BACKGROUND Post-endoscopic retrograde cholangiopancreatography(ERCP)pancreatitis is a common complication of the procedure.The effective prevention of post-ERCP pancreatitis(PEP)remains a key focus of clinical researc...BACKGROUND Post-endoscopic retrograde cholangiopancreatography(ERCP)pancreatitis is a common complication of the procedure.The effective prevention of post-ERCP pancreatitis(PEP)remains a key focus of clinical research.AIM To develop a prediction model for PEP based on multidimensional clinical indicators and evaluate its clinical application value.METHODS We retrospectively analyzed 183 patients with biliary tract diseases who underwent ERCP at Xuzhou Medical University from January 2020 to June 2023,divided into non-PEP(n=159)and PEP(n=24)groups based on PEP development.Baseline and intraoperative data were compared,and PEP-related factors examined via univariate and multivariate logistic regression.Using R,70%of patients were assigned to training and 30%to testing sets for PEP prediction model development.Model accuracy was evaluated using a calibration curve and receiver operating characteristic(ROC)area under the curve(AUC).RESULTS Age,total cholesterol level,history of pancreatitis,pancreatic ductography,bleeding,and intubation time differed significantly between the two groups when baseline data and intraoperative conditions were compared(P<0.05).Multifactorial logistic regression analysis demonstrated that age[odds ratio(OR)=0.192,95%confidence interval(CI):0.053-0.698],total cholesterol(OR=0.324,95%CI:0.152-0.694),history of pancreatitis(OR=6.159,95%CI:1.770-21.434),pancreatography(OR=3.726,95%CI:1.028-13.507),and bleeding(OR=3.059,95%CI:1.001-9.349)were independently associated with acute pancreatitis after ERCP.The predictive probabilities from the calibration curves had mean errors of 0.021 and 0.030,with ROC AUCs of 0.840 and 0.797 in the training and test sets,respectively.CONCLUSION Age,total cholesterol,pancreatitis history,pancreatic ductography,and bleeding influence the risk of acute PEP.A model incorporating these factors may aid early detection and intervention.展开更多
[ Objective] The study aimed to discuss the temporal-spatial distribution and short-range prediction indicators of hail weather in east central Haixi Prefecture of Qinghai Province. [Method] Using hail data of six sta...[ Objective] The study aimed to discuss the temporal-spatial distribution and short-range prediction indicators of hail weather in east central Haixi Prefecture of Qinghai Province. [Method] Using hail data of six stations in east central Haixi Prefecture from 1960 to 2010, the temporal and spatial distribution of hail weather was analyzed firstly. Afterwards, based on the high-altitude factual data of 30 case studies of hail during 2006 -2010, its high-altitude and ground weather situation and physical quantity field were studied to summarize short-term circulation pattern and shod- range prediction characteristics of hail weather. [ Result] In east central Haixi, hail appeared from April to September, and it was most frequently from May to August. Meanwhile, hail was frequent from 14：00 to 20：00. Among the six stations, hail was most frequent in Tianjun but least frequent in Wulan. Moreover, hail disaster mainly occurred in Wulan and Tianjun. In addition, there were three typos of circulation pattern of hail weather at 500 hPa. Hail mainly occurred under the effect of northwest airflow, and it had shortwave trough, cold center or trough, jet stream core or one of the three. Hail appeared frequently under the situation of upper-level divergence and low-level convergence, and abundant water vapor and water vapor flux convergence at low levels were important conditions for hailing. [ Conclusion] The research could provide scientific references for improving the accuracy of hail forecast.展开更多
Stock market trends forecast is one of the most current topics and a significant research challenge due to its dynamic and unstable nature.The stock data is usually non-stationary,and attributes are non-correlative to...Stock market trends forecast is one of the most current topics and a significant research challenge due to its dynamic and unstable nature.The stock data is usually non-stationary,and attributes are non-correlative to each other.Several traditional Stock Technical Indicators(STIs)may incorrectly predict the stockmarket trends.To study the stock market characteristics using STIs and make efficient trading decisions,a robust model is built.This paper aims to build up an Evolutionary Deep Learning Model(EDLM)to identify stock trends’prices by using STIs.The proposed model has implemented the Deep Learning(DL)model to establish the concept of Correlation-Tensor.The analysis of the dataset of three most popular banking organizations obtained from the live stock market based on the National Stock exchange(NSE)-India,a Long Short Term Memory(LSTM)is used.The datasets encompassed the trading days from the 17^(th) of Nov 2008 to the 15^(th) of Nov 2018.This work also conducted exhaustive experiments to study the correlation of various STIs with stock price trends.The model built with an EDLM has shown significant improvements over two benchmark ML models and a deep learning one.The proposed model aids investors in making profitable investment decisions as it presents trend-based forecasting and has achieved a prediction accuracy of 63.59%,56.25%,and 57.95%on the datasets of HDFC,Yes Bank,and SBI,respectively.Results indicate that the proposed EDLA with a combination of STIs can often provide improved results than the other state-of-the-art algorithms.展开更多
