Situational Awareness Research Articles

AI and IoT-Based Frameworks for Real-Time Crowd Monitoring and Security

Effective crowd management is critical for ensuring public safety during large-scale events and in densely populated urban environments. Recent advances in deep learning and computer vision have enabled real-time crowd behavior analysis, including the detection of abnormal actions such as pushing, which can lead to dangerous situations. This paper presents a review of cloud-based deep learning frameworks, focusing on the use of convolutional neural networks (CNN) and optical flow models for early detection of pushing behavior in crowded event entrances. We discuss the integration of pre-trained deep models with live video stream processing to achieve high accuracy and low latency. Existing datasets and evaluation metrics are examined, with reported detection accuracies reaching up to 87%. The review also highlights challenges such as data privacy, real-time processing constraints, and the need for comprehensive models that consider multiple behavioral and environmental factors. Finally, future directions are proposed for developing autonomous crowd safety systems that mimic human situational awareness in complex urban settings.

A miniaturized augmented reality head‐up display system based on real‐time holographic with dynamic depth variation

Abstract Augmented reality head‐up display (AR‐HUD) systems utilizing computer‐generated hologram technology have emerged as a focal point of optical innovation. Traditional display systems often rely on arrays of projectors or multiple spatial light modulators (SLMs) for multidepth projection; thus, these systems are typically complex and expensive. To address these challenges, the present study developed a miniaturized AR‐HUD system that integrates an advanced driver assistance system (ADAS) with holographic display technology. By leveraging a single SLM for spatial multiplexing, this AR‐HUD system achieves a streamlined design, enhancing real‐time data visualization and situational awareness. The proposed AR‐HUD system has a simple architecture and relatively low costs, and it advances driving safety and convenience by dynamically adjusting the depth of holographic images through deep learning techniques.

AI Enhanced Smart Surveillance

Abstract— To address the growing limitations of traditional surveillance systems, such as delayed response times, human error, and a lack of proactive monitoring, this project introduces an AI-driven smart surveillance system designed to detect and mitigate illegal activities such as theft, violations, accidents, and fighting in real time. Using advanced deep learning techniques such as YOLOv11 for precise object detection and autoencoders for anomaly detection, the system accurately identifies suspicious behaviors and sends instant alerts, including phone calls, to authenticated personnel, along with the incident location. The system's capacity to automate threat detection and response considerably decreases the need for manual monitoring, shortens response times, and improves overall security efficiency. Integrating real-time video analysis and cloud-based data storage. The system ensures scalability and seamless deployment across a variety of scenarios. Key findings illustrate the system's high precision in detecting and classifying numerous security concerns, allowing for prompt intervention via timely notifications. This study tackles important holes in modern surveillance by providing a scalable, flexible, and efficient approach that improves situational awareness and threat prevention. This initiative, which combines cutting-edge AI technology with real-time alert systems, lays the way for safer, more secure surroundings in both public and private places, representing a significant leap in the field of smart surveillance. KEYWORDS: Smart Surveillance, Artificial Intelligence (AI), Real-Time Threat Detection, YOLOv11, Anomaly Detection, Facial Recognition, Behavior Analysis, Cloud-Based Surveillance, Autonomous Monitoring, Theft Detection, Tamper Detection, Real-Time Alerts, Deep Learning, Machine Learning (ML), Video Analytics, Security Automation, Proactive Surveillance, Unlawful Activity Detection, Situational Awareness

Teaching pointing and calling (Shisa Kanko) to reduce error and improve performance

Paramedics operate in high-stakes, cognitively demanding environments where lapses in attention can jeopardize patient safety. While team-based communication strategies are commonly taught, there is a need for self-directed methods that support situational awareness and error prevention. ‘Pointing and Calling’ (P&C) is a Japanese technique that uses verbal and physical cues to heighten conscious attention and reduce mistakes. P&C was integrated into the Advanced Care Paramedic curriculum over three weeks covering conceptual instruction, guided practice through low-stakes activities, and application in high-fidelity simulations. Students employed P&C during critical tasks and received feedback during debriefings. Evaluation using the Kirkpatrick framework showed positive engagement, skill uptake, and transfer to other learning contexts. Several key lessons were identified for implementing training on P&C, including clarifying that P&C is a personal cognitive tool, not a directive to others. P&C’s simplicity, low cost, and existing evidence support implementation across healthcare settings. P&C can be effective in low and high-resource environments alike. P&C represents a practical, scalable approach to improving patient safety.

