ethanol not classified as dangerous goods. Based on this study's results, we recommend NaCl as a storage substrate for forensic samples in cases where no cooling/freezing conditions are available.

Human Micro-Expressions in Multimodal Social Behavioral Biometrics.

The advent of Social Behavioral Biometrics (SBB) in the realm of person identification has underscored the importance of understanding unique patterns of social interactions and communication. This paper introduces a novel multimodal SBB system that integrates human micro-expressions from text, an emerging biometric trait, with other established SBB traits in order to enhance online user identification performance. Including human micro-expression, the proposed method extracts five other original SBB traits for a comprehensive representation of the social behavioral characteristics of an individual. Upon finding the independent person identification score by every SBB trait, a rank-level fusion that leverages the weighted Borda count is employed to fuse the scores from all the traits, obtaining the final identification score. The proposed method is evaluated on a benchmark dataset of 250 Twitter users, and the results indicate that the incorporation of human micro-expression with existing SBB traits can substantially boost the overall online user identification performance, with an accuracy of 73.87% and a recall score of 74%. Furthermore, the proposed method outperforms the state-of-the-art SBB systems.

Exploration of Effective Time-Velocity Distribution for Doppler-Radar-Based Personal Gait Identification Using Deep Learning.

Personal identification based on radar gait measurement is an important application of biometric technology because it enables remote and continuous identification of people, irrespective of the lighting conditions and subjects' outfits. This study explores an effective time-velocity distribution and its relevant parameters for Doppler-radar-based personal gait identification using deep learning. Most conventional studies on radar-based gait identification used a short-time Fourier transform (STFT), which is a general method to obtain time-velocity distribution for motion recognition using Doppler radar. However, the length of the window function that controls the time and velocity resolutions of the time-velocity image was empirically selected, and several other methods for calculating high-resolution time-velocity distributions were not considered. In this study, we compared four types of representative time-velocity distributions calculated from the Doppler-radar-received signals: STFT, wavelet transform, Wigner-Ville distribution, and smoothed pseudo-Wigner-Ville distribution. In addition, the identification accuracies of various parameter settings were also investigated. We observed that the optimally tuned STFT outperformed other high-resolution distributions, and a short length of the window function in the STFT process led to a reasonable accuracy; the best identification accuracy was 99% for the identification of twenty-five test subjects. These results indicate that STFT is the optimal time-velocity distribution for gait-based personal identification using the Doppler radar, although the time and velocity resolutions of the other methods were better than those of the STFT.

Comparison of DNA preservation between adult and non-adult ancient skeletons.

Studies evaluating DNA preservation in non-adults, or comparing preservation in adults and non-adults, are very rare. This study compares the preservation of DNA in the skeletal remains of adults and non-adults. It compares the quality and quantity of DNA recovered from different skeletal elements of adults and non-adults, and from non-adults of different age classes. In addition, the preservation of DNA in males and females is compared. Bone DNA preservation was estimated by measuring nuclear DNA concentration and its degradation, and through STR typing success. The study analyzed 29 adult skeletons and 23 non-adult skeletons from the Ljubljana-Polje archeological site, dating from the seventeenth to nineteenth century, and up to four skeletal elements (petrous bone, femur, calcaneus, and talus) were included. After full demineralization extraction, the PowerQuant System and the PowerPlex ESI 17 Fast System (Promega) were used for qPCR and STR typing, respectively. The results showed that, among the four bone types analyzed, only the petrous bone proved to be a suitable source of DNA for STR typing of non-adult skeletal remains, and DNA yield is even higher than in the adult petrous bone, which can be attributed to the higher DNA degradation observed in the adult petrous bone. In adult skeletons, petrous bones and tali produced high STR amplification success and low DNA yield was observed in adult femurs. The results of this study are applicable for the sampling strategy in routine forensic genetics cases for solving identification cases, including badly preserved non-adult and also adult skeletons.

Comparison of DNA preservation between ribs and vertebrae.

