The relationship between precipitation types and meteorological factors was surveyed based on the effect analysis of main meteorological parameters on asphalt pavement surface icing conditions and prediction analysis ...The relationship between precipitation types and meteorological factors was surveyed based on the effect analysis of main meteorological parameters on asphalt pavement surface icing conditions and prediction analysis model of asphalt pavement temperature was established.This study aims to determine the correlation between icy pavement and meteorological factors and implement an accurate prediction of the icing condition of pavement.Considering the road slipperiness criterion presented by Norrman,a discriminative standard of icing condition of asphalt pavement surface in the central area of Zhejiang Province was proposed.Based on the above analysis results,a prediction model of pavement surface icing condition involved in asphalt pavement and ambient temperatures under the condition of different precipitation types was constructed by using support vector machine(SVM)method.Results demonstrate that(1)the distribution characteristics of daily mean air temperature,daily mean pavement temperature,daily average wind speed,and average daily rainfall have remarkable differences under the condition of different precipitation types,wherein the variation features of daily mean air temperature and daily mean pavement temperature are obvious;(2)the indirect prediction of precipitation type and pavement surface temperature could be accomplished in terms of meteorological monitoring data;(3)the influence of pavement surface icing conditions on driving safety is lower than that of rainwater freezing on a cold surface,melting snow at air temperature above O C,and melting snow at air temperature below 0 C;and(4)the SVM-based prediction model of pavement surface icing condition has an accurate analysis result with misreporting rate below 6%.The generalization ability of the proposed model is good and fully demonstrates the application prospects of SVM in the pavement weather prediction field.This study can provide theoretical and technical support for real-time warning about icy asphalt pavements in winter.展开更多
Based on the exploration project of a mining area in Haiyang,as well as data collection and groundwater monitoring,groundwater environmental impact was predicted,and emergency protection measures were proposed.The res...Based on the exploration project of a mining area in Haiyang,as well as data collection and groundwater monitoring,groundwater environmental impact was predicted,and emergency protection measures were proposed.The results show that after preventive and control measures were adopted under abnormal conditions,the mining activities in the mining area had a relatively small impact on groundwater and were acceptable,which can provide a simple and effective method for groundwater environmental prediction of similar projects.展开更多
Introduction:Rapid policy rollouts can trigger localized dissatisfaction that is difficult to detect using text-only monitoring and single-pass large language model pipelines.This study aimed to evaluate whether a mul...Introduction:Rapid policy rollouts can trigger localized dissatisfaction that is difficult to detect using text-only monitoring and single-pass large language model pipelines.This study aimed to evaluate whether a multimodal,multi-agent framework improves the accuracy,reliability,and early warning sensitivity of public response surveillance during a long-term care policy monitoring window.Methods:This comparative evaluation study analyzed multimodal public discourse captured during a predefined monitoring window by integrating text with images and videos.The sentiment classification outputs were assessed against a human-consensus reference standard using the F1 score.Summarization reliability was quantified as the rate of unverifiable or fabricated claims in the generated policy feedback summaries.Temporal dynamics were characterized using sentiment trajectories,engagement acceleration,and topic subcluster tracking,with policy-relevant drivers estimated as shares of negative discourse volume.Results:The multi-agent framework achieved a higher sentiment classification performance,with an F1 score of 0.89 compared with 0.82 for a single-pass baseline.Robustness improved most noticeably in sarcastic and implicit complaint content,where negative intent was consistently recovered despite superficially positive phrasing.Generative reliability improved sharply,with unverifiable or fabricated claims decreasing to 1.2%versus 14.0%from the baseline.Multimodal recovery increased the captured discourse volume by 34%and added 4,200 unique data points available only in the images and videos.Conclusion:Multimodal multi-agent monitoring strengthened sentiment validity,reduced summary fabrication,and detected topic-level escalation signals in the observed monitoring window.The framework may support earlier identification of policy implementation issues,but its outputs should be interpreted as decision support signals rather than as substitutes for formal policy evaluation.展开更多
