Dynamic Warning Research Articles

A Dynamic Early Warning Model for Flash Floods Based on Rainfall Pattern Identification

Abstract Flash floods are one of the most devastating natural hazards in mountainous and hilly areas. In this study, a dynamic warning model was proposed to improve the warning accuracy by addressing the problem of ignoring the randomness and uncertainty of rainfall patterns in flash flood warning. A dynamic identification method for rainfall patterns was proposed based on the similarity theory and characteristic rainfall patterns database. The characteristic rainfall patterns were constructed by k-means clustering of historical rainfall data. Subsequently, the dynamic flood early warning model was proposed based on the real-time correction of rainfall patterns and flooding simulation by the HEC-HMS (Hydrologic Engineering Center’s Hydrologic Modeling System) model. To verify the proposed model, three small watersheds in China were selected as case studies. The results show that the rainfall patterns identified by the proposed approach exhibit a high correlation with the observed rainfall. With the increase of measured rainfall information, the dynamic correction of the identified rainfall patterns results in corresponding flood forecasts with Nash-Sutcliffe efficiency (NSE) exceeding 0.8 at t = 4, t = 5, and t = 6, thereby improving the accuracy of flash flood warnings. Simultaneously, the proposed model extends the forecast lead time with high accuracy. For rainfall with a duration of six hours in the Xinxian watershed and eight hours in the Tengzhou watershed, the proposed model issues early warnings two hours and three hours before the end of the rainfall, respectively, with a warning accuracy of more than 0.90. The proposed model can provide technical support for flash flood management in mountainous and hilly watersheds.

Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databases.

The use of invasive mechanical ventilation (IMV) is crucial in rescuing patients with respiratory dysfunction. Accurately predicting the demand for IMV is vital for clinical decision-making. However, current techniques are invasive and challenging to implement in pre-hospital and emergency rescue settings. To address this issue, a real-time prediction method utilizing only non-invasive parameters was developed to forecast IMV demand in this study. The model introduced the concept of real-time warning and leveraged the advantages of machine learning and integrated methods, achieving an AUC value of 0.935 (95% CI 0.933-0.937). The AUC value for the multi-center validation using the AmsterdamUMCdb database was 0.727, surpassing the performance of traditional risk adjustment algorithms (OSI(oxygenation saturation index): 0.608, P/F(oxygenation index): 0.558). Feature weight analysis demonstrated that BMI, Gcsverbal, and age significantly contributed to the model's decision-making. These findings highlight the substantial potential of a machine learning real-time dynamic warning model that solely relies on non-invasive parameters to predict IMV demand. Such a model can provide technical support for predicting the need for IMV in pre-hospital and disaster scenarios.

Research on Early Warning Method of Plough Layer Thickness of Cultivated Land in Black Soil Driven by Rainfall Events

The thinning of the arable layer causes soil quality degradation, seriously affecting crop growth and even threatening national food security. This article focuses on the problems and needs of poor timeliness, high cost, and inability to dynamically warn about the thinning of the tillage layer in black soil farmland, and conducts research on corresponding warning methods. Based on daily rainfall data, the percentile method is used to calculate the threshold for erosive rainfall event driven warning. Based on erosive rainfall event driven coupling of external soil erosion stress meteorological elements and influencing processes, as well as the connotation of geographic events, the concept definition of geographic events for thinning warning of arable layer thickness is given. The semantic description and discovery method of geographic events are provided, and geographic event driven rules and the technical process of thinning warning of arable layer thickness are formulated. There is a significant correlation between rainfall and topsoil thickness, with a correlation coefficient of 0.83. A soil thickness thinning warning simulation was conducted based on the daily rainfall data of Hailun City, Heilongjiang Province in 2020. On June 14, 2020, when the daily rainfall exceeded the event threshold, an automatic warning for thinning of the plow layer was triggered, achieving a dynamic warning process for thinning of the plow layer. The research results indicate that this method is helpful in solving the problem of thinning warning of the cultivated layer thickness in black soil farmland, and can provide technical support for the quality construction, protection, and management of black soil farmland.

