Search

Recent generation Microsoft Kinect Camera captures a series of multimodal signals that provide RGB video, depth sequences, and skeleton information, thus it becomes an option to achieve enhanced human action recognition performance by fusing different data modalities. However, most existing fusion methods simply fuse different features, which ignores the underlying semantics between different models, leading to a lack of accuracy. In addition, there exists a large amount of background noise. In this work, we propose a Vision Transformer-based Bilinear Pooling and Attention Network (VT-BPAN) fusion mechanism for human action recognition. This work improves the recognition accuracy in the following ways: 1) An effective two-stream feature pooling and fusion mechanism is proposed. The RGB frames and skeleton are fused to enhance the spatio-temporal feature representation. 2) A spatial lightweight multiscale vision Transformer is proposed, which can reduce the cost of computing. The framework is evaluated based on three widely used video action datasets, and the proposed approach performs a more comparable performance with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Identifying evidence of human modification of extinct animal remains, such as Pleistocene megafauna, is challenging due to the similarity of anthropogenic and non-anthropogenic taphonomic features observed under optical microscopy. Here, we re-investigate a Late Pleistocene ground sloth tooth from northeast Brazil, previously suggested as human-modified based only on optical observation. To characterize the macro- and micro-morphological characteristics of the marks preserved in this tooth and evaluate potential human modification, we used stereomicroscope and scanning electron microscopy (SEM) supplemented by energy dispersive spectroscopy (EDS), UV photoluminescence (UV/PL), synchrotron-based X-ray fluorescence (SR-XRF), and synchrotron micro-computed tomography (SR-µCT). These methods allowed us to discriminate non-anthropogenic taphonomic features (root and sedimentary damage), anthropogenic marks, and histological features. The latter shows the infiltration of exogenous elements into the dentine from the sediments. Our evidence demonstrates the sequence of anthropogenic and non-anthropogenic taphonomic modification of this tooth and supports its initial intentional modification by humans. We highlight the benefits of emerging imaging and spectral imaging techniques to investigate and diagnose human modification in fossil and archaeological records and propose that human modification of tooth tissues should be further considered when studying possibly anthropogenically altered fossil remains. [ABSTRACT FROM AUTHOR]

This study aimed to identify which lumbar vertebral level above a lumbosacral transitional vertebra (LSTV) demonstrated the longest transverse process (TVP) lengths. In this exploratory quantitative osteological cohort study using a digital Vernier caliper, dried human cadaveric lumbar TVPs were measured for linear horizontal length at each lumbar vertebra, left and right sides. Data collection was conducted in South Africa at the Raymond A. Dart Collection of Modern Human Skeletons and the Pretoria Bone Collection. The LSTV cohort consisted of 110 spinal columns and an LSTV-free control cohort of a sex-balanced randomized selection of 30 male and 30 female spinal columns. Compared with the control cohort, the LSTV cohort demonstrated longer TVPs for every vertebral level, particularly L3, while the left side demonstrated longer TVPs overall. There were no statistical differences in TVP length within the LSTV cohort when comparing all levels (P > 0.05). The L3 TVPs demonstrated the longest mean lengths in both control (65%) and LSTV (58%) cohorts. The general trend was that the TVPs of L3 had the longest mean length for both the left and the right sides in both cohorts and both sexes. In the absence of whole-spine imaging, these findings indicate that L3 TVPs may offer an alternative bony landmark, which may aid in spinal enumeration estimation in the setting of LSTV. This is of value for radiograph appraisal and may aid with correct-level intervention. [ABSTRACT FROM AUTHOR]

Human action recognition from skeleton motion sequences is widely applied in various fields such as virtual reality, human-computer interaction and kinematic rehabilitation. With the wide use of graph neural networks for extracting spatial features from skeleton anatomy connectivity, spatial-temporal extension of single graph models on human skeleton may improve the network performance. In this paper, we propose a priori separation graph convolution (PS-GCN) network composition with a priori mixed GCN by introducing a hypergraph representation of the skeleton spatial features, and a dynamic adaptive GCN to describe the respective graph model for each sample at each layer of the network of spatial features. For temporal feature analysis, a global attention unit is added to describe the long-term relationship. Moreover, a feature fusion structure is applied for short-term temporal features in the input of the network. The proposed model is evaluated on the NTU-RGB+D, NTU-RGB+D 120 and NW-UCLA datasets via a comprehensive ablative study. The results show that our model is comparable in accuracy to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The feature extraction and analysis of gymnastics images is an essential foundation for estimating human posture. The primary step is to obtain various joint points of athletes based on basic information such as human texture and contour in the sports images. The reconstruction and analysis of the human skeleton is completed based on the feature data of the joint points. In this process, traditional algorithm models often have certain shortcomings in the accuracy of feature extraction for motion images. This paper combines multi-scale feature fusion algorithms to construct a gymnastics motion image feature extraction model, which can achieve more accurate and efficient analysis and research for the feature extraction process of motion images, further improving the detection accuracy of joint points in motion images; this lays an essential foundation for feature extraction of gymnastics images. At the same time, it also provides more methods for skeleton reconstruction based on image feature information during the motion process, improving the efficiency and accuracy of reconstruction. [ABSTRACT FROM AUTHOR]