Aiming at the difficulty of mining fault prognosis starting points and constructing prognostic models for remaining useful life(RUL)prediction of rolling bearings,a RUL prediction method is proposed based on health in...Aiming at the difficulty of mining fault prognosis starting points and constructing prognostic models for remaining useful life(RUL)prediction of rolling bearings,a RUL prediction method is proposed based on health indicator(HI)extraction and trajectory-enhanced particle filter(TE-PF).By extracting a HI that can accurately track the trending of bearing degradation and combining it with the early fault enhancement technology,early abnormal sample nodes can be mined to provide more samples with fault information for the construction and training of subsequent prediction models.Aiming at the problem that traditional degradation rate models based on PF are vulnerable to HI mutations,a TE-PF prediction method is proposed based on comprehensive utilization of historical degradation information to timely modify prediction model parameters.Results from a rolling bearing prognostic study show that prediction starting points can be accurately detected and a reasonable prediction model can be conveniently constructed by the RUL prediction method based on HI amplitude abnormal detection and TE-PF.Furthermore,aiming at the RUL prediction problem under the condition of HI mutation,RUL prediction with probability and statistics characteristics under a confidence interval can be obtained based on the method proposed.展开更多
To systematically incorporate multiple influencing factors,the coupled-state frequency memory(Co-SFM)network is proposed.This model integrates Copula estimation with neural networks,fusing multilevel data information,...To systematically incorporate multiple influencing factors,the coupled-state frequency memory(Co-SFM)network is proposed.This model integrates Copula estimation with neural networks,fusing multilevel data information,which is then fed into downstream learning modules.Co-SFM employs an upstream fusion module to incorporate multilevel data,thereby constructing a macro-plate-micro data structure.This configuration helps identify and integrate characteristics from different data levels,facilitating a deeper understanding of the internal links within the financial system.In the downstream model,Co-SFM uses a state-frequency memory network to mine hidden frequency information within stock prices,and the multifrequency patterns of sequential data are modeled.Empirical results show that Co-SFM s prediction accuracy for stock price trends is significantly better than that of other models.This is especially evident in multistep medium and long-term trend predictions,where integrating multilevel data results in notably improved accuracy.展开更多
This paper addresses the accuracy and timeliness limitations of traditional comprehensive prediction methods by proposing an approach of decision-level fusion of multisource data.A risk prediction indicator system was...This paper addresses the accuracy and timeliness limitations of traditional comprehensive prediction methods by proposing an approach of decision-level fusion of multisource data.A risk prediction indicator system was established for water and mud inrush in tunnels by analyzing advanced prediction data for specifi c tunnel segments.Additionally,the indicator weights were determined using the analytic hierarchy process combined with the Huber weighting method.Subsequently,a multisource data decision-layer fusion algorithm was utilized to generate fused imaging results for tunnel water and mud inrush risk predictions.Meanwhile,risk analysis was performed for different tunnel sections to achieve spatial and temporal complementarity within the indicator system and optimize redundant information.Finally,model feasibility was validated using the CZ Project Sejila Mountain Tunnel segment as a case study,yielding favorable risk prediction results and enabling effi cient information fusion and support for construction decision-making.展开更多