The choice of skeletal element types and their intra-bone parts is important because of differences in DNA preservation, and this must be considered when sampling bones for DNA testing. When incomplete skeletons are found, ribs and vertebrae have been shown to be the most suitable for genetic identification of bones from the torso. This study compares the preservation of DNA between 12th thoracic vertebrae and first ribs to determine which bone type is more suitable for genetic typing. The study analyzed 35 12th thoracic vertebrae and 29 first ribs from one mass grave from the Second World War with commingled skeletal remains excavated. Bone DNA preservation was estimated by measuring nuclear DNA concentration and its degradation and through short tandem repeat (STR) typing success. Previous studies performed on aged skeletal remains have shown that the DNA content of the first ribs and 12th thoracic vertebrae has high intra-bone variability, and this was considered when sampling the bones. After full demineralization extraction, the PowerQuant System (Promega) was used to measure the quantity and quality of DNA, and the GlobalFiler kit (Applied Biosystems) was used for STR typing. The results showed that DNA yield and degradation and STR typing success exhibited no statistically significant difference between first ribs and 12th thoracic vertebrae, and there was no intra-individual difference when comparing only paired bones from the same individuals. Consequently, with intra-bone DNA variability considered, the first ribs or the 12th thoracic vertebrae can be selected when sampling to genetically identify the skeletal remains of highly degraded torsos. HIGHLIGHTS: The first ribs and thoracic vertebrae are the most suitable bones for sampling from the torso. The proximal part of first rib and posterior vertebral column of the 12th thoracic vertebrae yielded the most DNA. The first ribs were compared with the 12th thoracic vertebrae, and the sampling process considered intra-bone DNA variability. The quality and quantity of nuclear DNA and success of STR typing were measured. The first ribs yielded the same DNA yields as well as STR typing success as the 12th thoracic vertebrae. When only the torso is present, it is not of high importance whether the first ribs or the 12th thoracic vertebrae are collected.

Capturing Features and Performing Human Detection from Human Gaits Using RFID.

Recently, radio frequency identification (RFID) sensing has attracted much attention due to its contact-free nature, low cost, light weight and other advantages. RFID-based person detection has also become a hot research topic, but there are still some problems in the existing research. First, most of the current studies cannot identify numerous people at a time well. Second, in order to detect more accurately, it is necessary to evaluate the whole-body activity of a person, which will consume a lot of time to process the data and cannot be applied in time. To solve these problems, in this paper we propose RF-Detection, a person detection system using RFID. First of all, RF-Detection takes step length as the standard for person detection, divides step length into specific sections according to the relationship between step length and height, and achieves high accuracy for new user detection through a large amount of training for a specific step length. Secondly, RF-Detection can better identify the number of people in the same space by segmenting continuous people. Finally, the data collection was reduced by expanding the data set, and the deep learning method was used to further improve the accuracy. The results show that the overall recognition accuracy of RF-Detection is 98.93%.

Online Boosting-Based Target Identification among Similar Appearance for Person-Following Robots.

It is challenging for a mobile robot to follow a specific target person in a dynamic environment, comprising people wearing similar-colored clothes and having the same or similar height. This study describes a novel framework for a person identification model that identifies a target person by merging multiple features into a single joint feature online. The proposed framework exploits the deep learning output to extract four features for tracking the target person without prior knowledge making it generalizable and more robust. A modified intersection over union between the current frame and the last frame is proposed as a feature to distinguish people, in addition to color, height, and location. To improve the performance of target identification in a dynamic environment, an online boosting method was adapted by continuously updating the features in every frame. Through extensive real-life experiments, the effectiveness of the proposed method was demonstrated by showing experimental results that it outperformed the previous methods.

EEG-Based Person Identification during Escalating Cognitive Load.

With the development of human society, there is an increasing importance for reliable person identification and authentication to protect a person's material and intellectual property. Person identification based on brain signals has captured substantial attention in recent years. These signals are characterized by original patterns for a specific person and are capable of providing security and privacy of an individual in biometric identification. This study presents a biometric identification method based on a novel paradigm with accrual cognitive brain load from relaxing with eyes closed to the end of a serious game, which includes three levels with increasing difficulty. The used database contains EEG data from 21 different subjects. Specific patterns of EEG signals are recognized in the time domain and classified using a 1D Convolutional Neural Network proposed in the MATLAB environment. The ability of person identification based on individual tasks corresponding to a given degree of load and their fusion are examined by 5-fold cross-validation. Final accuracies of more than 99% and 98% were achieved for individual tasks and task fusion, respectively. The reduction of EEG channels is also investigated. The results imply that this approach is suitable to real applications.

