Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same g...Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.展开更多
AIM To investigate the incidence of disadvantageous events by using the Global Trigger Tool in an intensive care unit(ICU).METHODS A retrospective descriptive study was performed in a 12-bed university ICU in the city...AIM To investigate the incidence of disadvantageous events by using the Global Trigger Tool in an intensive care unit(ICU).METHODS A retrospective descriptive study was performed in a 12-bed university ICU in the city of Medellin, Colombia. Clinical charts of hospitalized patients were reviewed, between January 1 and December 31, 2016, with the following inclusion criteria: subjects aged over 18 years, with at least 24 h of hospitalization and who had a complete medical history that could be accessed. Interventions: Trained reviewers conducted a retros pective examination of medical charts searching for clue events that elicit investigation, in order to detect an unfavorable event. Measurements: Information was processed through SPSS softwareversion 21; for numerical variables, the mean was reported with standard deviation(SD). Percentages were calculated for qualitative variables. RESULTS Two hundred and forty-four triggers occurred, with 82.4% of subjects having presented with at least one and an average of 3.37 (SD 3.47). A total of 178 adverse events (AEs) took place in 48 individuals, with an incidence of 52.1%. On average, four events per patient were recorded, and for each unfortunate event, 1.98 triggers were presented. The most frequent displeasing issues were: pressure ulcers(17.6%), followed by complications or reactions to medical devices(4.3%), and lacerations or skin defects(3.7%); the least frequent was delayed diagnosis or treatment (0.56%). Thirty-eight point four percent of mishap events caused temporary damage that required intervention, and 48.9% of AEs were preventable. Comparison between AEs and admission diagnoses found that hypertension and sepsis were the only diagnoses that had statistical significance (P = 0.042 and 0.022, respectively).CONCLUSION Almost half of the unfavorable issues were classified as avoidable, which leaves a very wide field of work in terms of preventative activities.展开更多
The SHRP2 Naturalistic Driving Study was used to evaluate the impact of various work zone and driver characteristics on back of queue safety critical events (crash, near-crash, or conflicts) The model included 43 SCE ...The SHRP2 Naturalistic Driving Study was used to evaluate the impact of various work zone and driver characteristics on back of queue safety critical events (crash, near-crash, or conflicts) The model included 43 SCE and 209 “normal” events which were used as controls. The traces included representing 209 unique drivers. A Mixed-Effects Logistic Regression model was developed with probability of a SCE as the response variable and driver and work zone characteristics as predictor variables. The final model indicated glances over 1 second away from the driving task and following closely increased risk of an SCE by 3.8 times and 2.9 times, respectively. Average speed was negatively correlated to crash risk. This is counterintuitive since in most cases, it is expected that higher speeds are related to back of queue crashes. However, most queues form under congested conditions. As a result, vehicles encountering a back of queue would be more likely to be traveling at lower speeds.展开更多
Monthly mean zonal wind data from the European Center for Medium-range Weather Forecasting(ECMWF) t'or December 1982, April 1983, October 1984 and ApriI 1985 are used in numerical integration as thebasic flow in a...Monthly mean zonal wind data from the European Center for Medium-range Weather Forecasting(ECMWF) t'or December 1982, April 1983, October 1984 and ApriI 1985 are used in numerical integration as thebasic flow in a non-linear critical-layer model. The subtropical high is extensive and limited in number if simulated with the basic now in December 1982 and April 1983. It consists of 2 to 3 cells that move westward at alloscillatory periods of 1~ 2 months. The subtropical high, simulated with the basic flow in October 1984 and April1 985. is weak and small in coverage, or distributed in strips that contain up to 4 cells. The high. merged or spillover a short time. is moving westward. The years 1982 ~ 1983 are a process of EI Nino while the years 1984- 1985one of La Nina. lt is known from the chart of energy flux that it oscillates by a much larger amplitude and longerperiod in the El Nino year than in the La Nina year. All the results above have indicated that the basic now' in theEl Nino year is enhancing the subtropical high lagging by about 4 months and that in the La Nina year is decay'ing it. It is consiStent with the well-known observational fact that the SSTA in the equatorial eastern Pacitlc ispositively correlated with the extent and intensity of the subtropical high in west Pacific lagging by 1 ~2 seasons.The result is also important for further study of the formation, maintenance and oscillation of the subtropicalhigh.展开更多