"Specialized, Refined, Unique, and New" Enterprise Green Quality Immune System Resilience Dynamic Warning

"Specialized, Refined, Unique, and New" Enterprise Green Quality Immune System Resilience Dynamic Warning

Intelligent Dynamic Warning Method of Rockburst Risk and Level Based on Recurrent Neural Network

Intelligent Dynamic Warning Method of Rockburst Risk and Level Based on Recurrent Neural Network

Research on Image Analysis and Dynamic Early Warning Mechanism of Power Marketing Operation Site Based on SSD Networks

Abstract Safety production is an important way to ensure the personal safety of workers and the safety of national property. This project focuses on addressing the safety generation problem in the power marketing profession, designing a set of intelligent dynamic warning systems for power marketing operations. MobileNetV1 is used as the backbone feature extraction network of SSD to create a lightweight target detection network, and it is combined with OpenVINO and NCS2 neural computation bars to construct an image analysis and dynamic warning model for power operation based on the SSD MobileNetV1 algorithm. We use the images of power marketing operation sites in a city as a dataset to test and compare the constructed model with other target detection algorithms, analyzing its dynamic warning effect on power operations and exploring the effectiveness of the model’s practical application. The results show that the SSD network model can significantly improve the detection efficiency and accuracy of the dynamic early warning system for electric power operations, and its accuracy is 15.15% and 18.82% higher than that of the Faster⁃RCNN algorithm and the YOLO algorithm, respectively. The early warning system reduced the irregular behavior of electric power marketing operations by 135.71%, demonstrating the effectiveness of the SSD model in detecting and warning electric power targets. This model not only meets practical requirements but also effectively reduces the irregular production behaviors of electric power marketing operations, thereby enhancing the safety coefficient of marketing field operations.

Establishment of a medical device adverse event management system for hospitals

BackgroundThe management of medical device adverse event (MDAE) is one of the most important aspects of improving medical quality and safety management. Nonetheless, hospitals still lack standardized and unified initiatives to improve MDAE management.MethodsThis study, thus, established a MDAE monitoring system on May 1 in 2011 for suspected adverse events and designed a hospital-based dynamic warning system, aiming to standardize the process of MDAE handling and provide real-time monitoring for MDAEs in a hospital. This system was used in the First Affiliated Hospital of Zhejiang University School of Medicine. Numbers and the compound growth rate of MDAE reports from 2010 to 2020 were compared to test the effectiveness of the MDAE monitoring system. Numbers of MDAE reported to the National Adverse Event Monitoring System were also compared over 2013 to 2020, due to the loss of data before 2013 after shutdown of the old system. Efficacy and usability of the hospital-based dynamic warning system was then verified by analyzing risk and warning levels of MDAEs in 2020. Descriptive statistics was used for data analysis in this study.ResultsResults showed that the compound annual growth rates of MDAE reports and those submitted to the National Adverse Event Monitoring System from 2013 to 2020 were 35.0% and 31.5%, respectively. A standardized management of MDAE with full participant, timely response and effective feedback was formed in the hospital by establishment of the MDAE system.ConclusionsThis system effectively improved the monitoring level of MDAEs, helping to improve early detection, early warning, and early intervention of risk of medical device. This study may provide suggestions for medical institutions to establish a MDAE monitoring system, and may promote development of medical quality and safety management for hospitals to some extent.