Intra-bone nuclear DNA variability and STR typing success in Second World War first ribs.

DNA sampling and typing are used for identifying missing persons or war victims. In recent forensic studies, little focus has been placed on determining intra-bone variability within a single skeletal element. When dealing with aged human bones, complete skeletal remains are rarely present. In cases in which only the torso is available, studies have shown that ribs are one of the most appropriate samples, but intra-bone variability has not yet been studied. A higher degree of remodeling was found to contribute to higher DNA yield in the parts of the skeletal element where the most strain is concentrated. This study explores intra-bone variability in proximal, middle, and distal parts of the first human rib by determining the quantity and quality of DNA using the PowerQuant System (Promega) and autosomal STR typing success using the PowerPlex ESI 17 Fast System (Promega). Thirty first ribs from a single Second World War mass grave were sampled. No variation in DNA degradation was observed across the individual rib. The highest quantity of DNA was measured in the proximal part of the first rib, and in all ribs except three, full or almost full genetic profiles were obtained. Thus, when only the torso is present in archaeological or medico-legal cases, first ribs are recommended to be collected if possible, and the proximal or vertebral ends should be sampled for genetic analysis.

Self-Relative Evaluation Framework for EEG-Based Biometric Systems.

In recent years, electroencephalogram (EEG) signals have been used as a biometric modality, and EEG-based biometric systems have received increasing attention. However, due to the sensitive nature of EEG signals, the extraction of identity information through processing techniques may lead to some loss in the extracted identity information. This may impact the distinctiveness between subjects in the system. In this context, we propose a new self-relative evaluation framework for EEG-based biometric systems. The proposed framework aims at selecting a more accurate identity information when the biometric system is open to the enrollment of novel subjects. The experiments were conducted on publicly available EEG datasets collected from 108 subjects in a resting state with closed eyes. The results show that the openness condition is useful for selecting more accurate identity information.

Deep user identification model with multiple biometric data.

BACKGROUND: Recognition is an essential function of human beings. Humans easily recognize a person using various inputs such as voice, face, or gesture. In this study, we mainly focus on DL model with multi-modality which has many benefits including noise reduction. We used ResNet-50 for extracting features from dataset with 2D data. RESULTS: This study proposes a novel multimodal and multitask model, which can both identify human ID and classify the gender in single step. At the feature level, the extracted features are concatenated as the input for the identification module. Additionally, in our model design, we can change the number of modalities used in a single model. To demonstrate our model, we generate 58 virtual subjects with public ECG, face and fingerprint dataset. Through the test with noisy input, using multimodal is more robust and better than using single modality. CONCLUSIONS: This paper presents an end-to-end approach for multimodal and multitask learning. The proposed model shows robustness on the spoof attack, which can be significant for bio-authentication device. Through results in this study, we suggest a new perspective for human identification task, which performs better than in previous approaches.

Modified Distance Transformation for ImageEnhancement in NIR Imaging of Finger Vein System.

Most of the current image processing methods used in the near-infrared imaging of fingervascular system concentrate on the extraction of internal structures (veins). In this paper, we proposea novel approach which allows to enhance both internal and external features of a finger. The methodis based on the Distance Transformation and allows for selective extraction of physiological structuresfrom an observed finger. We evaluate the impact of its parameters on the effectiveness of the alreadyestablished processing pipeline used for biometric identification. The new method was comparedwith five state-of-the-art approaches to features extraction (position-gray-profile-curve-PGPGC,maximum curvature points in image profiles-MC, Niblack image adaptive thresholding-NAT,repeated dark line tracking-RDLT, and wide line detector-WD) on the GustoDB database of imagesobtained in a wide range of NIR wavelengths (730-950 nm). The results indicate a clear superiorityof the proposed approach over the remaining alternatives. The method managed to reach over 90%identification accuracy for all analyzed datasets.

Face Recognition Systems: A Survey.