Despite of the small amount in the atmosphere,ozone is one of the most critical atmospheric component as it protects human beings and any other life on the earth from the sun's high frequency ultraviolet radiation...Despite of the small amount in the atmosphere,ozone is one of the most critical atmospheric component as it protects human beings and any other life on the earth from the sun's high frequency ultraviolet radiation. In recent decades,the global ozone depletion caused by human activities is w ell know n and produces an " ozone hole",the most direct consequence of w hich is the increase in ultraviolet radiation,w hich w ill affect human survival,climatic environment,ecological environment and other important adverse impacts. Due to the implementation of the M ontreal protocol and other agreement,the total amount of ozone depleting substance in the atmosphere has been prominent reduced,w hich w ill lead to a new round of regional climate change.Therefore,predicting the changes of the total ozone in the future w ill have an important guiding significance for predicting the future climate change and making reasonable measures to deal w ith the climate change. In this paper,based on the ozone data of 1979 to 2016 in the southern hemisphere and ARIM A model algorithm,using time series analysis,w e obtain prediction effect of ARIM A model is good by Ljung-Box Q-test and R^2,and the model can be used to predict the future ozone change. With the help of SPSS softw are,the future trend of the total ozone can be predicted in the future 50 years. Based on the above experiment results,the global ozone change in the future 50 years can be forecasted,namely the atmospheric ozone layer w ill return to its 1980's standard by the middle of this century at the global scale.展开更多
Objective: To re-analyze the data published in order to explore plausible biological pathways that can be used to explain the anti-aging effect of curcumin. Methods: Microarray data generated from other study aiming...Objective: To re-analyze the data published in order to explore plausible biological pathways that can be used to explain the anti-aging effect of curcumin. Methods: Microarray data generated from other study aiming to investigate effect of curcumin on extending lifespan of Drosophila melanogaster were further used for pathway prediction analysis. The differentially expressed genes were identified by using GeneSpdng GX with a criterion of 3.0-fold change. Two Cytoscape plugins including BisoGenet and molecular complex detection (MCODE) were used to establish the protein-protein interaction (PPI) network based upon differential genes in order to detect highly connected regions. The function annotation clustering tool of Database for Annotation, Visualization and Integrated Discovery (DAVID) was used for pathway analysis. Results: A total of 87 genes expressed differentially in D. melanogaster treated with curcumin were identified, among which 50 were up-regulated significantly and 37 were remarkably down-regulated in D. melanogaster treated with curcumin. Based upon these differential genes, PPI network was constructed with 1,082 nodes and 2,412 edges. Five highly connected regions in PPI networks were detected by MCODE algorithm, suggesting anti-aging effect of curcumin may be underlined through five different pathways including Notch signaling pathway, basal transcription factors, cell cycle regulation, ribosome, Wnt signaling pathway, and p53 pathway. Conclusion: Genes and their associated pathways in D. rnelanogaster treated with anti-aging agent curcumin were identified using PPI network and MCODE algorithm, suggesting that curnumin may be developed as an alternative therapeutic medicine for treating aging-associated diseases.展开更多
Achieving optimal mechanical performance in high-pressure die-cast(HPDC)Mg-based alloys through experimental methods is both costly and time-intensive due to significant variations in composition.This study leverages ...Achieving optimal mechanical performance in high-pressure die-cast(HPDC)Mg-based alloys through experimental methods is both costly and time-intensive due to significant variations in composition.This study leverages machine learning(ML)techniques to accelerate the development of high-performance Mg-based alloys.Data on alloy composition and mechanical properties were collected from literature sources,focusing on HPDC Mg-based alloys.Six ML models—extra trees,CatBoost,k-nearest neighbors,random forest,gradient boosting,and decision tree—were trained to predict mechanical behavior.Cat Boost yielded the highest prediction accuracy with R2 scores of 0.95 for ultimate tensile strength(UTS)and 0.92 for yield strength(YS).Further validation using published datasets reaffirmed its reliability,demonstrating R2 values of 0.956(UTS)and 0.936(YS),MAE of 1%and 2.8%,and RMSE of 1%and 3.5%,respectively.Among these,the CatBoost model demonstrated the highest predictive accuracy,outperforming other ML techniques across multiple optimization metrics.展开更多
