Search Results (5,356)

To improve collision risk prediction in high-traffic coastal waters and support real-time decision-making in maritime navigation, this study proposes a regional collision risk prediction system integrating the Computed Distance at Collision (CDC) method with an Adaptive Neuro-Fuzzy Inference System (ANFIS). Unlike Distance at Closest Point of Approach (DCPA), which depends on the position of Global Positioning System (GPS) antennas, Computed Distance at Collision (CDC) directly reflects the actual hull shape and potential collision point. This enables a more realistic assessment of collision risk by accounting for the hull geometry and boundary conditions specific to different ship types. The system was designed and validated using ship motion simulations involving bulk and container ships across varying speeds and crossing angles. The CDC method was used to define collision, almost-collision, and near-collision situations based on geometric and hydrodynamic criteria. Subsequently, the FIS–CDC model was constructed using the ANFIS by learning patterns in collision time and distance under each condition. A total of four input variables—ship speed, crossing angle, remaining time, and remaining distance—were used to infer the collision risk index (CRI), allowing for a more nuanced and vessel-specific assessment than traditional CPA-based indicators. Simulation results show that the time to collision decreases with higher speeds and increases with wider crossing angles. The bulk carrier exhibited a wider collision-prone angle range and a greater sensitivity to speed changes than the container ship, highlighting differences in maneuverability and risk response. The proposed system demonstrated real-time applicability and accurate risk differentiation across scenarios. This research contributes to enhancing situational awareness and proactive risk mitigation in Maritime Autonomous Surface Ship (MASS) and Vessel Traffic System (VTS) environments. Future work will focus on real-time CDC optimization and extending the model to accommodate diverse ship types and encounter geometries. Full article

Emotion regulation is essential for mental health. However, many people ignore their own emotional regulation or are deterred by the high cost of psychological counseling, which poses significant challenges to making effective support widely available. This review systematically examines the convergence of multimodal sensing technologies and large language models (LLMs) for the development of Automated Emotional Regulation (AER) systems. The review draws upon a comprehensive analysis of the existing literature, encompassing research papers, technical reports, and relevant theoretical frameworks. Key findings indicate that multimodal sensing offers the potential for rich, contextualized data pertaining to emotional states, while LLMs provide improved capabilities for interpreting these inputs and generating nuanced, empathetic, and actionable regulatory responses. The integration of these technologies, including physiological sensors, behavioral tracking, and advanced LLM architectures, presents the improvement of application, moving AER beyond simpler, rule-based systems towards more adaptive, context-aware, and human-like interventions. Opportunities for personalized interventions, real-time support, and novel applications in mental healthcare and other domains are considerable. However, these prospects are counterbalanced by significant challenges and limitations. In summary, this review synthesizes current technological advancements, identifies substantial opportunities for innovation and application, and critically analyzes the multifaceted technical, ethical, and practical challenges inherent in this domain. It also concludes that while the integration of multimodal sensing and LLMs holds significant potential for AER, the field is nascent and requires concerted research efforts to realize its full capacity to enhance human well-being. Full article

Background/Objectives: Physical activity is a cornerstone of diabetes mellitus (DM) management and is strongly recommended in the American Diabetes Association (ADA)’s guidelines. This study aims to investigate the self-reported physical activity levels of individuals with DM in Germany, as well as the barriers and facilitators they encounter. Methods: Individuals with type 1 DM (T1DM) and type 2 DM (T2DM) were asked to fill out an online questionnaire that was partly based on the International Physical Activity Questionnaire (IPAQ). Results: The questionnaire was completed by 338 persons with either T1DM (57.1%) or T2DM (42.9%) (females: 56.2%, males: 42.0%, gender diverse persons: 1.8%) of all age groups (at least 18 years). In total, 80.5% of respondents were aware of the current physical activity recommendations. Among the respondents, 58% reported meeting the recommendations for endurance-type physical activity, while only 30.5% reported meeting those for strength training. The three most frequently cited barriers to physical activity were lack of time, lack of motivation and current state of health. Supporting factors included coverage of costs, availability of exercise programs in close proximity to the patient’s home and target group specific exercise programs. Conclusions: The results imply that many individuals with DM in Germany do not meet ADA’s physical activity recommendations, especially considering that self-reports often overestimate actual behavior. In particular, the actual number of individuals who regularly engage in strength training may be too low. There is a clear need to better communicate the benefits of different forms of physical training and to provide physical activity programs aligned with patients’ individual needs. Full article