Over the past few decades, interest in theories and algorithms for face recognition has been growing rapidly. Video surveillance, criminal identification, building access control, and unmanned and autonomous vehicles are just a few examples of concrete applications that are gaining attraction among industries. Various techniques are being developed including local, holistic, and hybrid approaches, which provide a face image description using only a few face image features or the whole facial features. The main contribution of this survey is to review some well-known techniques for each approach and to give the taxonomy of their categories. In the paper, a detailed comparison between these techniques is exposed by listing the advantages and the disadvantages of their schemes in terms of robustness, accuracy, complexity, and discrimination. One interesting feature mentioned in the paper is about the database used for face recognition. An overview of the most commonly used databases, including those of supervised and unsupervised learning, is given. Numerical results of the most interesting techniques are given along with the context of experiments and challenges handled by these techniques. Finally, a solid discussion is given in the paper about future directions in terms of techniques to be used for face recognition.

Classification Algorithm for Person Identification and Gesture Recognition Based on Hand Gestures with Small Training Sets.

Classification algorithms require training data initially labelled by classes to build a model and then to be able to classify the new data. The amount and diversity of training data affect the classification quality and usually the larger the training set, the better the accuracy of classification. In many applications only small amounts of training data are available. This article presents a new time series classification algorithm for problems with small training sets. The algorithm was tested on hand gesture recordings in tasks of person identification and gesture recognition. The algorithm provides significantly better classification accuracy than other machine learning algorithms. For 22 different hand gestures performed by 10 people and the training set size equal to 5 gesture execution records per class, the error rate for the newly proposed algorithm is from 37% to 75% lower than for the other compared algorithms. When the training set consists of only one sample per class the new algorithm reaches from 45% to 95% lower error rate. Conducted experiments indicate that the algorithm outperforms state-of-the-art methods in terms of classification accuracy in the problem of person identification and gesture recognition.

Real-Time Person Identification in a Hospital Setting: A Systematic Review.

In the critical setting of a trauma team activation, team composition is crucial information that should be accessible at a glance. This calls for a technological solution, which are widely available, that allows access to the whereabouts of personnel. This diversity presents decision makers and users with many choices and considerations. The aim of this review is to give a comprehensive overview of available real-time person identification techniques and their respective characteristics. A systematic literature review was performed to create an overview of identification techniques that have been tested in medical settings or already have been implemented in clinical practice. These techniques have been investigated on a total of seven characteristics: costs, usability, accuracy, response time, hygiene, privacy, and user safety. The search was performed on 11 May 2020 in PubMed and the Web of Science Core Collection. PubMed and Web of Science yielded a total n = 265 and n = 228 records, respectively. The review process resulted in n = 23 included records. A total of seven techniques were identified: (a) active and (b) passive Radio-Frequency Identification (RFID) based systems, (c) fingerprint, (d) iris, and (e) facial identification systems and infrared (IR) (f) and ultrasound (US) (g) based systems. Active RFID was largely documented in the included literature. Only a few could be found about the passive systems. Biometric (c, d, and e) technologies were described in a variety of applications. IR and US techniques appeared to be a niche, as they were only spoken of in few (n = 3) studies.

Deep-Learning-Based Indoor Human Following of Mobile Robot Using Color Feature.

Human following is one of the fundamental functions in human-robot interaction for mobile robots. This paper shows a novel framework with state-machine control in which the robot tracks the target person in occlusion and illumination changes, as well as navigates with obstacle avoidance while following the target to the destination. People are detected and tracked using a deep learning algorithm, called Single Shot MultiBox Detector, and the target person is identified by extracting the color feature using the hue-saturation-value histogram. The robot follows the target safely to the destination using a simultaneous localization and mapping algorithm with the LIDAR sensor for obstacle avoidance. We performed intensive experiments on our human following approach in an indoor environment with multiple people and moderate illumination changes. Experimental results indicated that the robot followed the target well to the destination, showing the effectiveness and practicability of our proposed system in the given environment.

Adversarial Deep Learning in EEG Biometrics.

Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG. Furthermore, recent methods have mostly trained and evaluated based on single session EEG data. We address this problem from an invariant representation learning perspective. We propose an adversarial inference approach to extend such deep learning models to learn session-invariant person-discriminative representations that can provide robustness in terms of longitudinal usability. Using adversarial learning within a deep convolutional network, we empirically assess and show improvements with our approach based on longitudinally collected EEG data for person identification from half-second EEG epochs.