Anti-collision equipments system is developed to solve the collision problems of dam construction equipments, and in the system the determination of equipments' space state is important. A uniform moving equation of ...Anti-collision equipments system is developed to solve the collision problems of dam construction equipments, and in the system the determination of equipments' space state is important. A uniform moving equation of equipments is established based on the analysis prediction theory and the movements states of equipments. Method of least square was employed to deal with discrete data of equipments' space position. Fitting equation matched with the movement equation was presented to do data fitting, and a relevant algorithm was given. Applying the fitting equation, current and future space state of equipments can be accurately predicted. Finally, a case is given and results show that numerical values of data were steady and their precision was high. In LongTan dam construction of the equipments antiollision system, applying this method to forecast the equipments' space states and practical running of the system indicate that this method can improve the precision of position, obtain the better forecasting effect and increase the robustness of the system.展开更多
In this paper, the j, υ corrected formulae of the amplitudes and the phases of 58 astronomical constituents are given, and the models for the analysis and prediction of 169 constituents are presented. The new Cartwri...In this paper, the j, υ corrected formulae of the amplitudes and the phases of 58 astronomical constituents are given, and the models for the analysis and prediction of 169 constituents are presented. The new Cartwright's calculated results of the tidal potential are used, and the quadratic analysis is made. It has been proved by a number of trials that the harmonic constants of constituents are more stable and the accuracy of the predicted result reliable.展开更多
In order to study the variation o f the asphalt pavement water film thickness influenced by multi-factors,anew method for predicting water film thickness was developed by the combination o f the artificial neural netw...In order to study the variation o f the asphalt pavement water film thickness influenced by multi-factors,anew method for predicting water film thickness was developed by the combination o f the artificial neural network(ANN)a d two-dimensional shallow water equations based on hydrodynamic theory.Multi-factors included the rainfall intensity,pavement width,cross slope,longitudinal slope a d pavement roughness coefficient.The two-dimensional hydrodynamic method was validated by a natural rainfall event.Based on the design scheme o f Shen-Sha expressway engineering project,the limited training data obtained by the two-dimensional hydrodynamic simulation model was used to predict water film thickness.Furthermore,the distribution of the water film thickness influenced by multi-factors on the pavement was analyzed.The accuracy o f the ANN model was verified by the18sets o f data with a precision o f0.991.The simulation results indicate that the water film thickness increases from the median strip to the edge o f the pavement.The water film thickness variation is obviously influenced by rainfall intensity.Under the condition that the pavement width is20m and t e rainfall intensity is3m m/h,t e water film thickness is below10mm in the fast lane and20mm in t e lateral lane.Athough there is fluctuation due to the amount oftraining data,compared with the calculation on the basis o f the existing criterion and theory,t e ANN model exhibits a better performance for depicting the macroscopic distribution of the asphalt pavement water film.展开更多
The capability of accurately predicting mineralogical brittleness index (BI) from basic suites of well logs is desirable as it provides a useful indicator of the fracability of tight formations.Measuring mineralogical...The capability of accurately predicting mineralogical brittleness index (BI) from basic suites of well logs is desirable as it provides a useful indicator of the fracability of tight formations.Measuring mineralogical components in rocks is expensive and time consuming.However,the basic well log curves are not well correlated with BI so correlation-based,machine-learning methods are not able to derive highly accurate BI predictions using such data.A correlation-free,optimized data-matching algorithm is configured to predict BI on a supervised basis from well log and core data available from two published wells in the Lower Barnett Shale Formation (Texas).This transparent open