Multimodal sentiment analysis (MSA) faces key challenges such as incomplete modality inputs, long-range temporal dependencies, and suboptimal fusion strategies. To address these, we propose MGMR-Net, a Mamba-guided multimodal reconstruction and fusion network that integrates modality-aware reconstruction with text-centric fusion within an efficient state-space modeling framework. MGMR-Net consists of two core components: the Mamba-collaborative fusion module, which utilizes a two-stage selective state-space mechanism for fine-grained cross-modal alignment and hierarchical temporal integration, and the Mamba-enhanced reconstruction module, which employs continuous-time recurrence and dynamic gating to accurately recover corrupted or missing modality features. The entire network is jointly optimized via a unified multi-task loss, enabling simultaneous learning of discriminative features for sentiment prediction and reconstructive features for modality recovery. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that MGMR-Net consistently outperforms several baseline methods under both complete and missing modality settings, achieving superior accuracy, robustness, and generalization. Full article

In response to the stress commonly experienced by young people in high-pressure daily environments, a music-based stress-relief interactive system was developed by integrating music-assisted care with emotion-sensing technology. The design principles of the system were established through a literature review on stress, music listening, emotion detection, and interactive devices. A prototype was created accordingly and refined through interviews with four experts and eleven users participating in a preliminary experiment. The system is grounded in a four-stage guided imagery and music framework, along with a static activity model focused on relaxation-based stress management. Emotion detection was achieved using a wearable EEG device (NeuroSky’s MindWave Mobile device) and a two-dimensional emotion model, and the emotional states were translated into visual representations using seasonal and weather metaphors. A formal experiment involving 52 users was conducted. The system was evaluated, and its effectiveness confirmed, through user interviews and questionnaire surveys, with statistical analysis conducted using SPSS 26 and AMOS 23. The findings reveal that: (1) integrating emotion sensing with music listening creates a novel and engaging interactive experience; (2) emotional states can be effectively visualized using nature-inspired metaphors, enhancing user immersion and understanding; and (3) the combination of music listening, guided imagery, and real-time emotional feedback successfully promotes emotional relaxation and increases self-awareness. Full article

Landslide displacement prediction is crucial for disaster mitigation, yet traditional methods often fail to capture the complex, non-stationary spatiotemporal dynamics of slope evolution. This study introduces an enhanced prediction framework that integrates multi-scale signal processing with dynamic, geology-aware graph modeling. The proposed methodology first employs the Maximum Overlap Discrete Wavelet Transform (MODWT) to denoise raw Global Navigation Satellite System (GNSS)-monitored displacement time series data, enhancing the underlying deformation features. Subsequently, a geology-aware graph is constructed, using the temporal correlation of displacement series as a practical proxy for physical relatedness between monitoring nodes. The framework’s core innovation lies in a dynamic graph optimization model with low-rank constraints, which adaptively refines the graph topology to reflect time-varying inter-sensor dependencies driven by factors like mining activities. Experiments conducted on a real-world dataset from an active open-pit mine demonstrate the framework’s superior performance. The DCRNN-proposed model achieved the highest accuracy among eight competing models, recording a Root Mean Square Error (RMSE) of 2.773 mm in the Vertical direction, a 39.1% reduction compared to its baseline. This study validates that the proposed dynamic graph optimization approach provides a robust and significantly more accurate solution for landslide prediction in complex, real-world engineering environments. Full article

Path planning algorithms for mobile robots and autonomous systems have advanced considerably, yet challenges remain in navigating complex environments while satisfying non-holonomic constraints and achieving precise target orientation. Phase portraits are traditionally used to analyse dynamical systems via equilibrium points and system trajectories, and can be a powerful framework for addressing these challenges. In this work, we propose a novel orientation-aware path planning algorithm that uses phase portrait dynamics by treating both obstacles and target poses as equilibrium points within the environment. Unlike conventional approaches, our method explicitly incorporates non-holonomic constraints and target orientation requirements, resulting in smooth, feasible trajectories with high final pose accuracy. Simulation results across 28 diverse scenarios show that our method achieves zero final orientation error with path lengths comparable to Hybrid A*, and planning times reduced by $52\%$ on the indoor map and $84\%$ on the playpen map relative to Hybrid A*. These results highlight the potential of phase portrait-based planning as an effective and efficient method for real-time autonomous navigation. Full article

