Real-time Emergency Research Articles

Computationally efficient and stable real-world synthetic emergency room electronic health record data generation: high similarity and privacy preserving diffusion model approach: A retrospective cohort study

Purpose: This study aimed to develop real-world synthetic electronic health record (EHR) for emergency departments using computationally efficient and stable diffusion probabilistic models. Methods: In this study, we compared the performance of diffusion models and state-ofthe-art generative adversarial networks (GANs) in terms of statistical similarity, privacy, medical usefulness, and the feasibility of using synthetic data for machine learning purposes.Results: Our results demonstrate that diffusion models are significantly more computationally efficient than GANs and perform comparably or slightly better in terms of similarity, privacy, and utility. We also found that the data quality of the diffusion model is statistically very similar for both categorical and continuous values and can address class imbalance precisely. Moreover, the usefulness of synthetic data is almost identical to that of real EHR data. Our privacy analysis showed that the synthetic data generated by the diffusion models were private.Conclusion: These findings have significant implications for improving the efficiency of emergency settings and enabling real-time emergency room data modeling. This demonstrates the potential of diffusion models for generating computationally efficient high-quality synthetic data. The study concluded that diffusion models can generate real-world synthetic EHRs that are computationally efficient, private, and high-quality, and can be used for machine learning purposes in emergency settings.

Emergency voltage control strategy for power system transient stability enhancement based on edge graph convolutional network reinforcement learning

Emergency control is essential for maintaining the stability of power systems, serving as a key defense mechanism against the destabilization and cascading failures triggered by faults. Under-voltage load shedding is a popular and effective approach for emergency control. However, with the increasing complexity and scale of power systems and the rise in uncertainty factors, traditional approaches struggle with computation speed, accuracy, and scalability issues. Deep reinforcement learning holds significant potential for the power system decision-making problems. However, existing deep reinforcement learning algorithms have limitations in effectively leveraging diverse operational features, which affects the reliability and efficiency of emergency control strategies. This paper presents an innovative approach for real-time emergency voltage control strategies for transient stability enhancement through the integration of edge-graph convolutional networks with reinforcement learning. This method transforms the traditional emergency control optimization problem into a sequential decision-making process. By utilizing the edge-graph convolutional neural network, it efficiently extracts critical information on the correlation between the power system operation status and node branch information, as well as the uncertainty factors involved. Moreover, the clipped double Q-learning, delayed policy update, and target policy smoothing are introduced to effectively solve the issues of overestimation and abnormal sensitivity to hyperparameters in the deep deterministic policy gradient algorithm. The effectiveness of the proposed method in emergency control decision-making is verified by the IEEE 39-bus system and the IEEE 118-bus system.

Fault tolerant motion planning for a quadrotor subject to complete rotor failure

Assuring safety of a quadrotor subject to rotor failure has been heavily investigated at the control level in view of fault tolerant control (FTC) approach. Yet, the existing FTCs are often concerned with tracking the reference motion even when that reference may not be safely trackable due to the physical constraints of the quadrotor. This paper tackles the faulty quadrotor safety at the planner level, proposing a fault tolerant motion planner. Starting from the formal backward reachability problem formulation, the proposed motion planner generates the time trajectory of the coupled rotational and translational motions that safely guide the faulty quadrotor. The generated trajectory is theoretically guaranteed to be tracked by the embedded FTC without violating the physical constraints. Further, the trajectory is prescribed as an analytical closed-form expression and thus suitable for real-time emergency maneuvers. The effectiveness of the proposed motion planner is numerically validated in conjunction with the different FTC techniques and compared to the existing planning method. The simulation results clearly signify that the proposed planner can successfully complement the fault tolerance of quadrotor. The supplements including code implementations are available on GitHub repository: https://github.com/HMCL-UNIST/Fault-tolerant-motion-planner.