A Conflict Measures-Based Extreme Value Theory Approach to Predicting Truck Collisions and Identifying High-Risk Scenes on Two-Lane Rural Highways

Collision risk identification and prediction is an effective means to prevent truck accidents. However, most existing studies focus only on highways, not on two-lane rural highways. To predict truck collision probabilities and identify high-risk scenes on two-lane rural highways, this study first calculated time to collision and post-encroachment time using high-precision trajectory data and combined them with extreme value theory to predict the truck collision probability. Subsequently, a traffic feature parameter system was constructed with the driving behavior risk parameter. Furthermore, machine learning algorithms were used to identify critical feature parameters that affect truck collision risk. Eventually, extreme value theory based on time to collision and post-encroachment time incorporated a machine learning algorithm to identify high-risk truck driving scenes. The experiments showed that bivariate extreme value theory integrates the applicability of time to collision and post-encroachment time for different driving trajectories of trucks, resulting in significantly better prediction performances than univariate extreme value theory. Additionally, the horizontal curve radius has the most critical impact on truck collision; when a truck is driving on two-lane rural highways with a horizontal curve radius of 227 m or less, the frequency and probability of collision will be higher, and deceleration devices and central guardrail barriers can be installed to reduce risk. Second is the driving behavior risk: the driving behavior of truck drivers on two-lane rural highways has high-risk, and we recommend the installation of speed cameras on two-lane rural roads to control the driving speed of trucks and thus avoid dangerous driving behaviors. This study extends the evaluation method of truck collisions on two-lane rural highways from univariate to bivariate and provides a basis for the design of two-lane rural highways and the development of real-time dynamic warning systems and enforcement for trucks, which will help prevent and control truck collisions and alleviate safety problems on two-lane rural highways.

Dynamic Warning Method for Structural Health Monitoring Data Based on ARIMA: Case Study of Hong Kong-Zhuhai-Macao Bridge Immersed Tunnel.

Structural health monitoring (SHM) is gradually replacing traditional manual detection and is becoming a focus of the research devoted to the operation and maintenance of tunnel structures. However, in the face of massive SHM data, the autonomous early warning method is still required to further reduce the burden of manual analysis. Thus, this study proposed a dynamic warning method for SHM data based on ARIMA and applied it to the concrete strain data of the Hong Kong–Zhuhai–Macao Bridge (HZMB) immersed tunnel. First, wavelet threshold denoising was applied to filter noise from the SHM data. Then, the feasibility and accuracy of establishing an ARIMA model were verified, and it was adopted to predict future time series of SHM data. After that, an anomaly detection scheme was proposed based on the dynamic model and dynamic threshold value, which set the confidence interval of detected anomalies based on the statistical characteristics of the historical series. Finally, a hierarchical warning system was defined to classify anomalies according to their detection threshold and enable hierarchical treatments. The illustrative example of the HZMB immersed tunnel verified that a three-level (5.5 σ, 6.5 σ, and 7.5 σ) dynamic warning schematic can give good results of anomalies detection and greatly improves the efficiency of SHM data management of the tunnel.

Dynamical Alert of Thought and Politics Teaching Based on the Long- and Short-Term Memory Neural Network

To strengthen and develop the thought and politics work in state-owned schools, schools must explore the theoretical system of thought and politics construction in the practice of scientific development ideas guiding school development, actively innovate the practice model and implement early warning management for thought and politics projects. This is because only by accurately analyzing the problems and causes can we seek more reasonable measures for the laws of thought and politics practice education for modern students. At present, promoting the deep integration of thought and politics teaching projects with information technology has become an important means of thought and politics teaching projects in schools. However, with the explosive growth of network data, the structure becomes more and more complex, and learners face the problem of information overload as more and more information overflows in the network environment. Precise support for students with learning disabilities is a research direction for precision thinking education, and most existing support strategies in schools include manual statistics of failed subjects, written warnings, or corrective measures through simple correlation algorithms. In this paper, we propose a dynamical alert for thought and politics teaching based on the Long-Short-Term Memory Neural Network (LSTM), which uses a powerful global optimization function to optimize the parameters of the deep LSTM neural network. The experimental results show that the average execution time of LSTM is 19.46 seconds and 8.24 seconds lower than that of SCB-DBSCAN and CFSFDP, respectively, which shows that the execution time of the LSTM algorithm is faster and more accurate. Therefore, the LSTM algorithm is feasible and effective. The LSTM-based dynamic warning of thought and politics teaching can predict students’ subject performance more accurately and has certain validity and feasibility.

