Search Results (610)

Gait recognition is a reliable biometric approach that uniquely identifies individuals based on their natural walking patterns. It is widely used to recognize individuals who are challenging to camouflage and do not require a person’s cooperation. The general face-based person recognition system often fails to determine the offender’s identity when they conceal their face by wearing helmets and masks to evade identification. In such cases, gait-based recognition is ideal for identifying offenders, and most existing work leverages a deep learning (DL) model. However, a single model often fails to capture a comprehensive selection of refined patterns in input data when external factors are present, such as variation in viewing angle, clothing, and carrying conditions. In response to this, this paper introduces a fusion-based multi-model gait recognition framework that leverages the potential of convolutional neural networks (CNNs) and a vision transformer (ViT) in an ensemble manner to enhance gait recognition performance. Here, CNNs capture spatiotemporal features, and ViT features multiple attention layers that focus on a particular region of the gait image. The first step in this framework is to obtain the Gait Energy Image (GEI) by averaging a height-normalized gait silhouette sequence over a gait cycle, which can handle the left–right gait symmetry of the gait. After that, the GEI image is fed through multiple pre-trained models and fine-tuned precisely to extract the depth spatiotemporal feature. Later, three separate fusion strategies are conducted, and the first one is decision-level fusion (DLF), which takes each model’s decision and employs majority voting for the final decision. The second is feature-level fusion (FLF), which combines the features from individual models through pointwise addition before performing gait recognition. Finally, a hybrid fusion combines DLF and FLF for gait recognition. The performance of the multi-model fusion-based framework was evaluated on three publicly available gait databases: CASIA-B, OU-ISIR D, and the OU-ISIR Large Population dataset. The experimental results demonstrate that the fusion-enhanced framework achieves superior performance. Full article

The underground coal mine environment is complex and dynamic, making the application of visual algorithms for object detection a crucial component of underground safety management as well as a key factor in ensuring the safe operation of workers. We look at this in the context of helmet-wearing detection in underground mines, where over 25% of the targets are small objects. To address challenges such as the lack of effective samples for unworn helmets, significant background interference, and the difficulty of detecting small helmet targets, this paper proposes a novel underground helmet-wearing detection algorithm that combines dynamic background awareness with a limited number of valid samples to improve accuracy for underground workers. The algorithm begins by analyzing the distribution of visual surveillance data and spatial biases in underground environments. By using data augmentation techniques, it then effectively expands the number of training samples by introducing positive and negative samples for helmet-wearing detection from ordinary scenes. Thereafter, based on YOLOv10, the algorithm incorporates a background awareness module with region masks to reduce the adverse effects of complex underground backgrounds on helmet-wearing detection. Specifically, it adds a convolution and attention fusion module in the detection head to enhance the model’s perception of small helmet-wearing objects by enlarging the detection receptive field. By analyzing the aspect ratio distribution of helmet wearing data, the algorithm improves the aspect ratio constraints in the loss function, further enhancing detection accuracy. Consequently, it achieves precise detection of helmet-wearing in underground coal mines. Experimental results demonstrate that the proposed algorithm can detect small helmet-wearing objects in complex underground scenes, with a 14% reduction in background false detection rates, and thereby achieving accuracy, recall, and average precision rates of 94.4%, 89%, and 95.4%, respectively. Compared to other mainstream object detection algorithms, the proposed algorithm shows improvements in detection accuracy of 6.7%, 5.1%, and 11.8% over YOLOv9, YOLOv10, and RT-DETR, respectively. The algorithm proposed in this paper can be applied to real-time helmet-wearing detection in underground coal mine scenes, providing safety alerts for standardized worker operations and enhancing the level of underground security intelligence. Full article