Forecasting road network functionality states during extreme rainfall events to facilitate real-time emergency response planning

Rapid prediction of Road Network Functionality (RNF) during extreme rainfall-induced flooding is crucial for supporting proactive and real-time emergency planning, such as rescue, evacuation planning, and emergency supply distribution. Unlike normal operational conditions, extreme rainfall events introduce complex non-stationary, non-Euclidean characteristics to RNF due to intricate meteorological and hydrological processes, as well as the role of a community's road network in emergency response planning. Conventional physics-based flood simulations and flow-based road network analyses typically lack the computational efficiency required for real-time RNF predictions, hindering timely risk mitigation decisions. This study leverages the accuracy of physics-based simulations and the efficacy of deep-learning technologies to develop a deep learning-based surrogate model for Rain-to-RNF (R2R) predictions. This model couples Long Short-Term Memory (LSTM) networks with Spatial-Temporal Graph Convolutional Networks (ST-GCNs) to uniquely capture the spatiotemporal dynamics of RNF under extreme rainfall events. The predictive accuracy, stability, and versatility of the R2R surrogate model are demonstrated in four flood-prone communities in Zhejiang Province. Its implementation during Typhoon Fitow (2013) over a 30-hour intense rainfall showcases its promising predictive capacity and unparalleled computational efficiency. This research advances disaster management, enhancing the resilience and responsiveness of community infrastructure during extreme weather events.

Digital twin approach for enhancing urban resilience: A cycle between virtual space and the real world

Construction of disaster-resilient cities has attracted considerable attention. However, traditional methods of studying urban disaster resilience through experimental approaches are often constrained by various limitations, such as testing sites, costs and ethical considerations. To address these constraints, this paper proposes incorporating digital twin concepts into urban disaster resilience research. By establishing a connection between the physical realm of the city and its virtual counterpart, this approach utilizes digital simulations to overcome the limitations of experimental methods and enables dynamic deduction and control of the disaster process. This paper delves into three key aspects encompassing the acquisition of data from reality to the virtual space, disaster simulation within the virtual space, and translation of virtual insights into effective disaster prevention strategies in reality. It provides a comprehensive summary of relevant research endeavors from the authors’ research group and showcases the effectiveness and potential of the proposed techniques. These findings serve as references for pre-disaster planning, real-time emergency assessments, post-disaster rescue operations, and accident investigations for buildings and cities.

Threshold and real-time initiation mechanism of urban flood emergency response under combined disaster scenarios

Scientific and reasonable emergency response initiation mechanisms can provide important support for decision making regarding the emergency management of urban floods. However, there is a lack of a unified paradigm on how to calculate the threshold for emergency response initiation and reasonably initiate emergency response. Therefore, this study proposes a loss-driven urban flood emergency response initiation framework from the perspective of combined disasters. A discrimination mechanism of the emergency response initiation level was established based on the optimal threshold and loss function. And the rainfall event that occurred in Zhengzhou, China, on July 20, 2021, was taken as an example to realize real-time emergency response discrimination and initiation driven by forecast data. Results showed that the initiation time of the Level I emergency response using the proposed method was 9.5 h earlier than the time of the government release, thereby significantly increasing the preparation time for flood management personnel. In addition, the results of the optimal threshold selection indicated that the Natural Breakpoint method was the optimal method for loss threshold partitioning, with the comprehensive evaluation index (CEI) being 3.56–9.53 % higher than those of the K-means, Equal Interval, and Quantile method. These results constitute a reference for urban emergency management and related research.

Emergency Department Visits for Pedestrians Injured in Motor Vehicle Traffic Crashes - United States, January 2021-December 2023.

Traffic-related pedestrian deaths in the United States reached a 40-year high in 2021. Each year, pedestrians also suffer nonfatal traffic-related injuries requiring medical treatment. Near real-time emergency department visit data from CDC's National Syndromic Surveillance Program during January 2021-December 2023 indicated that among approximately 301 million visits identified, 137,325 involved a pedestrian injury (overall visit proportion=45.62 per 100,000 visits). The proportions of visits for pedestrian injury were 1.53-2.47 times as high among six racial and ethnic minority groups as that among non-Hispanic White persons. Compared with persons aged ≥65 years, proportions among those aged 15-24 and 25-34 years were 2.83 and 2.61 times as high, respectively. The visit proportion was 1.93 times as high among males as among females, and 1.21 times as high during September-November as during June-August. Timely pedestrian injury data can help collaborating federal, state, and local partners rapidly monitor trends, identify disparities, and implement strategies supporting the Safe System approach, a framework for preventing traffic injuries among all road users.