Objectives: This study assessed the effectiveness of a cognitive behavioral therapy (CBT)-based fine dust education program, grounded in the Health Belief Model (HBM), on elementary students’ fine dust knowledge, related behaviors, and mental health (depression, anxiety, stress, sleep quality). Methods: From September to November 2024, 95 students (grades 4–6) living near a coal-fired power plant in midwestern South Korea were assigned to either an intervention group (n = 44) or a control group (n = 51). The intervention group completed a three-session CBT-based education program; the control group received stress management education. Assessments were conducted at weeks 1, 2, 4, and 8 using standardized mental health and behavior scales (PHQ: Patient Health Questionnaire, GAD: Generalized Anxiety Disorder Assessment, PSS: Perceived Stress Scale, ISI: Insomnia Severity Index). Results: A chi-square test was conducted to compare pre- and post-test changes in knowledge and behavior related to PM2.5. The intervention group showed significant improvements in seven fine dust-related knowledge and behavior items (e.g., PM2.5 awareness rose from 33.3% to 75.0%; p < 0.05). The control group showed limited gains. Regarding mental health, based on a mixed-design ANCOVA, anxiety scores significantly declined over time in the intervention group, with group and interaction effects also significant (p < 0.05). Depression scores showed time effects, but group and interaction effects were not significant. No significant changes were observed for stress, sleep, or group × PM2.5 interactions. Conclusions: The CBT-based education program effectively enhanced fine dust knowledge, health behaviors, and reduced anxiety among students. It presents a promising, evidence-based strategy to promote environmental and mental health in school-aged children. Full article

To enable safe and effective human–robot collaboration (HRC) in smart manufacturing, it is critical to seamlessly integrate sensing, cognition, and prediction into the robot controller for real-time awareness, response, and communication inside a heterogeneous environment (robots, humans, and equipment). The proposed approach takes advantage of the prediction capabilities of nonlinear model predictive control (NMPC) to execute safe path planning based on feedback from a vision system. To satisfy the requirements of real-time path planning, an embedded solver based on a penalty method is applied. However, due to tight sampling times, NMPC solutions are approximate; therefore, the safety of the system cannot be guaranteed. To address this, we formulate a novel safety-critical paradigm that uses an exponential control barrier function (ECBF) as a safety filter. Several common human–robot assembly subtasks have been integrated into a real-life HRC assembly task to validate the performance of the proposed controller and to investigate whether integrating human pose prediction can help with safe and efficient collaboration. The robot uses OptiTrack cameras for perception and dynamically generates collision-free trajectories to the predicted target interactive position. Results for a number of different configurations confirm the efficiency of the proposed motion planning and execution framework, with a 23.2% reduction in execution time achieved for the HRC task compared to an implementation without human motion prediction. Full article

Prescriptive Maintenance (PsM) transforms industrial asset management by enabling autonomous decisions through simultaneous failure anticipation and optimal maintenance recommendations. Yet, despite increasing research interest, the conceptual clarity, technological maturity, and practical deployment of PsM remains fragmented. Here, we conduct a comprehensive and application-oriented Systematic Literature Review of studies published between 2013–2024. We identify key enablers—artificial intelligence and machine learning, horizontal and vertical integration, and deep reinforcement learning—that map the functional space of PsM across industrial sectors. The results from our multivariate meta-synthesis uncover three main thematic research clusters, ranging from decision-automation of technical (multi)component-level systems to strategic and organisational-support strategies. Notably, while predictive models are widely adopted, the translation of these capabilities to PsM remains limited. Primary reasons include semantic interoperability, real-time optimisation, and deployment scalability. As a response, a structured research agenda is proposed to emphasise hybrid architectures, context-aware prescription mechanisms, and alignment with Industry 5.0 principles of human-centricity, resilience, and sustainability. The review establishes a critical foundation for future advances in intelligent, explainable, and action-oriented maintenance systems. Full article

The growth and sustainability of today’s global economy heavily relies on smooth maritime operations. The increasing security concerns to marine environments pose complex security challenges, such as smuggling, illegal fishing, human trafficking, and environmental threats, for traditional surveillance methods due to their limitations. Artificial intelligence (AI), particularly deep learning, has offered strong capabilities for automating object detection, anomaly identification, and situational awareness in maritime environments. In this paper, we have reviewed the state-of-the-art deep learning models mainly proposed in recent literature (2020–2025), including convolutional neural networks, recurrent neural networks, Transformers, and multimodal fusion architectures. We have highlighted their success in processing diverse data sources such as satellite imagery, AIS, SAR, radar, and sensor inputs from UxVs. Additionally, multimodal data fusion techniques enhance robustness by integrating complementary data, yielding more detection accuracy. There still exist challenges in detecting small or occluded objects, handling cluttered scenes, and interpreting unusual vessel behaviours, especially under adverse sea conditions. Additionally, explainability and real-time deployment of AI models in operational settings are open research areas. Overall, the review of existing maritime literature suggests that deep learning is rapidly transforming maritime domain awareness and response, with significant potential to improve global maritime security and operational efficiency. We have also provided key datasets for deep learning models in the maritime security domain. Full article