The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster predic...The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster prediction.To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction,this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory(Bi-LSTM)network.The method involves three main modules,including microseismic spatio-temporal characteristic indicators construction,temporal prediction model,and spatial prediction model.To validate the effectiveness of the proposed method,engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia,focusing on 13 high-energy microseismic events with energy levels greater than 105 J.In terms of temporal prediction,the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions,and there is no false alarm detected throughout the entire testing period.Moreover,compared to the traditional threshold-based coal burst temporal prediction method,the accuracy of the proposed method is increased by 38.5%.In terms of spatial prediction,the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions,3 medium hazard predictions,and 4 weak hazard predictions.展开更多
The Jurassic Lianggaoshan Formation in eastern Sichuan Basin is a key target for shale oil exploration.It faces challenges in three-pressure prediction due to complex structural and sedimentary interactions,as well as...The Jurassic Lianggaoshan Formation in eastern Sichuan Basin is a key target for shale oil exploration.It faces challenges in three-pressure prediction due to complex structural and sedimentary interactions,as well as strong reservoir anisotropy.These issues often lead to wellbore instability and gas logging anomalies during drilling.This study presents an integrated workflow that combines residual moveout correction using correlation-based dynamic time warping(CDTW),high-resolution seismic waveform indication inversion,and three-pressure prediction of jointing well-seismic data.Applied to the LT1 well block,the workflow effectively corrects anisotropic residual moveout in image gathers,leading to a signal strength increase of over 10%in frequency bands above 30 Hz and enhancing event continuity.High-resolution rock mechanical parameters are obtained through seismic waveform inversion and regional calibration,enabling the prediction of three-dimensional pore pressure,collapse pressure and fracture pressure.The results are consistent with actual drilling gas shows and core data,confirming the method's accuracy and supporting mud weight planning and wellbore stability efforts.This cost-effective and technically robust approach proves highly reliable in complex environments with significant heterogeneity and anisotropy,assisting drilling decisions and risk management in eastern Sichuan and similar challenging geological settings.展开更多
Dear Editor,This letter focuses on the remaining useful life(RUL)prediction task under limited labeled samples.Existing machine-learning-based RUL prediction methods for this task usually pay attention to mining degra...Dear Editor,This letter focuses on the remaining useful life(RUL)prediction task under limited labeled samples.Existing machine-learning-based RUL prediction methods for this task usually pay attention to mining degradation information to improve the prediction accuracy of degradation value or health indicator for the next epoch.However,they ignore the cumulative prediction error caused by iterations before reaching the failure point.展开更多
文摘BACKGROUND Post-endoscopic retrograde cholangiopancreatography(ERCP)pancreatitis is a common complication of the procedure.The effective prevention of post-ERCP pancreatitis(PEP)remains a key focus of clinical research.AIM To develop a prediction model for PEP based on multidimensional clinical indicators and evaluate its clinical application value.METHODS We retrospectively analyzed 183 patients with biliary tract diseases who underwent ERCP at Xuzhou Medical University from January 2020 to June 2023,divided into non-PEP(n=159)and PEP(n=24)groups based on PEP development.Baseline and intraoperative data were compared,and PEP-related factors examined via univariate and multivariate logistic regression.Using R,70%of patients were assigned to training and 30%to testing sets for PEP prediction model development.Model accuracy was evaluated using a calibration curve and receiver operating characteristic(ROC)area under the curve(AUC).RESULTS Age,total cholesterol level,history of pancreatitis,pancreatic ductography,bleeding,and intubation time differed significantly between the two groups when baseline data and intraoperative conditions were compared(P<0.05).Multifactorial logistic regression analysis demonstrated that age[odds ratio(OR)=0.192,95%confidence interval(CI):0.053-0.698],total cholesterol(OR=0.324,95%CI:0.152-0.694),history of pancreatitis(OR=6.159,95%CI:1.770-21.434),pancreatography(OR=3.726,95%CI:1.028-13.507),and bleeding(OR=3.059,95%CI:1.001-9.349)were independently associated with acute pancreatitis after ERCP.The predictive probabilities from the calibration curves had mean errors of 0.021 and 0.030,with ROC AUCs of 0.840 and 0.797 in the training and test sets,respectively.CONCLUSION Age,total cholesterol,pancreatitis history,pancreatic ductography,and bleeding influence the risk of acute PEP.A model incorporating these factors may aid early detection and intervention.