Humans’ Use of AI Assistance: The Effect of Loss Aversion on Willingness to Delegate Decisions

As artificial intelligence (AI) tools have become pervasive in business applications, so too have interactions between AI and humans in business processes and decision-making. A growing area of research has focused on human decision and task delegation to AI assistants. Simultaneously, extensive research on algorithm aversion—humans’ resistance to algorithm-based decision tools—has demonstrated potential barriers and issues with AI applications in business. In this paper, we test a simple strategy for mitigating algorithm aversion in the context of AI task delegation. We show that simply changing the framing of decision tasks can allay algorithm aversion. Through multiple studies, we found that participants exhibited a strong preference for human assistance over AI assistance when they were rewarded for task performance (i.e., money was gained for good performance), even when the AI had been shown to outperform the human assistant on the task. Alternatively, when we reframed the task such that the participant experienced losses for poor performance (i.e., money was taken from their endowment for poor performance), the bias for preferring human assistance was removed. Under loss framing, participants delegated the decision task to human and AI assistants at similar rates. We demonstrate this finding across tasks at differing levels of complexity and at different incentive sizes. We also provide evidence that loss framing increases situational awareness, which drives the observed effects. Our results offer useful insights on reducing algorithm aversion that extend the literature and provide actionable suggestions for practitioners and managers. This paper has been This paper was accepted by Dongjun Wu for the Special Issue on the Human-Algorithm Connection. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.05585 .

Trajectrack: Intelligent Trajectory Estimation, Speed Analysis, and Lane Detection for Autonomous Vehicles

Autonomous vehicles (AVs) need complex perception systems for safe operation under dynamic traffic scenes. We introduce TrajecTrack, a machine learning-based platform that integrates real-time trajectory estimation, velocity estimation and lane detection from LiDAR and vision inputs. We apply DBSCAN clustering and the constant velocity model for predicted trajectories, with our speed estimation based on YOLOv8 and ByteTrack, plus a new module for lane detection based on edge detection and the Hough transform. Compared to the NuScenes dataset and sample video input, TrajecTrack provides high-accuracy visualizations of the trajectories, velocities and road lane markings and therefore improves the situational awareness of AVs. This paper contributes significantly to the field of AV perception in that it supports a scalable single solution, with future implications being in traffic violative detection.

The Future of Crisis Response Training: AI-Generated Feedback for Incident Commanders?

In today’s complex crisis landscape, effective incident command training relies on dynamic decision-making assessment frameworks. However, the Effective Command Behavioral Marker Framework (EC) momentarily demands a lot from human assessors, who must evaluate 72 criteria across a 5-point scale, leading to excessive cognitive load. This study explores whether AI-generated written feedback can support in the future assessors and possibly enhance learning outcomes by providing structured, data-driven insights of command training. We examine the assessment results from 85 incident commanders solutions to a virtual simulation ”School Fire” scenario. Key challenges brought out in the feedback included delayed decision-making, inter-agency coordination gaps, and situational awareness deficits. While expert feedback is valuable, the time constraints for compiling the written feedback create a discrepancy in the length and quality of the provided feedback. This study explores how AI can complement human assessor’s by reducing cognitive overload and enhancing incident command training through structured, data-driven feedback that supports assessors s expert judgment. Dynamic decision-making feedback systems using Human-AI collaboration may redefine training methodologies for next-generation incident commanders.

SAS-KNN-DPC: A Novel Algorithm for Multi-Sensor Multi-Target Track Association Using Clustering

The track-to-track association (T2TA) problem is a fundamental and critical challenge in information fusion, situational awareness, and target tracking. Existing algorithms based on statistical mathematics, fuzzy mathematics, gray theory, and artificial intelligence suffer from several limitations that are hard to solve, such as over-idealized models, unrealistic assumptions, insufficient real-time performance, and high computational complexity due to pairwise matching requirements. Considering these limitations, we propose a self-adaptive step-2-based K-nearest neighbor density peak clustering (SAS-KNN-DPC) algorithm to address T2TA problem. Firstly, the step-2 temporal neighborhood affinity matrix under a non-registration framework is defined and the calculation methods for multi-feature track-point fusion similarity matrix are given. Secondly, the proposed self-adaptive multi-feature similarity truncation matrix is defined to measure the multidimensional distance between track points and the self-adaptive step-2 truncation distance is also defined to enhance the adaptivity of the algorithm. Finally, we propose improved definitions of local distance and global relative distance to complete both cluster center selection and association assignment. The proposed algorithm eliminates the need for exhaustive pairwise matching between track sequences and avoids time alignment, significantly improving the real-time performance of T2TA. Simulation results demonstrate that compared to other algorithms, the proposed algorithm achieves higher accuracy, reduced computational time, and better real-time performance in complex scenarios.