Dynamic Warnings

People often unnecessarily disclose identity information online and puts their privacy at risk. Computer warnings mitigate needless identity disclosure. People, however, often click the OK button without reading warning messages. We utilize eye gaze information to provide dynamic warnings. The dynamic warnings are designed to display just-in-time and then fade out after users read them. They are shown right next to the location where users look. We built a restaurant reservation app to evaluate our dynamic warning system. We conducted an experiment with follow-up surveys. The results showed that our dynamic warnings reduced unnecessary identity disclosure and that they were around 5 times more effective than a Windows warning with a close button. We also found that the longer users’ eyes registered on dynamic warning, the less likely users were to provide their identify information in the dynamic warning condition experiment.

Risk Identification and Conflict Prediction from Videos Based on TTC-ML of a Multi-Lane Weaving Area

Crash risk identification and prediction are expected to play an important role in traffic accident prevention. However, most of the existing studies focus only on highways, not on multi-lane weaving areas. In this paper, a potential collision risk identification and conflict prediction model based on extending Time-to-Collision-Machine Learning (TTC-ML) for multi-lane weaving zone was proposed. The model can accurately learn various features, such as vehicle operation characteristics, risk and conflict distributions, and physical zoning characteristics in the weaving area. Specifically, TTC was used to capture the collision risk severity, and ML extracted vehicle trajectory features. After normalizing and dimensionality reduction of the vehicle trajectory dataset, Naive Bayes, Logistic Regression, and Gradient Boosting Decision Tree (GBDT) models were selected for traffic conflict prediction, and the experiments showed that the GBDT model outperforms two remaining models in terms of prediction accuracy, precision, false-positive rate (FPR) and Area Under Curve (AUC). The research findings of this paper help traffic management departments develop and optimize traffic control schemes, which can be applied to Intelligent Vehicle Infrastructure Cooperative Systems (IVICS) dynamic warning.

Quantitative Threshold of Energy Fractal Dimension for Immediate Rock Burst Warning in Deep Tunnel: A Case Study

Abstract Rock bursts are a serious geological disaster occurring in deep underground engineering operations, which will cause casualties and economic loss. The quantitative threshold of energy fractal dimension for immediate rock burst warning in a deep tunnel was studied. The study was conducted based on the immediate rock burst cases in the deep tunnels of Jinping Hydropower Station, China. Firstly, a fractal dimension calculation method was proposed for deep linear tunnels associated with microseismic monitoring to explore the energy fractal dimension during the 37 immediate rock bursts and their development to events of different intensities (intense and moderate events). On this basis, a mechanism analysis was undertaken to assess the distribution range and evolution of the energy fractal dimension in the development of the immediate rock bursts. Then, the energy fractal dimension, as a quantitative threshold, was taken as a criterion for judging the rock burst risk. Furthermore, the corresponding warning index and dynamic control method were established. This index and method were applied in the subsequent construction process. The results can be used as a guide to establish a dynamic warning system based on the microseismicity monitored and provide a scientific basis for the prediction, warning, and risk-control standard of rock burst disasters during excavation of deep tunnels.

An integrated LSTM-AM and SPRT method for fault early detection of forced-oxidation system in wet flue gas desulfurization

Safe and efficient operation of the forced-oxidation system is of importance to the wet flue gas desulfurization (WFGD). However, equipment and system failures are commonly found due to the long-time running, frequent blower switching, and heavy workload etc., especially after the ultra-low emission (ULE) renovation to meet strict emission standard in China. This work develops a fault early detection method to improve the predictive maintenance of the forced-oxidation system including blowers, pipes, and the slurry tank. A model based on long short-term memory (LSTM) network and attention mechanism (AM) is constructed to predict real-time operation parameters and compare with the measured values. Then the sequence probability ratio test (SPRT) is utilized to analyze the prediction-measurement residual and provide automatic and dynamic warning. All the data for model training and prediction are from the build-in distributed control system (DCS) without additional sensors. The LSTM-AM model proves to accurately predict time-dependent and highly relevant parameters. SPRT can sensitively perceive the fault-caused residual deviation while alleviating the noises. Industrial application to the cases in a 50 MW combined heat and power generation plant is then carried out. Results show that the bearing failure of the oxidation blower and branch pipes (immersed in the slurry tank) blockage can be forecast in advance when the incipient degradation occurs.