Real-time flood maps forecasting for dam-break scenarios with a transformer-based deep learning model

This paper presents a purely data-driven deep-learning approach for flood maps forecasting. For the first time in this context a Transformer-based algorithm is employed to address one of the main issues in early-warning systems for flood propagation, i.e., the long computational times required to forecast the inundation evolution in real time. The proposed model, named “FloodSformer”, is trained to extract the spatiotemporal information from a short sequence of water depth maps and predict the water depth map at one subsequent instant. Then, to forecast a sequence of future maps, we employ an autoregressive procedure based on the trained surrogate model. The method was applied to both synthetic dam-break scenarios and to a real case study, specifically the ideal failure of the Parma River dam (Italy). The training and testing datasets were generated numerically from two-dimensional hydraulic simulations. In the case of the real test case, the average Root Mean Square Error was found to be equal to 10.4 cm. The short computational time (e.g., the forecast of 90 maps, representing a lead time of 3 h, takes less than 1 min) makes the FloodSformer model a suitable tool for real-time emergency applications.

Real-Time Monitoring System with Digital Umbrella.

This research project focuses on enhancing the safety and convenience of street sellers and outdoor campers by developing a real-time monitoring system incorporating GSM, GPRS, GPS, and MCU nodes. The system provides live location tracking and an emergency button for immediate assistance. Designed for vegetable sellers, roadside vendors, and tourists, the project integrates security features and amenities like FM radio, mobile charging, lighting, and fan systems into an automated panel powered by solar energy. The solar umbrella captures and stores solar energy during the day to power LED lights and other devices at night, promoting sustainability. This innovative solution combines practicality with advanced technology, ensuring continuous energy supply and real-time emergency alerts, thus significantly improving user safety and convenience.

Enhancing Smart City Safety and Utilizing AI Expert Systems for Violence Detection

Violent attacks have been one of the hot issues in recent years. In the presence of closed-circuit televisions (CCTVs) in smart cities, there is an emerging challenge in apprehending criminals, leading to a need for innovative solutions. In this paper, the propose a model aimed at enhancing real-time emergency response capabilities and swiftly identifying criminals. This initiative aims to foster a safer environment and better manage criminal activity within smart cities. The proposed architecture combines an image-to-image stable diffusion model with violence detection and pose estimation approaches. The diffusion model generates synthetic data while the object detection approach uses YOLO v7 to identify violent objects like baseball bats, knives, and pistols, complemented by MediaPipe for action detection. Further, a long short-term memory (LSTM) network classifies the action attacks involving violent objects. Subsequently, an ensemble consisting of an edge device and the entire proposed model is deployed onto the edge device for real-time data testing using a dash camera. Thus, this study can handle violent attacks and send alerts in emergencies. As a result, our proposed YOLO model achieves a mean average precision (MAP) of 89.5% for violent attack detection, and the LSTM classifier model achieves an accuracy of 88.33% for violent action classification. The results highlight the model’s enhanced capability to accurately detect violent objects, particularly in effectively identifying violence through the implemented artificial intelligence system.

Telepalliative Care in Home-Based Nursing Care for Older Adults With Metastatic Cancer Post COVID-19: An Ethnoscientific Study.

The post-COVID-19 pandemic caused the whole world to make several changes to the nursing healthcare system. This sudden shift raised questions about telepalliative care in home-based nursing care in the context of healthcare utilization, including meeting the needs of older adults with metastatic cancer. The evidence suggests that telepalliative care in home-based nursing care is acceptable to most advanced practice nurses, but the extent of their use for metastatic cancer patients has not been defined. To explore the use of telepalliative care in home-based nursing care for older adults with metastatic cancer in central Thailand following the post-COVID-19 pandemic. A qualitative approach with an ethnoscientific design was used to collect data from a purposive sample of 15 advanced practice nurses from May to September 2023. The interview transcripts were analyzed using componential analysis (core coding, categorizing, theme, and emerging theory). The componential analysis revealed two themes of telepalliative care in home-based nursing care for older adults with metastatic cancer in the post COVID-19 pandemic. The first theme is telepalliative care delivery, with subthemes of delivering practice, nurse-mediated feedback and supportive care, remote monitoring of real-time emergencies, and transferring medical data. The second theme is advanced practice nurses' (APN) role in telepalliative nursing care, including the subthemes of virtual monitoring, life-threatening cancer, side effects, caregiving capacity, continuity of care, and long-term care services. The study found that caregiving capacity, continuity of care, and long-term care services were formed of telepalliative care in home-based nursing care for cancer patients following the COVID-19 pandemic. Telepalliative care in home-based nursing care is effective in delivering services to older adults with metastatic cancer during the post-COVID-19 pandemic. The findings suggested that remote monitoring of real-time emergencies, life-threatening cancer, and long-term care services are part of telepalliative care in home-based nursing care. Adapting the telepalliative competency standards of advanced practice nurses is needed to ensure high-quality healthcare access for older adults with metastatic cancer during the post-COVID-19 pandemic.