Detection of Criminal Activities and Anomalies through CCTV’s

The detection of criminal activities and anomalies through CCTV (Closed-Circuit Television) surveillance has be- come an essential component of modern security systems. With the rapid advancement of video analytics and machine learning techniques, CCTV systems are now capable of automatically identifying suspicious behavior, unauthorized access, and other criminal activities in real-time. This paper explores the use of AI- based algorithms, including object detection, motion analysis, and facial recognition, to enhance the capabilities of CCTV systems in crime prevention and anomaly detection. By leveraging Advanced deep learning methods, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), are utilized to enhance performance and accuracy in various applications, the proposed system can accurately detect abnormal events, track individuals, and flag potential security threats, significantly improving situational awareness. Furthermore, the integration of anomaly detection algorithms can provide proactive alerts for un- usual patterns, enabling quicker responses from law enforcement or security personnel. The study also addresses challenges such as false positives, privacy concerns, and scalability of such systems in large urban environments. Overall, this research highlights the importance of combining intelligent video analysis with traditional surveillance infrastructure to create a more efficient and effective crime detection framework.

Yolo-Panic: A Real-Time Ai-Based Gesture Recognition System for Smart Panic Alarm System

Rapid and effective responses during emergencies are critical in today’s fast-paced environments, including industrial facilities, commercial hubs, public institutions, and transportation networks. Traditional panic alarm systems largely depend on physical hardware—such as buttons or switches—which may be inaccessible or ineffective in high-stress or hazardous situations. To address these challenges, we introduce YOLO-Panic, a real-time AI-based gesture recognition system designed to activate smart panic alarms using intuitive hand gestures. Built upon a customized YOLO (You Only Look Once) deep learning architecture, the system is trained to detect a specific panic gesture—four fingers extended with the thumb folded inward—with exceptional accuracy. The YOLO-Panic model achieves outstanding performance metrics, including a precision of 98.56%, mAP@50 of 99.30%, and recall of 97.99%, ensuring high reliability with minimal false positives. To enhance spatial gesture interpretation, a keypoint-based module is also integrated, achieving 94.06% mAP@50 and 83.27% mAP@50–95, enabling robust, fine-grained analysis of hand poses. The system operates with a high degree of efficacy in real-time, rendering it exceptionally suitable for application in dynamic and bustling environments. As cities evolve into smarter and more connected ecosystems, YOLO-Panic offers a vital layer of safety and situational awareness. Its contactless, AI-driven approach aligns seamlessly with the goals of smart city infrastructure, where intelligent surveillance and rapid emergency response are paramount. By enabling intuitive human-machine interaction for crisis communication, YOLO-Panic represents a scalable, adaptive solution that enhances public safety, reduces emergency response times, and supports the development of resilient, technology-enabled urban environments.

0122 Total Sleep Deprivation Disrupts Working Memory Updating

Abstract Introduction Total sleep deprivation (TSD) leaves the ability to maintain information in working memory (WM), i.e., the focus of attention, relatively unaffected. However, its effect on the ability to update information into and out of WM is less clear, in part because many of the tasks used to assess WM updating do not differentiate between maintenance and updating processes. Using a task designed to isolate WM updating from WM maintenance, we anticipated that TSD disruptions to WM updating would impair the ability to flexibly adapt to environmental demands to maintain up-to-date information in the focus of attention. Methods N=16 healthy adults completed a 4-day (3-night) in-laboratory study. After a baseline night with a 9h sleep opportunity, participants were randomly assigned to either 39h TSD (n=9) or well-rested control (WRC; n=7). Participants completed a modified delayed match-to-sample (DMS) task approximately 15 minutes after a sham stress test at baseline (session 1) and again 24h later (session 2). On each trial of the DMS, participants encoded an initial pair of figures. They were then shown a second pair of figures and instructed to either begin maintaining the second pair instead or ignore it and continue maintaining the first pair. After a short delay, they saw a single probe figure and had to determine if it matched what should be held in WM. Results Mixed-effects ANOVA on instruction (update or ignore), session (1 or 2), condition (TSD or WRC), and their interactions revealed a significant session by condition interaction (p=0.006) and a significant effect of instruction (p=0.013). TSD participants had poorer accuracy in session 2, when sleep-deprived, than WRC participants (p=0.034) and their own rested baseline (p=0.002). In general, participants had better probe accuracy when they had to maintain the second versus first pair in WM (p=0.013). Conclusion TSD impaired the ability to recognize to-be-maintained information in WM when told to update or ignore the new pair, indicating that TSD disrupts the ability to appropriately update information. As WM updating is critical in a number of settings, TSD may compromise the ability to maintain situational awareness in both laboratory and real-world tasks (e.g., driving). Support (if any) W81XWH-20-1-0442