Introduction: A lot of literature is available on critical incidents and near misses but specialty based critical incidents are very scanty. Aim: In this audit, we aimed to report critical incident and near misses dur...Introduction: A lot of literature is available on critical incidents and near misses but specialty based critical incidents are very scanty. Aim: In this audit, we aimed to report critical incident and near misses during conduct of obstetric anesthesia over a period of two years. Methodology: Critical incident forms were collected, entered, analyzed and categorized on the basis of American Standards Association (ASA), phase of incidents, system involved, and type of errors, outcome and action taken. Human error was further categorized on the basis of their contributing factor marked in form. Results: During the reporting period, 5511 anaesthetics were administered and 55 reports were received out of which 53 reports were included in analysis. Fifty three reports were divided into 33 critical incidents and 20 near misses. Out of 33 critical incidents, 54.5% involved CVS system and musculoskeletal system, followed by neuromuscular (n = 5), drug related (n = 4), airway/respiratory system (n = 2), central nervous system (n = 2) and renal system (n = 1). Forty five incidents possess no untoward effect while 7 led to minor and only one to severe physiological disturbance. Human errors were (n = 30) 57% reports and failure to check was the main contributory factor. Conclusion: Critical incidents reporting needs to be introduced in sub-specialties at departmental, national and international level. Checking of equipment, medication and anesthesia machine must be part of regular checks in elective and emergency cases.展开更多
This study discussed the water sector as a critical infrastructural element in Jordan where the sector is exposed to the extreme events. The exposure of the country to extreme events has initiated this study. Such eve...This study discussed the water sector as a critical infrastructural element in Jordan where the sector is exposed to the extreme events. The exposure of the country to extreme events has initiated this study. Such events are Pollution accidents, flooding, draughts, overexploitation, failure in electricity supply, climate changes, earthquakes, landslides, failure of dams, failure of wastewater treatment plants, failure of desalination plants, sabotage, fire, water theft, migration and demographic changes (immigration and urban migration), relations to neighboring countries, epidemics, and others. These extreme events are discussed in this article and the results show that failures in the water infrastructure and water supply, in Jordan, with its water sector situation have rigorous percussions on the country’s health, food supply, economy, societal stability, the built environment, and on other water-related issues. The study concludes that developing national programs to protect the water infrastructure in the water-fragile country has become very crucial to reach a robust and resilient water sector which not only means providing the inhabitants with quantitatively sufficient and qualitatively healthy water but also aims to incorporate guaranteeing social, economic and political stability.展开更多
目的分析急诊科危重症患者院内转运不良事件风险因素,构建风险预测模型。方法采用方便抽样法选取2021年10月至2023年2月某院急诊科进行院内转运的870例危重症患者的临床资料,采用单因素和多因素Logistic回归分析建立风险预测模型,以受...目的分析急诊科危重症患者院内转运不良事件风险因素,构建风险预测模型。方法采用方便抽样法选取2021年10月至2023年2月某院急诊科进行院内转运的870例危重症患者的临床资料,采用单因素和多因素Logistic回归分析建立风险预测模型,以受试者工作特征(receiver operating characteristic,ROC)曲线下面积(area under curve,AUC)评价模型预测效果。结果英国国家早期预警评分(national early warning score,NEWS)、血氧饱和度、急诊B超、血管活性药物、机械通气是急诊科危重症患者发生病情不良事件的独立风险因素;血氧饱和度、携氧装置、Ⅲ类管路、护工参与转运是技术不良事件的独立风险因素(均P<0.05)。AUC分别为0.813,0.756。结论构建的急诊科危重症患者院内转运不良事件风险预测模型具有一定的参考价值。展开更多