The “Validated Entheses‐based Reconstruction of Activity” (V.E.R.A.) method has proven to be a reliable method for the quantification and analysis of entheses. However, this method has only been successfully applied to human hand bones and animal long bones. This study tests the general applicability of the V.E.R.A. method to the human humerus, focusing on evaluating its reliability and repeatability. The sample included 23 humeri of unknown origin and background. The V.E.R.A. method was applied to six entheses of the humerus, comprising the subscapularis, supraspinatus, infraspinatus, teres minor, common extensor origin, and common flexor origin. Lin's concordance correlation coefficient (CCC) and percentage of error statistics were used to measure intraobserver error. Interobserver error was assessed through analysis of variance (ANOVA) tests, the intraclass correlation coefficient (ICC), and Lin's CCC. Intraobserver rates were between 1.83% and 3.23%. Interobserver error values were excellent, with no significant differences found in the ANOVA tests; Lin's CCC values were all above 0.90, with only the common extensor origin being 0.87; and ICC values were all above 0.97. Our results showed that the V.E.R.A. method is highly reliable and reproducible for the six entheses of the human humerus selected for this study. These results demonstrate the vast potential for the V.E.R.A. method to be applied to other parts of the human skeleton. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the daily rehabilitation training of cardiovascular patients depends on directing by health care professions in rehabilitation centre, during assessing and correcting the movements system about cardiovascular patients independent rehabilitation training at home, this paper proposed an action assessment method for cardiovascular patients' rehabilitation training based on key points of the human skeleton (ASRT-PHS). Firstly, this paper constructed a dataset for rehabilitation training actions using a camera and data augmentation in accordance with the specified rehabilitation training specification for cardiovascular patients. Secondly, this paper employed a deep learning-based detector and pose estimator to capture human body positions and extract key points of the human skeleton, respectively, and then input the results into a convolutional neural network for action recognition. Thirdly, by calculating joint angle thresholds, joint distance ratio and assessing standard motions, this paper constructed a motion segmentation model based on joint distance ratios and an action assessment model based on action joint angle thresholds. This paper investigated the optimal combination of ASRT-PHS by assessing its performance with various joint angle thresholds and action recognition approaches. The results show that ASRT-PHS achieves an average action recognition, segmentation and assessment accuracy of 92.78%, 77.6% and 87%, respectively. Furthermore, case tests about the true cardiovascular patients show that the average accuracy of the prototype system is 71.3%, which provides a feasible intelligent auxiliary system for patients autonomous rehabilitation training at home. [ABSTRACT FROM AUTHOR]

In the action recognition field based on the characteristics of human skeleton joint points, the selection of keyframes in the skeleton sequence is a significant issue, which directly affects the action recognition accuracy. In order to improve the effectiveness of keyframes selection, this paper proposes inflection point frames, and transforms keyframes selection into a multi-objective optimization problem based on it. First, the pose features are extracted from the input skeleton joint point data, which used to construct the pose feature vector of each frame in time sequence; then, the inflection point frames in the sequence are determined according to the flow of momentum of each body part. Next, the pose feature vectors are input into the keyframes multi-objective optimization model, with the fusion of domain information and the number of keyframes; finally, the output keyframes are input to the action classifier. To verify the effectiveness of the method, the MSR-Action3D, the UTKinect-Action and Florence3D-Action, and the 3 public datasets, are chosen for simulation experiments and the results show that the keyframes sequence obtained by this method can significantly improve the accuracy of multiple action classifiers, and the average recognition accuracy of the three data sets can reach 94.6%, 97.6% and 94.2% respectively. Besides, combining the optimized keyframes with deep learning classifier on the NTU RGB + D dataset can make the accuracies reaching 83.2% and 93.7%. [ABSTRACT FROM AUTHOR]

Preclinical models (typically ovariectomized rats and genetically altered mice) have underpinned much of what we know about skeletal biology. They have been pivotal for developing therapies for osteoporosis and monogenic skeletal conditions, including osteogenesis imperfecta, achondroplasia, hypophosphatasia, and craniodysplasias. Further therapeutic advances, particularly to improve cortical strength, require improved understanding and more rigorous use and reporting. We describe here how trabecular and cortical bone structure develop, are maintained, and degenerate with aging in mice, rats, and humans, and how cortical bone structure is changed in some preclinical models of endocrine conditions (eg, postmenopausal osteoporosis, chronic kidney disease, hyperparathyroidism, diabetes). We provide examples of preclinical models used to identify and test current therapies for osteoporosis, and discuss common concerns raised when comparing rodent preclinical models to the human skeleton. We focus especially on cortical bone, because it differs between small and larger mammals in its organizational structure. We discuss mechanisms common to mouse and human controlling cortical bone strength and structure, including recent examples revealing genetic contributors to cortical porosity and osteocyte network configurations during growth, maturity, and aging. We conclude with guidelines for clear reporting on mouse models with a goal for better consistency in the use and interpretation of these models. [ABSTRACT FROM AUTHOR]

The timely detection of falls and alerting medical aid is critical for health monitoring in elderly individuals living alone. This paper mainly focuses on issues such as poor adaptability, privacy infringement, and low recognition accuracy associated with traditional visual sensor-based fall detection. We propose an infrared video-based fall detection method utilizing spatial-temporal graph convolutional networks (ST-GCNs) to address these challenges. Our method used fine-tuned AlphaPose to extract 2D human skeleton sequences from infrared videos. Subsequently, the skeleton data was represented in Cartesian and polar coordinates and processed through a two-stream ST-GCN to recognize fall behaviors promptly. To enhance the network's recognition capability for fall actions, we improved the adjacency matrix of graph convolutional units and introduced multi-scale temporal graph convolution units. To facilitate practical deployment, we optimized time window and network depth of the ST-GCN, striking a balance between model accuracy and speed. The experimental results on a proprietary infrared human action recognition dataset demonstrated that our proposed algorithm accurately identifies fall behaviors with the highest accuracy of 96%. Moreover, our algorithm performed robustly, identifying falls in both near-infrared and thermal-infrared videos. [ABSTRACT FROM AUTHOR]

Skeletal dysplasias (SKDs) are a heterogeneous group of more than 750 genetic disorders characterized by abnormal development, growth, and maintenance of bones or cartilage in the human skeleton. SKDs are often caused by variants in early patterning genes and in many cases part of multiple malformation syndromes and occur in combination with non‐skeletal phenotypes. The aim of this study was to investigate the underlying genetic cause of congenital SKDs in highly consanguineous Pakistani families, as well as in sporadic and familial SKD cases from India using multigene panel sequencing analysis. Therefore, we performed panel sequencing of 386 bone‐related genes in 7 highly consanguineous families from Pakistan and 27 cases from India affected with SKDs. In the highly consanguineous families, we were able to identify the underlying genetic cause in five out of seven families, resulting in a diagnostic yield of 71%. Whereas, in the sporadic and familial SKD cases, we identified 12 causative variants, corresponding to a diagnostic yield of 44%. The genetic heterogeneity in our cohorts was very high and we were able to detect various types of variants, including missense, nonsense, and frameshift variants, across multiple genes known to cause different types of SKDs. In conclusion, panel sequencing proved to be a highly effective way to decipher the genetic basis of SKDs in highly consanguineous families as well as sporadic and or familial cases from South Asia. Furthermore, our findings expand the allelic spectrum of skeletal dysplasias. [ABSTRACT FROM AUTHOR]