box (TOB) algorithm matches data records by calculating the sum of squared errors between their variables and selecting the best matches as those with the minimum squared errors.It then applies optimizers to adjust weights applied to individual variable errors to minimize the root mean square error (RMSE)between calculated and predicted (BI).The prediction accuracy achieved by TOB using just five well logs (Gr,ρb,Ns,Rs,Dt) to predict BI is dependent on the density of data records sampled.At a sampling density of about one sample per 0.5 ft BI is predicted with RMSE~0.056 and R2~0.790.At a sampling density of about one sample per0.1 ft BI is predicted with RMSE~0.008 and R2~0.995.Adding a stratigraphic height index as an additional (sixth)input variable method improves BI prediction accuracy to RMSE~0.003 and R2~0.999 for the two wells with only 1 record in 10,000 yielding a BI prediction error of>±0.1.The model has the potential to be applied in an unsupervised basis to predict BI from basic well log data in surrounding wells lacking mineralogical measurements but with similar lithofacies and burial histories.The method could also be extended to predict elastic rock properties in and seismic attributes from wells and seismic data to improve the precision of brittleness index and fracability mapping spatially.展开更多
New coronavirus disease(COVID-19)has constituted a global pandemic and has spread to most countries and regions in the world.Through understanding the development trend of confirmed cases in a region,the government ca...New coronavirus disease(COVID-19)has constituted a global pandemic and has spread to most countries and regions in the world.Through understanding the development trend of confirmed cases in a region,the government can control the pandemic by using the corresponding policies.However,the common traditional mathematical differential equations and population prediction models have limitations for time series population prediction,and even have large estimation errors.To address this issue,we propose an improved method for predicting confirmed cases based on LSTM(Long-Short Term Memory)neural network.This work compares the deviation between the experimental results of the improved LSTM prediction model and the digital prediction models(such as Logistic and Hill equations)with the real data as reference.Furthermore,this work uses the goodness of fitting to evaluate the fitting effect of the improvement.Experiments show that the proposed approach has a smaller prediction deviation and a better fitting effect.Compared with the previous forecasting methods,the contributions of our proposed improvement methods are mainly in the following aspects:1)we have fully considered the spatiotemporal characteristics of the data,rather than single standardized data.2)the improved parameter settings and evaluation indicators are more accurate for fitting and forecasting.3)we consider the impact of the epidemic stage and conduct reasonable data processing for different stage.展开更多
The channel back-siltation problem has been restricting the development of channels,and its monitoring is limited by funds and natural conditions.Moreover,predicting the channel back-siltation situation in a timely an...The channel back-siltation problem has been restricting the development of channels,and its monitoring is limited by funds and natural conditions.Moreover,predicting the channel back-siltation situation in a timely and accurate manner is difficult.Hence,a numerical simulation of the back-siltation problem in the sea area near the channel is of great significance to the maintenance of a channel.In this study,the back siltation of a deep-water channel in the Lanshan Port area of the Port of Rizhao after dredging is predicted.This paper relies on the MIKE 21 software to establish the wave,tidal current,and sediment numerical models and uses measured data from two observation stations in the study area for verification.On this basis,taking one month as an example,the entire project channel was divided into five sections,and three observation points were set on each section.The results show that the area with offshore siltation is located in the northerly direction of the artificial anti-wave building.Siltation occurred on the northern seabed in the sea a little farther from the shore.Siltation occurred on the seabed surface far away from the shoreline,and with the increase in the distance from the shoreline,the amount of siltation in the south,center,and north became gradually closed,and the results can be used to guide actual engineering practices.This study will play a positive role in promoting the dredging project of Rizhao Lanshan Port.展开更多
