Search Results (314)

Car accidents remain a leading cause of death worldwide, with drowsiness and distraction accounting for roughly 25% of fatal crashes in Ecuador. This study presents a real-time driver monitoring system that uses computer vision and deep learning to detect fatigue, distraction, and emotions from facial expressions. It combines a MobileNetV2-based CNN trained on RAF-DB for emotion recognition and MediaPipe’s 468 facial landmarks to compute the EAR (Eye Aspect Ratio), the MAR (Mouth Aspect Ratio), the gaze, and the head pose. Tests with 27 participants in both real and simulated driving environments showed strong results. There was a 100% accuracy in detecting distraction, 85.19% for yawning, and 88.89% for eye closure. The system also effectively recognized happiness (100%) and anger/disgust (96.3%). However, it struggled with sadness and failed to detect fear, likely due to the subtlety of real-world expressions and limitations in the training dataset. Despite these challenges, the results highlight the importance of integrating emotional awareness into driver monitoring systems, which helps reduce false alarms and improve response accuracy. This work supports the development of lightweight, non-invasive technologies that enhance driving safety through intelligent behavior analysis. Full article

The thoracolumbar region affects 60 to 80% of the 4 million spine fractures occurring annually, making them a global health threat. Management has evolved from early fixation systems to minimally invasive techniques, reducing muscle trauma and recovery time. Fractures are classified into compression, distraction, and translation types, with stability guiding treatment decisions. Surgical options include open and minimally invasive procedures, each with benefits and drawbacks. The choice of treatment depends on fracture type, neurological deficits, and patient factors. Advances in technology continue to improve outcomes, but further research is needed to determine optimal management strategies. Full article

Ensuring sustained driver attention is critical for intelligent transportation safety systems; however, the performance of data-driven driver distraction detection models is often limited by the high cost of large-scale manual annotation. To address this challenge, this paper proposes an adaptive semi-supervised driver distraction detection framework based on teacher–student learning and deformable pyramid feature fusion. The framework leverages a limited amount of labeled data together with abundant unlabeled samples to achieve robust and scalable distraction detection. An adaptive pseudo-label optimization strategy is introduced, incorporating category-aware pseudo-label thresholding, delayed pseudo-label scheduling, and a confidence-weighted pseudo-label loss to dynamically balance pseudo-label quality and training stability. To enhance fine-grained perception of subtle driver behaviors, a Deformable Pyramid Sparse Transformer (DPST) module is integrated into a lightweight YOLOv11 detector, enabling precise multi-scale feature alignment and efficient cross-scale semantic fusion. Furthermore, a teacher-guided feature consistency distillation mechanism is employed to promote semantic alignment between teacher and student models at the feature level, mitigating the adverse effects of noisy pseudo-labels. Extensive experiments conducted on the Roboflow Distracted Driving Dataset demonstrate that the proposed method outperforms representative fully supervised baselines in terms of mAP@0.5 and mAP@0.5:0.95 while maintaining a balanced trade-off between precision and recall. These results indicate that the proposed framework provides an effective and practical solution for real-world driver monitoring systems under limited annotation conditions. Full article