The COVID-19 pandemic caused immense physical disruptions, affecting young adults in the U.S. The Health Belief Model is a social psychological framework that predicts the likelihood of adopting health behavior. The purpose of this research is to investigate COVID-19-related health beliefs and dietary behaviors among undergraduate students during the pandemic. Using convenience sampling, a cross-sectional survey was completed by 304 individuals at a New Jersey state university. Survey data included the frequency of COVID-19 prevention behaviors (e.g., wearing an indoor mask, handwashing), and consumption of fruit and vegetables. The Health Belief Model constructs measured perceived susceptibility to COVID-19, severity, benefits, barriers, and self-efficacy. Frequency distributions, t-tests, and Kruskal–Wallis tests were investigated for racial subgroups (Whites, Blacks, Latinos, and Asians). The mean age of the sample was 21.7, with 27% males, and 46% self-identified as White. Whites adopted fewer COVID-19 prevention behaviors (p < 0.001) than non-Whites. Black students perceived less COVID-19 severity (p < 0.01) and stronger perceived benefits (p < 0.05) than the other subgroups. Latino students perceived greater susceptibility (p < 0.01) and greater barriers than non-Latinos. Asians practiced higher mask wearing frequency (p < 0.05) but less daily fruit intake than their counterparts (p < 0.01). This research highlights the importance of handwashing, wearing indoor masks, and consuming produce among university students. Addressing barriers to health action while promoting the benefits of enacting behaviors to mitigate the risk of COVID-19 is warranted. Full article

Fire events can impact physical and mental health through smoke exposure, evacuation, property loss, and/or other environmental stressors. In this study, we developed community-driven, cross-sectional online surveys to assess public attitudes, health impacts, and protective actions of residents affected by the Tustin hangar fire that burned for 24 days in southern California. Results showed the most frequently reported fire-related exposure concerns (93%) to be asbestos and general air pollution and the most commonly reported mental health impacts to be anxiety (41%), physical fatigue (37%), headaches (33%), and stress (26%). Nose/sinus irritation was the most commonly reported (26.0%) respiratory symptom, while skin- and eye-related conditions were reported by 63.0% and 72.2% of the survey population, respectively. The most commonly reported health-protective actions taken by residents included staying indoors and/or closing doors and windows (67%), followed by wearing face masks (37%) and the indoor use of air purifiers (35%). A higher proportion of low-income residents had to spend money on remediation or other health-protective actions compared to high-income residents. Participants overwhelmingly reported disapproval of their city’s and/or government’s response to the fire disaster. Findings from this study underscore the potential impacts of major pollution events on neighboring communities and offer critical insights to better position government agencies to respond during future disasters while effectively communicating with the public and addressing community needs. Full article

The natural features of the face exhibit significant symmetry. In practical applications, faces may be partially occluded due to factors like wearing masks or glasses, or the presence of other objects. Occluded-face restoration has broad application prospects in fields such as augmented reality, virtual reality, healthcare, security, etc. It is also of significant practical importance in enhancing public safety and providing efficient services. This research establishes an improved occluded-face restoration network based on facial feature points and Generative Adversarial Networks. A facial landmark prediction network is constructed based on an improved MobileNetV3-small network. On the foundation of U-Net, dilated convolutions and residual blocks are introduced to form an enhanced generator network. Additionally, an improved discriminator network is built based on Patch-GAN. Compared to the Contextual Attention network, under various occlusions, the improved face restoration network shows a maximum increase in the Peak Signal-to-Noise Ratio of 24.47%, and in the Structural Similarity Index of 24.39%, and a decrease in the Fréchet Inception Distance of 81.1%. Compared to the Edge Connect network, under various occlusions, the improved network shows a maximum increase in the Peak Signal-to-Noise Ratio of 7.89% and in the Structural Similarity Index of 10.34%, and a decrease in the Fréchet Inception Distance of 27.2%. Compared to the LaFIn network, under various occlusions, the improved network shows a maximum increase in the Peak Signal-to-Noise Ratio of 3.4% and in the Structural Similarity Index of 3.31%, and a decrease in the Fréchet Inception Distance of 9.19%. These experiments show that the improved face restoration network yields better restoration results. Full article