Floods caused by extreme weather events and climate change have increased in occurrence and severity all over the world,resulting in devastation and disruption of activities.Researchers and policy practitioners have i...Floods caused by extreme weather events and climate change have increased in occurrence and severity all over the world,resulting in devastation and disruption of activities.Researchers and policy practitioners have increasingly paid attention to the role of critical infrastructure(CI)in disaster risk reduction,flood resilience and climate change adaptation in terms of its backbone functions in maintaining societal services in hazard attacks.The analysed city in this study,Xinxiang(Henan province,China),was affected by an extreme flood event that occurred on 17–23 July 2021,which caused great socio-economic losses.However,few studies have focused on medium-sized cities and the flood cascading effects on CI during this event.Therefore,this study explores the damages caused by this flooding event with links to CI,such as health services,energy supply stations,shelters and transport facilities(HEST infrastructure).To achieve this,the study first combines RGB(red,green blue)composition and supervised classification for flood detection to monitor and map flood inundation areas.Second,it manages a multiscenario simulation and evaluates the cascading effects on HEST infrastructure.Diverse open-source data are employed,including Sentinel-1 synthetic aperture radar(SAR)data and Landsat-8 OIL data,point-of-interest(POI)and OpenStreetMap(OSM)data.The study reveals that this extreme flood event has profoundly affected croplands and villagers.Due to the revisiting period of Sentinel-1 SAR data,four scenarios are simulated to portray the retreated but‘omitted’floodwater:Scenario 0 is the flood inundation area on 27 July,and Scenarios 1,2 and 3 are built based on this information with a buffer of 50,100 and 150 m outwards,respectively.In the four scenarios,as the inundation areas expand,the affected HEST infrastructure becomes more clustered at the centre of the core study area,indicating that those located in the urban centre are more susceptible to flooding.Furthermore,the affected transport facilities assemble in the north and east of the core study area,implying that transport facilities located in the north and east of the core study area are more susceptible to flooding.The verification of the flood inundation maps and affected HEST infrastructure in the scenario simulation support the series method adopted in this study.The findings of this study can be used by flood managers,urban planners and other decision makers to better understand extreme historic weather events in China,improve flood resilience and decrease the negative impacts of such events on HEST infrastructure.展开更多
基金funded by the Fujian Province Science and Technology Plan,China(Grant Number 2019H0017).
文摘Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.
文摘AIM To investigate the incidence of disadvantageous events by using the Global Trigger Tool in an intensive care unit(ICU).METHODS A retrospective descriptive study was performed in a 12-bed university ICU in the city of Medellin, Colombia. Clinical charts of hospitalized patients were reviewed, between January 1 and December 31, 2016, with the following inclusion criteria: subjects aged over 18 years, with at least 24 h of hospitalization and who had a complete medical history that could be accessed. Interventions: Trained reviewers conducted a retros pective examination of medical charts searching for clue events that elicit investigation, in order to detect an unfavorable event. Measurements: Information was processed through SPSS softwareversion 21; for numerical variables, the mean was reported with standard deviation(SD). Percentages were calculated for qualitative variables. RESULTS Two hundred and forty-four triggers occurred, with 82.4% of subjects having presented with at least one and an average of 3.37 (SD 3.47). A total of 178 adverse events (AEs) took place in 48 individuals, with an incidence of 52.1%. On average, four events per patient were recorded, and for each unfortunate event, 1.98 triggers were presented. The most frequent displeasing issues were: pressure ulcers(17.6%), followed by complications or reactions to medical devices(4.3%), and lacerations or skin defects(3.7%); the least frequent was delayed diagnosis or treatment (0.56%). Thirty-eight point four percent of mishap events caused temporary damage that required intervention, and 48.9% of AEs were preventable. Comparison between AEs and admission diagnoses found that hypertension and sepsis were the only diagnoses that had statistical significance (P = 0.042 and 0.022, respectively).CONCLUSION Almost half of the unfavorable issues were classified as avoidable, which leaves a very wide field of work in terms of preventative activities.