Current self-supervised approaches for skeleton action representation learning often focus on constrained scenarios, where videos and skeleton data are recorded in laboratory settings. When dealing with estimated skeleton data in real-world videos, such methods perform poorly due to the large variations across subjects and camera viewpoints. To address this issue, we introduce ViA, a novel View-Invariant Autoencoder for self-supervised skeleton action representation learning. ViA leverages motion retargeting between different human performers as a pretext task, in order to disentangle the latent action-specific 'Motion' features on top of the visual representation of a 2D or 3D skeleton sequence. Such 'Motion' features are invariant to skeleton geometry and camera view and allow ViA to facilitate both, cross-subject and cross-view action classification tasks. We conduct a study focusing on transfer-learning for skeleton-based action recognition with self-supervised pre-training on real-world data (e.g., Posetics). Our results showcase that skeleton representations learned from ViA are generic enough to improve upon state-of-the-art action classification accuracy, not only on 3D laboratory datasets such as NTU-RGB+D 60 and NTU-RGB+D 120, but also on real-world datasets where only 2D data are accurately estimated, e.g., Toyota Smarthome, UAV-Human and Penn Action. Code and models will be publicly available at https://walker-a11y.github.io/ViA-project. [ABSTRACT FROM AUTHOR]

Lately, as a subset of human-centric studies, vision-oriented human action recognition has emerged as a pivotal research area, given its broad applicability in fields like healthcare, video surveillance, autonomous driving, sports, and education. This brief applies Lie algebra and standard bone length data to represent human skeleton data. A multi-layer long short-term memory (LSTM) recurrent neural network and convolutional neural network (CNN) are applied for human motion recognition. Finally, the trained network weights are converted into the crossbar-based memristor circuit, which can accelerate the network inference, reduce energy consumption, and obtain an excellent computing performance. [ABSTRACT FROM AUTHOR]

This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit (PSECNN- BiGRU) fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home environments. Firstly, the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton, thereby obtaining a human posture feature set. Thereafter, a double-layer BiGRU algorithm is utilized to extract multi-layer, bidirectional temporal features from the human posture feature set, and a CNN network with an exponential linear unit (ELU) activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human posture. Furthermore, a squeeze and excitation networks (SENet) module is introduced to adaptively learn the importance weights of each channel, enhancing the network's focus on important features. Finally, comparative experiments are performed on available datasets, including the public human activity recognition using smartphone dataset (UCIHAR), the public human activity recognition 70 plus dataset (HAR70PLUS), and the independently developed home abnormal behavior recognition dataset (HABRD) created by the authors' team. The results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%, 89.42%, and 98.90%, respectively, which are 5.24%, 5.83%, and 3.19% higher than the average accuracy of the five models proposed in the comparative literature, including CNN, GRU, and others. The F1-score for abnormal posture recognition reaches 98.84% (heartache), 97.18% (fall), 99.6% (bellyache), and 98.27% (climbing) on the self-builtHABRDdataset, thus verifying the effectiveness, generalization, and robustness of the proposed model in enhancing human posture recognition. [ABSTRACT FROM AUTHOR]

Men with writing proficiency enjoyed a privileged position in ancient Egyptian society in the third millennium BC. Research focusing on these officials of elevated social status ("scribes") usually concentrates on their titles, scribal statues, iconography, etc., but the individuals themselves, and their skeletal remains, have been neglected. The aim of this study is to reveal whether repetitive tasks and maintained postures related to scribal activity can manifest in skeletal changes and identify possible occupational risk factors. A total of 1767 items including entheseal changes, non-metric traits, and degenerative changes were recorded from the human remains of 69 adult males of well-defined social status categories from the necropolis at Abusir (2700–2180 BC). Statistically significant differences between the scribes and the reference group attested a higher incidence of changes in scribes and manifested themselves especially in the occurrence of osteoarthritis of the joints. Our research reveals that remaining in a cross-legged sitting or kneeling position for extended periods, and the repetitive tasks related to writing and the adjusting of the rush pens during scribal activity, caused the extreme overloading of the jaw, neck and shoulder regions. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel, vision-transformer-based end-to-end pose estimation method, LidPose, for real-time human skeleton estimation in non-repetitive circular scanning (NRCS) lidar point clouds. Building on the ViTPose architecture, we introduce novel adaptations to address the unique properties of NRCS lidars, namely, the sparsity and unusual rosetta-like scanning pattern. The proposed method addresses a common issue of NRCS lidar-based perception, namely, the sparsity of the measurement, which needs balancing between the spatial and temporal resolution of the recorded data for efficient analysis of various phenomena. LidPose utilizes foreground and background segmentation techniques for the NRCS lidar sensor to select a region of interest (RoI), making LidPose a complete end-to-end approach to moving pedestrian detection and skeleton fitting from raw NRCS lidar measurement sequences captured by a static sensor for surveillance scenarios. To evaluate the method, we have created a novel, real-world, multi-modal dataset, containing camera images and lidar point clouds from a Livox Avia sensor, with annotated 2D and 3D human skeleton ground truth. [ABSTRACT FROM AUTHOR]