Background: Feigned restriction of shoulder joint movement for secondary gain is clinically relevant and may misdirect care, distort disability determinations, and inflate system costs. Distinguishing feigning from structural pathology and from functional or psychosocial presentations is difficult because pain is subjective, performance varies, and no single sign or test is definitive. This comprehensive review hypothesizes that the systematic integration of clinical examination, objective biomechanical and neurophysiological testing, and emerging technologies can substantially improve detection accuracy and provide defensible medicolegal documentation. Methods: PubMed and reference lists were searched within a prespecified time frame (primarily 2015–2025, with foundational earlier works included when conceptually essential) using terms related to shoulder movement restriction, malingering/feigning, symptom validity, effort testing, functional assessment, and secondary gain. Evidence was synthesized narratively, emphasizing objective or semi-objective quantification of motion and effort (goniometry, dynamometry, electrodiagnostics, kinematic sensing, and imaging). Results: Detection is best approached as a stepwise, multidimensional evaluation. First-line clinical assessment focuses on reproducible incongruence: non-anatomic patterns, internal inconsistencies, distraction-related improvement, and mismatch between claimed disability and observed function. Repeated examinations and documentation strengthen inference. Instrumented strength testing improves quantification beyond manual testing but remains effort-dependent; repeat-trial variability and atypical agonist–antagonist co-activation can indicate submaximal performance without proving intent. Imaging primarily tests plausibility by confirming lesions or highlighting discordance between claimed limitation and minimal pathology, while recognizing that normal imaging does not exclude pain. Diagnostic anesthetic injections and electrodiagnostics can clarify pain-mediated restriction or exclude neuropathic weakness but require cautious interpretation. Motion capture and inertial sensors can document compensatory strategies and context-dependent normalization, yet validated standalone thresholds are limited. Conclusions: Feigned shoulder impairment cannot be confirmed by any single test. The desirable strategy combines structured assessment of inconsistencies with objective biomechanical and neurophysiologic measurements, interpreted within the whole clinical context and rigorously documented; however, prospective validation is still needed before routine implementation. Full article

Driving safety under low-visibility or distracted conditions remains a critical challenge for intelligent transportation systems. This paper presents Edge-VisionGuard, a lightweight framework that integrates signal processing and edge artificial intelligence to enhance real-time driver monitoring and hazard detection. The system fuses multi-modal sensor data—including visual, inertial, and illumination cues—to jointly estimate driver attention and environmental visibility. A hybrid temporal–spatial feature extractor (TS-FE) is introduced, combining convolutional and B-spline reconstruction filters to improve robustness against illumination changes and sensor noise. To enable deployment on resource-constrained automotive hardware, a structured pruning and quantization pipeline is proposed. Experiments on synthetic VR-based driving scenes demonstrate that the full-precision model achieves 89.6% driver-state accuracy (F1 = 0.893) and 100% visibility accuracy, with an average inference latency of 16.5 ms. After 60% parameter reduction and short fine-tuning, the pruned model preserves 87.1% accuracy (F1 = 0.866) and <3 ms latency overhead. These results confirm that Edge-VisionGuard maintains near-baseline performance under strict computational constraints, advancing the integration of computer vision and Edge AI for next-generation safe and reliable driving assistance systems. Full article

Early Onset Scoliosis (EOS), defined as presenting before 10 years of age, often has a significant adverse impact on pulmonary function, due to a complex interrelationship between the spine, chest, pulmonary structures and their development. Left untreated, EOS leads to premature death, with early fusion surgery to arrest curve progression making little impact on this. To date, the natural history has not been clearly established as compounded by the heterogeneity of pathologies, causing EOS and challenges in objective measurements of pulmonary function in this young age group. A desire to address this poor natural history has motivated interest in pursuing ‘growth friendly’ surgical strategies. The implants used have evolved with time, often to address compromises and poor results, with multiple options now available based on treatment principles (distraction, compression, or guided growth systems). The aims of such strategies are to control the structural spinal deformity, whilst allowing spinal and thoracic growth, with the seemingly reasonable expectation that this will result in improved pulmonary function and avoidance of premature death. Most studies have focused on radiological outcome measures such as Cobb angle and thoracic height to gauge the success of surgery, with these measures acting as surrogate markers of improved pulmonary outcome. This assumption, however, is not supported by more recent clinical data which has attempted to assess directly the pulmonary outcomes associated with growth-friendly surgical strategies. This literature review therefore sets out to characterise the effect of EOS on pulmonary function and to critically analyse the impact surgical treatment options will have while addressing this. Full article