文摘The SHRP2 Naturalistic Driving Study was used to evaluate the impact of various work zone and driver characteristics on back of queue safety critical events (crash, near-crash, or conflicts) The model included 43 SCE and 209 “normal” events which were used as controls. The traces included representing 209 unique drivers. A Mixed-Effects Logistic Regression model was developed with probability of a SCE as the response variable and driver and work zone characteristics as predictor variables. The final model indicated glances over 1 second away from the driving task and following closely increased risk of an SCE by 3.8 times and 2.9 times, respectively. Average speed was negatively correlated to crash risk. This is counterintuitive since in most cases, it is expected that higher speeds are related to back of queue crashes. However, most queues form under congested conditions. As a result, vehicles encountering a back of queue would be more likely to be traveling at lower speeds.
文摘Monthly mean zonal wind data from the European Center for Medium-range Weather Forecasting(ECMWF) t'or December 1982, April 1983, October 1984 and ApriI 1985 are used in numerical integration as thebasic flow in a non-linear critical-layer model. The subtropical high is extensive and limited in number if simulated with the basic now in December 1982 and April 1983. It consists of 2 to 3 cells that move westward at alloscillatory periods of 1~ 2 months. The subtropical high, simulated with the basic flow in October 1984 and April1 985. is weak and small in coverage, or distributed in strips that contain up to 4 cells. The high. merged or spillover a short time. is moving westward. The years 1982 ~ 1983 are a process of EI Nino while the years 1984- 1985one of La Nina. lt is known from the chart of energy flux that it oscillates by a much larger amplitude and longerperiod in the El Nino year than in the La Nina year. All the results above have indicated that the basic now' in theEl Nino year is enhancing the subtropical high lagging by about 4 months and that in the La Nina year is decay'ing it. It is consiStent with the well-known observational fact that the SSTA in the equatorial eastern Pacitlc ispositively correlated with the extent and intensity of the subtropical high in west Pacific lagging by 1 ~2 seasons.The result is also important for further study of the formation, maintenance and oscillation of the subtropicalhigh.
文摘Introduction: A lot of literature is available on critical incidents and near misses but specialty based critical incidents are very scanty. Aim: In this audit, we aimed to report critical incident and near misses during conduct of obstetric anesthesia over a period of two years. Methodology: Critical incident forms were collected, entered, analyzed and categorized on the basis of American Standards Association (ASA), phase of incidents, system involved, and type of errors, outcome and action taken. Human error was further categorized on the basis of their contributing factor marked in form. Results: During the reporting period, 5511 anaesthetics were administered and 55 reports were received out of which 53 reports were included in analysis. Fifty three reports were divided into 33 critical incidents and 20 near misses. Out of 33 critical incidents, 54.5% involved CVS system and musculoskeletal system, followed by neuromuscular (n = 5), drug related (n = 4), airway/respiratory system (n = 2), central nervous system (n = 2) and renal system (n = 1). Forty five incidents possess no untoward effect while 7 led to minor and only one to severe physiological disturbance. Human errors were (n = 30) 57% reports and failure to check was the main contributory factor. Conclusion: Critical incidents reporting needs to be introduced in sub-specialties at departmental, national and international level. Checking of equipment, medication and anesthesia machine must be part of regular checks in elective and emergency cases.