Analysis of Small and Medium–Scale River Flood Risk in Case of Exceeding Control Standard Floods Using Hydraulic Model

Exceeding control standard floods pose threats to the management of small and medium–scale rivers. Taking Fuzhouhe river as an example, this paper analyzes the submerged depth, submerged area and arrival time of river flood risk in the case of exceeding control standard floods (with return period of 20, 50, 100 and 200 years) through a coupled one– and two–dimensional hydrodynamic model, draws the flood risk maps and proposes emergency plans. The simulation results of the one–dimensional model reveal that the dikes would be at risk of overflowing for different frequencies of floods, with a higher level of risk on the left bank. The results of the coupled model demonstrate that under all scenarios, the inundation area gradually increases with time until the flood peak subsides, and the larger the flood peak, the faster the inundation area increases. The maximum submerged areas are 42.73 km2, 65.95 km2, 74.86 km2 and 82.71 km2 for four frequencies of flood, respectively. The change of submerged depth under different frequency floods shows a downward–upward–downward trend and the average submerged depth of each frequency floods is about 1.4 m. The flood risk maps of different flood frequencies are created by GIS to analyze flood arrival time, submerged area and submerged depth to plan escape routes and resettlement units. The migration distances are limited within 4 km, the average migration distance is about 2 km, the vehicle evacuation time is less than 20 min, and the walking evacuation time is set to about 70 min. It is concluded that the flood risk of small and medium–scale rivers is a dynamic change process, and dynamic flood assessment, flood warning and embankment modification scheme should be further explored.

Dynamic early-warning model of dam deformation based on deep learning and fusion of spatiotemporal features

The reasonable formulation of early warning indicators is essential for dam deformation safety assessment. Previous studies on dam deformation early warning, however, failed to consider the spatiotemporal features, especially the spatial deep nonlinearity between the multiple environmental factors and multipoint displacements, and the randomness and fuzziness in the description of deformation time-domain distribution, limiting the updating ability of models and the reliability of early-warning indicators. To solve these issues, based on proper orthogonal decomposition (POD), the deep kernel extreme learning machine (DKELM) and a cloud model, a novel dynamic early-warning model using deep learning and spatiotemporal features fusion is proposed for dam deformation. In which, the POD and the correntropy-improved DKELM are coupled to extract the spatial principal component (SPC) of the deformation and to restrain the interference of outliers, and robust deep nonlinear mapping is established to enhance the dynamic updating ability. Moreover, embedding the concept transformation and fusion rule of the cloud model, the deformation early-warning indicator considering the randomness and fuzziness can be formulated and updated, and its reliability can be improved by the time-domain feature fusion of the SPC distribution. Hence, the dynamic warning of dam deformation is achieved by comparing the forecasted SPC and the early-warning indicators. A real dam application and model comparison demonstrate that the proposed model performs well in deformation SPC prediction and gives global and local early-warning indicators with the advantage of dynamic updating, which provides a more abundant and reliable basis for the dynamic safety warning of dam deformation.