Objectives: Ecogeographic variation in human nasal anatomy has historically been analyzed on skeletal morphology and interpreted in the context of climatic adaptations to respiratory air‐conditioning. Only a few studies have analyzed nasal soft tissue morphology, actively involved in air‐conditioning physiology. Materials and Methods: We used in vivo computer tomographic scans of (N = 146) adult individuals from Cambodia, Chile, Russia, and Spain. We conducted (N = 438) airflow simulations during inspiration using computational fluid dynamics to analyze the air‐conditioning capacities of the nasal soft tissue in the inflow, functional, and outflow tract, under three different environmental conditions: cold–dry; hot–dry; and hot–humid. We performed statistical comparisons between populations and sexes. Results: Subjects from hot–humid regions showed significantly lower air‐conditioning capacities than subjects from colder regions in all the three conditions, specifically within the isthmus region in the inflow tract, and the anterior part of the internal functional tract. Posterior to the functional tract, no differences were detected. No differences between sexes were found in any of the tracts and under any of the conditions. Discussion: Our statistical analyses support models of climatic adaptations of anterior nasal soft tissue morphology that fit with, and complement, previous research on dry skulls. However, our results challenge a morpho‐functional model that attributes air‐conditioning capacities exclusively to the functional tract located within the nasal cavity. Instead, our findings support studies that have suggested that both, the external nose and the intra‐facial soft tissue airways contribute to efficiently warming and humidifying air during inspiration. This supports functional interpretations in modern midfacial variation and evolution. [ABSTRACT FROM AUTHOR]

This article discusses the use of X-ray fluorescence analysis (RFA) and gamma spectroscopy as analytical techniques in chemistry education. The experiments described in the article focus on exploring atomic models and characterizing different materials. RFA is used to determine the composition of compounds and metals, while gamma spectroscopy can detect gamma radiation emitted by isotopes. The article provides examples of using these techniques to analyze specific materials, such as coins and white pigments. The authors suggest that the benefits of these techniques justify the cost of acquiring the necessary equipment. [Extracted from the article]

SUMMARY: Over the past decade, the history of tobacco's introduction to Europe and its societal impact has been extensively studied, resulting in prevailing narratives about its adoption and consumption. In the Netherlands, historical records generally concur that: (I) tobacco rose in popularity among all socioeconomic classes between 1590 and 1630 CE; and (II) it spread throughout the Country as a male habit. However, the presence and consumption of tobacco have exhibited profound variations across diverse societies throughout history, manifesting dissimilar patterns of employment and significance over varying temporal and spatial dimensions. By analysing a sample of 351 human skeletons dating from 1300 to 1829 CE, the present study challenges the limited historical narratives presented above and emphasizes the diverse contextual factors that influenced tobacco's prevalence in two different Dutch centres. Our results suggest that in certain areas of the Netherlands tobacco was likely present and widely consumed well before 1630 CE, while also highlighting overall substantial female participation in the practice. Furthermore, our analysis hints at the possibility of divergent methods of tobacco consumption between sexes, suggesting that the historical narrative of tobacco as solely a male habit may warrant reconsideration. Overall, our study contributes to a deeper understanding of the complex history of tobacco in the Netherlands, shedding light on historical trends and cultural practices. [ABSTRACT FROM AUTHOR]

Objective: This study aims to improve workers’ postures and thus reduce the risk of musculoskeletal disorders in human-robot collaboration by developing a novel model-free reinforcement learning method. Background: Human-robot collaboration has been a flourishing work configuration in recent years. Yet, it could lead to workrelated musculoskeletal disorders if the collaborative tasks result in awkward postures for workers. Methods: The proposed approach follows two steps: first, a 3D human skeleton reconstruction method was adopted to calculate workers’ continuous awkward posture (CAP) score; second, an online gradient-based reinforcement learning algorithm was designed to dynamically improve workers’ CAP score by adjusting the positions and orientations of the robot end effector. Results: In an empirical experiment, the proposed approach can significantly improve the CAP scores of the participants during a human-robot collaboration task when compared with the scenarios where robot and participants worked together at a fixed position or at the individual elbow height. The questionnaire outcomes also showed that the working posture resulted from the proposed approach was preferred by the participants. Conclusion: The proposed model-free reinforcement learning method can learn the optimal worker postures without the need for specific biomechanical models. The data-driven nature of this method can make it adaptive to provide personalized optimal work posture. [ABSTRACT FROM AUTHOR]

The article, "Red and Wolfe," recounts the tale of Red, a witch, and Wolfe, a wolf, who live in seclusion in a cabin in the woods. When their neighbors, Hans and Gretel, purchase the gingerbread house and plan to construct a condominium complex, Red recognizes their magical abilities and hopes they can help fix the damage caused by Wolfe. However, Wolfe overhears a conversation among The Pigs, real estate developers, discussing the murder of a witch, leading him to suspect Red. He flees into the forest, leaving Red trapped in a shed. The Pigs demolish the cabin and build the condos, while Wolfe disappears. The article explores the belief that new buildings cannot be haunted or constructed by pigs, though some claim to hear faint screams at night. The author presents this as a topic of discussion without taking a stance, aiming to inform library patrons conducting research on specific subjects. [Extracted from the article]

The class imbalance problem occurs when there is an unequal distribution of classes in a dataset and is a significant issue in various artificial intelligence applications. This study focuses on the severe multiclass imbalance problem of human activity recognition in rehabilitation exercises for people with disabilities. To overcome this problem, we present a novel human action-centric augmentation method for human skeleton-based pose estimation. This study proposes the state transition-oriented conditional variational autoencoder (STO-CVAE) to capture action patterns in repeated exercises. The proposed approach generates action samples by capturing temporal information of human skeletons to improve the identification of minority disability classes. We conducted experimental studies with a real-world dataset gathered from rehabilitation exercises and confirmed the superiority and effectiveness of the proposed method. Specifically, all investigated classifiers (i.e., random forest, support vector machine, extreme gradient boosting, light gradient boosting machine, and TabNet) trained with the proposed augmentation method outperformed the models trained without augmentation in terms of the F1-score and accuracy, with F1-score showing the most improvement. Overall, the prediction accuracy of most classes was improved; in particular, the prediction accuracy of the minority classes was greatly improved. Hence, the proposed STO-CVAE can be used to improve the accuracy of disability classification in the field of physical medicine and rehabilitation and to provide suitable personal training and rehabilitation exercise programs. [ABSTRACT FROM AUTHOR]