Background: Postoperative bone healing can be impaired by systemic factors and surgical trauma, leading to delayed recovery. Photobiomodulation therapy (PBMT) has been proposed as a non-invasive method to enhance osteogenesis, but variability in protocols and outcomes limits its clinical use. Aim: To systematically review and synthesize evidence from randomized controlled trials (RCTs) evaluating PBMT’s effectiveness in promoting postoperative osteogenesis. Methods: A systematic search of PubMed, Embase, Scopus, and Cochrane Library was conducted following the PRISMA 2020 guidelines. Only RCTs comparing PBMT with sham treatment or standard care were included. Data on laser parameters, surgical indications, and outcomes such as bone regeneration, healing time, and implant stability were extracted. The risk of bias of the included randomized studies was evaluated using the Cochrane Risk of Bias 2 (RoB version 2) tool. Results: Twelve RCTs were included. PBMT consistently improved early soft tissue healing and reduced postoperative inflammation and edema. Some studies showed accelerated bone maturation, especially in grafted sockets and distraction osteogenesis, while others reported no significant long-term effects on implant stability or chronic lesion healing. Heterogeneity in laser parameters limited comparability. Conclusions: PBMT is a safe adjunct that reliably enhances early postoperative healing and may promote bone remodeling in selected cases. Standardized protocols and larger, high-quality RCTs are needed to confirm long-term benefits and optimize treatment parameters. Full article

Driver distraction, particularly mobile phone use while driving, remains one of the leading causes of road traffic incidents worldwide. In response to this issue and leveraging recent technological advances and increased access to intelligent systems, this research presents the development of an application running on an intelligent embedded architecture for the automatic detection of mobile phone use by drivers, integrating computer vision, inertial sensing, and edge computing. The system, based on the YOLOv8n model deployed on a Jetson Xavier NX 16Gb—Nvidia, combines real-time inference with an inertial activation mechanism and cloud storage via Firebase Firestore, enabling event capture and traceability through a lightweight web-based HMI interface. The proposed solution achieved an overall accuracy of 81%, an inference rate of 12.8 FPS, and an average power consumption of 8.4 W, demonstrating a balanced trade-off between performance, energy efficiency, and thermal stability. Experimental tests under diverse driving scenarios validated the effectiveness of the system, with its best performance recorded during daytime driving—83.3% correct detections—attributed to stable illumination and enhanced edge discriminability. These results confirm the feasibility of embedded artificial intelligence systems as effective tools for preventing driver distraction and advancing intelligent road safety. Full article

Artificial intelligence (AI) is increasingly embedded in education through adaptive platforms, intelligent tutoring systems, and generative tools. While these technologies promise efficiency and personalization, they also raise concerns about pedagogical deskilling, reduced teacher autonomy, and ethical risks. This paper conceptualizes the potential impacts of AI on teaching expertise and instructional design through the lens of Cognitive Load Theory (CLT). The aim is to conceptualize how AI may reshape the management of intrinsic, extraneous, and germane cognitive loads. The study proposes that AI may effectively scaffold intrinsic load and reduce extraneous distractions but displace teacher judgment in ways that undermine germane learning and reflective practice. Additionally, opacity, algorithmic bias, and inequities in access may create new forms of cognitive and ethical burden. The conceptualization presented in this paper contributes to scholarship by foregrounding teacher cognition, an underexplored dimension of AI research, conceptualizing the teacher as a cognitive orchestrator who balances human and algorithmic inputs, and integrating ethical and equity considerations into a cognitive framework. Recommendations are provided for teacher education, policy, and AI design, emphasizing the need for pedagogy-driven integration that preserves teacher expertise and supports deep learning. Full article

To overcome the issues of excessive computation and resource usage in distracted driving detection systems, this study introduces a compact detection framework named YOLOv8s-FPNE, built upon the YOLOv8 architecture. The proposed model incorporates FasterNet, Partial Convolution (PConv) layers, a Normalized Attention Mechanism (NAM), and the Focal-EIoU loss to achieve an optimal trade-off between accuracy and efficiency. FasterNet together with PConv enhances feature extraction while reducing redundancy, NAM strengthens the model’s sensitivity to key spatial and channel information, and Focal-EIoU refines bounding-box regression, particularly for hard-to-detect samples. Experimental evaluations on a public distracted driving dataset show that YOLOv8s-FPNE reduces the number of parameters by 21.7% and computational cost (FLOPS) by 23.6% relative to the original YOLOv8s, attaining an mAP@0.5 of 81.6%, which surpasses existing lightweight detection methods. Ablation analyses verify the contribution of each component, and comparative studies further confirm the advantages of NAM and Focal-EIoU. The results demonstrate that the proposed method provides a practical and efficient solution for real-time distracted driving detection on embedded and resource-limited platforms. Full article