文摘This study discussed the water sector as a critical infrastructural element in Jordan where the sector is exposed to the extreme events. The exposure of the country to extreme events has initiated this study. Such events are Pollution accidents, flooding, draughts, overexploitation, failure in electricity supply, climate changes, earthquakes, landslides, failure of dams, failure of wastewater treatment plants, failure of desalination plants, sabotage, fire, water theft, migration and demographic changes (immigration and urban migration), relations to neighboring countries, epidemics, and others. These extreme events are discussed in this article and the results show that failures in the water infrastructure and water supply, in Jordan, with its water sector situation have rigorous percussions on the country’s health, food supply, economy, societal stability, the built environment, and on other water-related issues. The study concludes that developing national programs to protect the water infrastructure in the water-fragile country has become very crucial to reach a robust and resilient water sector which not only means providing the inhabitants with quantitatively sufficient and qualitatively healthy water but also aims to incorporate guaranteeing social, economic and political stability.
文摘目的分析急诊科危重症患者院内转运不良事件风险因素,构建风险预测模型。方法采用方便抽样法选取2021年10月至2023年2月某院急诊科进行院内转运的870例危重症患者的临床资料,采用单因素和多因素Logistic回归分析建立风险预测模型,以受试者工作特征(receiver operating characteristic,ROC)曲线下面积(area under curve,AUC)评价模型预测效果。结果英国国家早期预警评分(national early warning score,NEWS)、血氧饱和度、急诊B超、血管活性药物、机械通气是急诊科危重症患者发生病情不良事件的独立风险因素;血氧饱和度、携氧装置、Ⅲ类管路、护工参与转运是技术不良事件的独立风险因素(均P<0.05)。AUC分别为0.813,0.756。结论构建的急诊科危重症患者院内转运不良事件风险预测模型具有一定的参考价值。
基金This research is co-funded by the National Youth Science Fund Project of the National Natural Science Foundation of China(52108050)the Guangdong Basic and Applied Basic Research Foundation(2023A1515011653)+2 种基金the Guangzhou Science and Technology Program(202201010503)the State Key Laboratory of Subtropical Building Science at South China University of Technology(2022ZB08)the China Postdoctoral Science Foundation(2021M701238).
文摘Floods caused by extreme weather events and climate change have increased in occurrence and severity all over the world,resulting in devastation and disruption of activities.Researchers and policy practitioners have increasingly paid attention to the role of critical infrastructure(CI)in disaster risk reduction,flood resilience and climate change adaptation in terms of its backbone functions in maintaining societal services in hazard attacks.The analysed city in this study,Xinxiang(Henan province,China),was affected by an extreme flood event that occurred on 17–23 July 2021,which caused great socio-economic losses.However,few studies have focused on medium-sized cities and the flood cascading effects on CI during this event.Therefore,this study explores the damages caused by this flooding event with links to CI,such as health services,energy supply stations,shelters and transport facilities(HEST infrastructure).To achieve this,the study first combines RGB(red,green blue)composition and supervised classification for flood detection to monitor and map flood inundation areas.Second,it manages a multiscenario simulation and evaluates the cascading effects on HEST infrastructure.Diverse open-source data are employed,including Sentinel-1 synthetic aperture radar(SAR)data and Landsat-8 OIL data,point-of-interest(POI)and OpenStreetMap(OSM)data.The study reveals that this extreme flood event has profoundly affected croplands and villagers.Due to the revisiting period of Sentinel-1 SAR data,four scenarios are simulated to portray the retreated but‘omitted’floodwater:Scenario 0 is the flood inundation area on 27 July,and Scenarios 1,2 and 3 are built based on this information with a buffer of 50,100 and 150 m outwards,respectively.In the four scenarios,as the inundation areas expand,the affected HEST infrastructure becomes more clustered at the centre of the core study area,indicating that those located in the urban centre are more susceptible to flooding.Furthermore,the affected transport facilities assemble in the north and east of the core study area,implying that transport facilities located in the north and east of the core study area are more susceptible to flooding.The verification of the flood inundation maps and affected HEST infrastructure in the scenario simulation support the series method adopted in this study.The findings of this study can be used by flood managers,urban planners and other decision makers to better understand extreme historic weather events in China,improve flood resilience and decrease the negative impacts of such events on HEST infrastructure.