The biological profile estimation is the first step toward positive identification. However, it is not always possible to access a complete and well-preserved skeleton due to postmortem damage and taphonomic changes. As such, there is a need to develop new alternatives to analyze different bones of the human skeleton. The present study aims to analyze the patellar osteometry, with attention to its degree of sexual dimorphism, to establish a simple method for estimating sex in Portuguese adults. Six measurements were taken from 222 patella pairs, including 117 females and 105 males from the XXI Century Identified Skeleton Collection of the University of Coimbra. Subsequently, this method was validated in a different sample of 50 individuals equally representing both sexes. Maximum height stands out with a 77.0% of correct sex estimation, reaching 98.0% when applied to the new sample. The linear discriminant function analysis containing all the six variables showed the best results, with 80.2% of correct classification after cross-validation and 96.0% when applied to the independent sample. [ABSTRACT FROM AUTHOR]

Graph theory originated as a fun way to solve math problems, but it has now evolved into a significant mathematics subject with several applications in computer vision. The human skeleton has garnered much attention in recent years as a simple depiction of human motion. Three-dimensional joints have limitations in terms of dependability, compatibility, and flexibility, notwithstanding the optimistic results of previous investigations. CPG-3D is a new technique for skeleton-based action recognition that focuses solely on 3D skeleton joint points and their placements as the basic expression of human skeletons rather than any additional information. CPG-3D outperforms previous action recognition algorithms in learning how to describe, is more resilient to pose estimation disturbances, and generalises better across data sets. CPG-3D can also manage various alternatives without incurring additional computational expenses, and its capabilities can be readily fused with other modalities during the early phases of fusion, offering a broad design space to increase efficiency further. CPG-3D consistently beats the competition on four complicated and hard datasets when used alone on three-dimensional skeletal joints. [ABSTRACT FROM AUTHOR]

Human motion capture technology, which leverages sensors to track the movement trajectories of key skeleton points, has been progressively transitioning from industrial applications to broader civilian applications in recent years. It finds extensive use in fields such as game development, digital human modeling, and sport science. However, the affordability of these sensors often compromises the accuracy of motion data. Low-cost motion capture methods often lead to errors in the captured motion data. We introduce a novel approach for human motion reconstruction and enhancement using spatio-temporal attention-based graph convolutional networks (ST-ATGCNs), which efficiently learn the human skeleton structure and the motion logic without requiring prior human kinematic knowledge. This method enables unsupervised motion data restoration and significantly reduces the costs associated with obtaining precise motion capture data. Our experiments, conducted on two extensive motion datasets and with real motion capture sensors such as the SONY (Tokyo, Japan) mocopi, demonstrate the method's effectiveness in enhancing the quality of low-precision motion capture data. The experiments indicate the ST-ATGCN's potential to improve both the accessibility and accuracy of motion capture technology. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The current thyroid ultrasound relies heavily on the experience and skills of the sonographer and the expertise of the radiologist, and the process is physically and cognitively exhausting. In this paper, we report a fully autonomous robotic ultrasound system, which is able to scan thyroid regions without human assistance and identify malignant nod- ules. In this system, human skeleton point recognition, reinforcement learning, and force feedback are used to deal with the difficulties in locating thyroid targets. The orientation of the ultrasound probe is adjusted dynamically via Bayesian optimization. Experimental results on human participants demonstrated that this system can perform high-quality ultrasound scans, close to manual scans obtained by clinicians. Additionally, it has the potential to detect thyroid nodules and provide data on nodule characteristics for American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) calculation. Current thyroid ultrasounds rely heavily on the experience and skills of the sonographer and of the radiologist, and the process is physically and cognitively exhausting. Here, the authors show a fully autonomous robotic ultrasound system, which is able to scan thyroid regions without human assistance and identify malignant nodules. [ABSTRACT FROM AUTHOR]

Objectives: This study aims to enhance supervised human activity recognition based on spatiotemporal graph convolutional neural networks by addressing two key challenges: (1) extracting local spatial feature information from implicit joint connections that is unobtainable through standard graph convolutions on natural joint connections alone. (2) Capturing long-range temporal dependencies that extend beyond the limited temporal receptive fields of conventional temporal convolutions. Methods: To achieve these objectives, we propose three novel modules integrated into the spatiotemporal graph convolutional framework: (1) a connectivity feature extraction module that employs attention to model implicit joint connections and extract their local spatial features. (2) A long-range frame difference feature extraction module that captures extensive temporal context by considering larger frame intervals. (3) A coordinate transformation module that enhances spatial representation by fusing Cartesian and spherical coordinate systems. Findings: Evaluation across multiple datasets demonstrates that the proposed method achieves significant improvements over baseline networks, with the highest accuracy gains of 2.76 % on the NTU-RGB+D 60 dataset (Cross-subject), 4.1 % on NTU-RGB+D 120 (Cross-subject), and 4.3 % on Kinetics (Top-1), outperforming current state-of-the-art algorithms. This paper delves into the realm of behavior recognition technology, a cornerstone of autonomous systems, and presents a novel approach that enhances the accuracy and precision of human activity recognition. [ABSTRACT FROM AUTHOR]

This study examines the change of urban identity from the socialist period to post-socialist Tirana, evaluating the role of landmarks. The continuously changing city image in the post-socialist period, associated with the construction of new high-rise buildings, is the commencement of this research. The aim is to measure to what extent the change of the landmarks in the post-socialist period impacts Tirana's identity. To achieve this goal, we interviewed Tirana citizens (N = 209) about the socialist/post-socialist period landmarks representing city identity. The methodology includes surveying, mapping, visualization, and clustering. Through a conceptual diagram, the study emphasizes the role of landmarks within the urban identity concept by utilizing their salience-providing features, which are visual, semantic, and locational. The results reveal that the socialist city identity is represented by landmarks that possess a strong image and semantic values. In contrast, post-socialist city identity is represented by new landmarks, which are reported as many and emphasize the rise of experience-oriented landmarks in an entertainment district. The study found a location shift in the landmarks representing Tirana's urban identity from the socialist to post-socialist city. However, in both periods, the majority are on the city's main Boulevard (city spine), which works as a mental skeleton. [ABSTRACT FROM AUTHOR]