The paper presents the prediction of total energy production and consumption in all provinces and autonomous regions as well as determination of the variation of gravity center of the energy production, consumption an...The paper presents the prediction of total energy production and consumption in all provinces and autonomous regions as well as determination of the variation of gravity center of the energy production, consumption and total discharge of industrial waste water, gas and residue of China via the energy and environmental quality data from 1978 to 2009 in China by use of GM(1,1) model and gravity center model, based on which the paper also analyzes the dynamic variation in regional difference in energy production, consumption and environmental quality and their relationship. The results are shown as follows. 1) The gravity center of energy production is gradually moving southwestward and the entire movement track approxi-mates to linear variation, indicating that the difference of energy production between the east and west, south and north is narrowing to a certain extent, with the difference between the east and the west narrowing faster than that between the south and the north. 2) The gravity center of energy consumption is moving southwestward with perceptible fluctuation, of which the gravity center position from 2000 to 2005 was relatively stable, with slight annual position variation, indicating that the growth rates of all provinces and autonomous regions are basically the same. 3) The gravity center of the total discharge of industrial waste water, gas and residue is characterized by fluctuation in longitude and latitude to a certain degree. But, it shows a southwestward trend on the whole. 4) There are common ground and discrepancy in the variation track of the gravity center of the energy production consumption of China, and the comparative analysis of the gravity center of them and that of total discharge of industrial waste water, gas and residue shows that the environmental quality level is closely associated with the energy production and consumption (especially the energy consumption), indicating that the environment cost in economy of energy is higher in China.展开更多
Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process mi...Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen(T-N) impact on the effluent water quality. The objective of this study is to establish two machine learning models-artificial neural networks(ANNs) and support vector machines(SVMs), in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination(R^2), Nash-Sutcliff efficiency(NSE), relative efficiency criteria(d rel). Additionally, Latin-Hypercube one-factor-at-a-time(LH-OAT) and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage.However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.展开更多
BACKGROUND An accurate identification of individuals at ultra-high risk(UHR)based on psychometric tools to prospectively identify psychosis as early as possible is required for indicated preventive intervention.The di...BACKGROUND An accurate identification of individuals at ultra-high risk(UHR)based on psychometric tools to prospectively identify psychosis as early as possible is required for indicated preventive intervention.The diagnostic comparability of several psychometric tools,including the comprehensive assessment of at risk mental state(CAARMS),the structured interview for psychosis-risk syndrome(SIPS)and the bonn scale for the assessment of basic symptoms(BSABS),is unknown.AIM To address the psychometric comparability of CAARMS,SIPS and BSABS for subjects who are close relatives of patients with schizophrenia.METHODS In total,189 participants aged 18-58 years who were lineal relative by blood and collateral relatives by blood up to the third degree of kinship of patients with schizophrenia were interviewed in the period of May 2017 to January 2019.Relatives of the participants diagnosed schizophrenia were excluded.All the participants were assessed for a UHR state by three psychometric tools(CAARMS,SIPS and BSABS).The psychometric diagnosis results included at risk of psychosis(UHR+),not at risk of psychosis(UHR-)and psychosis.Demographic and clinical characteristics were also measured.The inter-rater agreement was assessed for evaluation of the coherence of the three scales.Transition rates for UHR+subjects to psychosis within 2 years were also recorded.RESULTS The overall agreement percentages were 93.12%,92.06%and 93.65%of CAARMS and SIPS,SIPS and BSABS and CAARMS and BSABS,respectively.The overall agreement percentage of the relative functional impairment of the three groups(UHR+,not at risk of psychosis and psychosis)were 89.24%,86.36%and 88.12%,respectively.The inter-rater reliability of the CAARMS,SIPS and BSABS total score was 0.90,0.89 and 0.85.The inter-rater reliability was very good to excellent for all the subscales of these three instruments.For CAARMS,SIPS and BSABS,the kappa coefficient about UHR criteria agreement was 0.87,0.84 and 0.82,respectively(P<0.001).The transition rates of UHR+to psychosis within 2 years were 16.7%(CAARMS),10.0%(SIPS)and 17.7%(BSABS).CONCLUSION There is good diagnostic agreement between the CAARMS,SIPS and BSABS towards identification of UHR participants who are close relatives of patients with schizophrenia.展开更多