Mitigating vulnerability of a multimodal public transit system for sustainable megacities: a real-time operational control method

The multimodal public transit system (MPTS) has been recognized as a primary mobility support system for sustainable megacities. However, it is often vulnerable to various service disruptions, and the most severe circumstance is the interdependent cascading failures interacting among urban rail transit, bus transit, and road transit networks. The vulnerability of an MPTS against this severe failure, associated with extreme performances, limits the building of future resilient megacities. In this paper, a real-time operational control method based on the system emergency capability (SEC) is developed to block the dynamic unfolding paths of this severe failure considering network topology characteristics and dynamic evolution characteristics. This method is immediately available for real-time emergency control, while previous studies on qualitative optimization strategies cannot. Remarkably, a three-stage association design process is conducted to explore the most efficient SEC loading strategy, involved with multiple intertwined influential factors, including the target loading stations, loading time-step intervals, and loading interval length and loading strength. Finally, a case simulation is undertaken to indicate the adaptability of the proposed method. This work can provide critical insights into real-world emergency resource allocation and an underlying simulator with search direction knowledge for future intelligent algorithm-based optimal control.

Smart Crosswalk: Machine Learning and Image Processing based Pedestrian and Vehicle Monitoring System

The conventional pedestrian crossing system's shortcomings require urgent reform to enhance the safety of pedestrians and improve urban mobility. Issues such as insufficient time for pedestrians to cross, prolong waiting times, neglection of emergency vehicles, and the absence of effective 24/7 response mechanisms at traditional crosswalks present significant safety concerns in urban areas. Our primary intention is to develop a cutting-edge pedestrian crossing system that relies on deep learning and image processing technologies as its foundation. This research addresses to innovate an advanced smart crosswalk consisting of four essential components: a real-time Pedestrian Detection and Priority System customized for individuals with special needs, a responsive system for detecting road conditions, vehicle availability and speed near crosswalks, a real-time Emergency Vehicle Detection and Priority System strengthened by rigorous verification procedures, and a robust framework for identifying pedestrian accidents and violations of crosswalk rules. The entire system has been meticulously designed not only to enhance pedestrian safety by identifying potential dangers but also to optimize traffic flow. In essence, it aims to provide an improved pedestrian crossing experience characterized by increased safety and efficiency.

A WeChat applet-based national remote emergency system for malignant hyperthermia in China: a usability study

BackgroundMalignant hyperthermia (MH) is a rare anesthetic emergency with a high mortality rate in China. We developed a WeChat applet–based National Remote Emergency System for Malignant Hyperthermia (MH-NRES) to provide a real-time emergency system to help Chinese anesthesiologists deal with MH crises. However, it is imperative that close attention should be paid to the usability of the applet.PurposeThe objectives of this study were to (1) evaluate the usability of the applet-based MH-NRES for anesthesiologists; and (2) to test the validity and reliability of a modified mHealth app usability questionnaire.MethodsA modified User Version of the Mobile Application Rating Scale (uMARS) was designed. Together with System Usability Scale (SUS) and Post-Study System Usability Questionnaire (PSSUQ), another two well-validated questionnaires, uMARS were then used to evaluate the usability of MH-NRES. The Cronbach alpha of the total score and the subscales of uMARS was calculated to evaluate the internal consistency. The correlation coefficients among three questionnaires were calculated.ResultsIn this study, 118 anesthesiologists provided responses to the questionnaire. The overall mean uMARS score was 4.43 ± 0.61, which ranged from 3 to 5. The mean PSSUQ score were in good to excellent range with mean of 6.02 ± 0.97, which ranged from 3.19 to 7. The overall SUS score was 76.0 ± 17.6, which ranged from 45 to 100. The total uMARS score had excellent internal consistency (Cronbach alpha = 0.984). uMARS and its subscales were strongly correlated with PSSUQ (coefficient 0.758–0.819, P < 0.001) and SUS (coefficient 0.535–0.561, P < 0.001), respectively.ConclusionsData obtained from the usability evaluation questionnaires in this study indicated a high quality of the MH-NRES on the ease of use, satisfaction and perceived usefulness, which suggest this system might be a useful tool for anesthesiologists’ education and management of MH crises. Future feedback from high-fidelity simulation and clinical scenarios are need for further usability evaluation of this system.