Aimed at the problem of human–machine interaction between patients and robots in the process of using rehabilitation robots for rehabilitation training, this paper proposes a human–machine interactive control method based on an independently developed upper limb rehabilitation robot. In this method, the camera is used as a sensor, the human skeleton model is used to analyse the moving image, and the key points of the human body are extracted. Then, the three-dimensional coordinates of the key points of the human arm are extracted by depth estimation and spatial geometry, and then the real-time motion data are obtained, and the control instructions of the robot are generated from it to realise the real-time interactive control of the robot. This method can not only improve the adaptability of the system to individual patient differences, but also improve the robustness of the system, which is less affected by environmental changes. The experimental results show that this method can realise real-time control of the rehabilitation robot, and that the robot assists the patient to complete the action with high accuracy. The results show that this control method is effective and can be applied to the fields of robot control and robot-assisted rehabilitation training. [ABSTRACT FROM AUTHOR]

Hypergraphs have received widespread attention in modeling complex data correlations due to their superior performance. In recent years, some researchers have used hypergraph structures to characterize complex non-pairwise joints in the human skeleton and model higher-order correlations of the human skeleton. However, traditional methods of constructing hypergraphs based on physical connections ignore the dependencies among non-physically connected joints or bones, and it is difficult to model the correlation among joints or bones that are highly correlated in human action but are physically connected at long distances. To address these issues, we propose a skeleton-based action recognition method for hypergraph learning based on skeleton correlation, which explores the effects of physically and non-physically connected skeleton information on accurate action recognition. Specifically, in this paper, spatio-temporal correlation modeling is performed on the natural connections inherent in humans (physical connections) and the joints or bones that are more dependent but not directly connected (non-physical connection) during human actions. In order to better learn the hypergraph structure, we construct a spatio-temporal hypergraph neural network to extract the higher-order correlations of the human skeleton. In addition, we use an attentional mechanism to compute the attentional weights among different hypergraph features, and adaptively fuse the rich feature information in different hypergraphs. Extensive experiments are conducted on two datasets, NTU-RGB+D 60 and Kinetics-Skeleton, and the results show that compared with the state-of-the-art skeleton-based methods, our proposed method can achieve an optimal level of performance with significant advantages, providing a more accurate environmental perception and action analysis for the development of embodied intelligence. [ABSTRACT FROM AUTHOR]

Considering that the Asian group is huge and consists of many sub-populations in terms of genetics and geographic locations, it is imperative to develop population-specific standards for forensic practice. However, baseline data for a Malaysian population are not readily available. We wish to apply the methodology of Gill et al. (1988) on linear measurements of the mid-facial skeleton observed in physical skulls of North Americans to post-mortem computed tomographic images of Malaysian individuals, together with cephalic and nasal indices. A total of 300 skull scans of equal distribution according to sex and ethnic groups were examined by an experienced observer. Mean values (±SD) in mm for maxillofacial breadth, mid-orbital breadth, alpha cord, naso-maxillofrontal subtense, naso-zygoorbital subtense, naso-alpha subtense, maximum cranial length, maximum cranial breadth, nasal height and nasal breadth in males are 24.98 ± 0.54; 54.84 ± 1.72; 25.20 ± 1.26; 12.52 ± 0.44; 19.70 ± 1.23; 21.33 ± 1.09; 180.36 ± 4.78; 143.02 ± 3.47; 51.76 ± 1.18; 24.99 ± 0.35; respectively. Findings for their female counterparts are 23.58 ± 0.69; 52.74 ± 2.36; 23.38 ± 1.21; 11.19 ± 0.5; 17.71 ± 1.36; 17.55 ± 1.19; 170.45 ± 24.18; 137.75 ± 16.95; 49.19 ± 0.99; 23.87 ± 0.39; respectively. Even though these craniofacial measurements are not able to confidently separate the three different ethnic groups, our study presented the preliminary measurements of Malaysian individuals comparatively to other global populations specifically in the Asian region. [ABSTRACT FROM AUTHOR]

In the field of skeleton-based action recognition, accurately recognizing human actions is crucial for applications such as virtual reality and motion analysis. However, this task faces challenges such intraindividual action differences and long-term temporal dependencies. To address these challenges, we propose an innovative model called spatial-temporal graph neural ordinary differential equations (STG-NODE). First, in the data preprocessing stage, the dynamic time warping (DTW) algorithm is used to normalize and calculate 3D skeleton data to facilitate the derivation of customized adjacency matrices for improving the influence of intraindividual action differences. Secondly, a custom ordinary differential equation (ODE) integrator is applied based on the initial conditions of the temporal features, producing a solution function that simulates the dynamic evolution trend of the events of interest. Finally, the outstanding ODE solver is used to numerically solve the time features based on the solution function to increase the influence of long-term dependencies on the recognition accuracy of the model and provide it with a more powerful temporal modeling ability. Through extensive experiments conducted on the NTU RGB+D 60 and Kinetics Skeleton 400 benchmark datasets, we demonstrate the superior performance of STG-NODE in the action recognition domain. The success of the STG-NODE model also provides new ideas and methods for the future development of the action recognition field. [ABSTRACT FROM AUTHOR]

Due to the robustness of skeleton data to human scale, illumination changes, dynamic camera views, and complex backgrounds, great progress has been made in skeleton‐based video anomaly detection in recent years. The spatio‐temporal graph convolutional network has been proven to be effective in modelling the spatio‐temporal dependencies of non‐Euclidean data such as human skeleton graphs, and the autoencoder based on this basic unit is widely used to model sequence features. However, due to the limitations of the convolution kernel, the model cannot capture the correlation between non‐adjacent joints, and it is difficult to deal with long‐term sequences, resulting in an insufficient understanding of behaviour. To address this issue, this paper applies the Transformer to the human skeleton and proposes the Spatio‐Temporal Enhanced Graph‐Transformer AutoEncoder (STEGT‐AE) to improve the capability of modelling. In addition, the multi‐memory model with skip connections is employed to provide different levels of coding features, thereby enhancing the ability of the model to distinguish similar heterogeneous behaviours. Furthermore, the STEGT‐AE has a single encoder‐double decoder architecture, which can improve the detection performance by the combining reconstruction and prediction error. The experimental results show that performances of STEGT‐AE is significantly better than other advanced algorithms on four baseline datasets. [ABSTRACT FROM AUTHOR]