Conveyor belts are critical in various industries, particularly in the barrier eddy current separator systems used in recycling processes. However, hidden issues, such as belt misalignment, excessive heat that can lead to fire hazards, and the presence of sharp or irregularly shaped materials, reduce operational efficiency and pose serious threats to the health and safety of personnel on the production floor. This study presents an intelligent monitoring and protection system for barrier eddy current separator conveyor belts designed to safeguard machinery and human workers simultaneously. In this system, a thermal camera continuously monitors the surface temperature of the conveyor belt, especially in the area above the magnetic drum—where unwanted ferromagnetic materials can lead to abnormal heating and potential fire risks. The system detects temperature anomalies in this critical zone. The early detection of these risks triggers audio–visual alerts and IoT-based warning messages that are sent to technicians, which is vital in preventing fire-related injuries and minimizing emergency response time. Simultaneously, a machine vision module autonomously detects and corrects belt misalignment, eliminating the need for manual intervention and reducing the risk of worker exposure to moving mechanical parts. Additionally, a line-scan camera integrated with the YOLOv11 AI model analyses the shape of materials on the conveyor belt, distinguishing between rounded and sharp-edged objects. This system enhances the accuracy of material separation and reduces the likelihood of injuries caused by the impact or ejection of sharp fragments during maintenance or handling. The YOLOv11n-seg model implemented in this system achieved a segmentation mask precision of 84.8 percent and a recall of 84.5 percent in industry evaluations. Based on this high segmentation accuracy and consistent detection of sharp particles, the system is expected to substantially reduce the frequency of sharp object collisions with the BECS conveyor belt, thereby minimizing mechanical wear and potential safety hazards. By integrating these intelligent capabilities into a compact, cost-effective solution suitable for real-world recycling environments, the proposed system contributes significantly to improving workplace safety and equipment longevity. This project demonstrates how digital transformation and artificial intelligence can play a pivotal role in advancing occupational health and safety in modern industrial production. Full article

Rock imagery in the Puebloan region of the American Southwest often combines elements from different animal, human, plant, and natural sources. Blended elements may depict or refer to other-wordly states of existence or to creation narratives. Beings with combined elements can shift from shapes familiar in the present world and transport the viewer’s frame of reference to the spirit world. Puebloan belief in layering worlds below and above the present world is an important underlying social construct. Other worlds, especially those below, refer to past mythical times when animals and humans existed in primordial forms or were not fully formed, or may refer to the land of the dead or the underworld. Certain animal forms may have been selected because they are spirit guides, have specific powers, or were guardian-gods of cardinal directions. Some animals, such as birds, were chosen as messengers of prayers or offerings, while others (such as bears) had healing powers. The placement of images on the landscape or in relation to natural features imparts added power to the imagery. Ambiguity and multiple meanings also enhance these powers and incorporate concepts of emergence and transformation. Some images refer to the transformation that occurs when dancers wear kachina masks and then assume the attributes of those kachinas. Examples will be presented from images dating to the pre-European contact period (1300 to 1540 AD) found at Petroglyph National Monument, in the central Rio Grande valley of New Mexico. Comparisons to painted wall murals in kivas (ceremonial rooms) made during the same time period are presented. Full article

The accurate characterization of wear debris is crucial for assessing the health of rotating engine components and for conducting simulation experiments in debris detection. This study proposed an intelligent recognition method for ferrography wear debris images, leveraging several improved Mask Region-based Convolutional Neural Network (Mask R-CNN) algorithms to quantitatively calculate both the number of debris particles and their coverage areas. The improvement on the Mask R-CNN focuses on two key aspects: enhancing feature extraction through the feature pyramid network structure and integrating attention mechanisms. The most suitable attention mechanism for wear debris detection was determined through ablation experiments. The improved Mask R-CNN combined with the Convolutional Block Attention Module achieves the best Mean Pixel Accuracy of 87.63% at a processing speed of 7.6 frames per second, demonstrating its high accuracy and efficiency in wear particle segmentation. Furthermore, the quantitative and qualitative analysis of wear debris, including the number and area of debris particles and their classification, provides valuable insights into the severity of wear. These insights are essential for understanding the extent of wear damage and guiding maintenance decisions. Full article