Cloud computing offers a broad spectrum of services to users, particularly in multi-cloud environments where service-centric features are introduced to support users from multiple endpoints. To improve service availability and optimize the utilization of required services, cloud brokerage has been integrated into multi-cloud systems. The primary objective of a cloud broker is to ensure the quality and outcomes of services offered to customers. However, traditional cloud brokers face limitations in measuring service trust, ensuring validity, and anticipating future enhancements of services across different cloud platforms. To address these challenges, the proposed intelligent cloud broker integrates an intelligence mechanism that enhances decision-making within a multi-cloud environment. This broker performs a comprehensive validation and verification of service trustworthiness by analyzing various trust factors, including service response time, sustainability, suitability, accuracy, transparency, interoperability, availability, reliability, stability, cost, throughput, efficiency, and scalability. Customer feedback is also incorporated to assess these trust factors prior to service recommendation. The proposed model calculates service ranking (SR) values for available cloud services and dynamically includes newly introduced services during the validation process by mapping them with existing entries in the Service Collection Repository (SCR). Performance evaluation using the Google cluster-usage traces dataset demonstrates that the ICB outperforms existing approaches such as the Clustering-Based Trust Degree Computation (CBTDC) algorithm and the Service Context-Aware QoS Prediction and Recommendation (SCAQPR) model. Results confirm that the ICB significantly enhances the effectiveness and reliability of cloud service recommendations for users. Full article

The eastern North Pacific Ocean coastline (from the Salish Sea to the western Aleutian Islands) is highly glaciated with relic sediment deposits scattered throughout a highly contoured and variable bathymetry. Oceanographic conditions feature strong currents and tidal exchange. Sand wave fields are prominent features within these glaciated shorelines and provide critical habitat to sand lance (Ammodytes spp.). Despite an awareness of the importance of these benthic habitats, attributes related to their structure and characteristics remain undocumented. We explored the micro-bathymetric morphology of a subtidal sand wave field known to be a consistent habitat for sand lance. We calculated geomorphic attributes of the bedform habitat, analyzed sediment composition, and measured oceanographic properties of the associated water column. This feature has a streamlined teardrop form, tapered in the direction of the predominant tidal current. Consistent flow paths along the long axis contribute to well-defined and maintained bedform morphology and margin. Distinct patterns in amplitude and period of sand waves were documented. Strong tidal exchange has resulted in well-sorted medium-to-coarse-grained sediments with coarser sediments, including gravel and cobble, within wave troughs. Extensive mixing related to tidal currents results in a highly oxygenated water column, even to depths of 80 m. Our analysis provides unique insights into the physical characteristics that define high-quality habitat for these fish. Further work is needed to identify, enumerate, and map the presence and relative quality of these benthic habitats and to characterize the oceanographic properties that maintain these benthic habitats over time. Full article

The converter valve is the core component of the ultra-high voltage direct current (UHVDC) transmission system, and its fault detection is very important to ensure the safe and stable operation of the transmission system. However, the voiceprint signals collected by converter stations under complex operating conditions are often affected by background noise, spikes, and nonlinear interference. Traditional methods make it difficult to achieve high-precision detection due to the lack of feature extraction ability and poor noise robustness. This paper proposes a fault-aware variational self-encoder model (FAVAE-AS) based on a weak correlation between attention and self-supervised learning. It extracts probability features via a conditional variational autoencoder, strengthens feature representation using multi-layer convolution and residual connections, and introduces a weak correlation attention mechanism to capture global time point relationships. A self-supervised learning module with six signal transformations improves generalization, while KL divergence-based correlation inconsistency quantization with dynamic thresholds enables accurate anomaly detection. Experiments show that FAVAE-AS achieves 0.925 accuracy in fault detection, which is 5% higher than previous methods, and has strong robustness. This research provides critical technical support for UHVDC system safety by addressing converter valve acoustic anomaly detection. It proposes an extensible framework for industrial intelligent maintenance. Full article

Teleoperation emerged as a promising fallback for situations beyond the capabilities of automated vehicles. Nevertheless, teleoperation still faces challenges, such as reduced situational awareness. Since situational awareness is primarily built through the remote operator’s visual perception, the graphical user interface (GUI) design is critical. In addition to video feed, supplemental informational elements are crucial—not only for the predominantly studied remote driving, but also for emerging desk-based remote assistance concepts. This work develops a GUI for different teleoperation concepts by identifying key informational elements during the teleoperation process through expert interviews (N = 9). Following this, a static and dynamic GUI prototype was developed and evaluated in a click dummy study (N = 36). Thereby, the dynamic GUI adapts the number of displayed elements according to the teleoperation phase. Results show that both GUIs achieve good system usability scale (SUS) ratings, with the dynamic GUI significantly outperforming the static version in both usability and task completion time. However, the results might be attributable to a learning effect due to the lack of randomization. The user experience questionnaire (UEQ) score shows potential for improvement. To enhance the user experience, the GUI should be evaluated in a follow-up study that includes interaction with a real vehicle. Full article