文摘[ Objective] The study aimed to discuss the temporal-spatial distribution and short-range prediction indicators of hail weather in east central Haixi Prefecture of Qinghai Province. [Method] Using hail data of six stations in east central Haixi Prefecture from 1960 to 2010, the temporal and spatial distribution of hail weather was analyzed firstly. Afterwards, based on the high-altitude factual data of 30 case studies of hail during 2006 -2010, its high-altitude and ground weather situation and physical quantity field were studied to summarize short-term circulation pattern and shod- range prediction characteristics of hail weather. [ Result] In east central Haixi, hail appeared from April to September, and it was most frequently from May to August. Meanwhile, hail was frequent from 14：00 to 20：00. Among the six stations, hail was most frequent in Tianjun but least frequent in Wulan. Moreover, hail disaster mainly occurred in Wulan and Tianjun. In addition, there were three typos of circulation pattern of hail weather at 500 hPa. Hail mainly occurred under the effect of northwest airflow, and it had shortwave trough, cold center or trough, jet stream core or one of the three. Hail appeared frequently under the situation of upper-level divergence and low-level convergence, and abundant water vapor and water vapor flux convergence at low levels were important conditions for hailing. [ Conclusion] The research could provide scientific references for improving the accuracy of hail forecast.
基金Funding is provided by Taif University Researchers Supporting Project Number(TURSP-2020/10),Taif University,Taif,Saudi Arabia.
文摘Stock market trends forecast is one of the most current topics and a significant research challenge due to its dynamic and unstable nature.The stock data is usually non-stationary,and attributes are non-correlative to each other.Several traditional Stock Technical Indicators(STIs)may incorrectly predict the stockmarket trends.To study the stock market characteristics using STIs and make efficient trading decisions,a robust model is built.This paper aims to build up an Evolutionary Deep Learning Model(EDLM)to identify stock trends’prices by using STIs.The proposed model has implemented the Deep Learning(DL)model to establish the concept of Correlation-Tensor.The analysis of the dataset of three most popular banking organizations obtained from the live stock market based on the National Stock exchange(NSE)-India,a Long Short Term Memory(LSTM)is used.The datasets encompassed the trading days from the 17^(th) of Nov 2008 to the 15^(th) of Nov 2018.This work also conducted exhaustive experiments to study the correlation of various STIs with stock price trends.The model built with an EDLM has shown significant improvements over two benchmark ML models and a deep learning one.The proposed model aids investors in making profitable investment decisions as it presents trend-based forecasting and has achieved a prediction accuracy of 63.59%,56.25%,and 57.95%on the datasets of HDFC,Yes Bank,and SBI,respectively.Results indicate that the proposed EDLA with a combination of STIs can often provide improved results than the other state-of-the-art algorithms.
基金supported by the National Key Research and Development Program of China (No.2018YFB1702401)National Natural Science Foundation of China (Grant No.51975576,51475463).
文摘Aiming at the difficulty of mining fault prognosis starting points and constructing prognostic models for remaining useful life(RUL)prediction of rolling bearings,a RUL prediction method is proposed based on health indicator(HI)extraction and trajectory-enhanced particle filter(TE-PF).By extracting a HI that can accurately track the trending of bearing degradation and combining it with the early fault enhancement technology,early abnormal sample nodes can be mined to provide more samples with fault information for the construction and training of subsequent prediction models.Aiming at the problem that traditional degradation rate models based on PF are vulnerable to HI mutations,a TE-PF prediction method is proposed based on comprehensive utilization of historical degradation information to timely modify prediction model parameters.Results from a rolling bearing prognostic study show that prediction starting points can be accurately detected and a reasonable prediction model can be conveniently constructed by the RUL prediction method based on HI amplitude abnormal detection and TE-PF.Furthermore,aiming at the RUL prediction problem under the condition of HI mutation,RUL prediction with probability and statistics characteristics under a confidence interval can be obtained based on the method proposed.
基金The National Natural Science Foundation of China(No.72173018).
文摘To systematically incorporate multiple influencing factors,the coupled-state frequency memory(Co-SFM)network is proposed.This model integrates Copula estimation with neural networks,fusing multilevel data information,which is then fed into downstream learning modules.Co-SFM employs an upstream fusion module to incorporate multilevel data,thereby constructing a macro-plate-micro data structure.This configuration helps identify and integrate characteristics from different data levels,facilitating a deeper understanding of the internal links within the financial system.In the downstream model,Co-SFM uses a state-frequency memory network to mine hidden frequency information within stock prices,and the multifrequency patterns of sequential data are modeled.Empirical results show that Co-SFM s prediction accuracy for stock price trends is significantly better than that of other models.This is especially evident in multistep medium and long-term trend predictions,where integrating multilevel data results in notably improved accuracy.