The mammalian cranium (skull without lower jaw) is representative of mammalian diversity and is thus of particular interest to mammalian biologists across disciplines. One widely retrieved pattern accompanying mammalian cranial diversification is referred to as 'craniofacial evolutionary allometry' (CREA). This posits that adults of larger species, in a group of closely related mammals, tend to have relatively longer faces and smaller braincases. However, no process has been officially suggested to explain this pattern, there are many apparent exceptions, and its predictions potentially conflict with well‐established biomechanical principles. Understanding the mechanisms behind CREA and causes for deviations from the pattern therefore has tremendous potential to explain allometry and diversification of the mammalian cranium. Here, we propose an amended framework to characterise the CREA pattern more clearly, in that 'longer faces' can arise through several kinds of evolutionary change, including elongation of the rostrum, retraction of the jaw muscles, or a more narrow or shallow skull, which all result in a generalised gracilisation of the facial skeleton with increased size. We define a standardised workflow to test for the presence of the pattern, using allometric shape predictions derived from geometric morphometrics analysis, and apply this to 22 mammalian families including marsupials, rabbits, rodents, bats, carnivores, antelopes, and whales. Our results show that increasing facial gracility with size is common, but not necessarily as ubiquitous as previously suggested. To address the mechanistic basis for this variation, we then review cranial adaptations for harder biting. These dictate that a more gracile cranium in larger species must represent a structural sacrifice in the ability to produce or withstand harder bites, relative to size. This leads us to propose that facial gracilisation in larger species is often a product of bite force allometry and phylogenetic niche conservatism, where more closely related species tend to exhibit more similar feeding ecology and biting behaviours and, therefore, absolute (size‐independent) bite force requirements. Since larger species can produce the same absolute bite forces as smaller species with less effort, we propose that relaxed bite force demands can permit facial gracility in response to bone optimisation and alternative selection pressures. Thus, mammalian facial scaling represents an adaptive by‐product of the shifting importance of selective pressures occurring with increased size. A reverse pattern of facial 'shortening' can accordingly also be found, and is retrieved in several cases here, where larger species incorporate novel feeding behaviours involving greater bite forces. We discuss multiple exceptions to a bite force‐mediated influence on facial proportions across mammals which lead us to argue that ecomorphological specialisation of the cranium is likely to be the primary driver of facial scaling patterns, with some developmental constraints as possible secondary factors. A potential for larger species to have a wider range of cranial functions when less constrained by bite force demands might also explain why selection for larger sizes seems to be prevalent in some mammalian clades. The interplay between adaptation and constraint across size ranges thus presents an interesting consideration for a mechanistically grounded investigation of mammalian cranial allometry. [ABSTRACT FROM AUTHOR]

Automated mental retardation (MR) assessment is potential for improving the diagnostic efficiency and objectivity in clinical practice. Based on the researches on abnormal behavior characteristics of patients with MR, we propose an extension and supplement shift multi-scale G3D (ESS MS-G3D) network for video-based assessment of MR. Specifically, all videos are collected from clinical diagnostic scenarios and the skeleton sequence of human body is extracted from videos through an advanced pose estimation model. To solve the shortcomings of existing behavior characteristic learning methods, we present: (1) three G3D styles, enable the network to have different input forms; (2) two G3D graphs and two extension graphs, redefine and extend the graph structure of spatial–temporal nodes; (3) two learnable parameters, realize adaptive adjustment of graph structure; (4) a shift layer, enable the network to learn global features. Finally, we construct a three-branch model ESS MS-STGC, which can capture the discriminative spatial–temporal features and explore the co-occurrence relationship between spatial and temporal domains. Experiments in clinical video data set show that our proposed model has good performance in MR assessment and is superior to the existing vision-based methods. In two-classification task, our model with joint stream achieves the highest accuracy of 94.63 % in validation set and 89.13 % in test set. The results are further improved to 96.52 % and 93.22 % , respectively, by utilizing multi-stream fusion strategy. In four-classification task, our model obtains Top1 accuracy of 78.84 % and Top2 accuracy of 91.34 % in test set. The proposed method provides a new idea for clinical mental retardation assessment. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Falls can cause severe injuries, if an elderly person has a "long-life." In the presented research work, we have applied the widely known benchmark dataset "L2ei" and the customized "Geriatric-2000" dataset, which contains more than 6,000 elderly fall video sequences. The 25 human skeleton features are extracted using the customized 3D Open Pose methodology. The proposed research work presents a customized 3D Context-based LSTM-CNN enabled CareVision framework for fall position classification for elderlies. Furthermore, the proposed research work is compared with other customized AI-enabled computer vision approaches such as Fine KNN, Medium KNN, Decision Tree, long shortterm memory network (LSTM), Bi-LSTM and Recurrent Neural Network (RNN). The proposed 3D CareVision Framework has achieved an accuracy of 98.23 percent and a ROC value of 0.96. The indicated results demonstrate the efficiency and reliability of the proposed 3D CareVision Framework for elderly fall position classifications. The proposed 3D CareVision Framework will assist elderly personnels in case of emergencies and notify house members by sending emergency fall alerts. [ABSTRACT FROM AUTHOR]