Authentication of automatic identification system messages based on the use of digital watermarking technology

The Automatic Identification System (AIS) is one of the key technologies in modern maritime navigation, enhancing both the safety and efficiency of maritime transportation. AIS transponder data improves situational awareness, overcomes the limitations of radar, and supports various maritime services. However, the open nature of AIS radio channels makes the system vulnerable to cyberattacks, particularly through data falsification, which poses risks to navigational safety. Message authentication is an effective countermeasure against such threats. This paper proposes a method for authenticating AIS messages using digital watermarking technology. The proposed method minimizes the overhead required to detect spoofed transmissions and AIS data substitution. The developed algorithm Carrier Reconstruction Watermark Decoding (CRWD) enables the integration of additional authentication data into the AIS signal without degrading its noise immunity and maintains compatibility with standard shipboard transponders. This authentication approach can be incorporated within the TESLA cryptographic protocol, which has become a de facto standard for maritime digital communication channels due to its combined advantages of symmetric and asymmetric cryptography.

Improved configuration management for greener approaches: evaluation of a novel pilot support concept

Abstract Carrying out a safe approach under fluctuating wind and weather conditions while following air traffic control (ATC) instructions imposes a significant workload on the flight crew, especially with the limited systems support and information availability on the flight deck today. Individual skills of the pilots including correct anticipation of the weather situation and ATC instructions are necessary to optimally manage speed and configuration changes of the aircraft. Consequently, approach operations at busy airports are virtually always noisier and less fuel-efficient than technically possible. The DYNCAT project combined all relevant data sources (on-board operational data, ATC commands, noise measurement data, surrounding traffic, and weather information) to evaluate individual approach operations in their full context, exemplarily for the Airbus A320 at Zurich airport. Based on this analysis, an operational concept was developed to support pilots and controllers through extended information exchange, thus increasing predictability of the lateral and vertical flight profiles for both sides. A central component is a novel airborne energy management assistance system including a configuration management functionality, implemented through an extension of the Flight Management System (FMS) and Cockpit Display System (CDS) capabilities. These features were evaluated regarding operational (pilots’ workload and situational awareness) and environmental (fuel burn and noise exposure levels) improvements through piloted simulator trials on a fixed-based test bench. The present partial and initial implementation of the functions for the Airbus A320 family evaluates favourably with respect to the above criteria when compared with the state of the art, i.e., support by current FMS functions.

Effectiveness of Finnish SISU training in enhancing prehospital personnels’ work performance: A randomised controlled pilot study

BackgroundResilience means coping with and recovering quickly from adversities. This is a highly beneficial quality for prehospital personnel, who encounter many unforeseen stressors while on duty. This study investigated whether a novel pre-emptive resilience coaching programme, ‘Finnish SISU training’ (hereafter SISU), based on the validated International Performance Resilience and Efficacy Program (iPREP), would improve the work performance by enhancing situational and decision-making skills of prehospital personnel. ‘Sisu’ is a Finnish word meaning the combination of toughness and resilience.MethodsThis randomised controlled pilot study was conducted in Päijät-Häme, Finland. The sample comprised 16 paramedics, divided equally between the intervention and control groups. SISU was administered to the intervention group. Three full-scale simulation scenarios were then conducted. A blinded observer evaluated the participants’ situational awareness and decision-making skills using a structured observer form, awarding them a maximum of 10 points. Participants completed a self-evaluation form before and after each simulation scenario and the responses were rated on a 5-point Likert scale. The results of these forms were compared between groups. We also compared the median values of heart rate variability (HRV), maximum heart rate, and respiratory rate between the groups.ResultsAfter 16 h of pre-emptive SISU, the intervention group improved their situational awareness and decision-making skills in the third simulation scenario (observer form results: intervention group median 10 [IQR 9–10] and control group median 6 [IQR 5–7], p ≤ 0.01). In contrast, observer ratings of the control group showed a diminishing trend in work performance across the three simulation scenarios. Self-evaluation revealed increased confidence in work performance in both study groups, in contrast to the blinded observer findings. Regarding HRV, the intervention group in contrast to the control group, recovered in minutes following the simulation scenarios, especially after the third simulation scenario (third defusing session: intervention group median HRV 27 [IQR 21–28], control group median HRV 21 [IQR 17–22], p < 0.01).ConclusionSISU improved work performance, which was measured by situational awareness and decision-making skills under stressful conditions. Resilience, a skill gained from this novel training, may have positive effects on coping with stress.Trial registrationISRCTN10221308. Registered at 19.3.2024. Retrospectively registered. https//www.isrctn.com/ISRCTN10221308.