Robust Generation Dispatch With Strategic Renewable Power Curtailment and Decision-Dependent Uncertainty

As renewable energy sources replace traditional power sources (such as thermal generators), uncertainty grows while there are fewer controllable units. To reduce operational risks and avoid frequent real-time emergency controls, a preparatory schedule of renewable generation curtailment is required. This paper proposes a novel two-stage robust generation dispatch (RGD) model, where the preparatory curtailment threshold is optimized in the pre-dispatch stage. The curtailment threshold will then influence the variation range of real-time renewable power outputs, resulting in a decision-dependent uncertainty (DDU) set. In the re-dispatch stage, the controllable units adjust their outputs within their reserve contributions to maintain power balancing. To overcome the difficulty in solving the RGD with DDU, an adaptive column-and-constraint generation (AC&CG) algorithm is developed. We prove that the proposed algorithm can generate the optimal solution in a finite number of iterations. Numerical studies show the advantages of the proposed model and algorithm and validate their practicability and scalability.

Self-Adaptive Predictive Passenger Flow Modeling for Large-Scale Railway Systems

Intelligent transportation system (ITS) is a crucial symbol of smart cities, which aims to provide sustainable and efficient services to residents. Playing a vital role in ITS, railway systems have been integrating with multiple Internet of Things (IoT) devices to monitor real-time inbound passenger flows to ensure pedestrian safety. But it remains difficult to consolidate real-time information from different IoT sources and accurately estimate the future flow due to the coarse-grained data, potential impacts of dynamic interchanged passengers, and real-time predictive capability, which have greatly hindered the progress of ITS transformation in smart cities. To tackle these challenges, we propose a two-stage self-adaptive model for accurately and timely predicting passenger flow in metropolitan railway systems. In the first stage, a self-attention-based prediction model is introduced to predict the next-day passenger flow based on the historical boarding records captured by IoT devices. The proposed decomposing components transferring the discrete boarding records into continuous patterns enable the module to deliver a robust minute-level prediction. In the second stage, a real-time fine-tuning model is developed to adjust the predicted passenger flow based on real-time emergencies and short-term changes in passenger flows from IoT devices. The combination of an offline deep learning mechanism and a real-time reallocation algorithm ensures the real-time response without loss of accuracy. Our end-to-end framework has been deployed to the railway system in Greater Sydney Area, Australia, which can offer accurate predictions to trip planners for timetable design and provide timely decision support for controllers when emergencies happen.

Intelligent contributions of the artificial orca algorithm for continuous problems and real-time emergency medical services.

The Artificial Orca Algorithm (AOA) is an existing swarm intelligence algorithm, empowered in this paper by two well-known mutation operators and opposition-based learning, yielding the novel methods Deep Self-Learning Artificial Orca Algorithm (DSLAOA), Opposition Deep Self-Learning Artificial Orca Algorithm (ODSLAOA), and Opposition Artificial Orca Learning Algorithm. The DSLAOA and ODSLAOA are based on the Cauchy and Gauss mutation operators. Their effectiveness is evaluated on both continuous and discrete problems. The suggested algorithms are tested and compared to seven recent state-of-the-art metaheuristics in the continuous context. The results demonstrate that, when compared to the other algorithms, DSLAOA based on the Cauchy operator is the most effective technique. After that, a specific real-world scenario involving emergency medical services in a dire situation is tackled. The Ambulance Dispatching and Emergency Calls Covering Problem is the addressed problem, and a mathematical formulation is made to model this issue. AOA, DSLAOAC, and DSLAOAG are tested and contrasted with a successful recent heuristic in this field. The experiments are run on real data, and the results show that the swarm approaches are effective and helpful in determining the resources required in this kind of emergency.