Food waste is a global issue, and Macau is no exception. Throughout this study, it was found that most local bakeries in Macau employed promotional strategies to reduce surplus bread waste; however, a significant amount of unsold bread was still discarded. Meanwhile, as consumer behavior shifts toward environmental consciousness, technologies such as augmented reality (AR) are reshaping market dynamics. Many apps now incorporate the Sustainable Development Goals (SDGs) to raise consumer awareness. Within this context, this study recorded unsold bread types in real-time for four bakeries in Macau and integrated this information into an app system featuring interactive AR scanning technology to engage users and facilitate operations. Applying the Technology Acceptance Model (TAM), this study surveyed 163 local participants in Macau. Users expressed interest in immersive AR experiences that incorporated entertainment elements, allowing them to quickly search for and purchase surplus bread products, thereby reducing bread waste. However, excessive entertainment features were found to distract users from their purchasing goals, causing operational difficulties. Therefore, integrating AR into a well-structured shopping information system with streamlined operations would be more effective than adding excessive entertainment features. Future enhancements could include the addition of a comment section to facilitate discussion of the role of various virtual interactive systems in explaining surplus food concepts through experience. Emphasis should be placed on integrating sustainable practices into emerging technologies to increase users’ environmental awareness and achieve the Sustainable Development Goals. Full article

With the ongoing integration of advanced technologies into modern vehicle systems, understanding user interaction becomes a critical factor for safe and intuitive operation—especially in the transition towards autonomous driving. This article uncovers user-reported challenges of UX and in-vehicle UIs. The analysis is based on quantitative and qualitative evaluations of user-generated content (UGC) from automotive-focused online forums. The quantitative analysis is conducted by Natural Language Processing (NLP), while qualitative evaluation is performed through Mayring, applying a deductive–inductive category formation approach. The study investigates challenges related to interface complexity, driver distraction, and missing user diversity in the context of increasing digitalization. Based on the analysis, a set of practical design implications is presented, emphasizing context-sensitive function reduction, multimodal interface concepts, and UX strategies for reducing complexity. It has become evident that UX concepts in the automotive context can only succeed if they are adaptive, safety-oriented, and tailored to the needs of heterogeneous user groups. This leads to the development of an interaction strategy model, serving as a transitional framework for guiding the shift from manual to fully automated driving scenarios. The paper concludes with an outlook on further research to validate and refine the implications and UX framework. Full article

University website research to date tends to focus on conformity with technical standards. It rarely analyses the systemic nature of digital noise and its cognitive impacts. The study measures the intensity of digital noise on public websites of Polish universities (n = 65) and identifies its most common sources. The author investigates five dimensions: Distraction Intensity, Content Overload, Readability, Visual Balance, and Signal-to-Noise Ratio. The results are aggregated into a synthetic Noise Level Score (NLS) and analysed statistically. Four categories of digital noise have emerged from the observations: obligatory, compensated, ornamental, and habitual. This categorisation indicates that digital noise is not always random. It can be a supervised or even intentionally designed phenomenon when specific elements (such as disclaimers, system alerts, or consent layers) are not only expected but required by the user or the law. The study reveals a highly homogeneous sample and strong convergence of the results, indicating a systemic problem. Over 47% of the websites exhibited high NLS, while only 9% scored low. This means that content, visual, and interaction overloads are not incidental. Instead, it follows from the institutional and technological constraints on Polish higher education. The results ought to be interpreted in the context of the institutional communication imperative, defined as a constant pressure from legal obligations, standards, PR, market, and organisational factors towards constant publishing for multiple audiences through multiple channels. Full article