Role-ing within the process: effects of followership education on team member performance

PurposeThe purpose of this study is to explore the impact of followership education on student team performance in competitive environments. By emphasizing the importance of followership, the study aims to address gaps in traditional leadership education, which often overlook the role of effective followership. Using phenomenological methods, the research captures student experiences to understand how followership education fosters adaptability and dynamic role-shifting between leading and following. The findings provide practical insights for educators seeking to enhance team effectiveness and individual leadership development through an increased focus on followership skills.Design/methodology/approachThis study utilized a phenomenological approach to explore student experiences with followership education in a competitive environment. Data were collected through semi-structured interviews with nine participants, allowing for in-depth exploration of their perceptions. Thematic analysis was conducted to identify recurring patterns related to the impact of followership on team dynamics. The transcriptions were double-checked for accuracy, and coding was conducted collaboratively to ensure reliability. This design allowed us to capture how followership education influences adaptability and role flexibility within student teams.FindingsThe study found that followership education positively influenced student team dynamics by fostering adaptability and role flexibility. Participants reported increased confidence in navigating both leadership and followership roles, emphasizing the importance of situational awareness and collaborative learning. The themes that emerged from the analysis highlighted the value of psychological safety in enabling students to experiment with different roles. This adaptability was linked to improved team cohesion and performance, demonstrating that followership education is a crucial component of comprehensive leadership development.Research limitations/implicationsThe study’s small sample size limits the generalizability of the findings, as it focuses on a specific group of students in a competitive environment. The phenomenological approach emphasizes depth over breadth, which means that while rich insights were obtained, broader conclusions should be drawn cautiously. Additionally, the study relied on self-reported data, which may influence participants’ perceptions and biases. Future research should include larger, more diverse samples and explore followership education in different contexts to further validate these findings and understand their applicability across varied settings.Practical implicationsThe findings suggest that incorporating followership education into leadership programs can enhance student adaptability and team cohesion. Educators can use these insights to create curricula focusing on leadership and followership roles, enabling students to practice role flexibility in real-world scenarios. Instructors can encourage students to experiment with different roles by fostering psychological safety and improving overall team dynamics. The study underscores the value of emphasizing followership as an integral part of leadership development, which can be especially beneficial in preparing students for collaborative and adaptive professional environments.Social implicationsThis study highlights the importance of followership education in creating more collaborative and adaptable teams. By emphasizing the value of followership, educational institutions can foster environments where students learn the significance of both leading and following effectively. These skills are crucial for social settings that require collective problem-solving and shared leadership. Promoting followership education can help address hierarchical mindsets, encourage inclusivity and empower individuals to take initiative within a team context, contributing to healthier organizational cultures and more cohesive communities.Originality/valueThis study is unique in its focus on followership education within a competitive, team-based environment, addressing a critical gap in traditional leadership programs that often overlook followership. By using a phenomenological approach, the research provides an in-depth exploration of students’ experiences, highlighting the role of followership in fostering adaptability and dynamic team performance. The value lies in offering practical insights for educators on how followership education can be integrated to enhance leadership curricula, contributing to a more balanced understanding of both leading and following as essential components of effective teamwork and leadership development.