With advancements in hardware, high-quality head-mounted display (HMD) devices are being developed by numerous companies, driving increased consumer interest in AR, VR, and MR applications. This proliferation of HMD devices opens up possibilities for a wide range of applications beyond entertainment. Most commercially available HMD devices are equipped with internal inward-facing cameras to record the periocular areas. Given the nature of these devices and captured data, many applications such as biometric authentication and gaze analysis become feasible. To effectively explore the potential of HMDs for these diverse use-cases and to enhance the corresponding techniques, it is essential to have an HMD dataset that captures realistic scenarios. In this work, we present a new dataset of periocular videos acquired using a virtual reality headset called VRBiom. The VRBiom, targeted at biometric applications, consists of 900 short videos acquired from 25 individuals recorded in the NIR spectrum. These 10 s long videos have been captured using the internal tracking cameras of Meta Quest Pro at 72 FPS. To encompass real-world variations, the dataset includes recordings under three gaze conditions: steady, moving, and partially closed eyes. We have also ensured an equal split of recordings without and with glasses to facilitate the analysis of eye-wear. These videos, characterized by non-frontal views of the eye and relatively low spatial resolutions ($400\times 400$), can be instrumental in advancing state-of-the-art research across various biometric applications. The VRBiom dataset can be utilized to evaluate, train, or adapt models for biometric use-cases such as iris and/or periocular recognition and associated sub-tasks such as detection and semantic segmentation. In addition to data from real individuals, we have included around 1100 presentation attacks constructed from 92 PA instruments. These PAIs fall into six categories constructed through combinations of print attacks (real and synthetic identities), fake 3D eyeballs, plastic eyes, and various types of masks and mannequins. These PA videos, combined with genuine (bona fide) data, can be utilized to address concerns related to spoofing, which is a significant threat if these devices are to be used for authentication. The VRBiom dataset is publicly available for research purposes related to biometric applications only. Full article

Traditional VO_2max testing methods are often impractical for manual wheelchair users, as they rely on lower-body exercise protocols, require specialized equipment, and trained personnel. The 6-Minute Push Test (6MPT) is a widely used cardiovascular assessment that may provide a feasible alternative for estimating aerobic capacity in this population. This study aimed to develop a predictive model for VO_2max using physiological variables recorded during the 6MPT. Twenty-eight participants (14 novice and 14 expert manual wheelchair users) completed the test while wearing a VO₂ mask and heart rate monitor. Spearman correlation analysis showed that distance covered during the 6MPT significantly correlated with VO_2max (r = 0.685, p < 0.001). A stepwise linear regression identified two predictive models: one using distance alone (R² = 0.416, p < 0.001) and another incorporating both distance and maximum heart rate (R² = 0.561, p < 0.001). These models offer practical estimations of VO_2max, eliminating separate protocols. Our findings suggest that the 6MPT can serve as a simple, cost-effective alternative to laboratory-based VO₂ testing, facilitating routine cardiovascular fitness assessments for manual wheelchair users in clinical and community settings. Future research should focus on validating these models in a larger, more diverse cohort to enhance their generalizability. Full article

Background/Objectives: Mask-wearing-induced discomfort often leads to unconscious loosening of the mask to relieve the discomfort, thereby compromising protective efficacy. This study investigated how leakage flows affect mask-associated thermoregulation and vapor trapping to inform better mask designs. An integrated ambience–mask–face–airway model with various mask-wearing misfits was developed. Methods: The transient warming/cooling effects, thermal buoyancy force, tissue heat generation, vapor phase change, and fluid/heat/mass transfer through a porous medium were considered in this model, which was validated using Schlieren imaging, a thermal camera, and velocity/temperature measurements. Leakages from the top and side of the mask were analyzed in comparison to a no-leak scenario under cyclic respiration conditions. Results: A significant inverse relationship was observed between mask leakage and facial temperature/humidity. An equivalent impact from buoyancy forces and exhalation flow inertia was observed both experimentally and numerically, indicating a delicate balance between natural convection and forced convection, which is sensitive to leakage flows and critical in thermo-humidity regulation. For a given gap, the leakage fraction was not constant within one breathing cycle but constantly increased during exhalation. Persistently higher temperatures were found in the nose region throughout the breathing cycle in a sealed mask and were mitigated during inhalation when gaps were present. Vapor condensation occurred within the mask medium during exhalation in all mask-wearing cases. Conclusions: The thermal and vapor temporal variation profiles were sensitive to the location of the gap, highlighting the feasibility of leveraging temperature and relative humidity to test mask fit and quantify leakage fraction. Full article