The first thunderstorm weather appeared in southern Shenyang on May 2,2010 and did not bring about severe lightning disaster for Shenyang region,but forecast service had poor effect without forecasting thunderstorm we...The first thunderstorm weather appeared in southern Shenyang on May 2,2010 and did not bring about severe lightning disaster for Shenyang region,but forecast service had poor effect without forecasting thunderstorm weather accurately.In our paper,the reasons for missing report of this thunderstorm weather were analyzed,and analysis on thunderstorm potential was carried out by means of mesoscale analysis technique,providing technical index and vantage point for the prediction of thunderstorm potential.The results showed that the reasons for missing report of this weather process were as follows:surface temperature at prophase was constantly lower going against the development of convective weather;the interpreting and analyzing ability of numerical forecast product should be improved;the forecast result of T639 model was better than that of Japanese numerical forecast;the study and application of mesoscale analysis technique should be strengthened,and this service was formally developed after thunderstorm weather on June 1,2010.展开更多
The prediction of the stress field of deep-buried tunnels is a fundamental problem for scientists and engineers.In this study,the authors put forward a systematic solution for this problem.Databases from the World Str...The prediction of the stress field of deep-buried tunnels is a fundamental problem for scientists and engineers.In this study,the authors put forward a systematic solution for this problem.Databases from the World Stress Map and the Crustal Stress of China,and previous research findings can offer prediction of stress orientations in an engineering area.At the same time,the Andersonian theory can be used to analyze the possible stress orientation of a region.With limited in-situ stress measurements,the Hock-Brown Criterion can be used to estimate the strength of rock mass in an area of interest by utilizing the geotechnical investigation data,and the modified Sheorey's model can subsequently be employed to predict the areas'stress profile,without stress data,by taking the existing in-situ stress measurements as input parameters.In this paper,a case study was used to demonstrate the application of this systematic solution.The planned Kohala hydropower plant is located on the western edge of Qinghai-Tibet Plateau.Three hydro-fracturing stress measurement campaigns indicated that the stress state of the area is SH-Sh〉Sv or SH〉Sv〉Sh.The measured orientation of Sn is NEE(N70.3°-89°E),and the regional orientation of SH from WSM is NE,which implies that the stress orientation of shallow crust may be affected by landforms.The modified Sheorey model was utilized to predict the stress profile along the water sewage tunnel for the plant.Prediction results show that the maximum and minimum horizontal principal stres-ses of the points with the greatest burial depth were up to 56.70 and 40.14 MPa,respectively,and the stresses of areas with a burial depth of greater than 500 m were higher.Based on the predicted stress data,large deformations of the rock mass surrounding water conveyance tunnels were analyzed.Results showed that the large deformations will occur when the burial depth exceeds 300 m.When the burial depth is beyond 800 m,serious squeezing deformations will occur in the surrounding rock masses,thus requiring more attention in the design and construction.Based on the application efficiency in this case study,this prediction method proposed in this paper functions accurately.展开更多
An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and...An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and consistent state estimation performance of vision-based navigation systems. The methodology leverages an efficient EOG-based observability analysis and a motion primitive-based path sampling technique to realize the local observability prediction with a real-time performance. The observability conditions of potential motion trajectories are evaluated,and an informed motion direction is selected to ensure the observability efficiency for the state estimation system. The proposed approach is specialized to a representative optimizationbased monocular vision-based state estimation formulation and demonstrated through simulation and experiments to evaluate the ability of estimation degradation prediction and efficacy of motion direction suggestion.展开更多