Design of Automotive HMI: New Challenges in Enhancing User Experience, Safety, and Security

Human–Machine Interfaces (HMIs) in traditional automobiles are essential in connecting drivers, passengers, and vehicle systems. In automated vehicles, the HMI has become a critical component. A well-designed HMI facilitates effective human oversight, enhances situational awareness, and mitigates risks associated with system failures or unexpected scenarios. Simultaneously, it serves as a crucial safeguard against cyber threats, preventing unauthorized access and ensuring the integrity of vehicular operations in increasingly connected environments. This narrative review delves into the evolving landscape of automotive HMI design, emphasizing its role in enhancing user experience (UX) and safety. By exploring usability challenges, technological advancements, and the integration of rapidly evolving technologies such as AI (Artificial Intelligence), AR (Augmented Reality), and gesture-based controls, this study highlights how effective HMIs minimize cognitive load while maintaining functionality. Significant attention is given to the new challenges that arise from technological advancements in terms of security and safety.

A Comprehensive Study on Enhancing Disaster Management with RescueNet: A Usability and Effectiveness Analysis

This research paper explores RescueNet, a web-based application designed to enhance disaster management through real-time geospatial technology. RescueNet leverages geofencing to streamline emergency response, optimize resource allocation, and facilitate efficient coordination in both pre- and post-disaster scenarios. This study examines its key features, including its robust architecture, user-friendly interface, and ability to improve disaster preparedness and recovery efforts. By systematically reviewing related works and iterative development processes, this research highlights current challenges and opportunities in geofencing-based disaster management systems. RescueNet enables real-time alerts, situational awareness, and automated emergency task assignments, minimizing response time and maximizing efficiency in crisis situations. The system ensures accurate and timely notifications without requiring manual input, allowing responders and affected individuals to take prompt action. Additionally, this paper discusses system scalability, data privacy considerations, and future advancements for enhancing RescueNet’s impact in disaster resilience. Overall, RescueNet represents a significant step toward smarter, technology-driven disaster management, ensuring faster and more effective responses in an increasingly unpredictable world. Keywords: disaster response, emergency management, geofencing, real-time alerts, crisis coordination, GPS optimization, situational awareness, resource allocation, location-based notifications, disaster resilience.

Embodied Cognition: Redefining Human Experience Through AI and Extended Reality

Abstract: This research explores how embodied cognitive can be computationally modeled and enhanced through the integration of Artificial Intelligence (AI) and Extended Reality (XR). Moving beyond traditional disembodied approaches to human-computer interaction, the study employs immersive, adaptive XR environments augmented by AI agents to simulate perception-action loops, contextual learning, and emotional responsiveness. Through mixed-method experiments involving biometric tracking, cognitive task performance, and real-time environmental adaptation, the study demonstrates that AI-XR systems significantly improve cognitive engagement, task accuracy, and situational awareness. The findings establish a foundational framework for next-generation human-machine symbiosis, offering scalable applications in education, therapy, and human augmentation. Keywords: Embodied cognitive Artificial Intelligence, Extended Reality, Human-computer interaction, Neuroadaptive systems, Cognitive performance, Biometric analytics, Immersive learning, Human-machine symbiosis, Adaptive environments

The Impact of Constant Observation in Pediatric Mental Health Emergencies: Perspectives from Emergency Department Staff

ABSTRACT Background Emergency departments are critical care settings for children in mental and behavioral health crises. Psychiatrists and psychiatric-mental health nurses collaborate with emergency department teams to manage safety risks for these patients, which often involves constant patient observation, particularly for agitated or suicidal patients. Objective This paper aims to understand emergency department staff’s perspectives on constant observation of pediatric mental and behavioral health patients and the impact of this practice on emergency department workflows. Methods This qualitative study thematically analyzes 55 semi-structured interviews with members of the emergency department team, including patient observers, from four different hospitals. Results Eight themes were identified as impacting emergency department workflows and patient care. The most commonly mentioned themes included the impact of constant observation on emergency department workflow, situational awareness and clear sightlines to the patient, and compliance with constant observation-related organizational policies. Conclusions Findings provide insights for optimizing the role of the patient observer, incorporating remote monitoring to increase patient safety, enhancing the emergency department physical environment to enhance the quality of care, optimizing patient outcomes, and maintaining a safe environment. This study’s results support advanced psychiatric-mental health practice nurses and emergency and psychiatric-mental health clinical nurses in improving the quality of care and safety for this vulnerable population.

Situational Awareness and Fault Warning for Smart Grids Combined with Deep Learning Technology: Application of Digital Twin Technology and Long Short Term Memory Networks

Situational Awareness and Fault Warning for Smart Grids Combined with Deep Learning Technology: Application of Digital Twin Technology and Long Short Term Memory Networks