Design of Online Learning Early Warning System based on Learning Behavior Analysis

The objective of this study is to design an academic warning system to identify students with abnormal learning behaviours, to give early warning of students' learning status, and to help students successfully complete their studies. In this study, the comprehensive academic performance of university students is taken as the research object, and the basic information data, academic performance data, and online data are collected. After analysing the students' learning behaviour, an online learning warning system is constructed based on grid based on clustering by fast search and find of density peaks (GBCFSFDP) algorithm, and the system is divided into dynamic warning and static warning. It found that the clustering of students' learning behaviour completed by GBCFSFDP algorithm can be divided into six specific categories, and the attributes that influence the learning performance can be differentiated by weighted naive Bayes classification algorithm based on fruit fly optimisation algorithm (WNBC-FOA). The results show that the time spent online have the greatest impact on students' performance. Therefore, this online learning early warning system can make it easier for students and teachers to understand the reasons for learning abnormalities and the correlation between different behaviours and academic performance, so as to make corresponding improvements.

Design of an online learning early warning system based on learning behaviour analysis

The objective of this study is to design an academic warning system to identify students with abnormal learning behaviours, to give early warning of students' learning status, and to help students successfully complete their studies. In this study, the comprehensive academic performance of university students is taken as the research object, and the basic information data, academic performance data, and online data are collected. After analysing the students' learning behaviour, an online learning warning system is constructed based on grid based on clustering by fast search and find of density peaks (GBCFSFDP) algorithm, and the system is divided into dynamic warning and static warning. It found that the clustering of students' learning behaviour completed by GBCFSFDP algorithm can be divided into six specific categories, and the attributes that influence the learning performance can be differentiated by weighted naive Bayes classification algorithm based on fruit fly optimisation algorithm (WNBC-FOA). The results show that the time spent online have the greatest impact on students' performance. Therefore, this online learning early warning system can make it easier for students and teachers to understand the reasons for learning abnormalities and the correlation between different behaviours and academic performance, so as to make corresponding improvements.

Real-Time Dynamic Warning on Deflection Abnormity of Cable-Stayed Bridges Considering Operational Environment Variations

AbstractLong-span bridges face various threats every day due to their sophisticated operational environments. To investigate the operational state of bridges, a real-time dynamic warning method on ...

Increasing maize production and preventing water deficits in semi-arid areas: A study matching fertilization with regional precipitation under mulch planting

Maize production in semi-arid areas is increasingly at risk due to limited and uneven precipitation, and is further constrained by unvalidated nutrition management practices. Matching fertilization levels to regional precipitation, however, can ensure sustainable water use and crop productivity. From 2014–2017, a 4-year field experiment was performed to evaluate the effects of fertilization at five levels (N 0+P2O5 0 kg ha−1, N 117+ P2O5 59 kg ha−1, N 173+ P2O5 87 kg ha−1, N 229+ P2O5115 kg ha−1, and N 285+ P2O5143 kg ha−1) under two typical ridge-furrow mulch plantings (full plastic film mulching, RFF; half plastic film mulching, RFH) on soil water storage, maize yield performance, and water use efficiency (WUE) in a rainfed semi-arid region of the Loess Plateau, China (430 mm and 8 °C in average annual precipitation and air temperature respectively). Fertilization promoted evapotranspiration (ET) and increased maize grain yields by 97.9–141.8 % and WUE by 94.4–122.5 % under both mulch plantings. However, soil water storage at sowing (SWSs) was reduced from 575.5 mm in 2014 to 358.8–500.0 mm under RFF and to 327.4–460.3 mm under RFH in 2017, with the water imbalance exacerbated by the increase in fertilization level. This study reveals that coordinating fertilization with SWSs to optimize ET can promote sustainable water use and maize yields, and thus fertilization at N 180.9+P2O5 90.5 kg ha−1 is recommended under RFF, while that at N 120.1+P2O5 60.5 kg ha−1 under RFH in the semi-arid rain-fed agricultural areas. Although RFF can maintain sustainable water use at higher fertilization level and achieve higher grain yields and WUE compared with RFH, RFH performances a water-saving potential of 60 mm compared with RFF, as evidence shows that the available water (SWSs plus precipitation) to ensure sustainable use of water requires 370–760 mm under RFH, but 440–825 mm under RFF according to a dynamic warning system to avoid water deficit.