Background: Myogenous temporomandibular disorders (TMDs) typically present with pain but without obvious restriction of mandibular motion, making subtle dysfunctions difficult to detect clinically. In this study, we evaluated mandibular kinematics in myogenous TMDs using an electronic axiography system (Cadiax Diagnostic). The specific objective of this study was to evaluate whether patients with myogenous temporomandibular disorders exhibit qualitative abnormalities in mandibular movements that are not detectable using conventional clinical examination. Methods: Twenty-six patients with myogenous TMD (muscle pain without intra-articular disorders, diagnosed per DC/TMD) and 26 matched controls were examined. Clinical assessment (DC/TMD Axis I) measured mandibular range of motion and deviations. Instrumental recordings of maximal opening, protrusion, and laterotrusion were obtained with Cadiax 4. Quantitative (excursion ranges) and qualitative (movement symmetry and sagittal deviations) parameters were analyzed. Condylar position changes between the reference position and maximum intercuspation were evaluated (Condyle Position Measurement, CPM). Exact χ² or Fisher tests were applied with effect sizes (φ) and 95% confidence intervals (CI). Results: Maximal opening, lateral excursions, and protrusion ranges were statistically similar between groups (mean opening: 47.96 ± 6.5 mm in TMDs vs. 49.46 ± 5.4 mm in controls, p = 0.40; 95% CI of difference −1.8 to 4.8 mm). However, qualitative deviations were more frequent in TMD. Of note, 12/26 (46.2%) patients vs. 6/26 (23.1%) controls showed a ΔY deflection during protrusion (χ² = 3.06, p = 0.08; φ ≈ 0.24; difference = 23.1%, 95% CI −2.0–48.2%). Identical proportions (46.2% vs. 23.1%) showed a ΔY deflection upon opening (χ² = 3.06, p = 0.08). Inferior condylar shifts (distractions) on closing into intercuspation occurred only in the mTMD group: 5/26 (19.2%) left condyles vs. 0% (p ≈ 0.05; 95% CI diff 4.1–34.4%) and 2/26 (7.7%) right vs. 0% (p ≈ 0.49; 95% CI −2.5–17.9%). Condylar compressions (superior shifts) were similar between groups. In summary, roughly half of TMD patients exhibited lateral jaw deflections (ΔY) and exclusive condylar “distraction” on closure; upon comparison, these conditions were rare in controls. Conclusions: Despite normal mandibular range of motion, patients with myogenous TMDs exhibited qualitative abnormalities in jaw kinematics, including movement deflections, condylar asymmetries, and centric–intercuspal discrepancies. Axiographic analysis with Cadiax enabled detection of subtle functional changes not identifiable in routine examinations, underscoring its diagnostic value in early dysfunction and potential therapeutic planning. The detection of kinematic abnormalities could influence early diagnosis or treatment planning for myogenous TMDs. Full article

In the dynamic and complex environment of highly automated vehicles, ensuring driver safety is the most critical task. While automation promises to reduce human error, the driver’s role is shifting to that of a teammate who must remain vigilant and ready to intervene, making it essential to monitor their attention level. However, a significant challenge in this domain is the considerable inter-individual variability in how people physiologically respond to cognitive states, such as distraction. This study addresses this by developing a methodology that first groups drivers into distinct physiology-based clusters before training a predictive model. The study was conducted in a high-fidelity driving simulator, where multimodal data streams, including heart rate variability and electrodermal activity, were collected from 30 participants during conditional-automated driving experiments. Using a time-series k-means clustering algorithm, the researchers successfully partitioned the drivers into clusters based on their physiological and behavioral patterns, which did not correlate with demographic factors. Then, a Long Short-Term Memory model was trained for each cluster, which achieved similar predictive performance compared to a single, generalized model. This finding demonstrates that a personalized, cluster-based approach is feasible for physiology-based driver monitoring, providing a robust and replicable solution for developing accurate and reliable attention estimation systems. Full article