This research introduces a novel method for fusing multi-view skeleton data to address the limitations encountered by a single vision sensor in capturing motion data, such as skeletal jitter, self-pose occlusion, and the reduced accuracy of three-dimensional coordinate data for human skeletal joints due to environmental object occlusion. Our approach employs two Kinect vision sensors concurrently to capture motion data from distinct viewpoints extract skeletal data and subsequently harmonize the two sets of skeleton data into a unified world coordinate system through coordinate conversion. To optimize the fusion process, we assess the contribution of each joint based on human posture orientation and data smoothness, enabling us to fine-tune the weight ratio during data fusion and ultimately produce a dependable representation of human posture. We validate our methodology using the FMS public dataset for data fusion and model training. Experimental findings demonstrate a substantial enhancement in the smoothness of the skeleton data, leading to enhanced data accuracy and an effective improvement in human posture recognition following the application of this data fusion method. [ABSTRACT FROM AUTHOR]

The brain is thought to be among the first human organs to decompose after death. The discovery of brains preserved in the archaeological record is therefore regarded as unusual. Although mechanisms such as dehydration, freezing, saponification, and tanning are known to allow for the preservation of the brain on short time scales in association with other soft tissues (≲4000 years), discoveries of older brains, especially in the absence of other soft tissues, are rare. Here, we collated an archive of more than 4400 human brains preserved in the archaeological record across approximately 12 000 years, more than 1300 of which constitute the only soft tissue preserved amongst otherwise skeletonized remains. We found that brains of this type persist on time scales exceeding those preserved by other means, which suggests an unknown mechanism may be responsible for preservation particular to the central nervous system. The untapped archive of preserved ancient brains represents an opportunity for bioarchaeological studies of human evolution, health and disease. [ABSTRACT FROM AUTHOR]

Skeleton-based human interaction recognition is a challenging task in the field of vision and image processing. Graph Convolutional Networks (GCNs) achieved remarkable performance by modeling the human skeleton as a topology. However, existing GCN-based methods have two problems: (1) Existing frameworks cannot effectively take advantage of the complementary features of different skeletal modalities. There is no information transfer channel between various specific modalities. (2) Limited by the structure of the skeleton topology, it is hard to capture and learn the information about two-person interactions. To solve these problems, inspired by the human visual neural network, we propose a multi-modal enhancement transformer (ME-Former) network for skeleton-based human interaction recognition. ME-Former includes a multi-modal enhancement module (ME) and a context progressive fusion block (CPF). More specifically, each ME module consists of a multi-head cross-modal attention block (MH-CA) and a two-person hypergraph self-attention block (TH-SA), which are responsible for enhancing the skeleton features of a specific modality from other skeletal modalities and modeling spatial dependencies between joints using the specific modality, respectively. In addition, we propose a two-person skeleton topology and a two-person hypergraph representation. The TH-SA block can embed their structural information into the self-attention to better learn two-person interaction. The CPF block is capable of progressively transforming the features of different skeletal modalities from low-level features to higher-order global contexts, making the enhancement process more efficient. Extensive experiments on benchmark NTU-RGB+D 60 and NTU-RGB+D 120 datasets consistently verify the effectiveness of our proposed ME-Former by outperforming state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The human skeleton is a metabolically active system that is constantly regenerating via the tightly regulated and highly coordinated processes of bone resorption and formation. Emerging evidence reveals fascinating new insights into the role of sphingolipids, including sphingomyelin, sphingosine, ceramide, and sphingosine-1-phosphate, in bone homeostasis. Sphingolipids are a major class of highly bioactive lipids able to activate distinct protein targets including, lipases, phosphatases, and kinases, thereby conferring distinct cellular functions beyond energy metabolism. Lipids are known to contribute to the progression of chronic inflammation, and notably, an increase in bone marrow adiposity parallel to elevated bone loss is observed in most pathological bone conditions, including aging, rheumatoid arthritis, osteoarthritis, and osteomyelitis. Of the numerous classes of lipids that form, sphingolipids are considered among the most deleterious. This review highlights the important primary role of sphingolipids in bone homeostasis and how dysregulation of these bioactive metabolites appears central to many chronic bone-related diseases. Further, their contribution to the invasion, virulence, and colonization of both viral and bacterial host cell infections is also discussed. Many unmet clinical needs remain, and data to date suggest the future use of sphingolipid-targeted therapy to regulate bone dysfunction due to a variety of diseases or infection are highly promising. However, deciphering the biochemical and molecular mechanisms of this diverse and extremely complex sphingolipidome, both in terms of bone health and disease, is considered the next frontier in the field. [ABSTRACT FROM AUTHOR]

A method based on kernel extreme learning machine is proposed for accurate localization and recognition of human bones. In this method, the human skeleton is divided into 16 key nodes based on physiology, and the human skeleton model is formed by connecting lines between the nodes. The sequence images of human actions are taken as input and fed into the input and hidden layers of the extreme learning machine. During the learning and training process, a kernel function is used to construct a kernel matrix to complete weight allocation. The experimental study was conducted on the action sequences of figure skaters, and the results showed that our method achieved an accuracy rate of over 90% in recognizing human bones, with individual sequences achieving an accuracy rate of over 95%, which is superior to convolutional neural network (CNN) and long short-term memory (LSTM) methods. [ABSTRACT FROM AUTHOR]

In recent years, skeleton-based action recognition has made great achievements in Computer Vision. A graph convolutional network (GCN) is effective for action recognition, modelling the human skeleton as a spatiotemporal graph. Most GCNs define the graph topology by physical relations of the human joints. However, this predefined graph ignores the spatial relationship between non-adjacent joint pairs in special actions and the behavior dependence between joint pairs, resulting in a low recognition rate for specific actions with implicit correlation between joint pairs. In addition, existing methods ignore the trend correlation between adjacent frames within an action and context clues, leading to erroneous action recognition with similar poses. Therefore, this study proposes a learnable GCN based on behavior dependence, which considers implicit joint correlation by constructing a dynamic learnable graph with extraction of specific behavior dependence of joint pairs. By using the weight relationship between the joint pairs, an adaptive model is constructed. It also designs a self-attention module to obtain their inter-frame topological relationship for exploring the context of actions. Combining the shared topology and the multi-head self-attention map, the module obtains the context-based clue topology to update the dynamic graph convolution, achieving accurate recognition of different actions with similar poses. Detailed experiments on public datasets demonstrate that the proposed method achieves better results and realizes higher quality representation of actions under various evaluation protocols compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]