基金supported by the National Natural Science Foundation of China (grant numbers 42293351, and U2468221)。
文摘This paper addresses the accuracy and timeliness limitations of traditional comprehensive prediction methods by proposing an approach of decision-level fusion of multisource data.A risk prediction indicator system was established for water and mud inrush in tunnels by analyzing advanced prediction data for specifi c tunnel segments.Additionally,the indicator weights were determined using the analytic hierarchy process combined with the Huber weighting method.Subsequently,a multisource data decision-layer fusion algorithm was utilized to generate fused imaging results for tunnel water and mud inrush risk predictions.Meanwhile,risk analysis was performed for different tunnel sections to achieve spatial and temporal complementarity within the indicator system and optimize redundant information.Finally,model feasibility was validated using the CZ Project Sejila Mountain Tunnel segment as a case study,yielding favorable risk prediction results and enabling effi cient information fusion and support for construction decision-making.
基金supported by the National Research and Development Program(2022YFC3004603)the Jiangsu Province International Collaboration Program-Key National Industrial Technology Research and Development Cooperation Projects(BZ2023050)+1 种基金the Natural Science Foundation of Jiangsu Province(BK20221109)the National Natural Science Foundation of China(52274098).
文摘The increasingly severe state of coal burst disaster has emerged as a critical factor constraining coal mine safety production,and it has become a challenging task to enhance the accuracy of coal burst disaster prediction.To address the issue of insufficient exploration of the spatio-temporal characteristic of microseismic data and the challenging selection of the optimal time window size in spatio-temporal prediction,this paper integrates deep learning methods and theory to propose a novel coal burst spatio-temporal prediction method based on Bidirectional Long Short-Term Memory(Bi-LSTM)network.The method involves three main modules,including microseismic spatio-temporal characteristic indicators construction,temporal prediction model,and spatial prediction model.To validate the effectiveness of the proposed method,engineering application tests are conducted at a high-risk working face in the Ordos mining area of Inner Mongolia,focusing on 13 high-energy microseismic events with energy levels greater than 105 J.In terms of temporal prediction,the analysis indicates that the temporal prediction results consist of 10 strong predictions and 3 medium predictions,and there is no false alarm detected throughout the entire testing period.Moreover,compared to the traditional threshold-based coal burst temporal prediction method,the accuracy of the proposed method is increased by 38.5%.In terms of spatial prediction,the distribution of spatial prediction results for high-energy events comprises 6 strong hazard predictions,3 medium hazard predictions,and 4 weak hazard predictions.
基金supported by Science and Technology Cooperation Project of the CNPC-SWPU Innovation Alliance(No.2020CX010202).
文摘The Jurassic Lianggaoshan Formation in eastern Sichuan Basin is a key target for shale oil exploration.It faces challenges in three-pressure prediction due to complex structural and sedimentary interactions,as well as strong reservoir anisotropy.These issues often lead to wellbore instability and gas logging anomalies during drilling.This study presents an integrated workflow that combines residual moveout correction using correlation-based dynamic time warping(CDTW),high-resolution seismic waveform indication inversion,and three-pressure prediction of jointing well-seismic data.Applied to the LT1 well block,the workflow effectively corrects anisotropic residual moveout in image gathers,leading to a signal strength increase of over 10%in frequency bands above 30 Hz and enhancing event continuity.High-resolution rock mechanical parameters are obtained through seismic waveform inversion and regional calibration,enabling the prediction of three-dimensional pore pressure,collapse pressure and fracture pressure.The results are consistent with actual drilling gas shows and core data,confirming the method's accuracy and supporting mud weight planning and wellbore stability efforts.This cost-effective and technically robust approach proves highly reliable in complex environments with significant heterogeneity and anisotropy,assisting drilling decisions and risk management in eastern Sichuan and similar challenging geological settings.
基金supported in part by the National Natural Science Foundation of China(U2034209)the Postdoctoral Science Foundation of Chongqing(cstc2021jcyj-bsh X0047)+1 种基金the Fundamental Research Funds for the Central Universities(2022CDJJMRH-008)the National Natural Science Foundation of China(62203075)
文摘Dear Editor,This letter focuses on the remaining useful life(RUL)prediction task under limited labeled samples.Existing machine-learning-based RUL prediction methods for this task usually pay attention to mining degradation information to improve the prediction accuracy of degradation value or health indicator for the next epoch.However,they ignore the cumulative prediction error caused by iterations before reaching the failure point.