A new method for near real-time, nationwide surveillance of nosocomial COVID-19 in Norway: providing data at all levels of the healthcare system, March 2020 to March 2022.

BackgroundGreat efforts have been made to minimise spread and prevent outbreaks of COVID-19 in hospitals. However, there is uncertainty in identifying nosocomial vs community-acquired infections. To minimise risks and evaluate measures, timely data on infection risk in healthcare institutions are required.AimsTo design an automated nationwide surveillance system for nosocomial COVID-19 using existing data to analyse the impact of community infection rates on nosocomial infections, to explore how changes in case definitions influence incidence and to identify patients and wards at highest risk and effects of SARS-CoV-2 variants.MethodsWe used data from the Norwegian real-time emergency preparedness register (Beredt C19), which includes all patients nationwide admitted to Norwegian hospitals between March 2020 and March 2022 with a positive SARS-CoV-2 PCR test during their hospital stay or within 7 days post-discharge. COVID-19 cases were assigned to categories depending on the time between admission and testing.ResultsInfection rates for definite/probable nosocomial COVID-19 increased from 0.081% in year 1 to 0.50% in year 2 in hospital admissions 7 days or longer. Varying the definitions resulted in large changes in registered nosocomial infections. Infection rates were similar across different ward types. By 2022, 58% of patients with a definite/probable nosocomial infection had received three vaccine doses.ConclusionAutomated national surveillance for nosocomial COVID-19 is possible based on existing data sources. Beredt C19 provided detailed information with only 5% missing data on hospitals/wards. Epidemiological definitions are possible to standardise, enabling easier comparison between regions and countries.

Real-Time Emergency Collision Avoidance for Unmanned Surface Vehicles with COLREGS Flexibly Obeyed

This paper presents a real-time emergency collision-avoidance method for unmanned surface vehicles (USVs) with the International Regulations for Preventing Collisions at Sea (COLREGS) flexibly obeyed. The pivotal issue is that some traffic vessels may violate the demands of this convention, which would increase the risk of collision if the USV blindly obeys the COLREGS rules. To avoid mandatory compliance with these COLREGS rules, a real-time truncated velocity obstacle (TVO) algorithm is proposed to assign a collision-free velocity vector for the control system to realize. Considering a reasonable trade-off between safety and the COLREGS rules, the proposed collision-avoidance method expands the TVO’s area based on the velocity uncertainties of traffic vessels, which greatly enhance the safety of collision-avoidance operations and encourage the USV to follow the COLREGS rules. To promptly realize an assigned collision-free velocity, this paper also develops a discrete simultaneous planning and executing (SPAE) controller design. The proposed discrete controller is divided into three parts: online polynomial planning to satisfy the constraints of tracking errors, an accurate uncertainty estimation, and an algebraic control law to promptly execute the planned polynomial. Numerical results have validated the reliability and intelligibility of the proposed collision-avoidance method. Furthermore, simulated and experimental results have validated the effectiveness of the proposed controller design.

Guest Editorial: Artificial Intelligence Enabled Internet of UAVs for Emergency Communications

The unprecedented demands for high-quality and ubiquitous wireless services impose enormous challenges to the existing cellular networks to meet the challenges of connectivity, reliability, etc. The targeted applications in designing the beyond fifth generation (BSG) systems include enhanced mobile broadband (eMBB), ultra-reliable, low latency communications (URLLC), and massive machine-type communications (mMTC). Recently to meet those diverse requirements, the latest technologies like millimeter wave (mmWave) communications, ultra-dense networks (UDN), and massive multiple-input and multiple-output (MIMO) are under consideration. Moreover, we also require an evolution in an architectural platform that performs joint communications, sensing, localization, and computing while ensuring ultra-high throughput, ultra-low latency, and ultra-high reliability for real-time emergency communications.