By 2050, 700 million people will have hearing loss, requiring rehabilitation services. For about 80% of deaf and hard-hearing individuals, face coverings hinders their ability to lip-read. Also, the normal hearing population experiences issues socializing when wearing face masks. Therefore, there is a need to evaluate and further develop transparent face masks. In this work, the properties of polymers used in ten commercial transparent face masks were determined. The chemical composition of the polymers including nose bridges and ear loops was determined by FTIR spectroscopy. The focus of the characterizations was on the polymers in the transparent portion of each face mask. In half of the masks, the transparent portion contained PET, while in the other masks it consisted of PETG, PC, iPP, PVC, or SR (silicone rubber). Most masks had been coated with anti-fog material, and a few with scratch-resistant compounds, as indicated by XRF/EDX, SEM/EDX, and contact angle measurements. Thermal, molecular weight, and mechanical properties were determined by TGA/DSC, SEC, and tensile tests, respectively. To measure optical properties, UV-Vis reflectance and UV-Vis haze were applied. An assessment of the ten masks and recommendations to develop better transparent face masks were made, including improvement of their sustainability. Full article

Personal protective equipment (PPE) is crucial for infection prevention and is effective only when worn correctly and consistently. Health organizations often use education or inspections to mitigate non-compliance, but these are costly and have limited success. This study developed a novel on-device, AI-based computer vision system to monitor healthcare worker PPE adherence in real time. Using a custom-built image dataset of 7142 images of 11 participants wearing various combinations of PPE (mask, gloves, gown), we trained a series of binary classifiers for each PPE item. By utilizing a lightweight MobileNetV3 model, we optimized the system for edge computing on a Raspberry Pi 5 single-board computer, enabling rapid image processing without the need for external servers. Our models achieved high accuracy in identifying individual PPE items (93–97%), with an overall accuracy of 85.58 ± 0.82% when all items were correctly classified. Real-time evaluation with 11 unseen medical staff in a cardiac intensive care unit demonstrated the practical viability of our system, maintaining a high per-item accuracy of 87–89%. This study highlights the potential for AI-driven solutions to significantly improve PPE compliance in healthcare settings, offering a cost-effective, efficient, and reliable tool for enhancing patient safety and mitigating infection risks. Full article

Background/Objectives: The COVID-19 pandemic has significantly affected children’s lives, particularly preschool-aged children who undergo rapid biological and psychosocial development. This study aimed to investigate the effects of the COVID-19 pandemic on the language skills of preschool children in Greece. Methods: To that end, a widely used screening tool was applied in a screening project involving 213 preschoolers. Language skills were assessed in three groups of children aged 2–4 years old before, during and after the pandemic. Results: A significant increase in the number of children with atypical language skills profile was identified in relation to the preschoolers after the pandemic versus those before or during the pandemic period. A higher prevalence of atypical profiles was observed in girls than in boys. Interestingly, an increase in the number of successfully produced or repeated words and pseudowords, along with enhanced expressive abilities, was observed during the pandemic compared to the periods before and after. Conclusions:Our findings suggest that post-pandemic preschool children exhibit higher rates of atypical language skill profiles compared to those assessed before and during the pan-demic. Given the importance of language development as a critical aspect of children’s overall personality and well-being, further research is needed to explore the impact of specific pandemic-related factors on language competency. These factors include mask-wearing, increased screen time, reduced social interaction and exposure to language-rich environments, as well as impaired mental health and parental distress. Additionally, personalized interventions should be developed to support healthier developmental outcomes. Full article

The use of non-pharmaceutical interventions (NPIs) was imperative to avoid prolonged school closures during the COVID-19 pandemic. The purpose of this study was to understand the levels of adherence to and attitudes towards NPIs from February 2021 to December 2023 in schools in Ontario, Canada. Participants reported how frequently they, their coworkers, and their students used five NPIs: hand hygiene, covering coughs, staying home when ill, wearing a mask, and physically distancing. Open text comments provided participants with the option to provide additional details. Our mixed methods approach incorporated a series of descriptive statistics calculated at consecutive time points and thematic analysis. Participants reported higher adherence to NPIs than their coworkers and students, with less than perfect adherence that declined over time. Six themes emerged from the qualitative analysis on NPI use in schools: (1) the influence of time; (2) managing competing priorities; (3) a lack of enabling factors; (4) a lack of reinforcing factors; (5) the responsive use of NPIs; and (6) an emotional toll. To reduce the transmission of future communicable diseases and resultant staff and student sick days, ongoing commitment to hand hygiene, covering coughs, and staying home when ill is required. Full article