Along with the speedy development of the economic growth in China, the shortage of oil and gas becomes more and more serious. Based on summarizing some related research results, the prediction of China's oil demand a...Along with the speedy development of the economic growth in China, the shortage of oil and gas becomes more and more serious. Based on summarizing some related research results, the prediction of China's oil demand and supply in the year 2010 and the year 2020 has been given in the paper. The oil supply and demand situation is discussed on three different levels. Accordingly, suggestions about the oil supply safety and the national economy safety strategies have been given.展开更多
基金Supported by the Natural Science Foundation of Zhejiang Province of China(No.LY18E080020)the Natural Science Foundation of China(No.51408550)。
摘要The relationship between precipitation types and meteorological factors was surveyed based on the effect analysis of main meteorological parameters on asphalt pavement surface icing conditions and prediction analysis model of asphalt pavement temperature was established.This study aims to determine the correlation between icy pavement and meteorological factors and implement an accurate prediction of the icing condition of pavement.Considering the road slipperiness criterion presented by Norrman,a discriminative standard of icing condition of asphalt pavement surface in the central area of Zhejiang Province was proposed.Based on the above analysis results,a prediction model of pavement surface icing condition involved in asphalt pavement and ambient temperatures under the condition of different precipitation types was constructed by using support vector machine(SVM)method.Results demonstrate that(1)the distribution characteristics of daily mean air temperature,daily mean pavement temperature,daily average wind speed,and average daily rainfall have remarkable differences under the condition of different precipitation types,wherein the variation features of daily mean air temperature and daily mean pavement temperature are obvious;(2)the indirect prediction of precipitation type and pavement surface temperature could be accomplished in terms of meteorological monitoring data;(3)the influence of pavement surface icing conditions on driving safety is lower than that of rainwater freezing on a cold surface,melting snow at air temperature above O C,and melting snow at air temperature below 0 C;and(4)the SVM-based prediction model of pavement surface icing condition has an accurate analysis result with misreporting rate below 6%.The generalization ability of the proposed model is good and fully demonstrates the application prospects of SVM in the pavement weather prediction field.This study can provide theoretical and technical support for real-time warning about icy asphalt pavements in winter.
摘要Based on the exploration project of a mining area in Haiyang,as well as data collection and groundwater monitoring,groundwater environmental impact was predicted,and emergency protection measures were proposed.The results show that after preventive and control measures were adopted under abnormal conditions,the mining activities in the mining area had a relatively small impact on groundwater and were acceptable,which can provide a simple and effective method for groundwater environmental prediction of similar projects.
基金Supported by the Open Program of the Hospital Management Institute of Anhui Medical University(Grant No.2024gykjwz05).
摘要Introduction:Rapid policy rollouts can trigger localized dissatisfaction that is difficult to detect using text-only monitoring and single-pass large language model pipelines.This study aimed to evaluate whether a multimodal,multi-agent framework improves the accuracy,reliability,and early warning sensitivity of public response surveillance during a long-term care policy monitoring window.Methods:This comparative evaluation study analyzed multimodal public discourse captured during a predefined monitoring window by integrating text with images and videos.The sentiment classification outputs were assessed against a human-consensus reference standard using the F1 score.Summarization reliability was quantified as the rate of unverifiable or fabricated claims in the generated policy feedback summaries.Temporal dynamics were characterized using sentiment trajectories,engagement acceleration,and topic subcluster tracking,with policy-relevant drivers estimated as shares of negative discourse volume.Results:The multi-agent framework achieved a higher sentiment classification performance,with an F1 score of 0.89 compared with 0.82 for a single-pass baseline.Robustness improved most noticeably in sarcastic and implicit complaint content,where negative intent was consistently recovered despite superficially positive phrasing.Generative reliability improved sharply,with unverifiable or fabricated claims decreasing to 1.2%versus 14.0%from the baseline.Multimodal recovery increased the captured discourse volume by 34%and added 4,200 unique data points available only in the images and videos.Conclusion:Multimodal multi-agent monitoring strengthened sentiment validity,reduced summary fabrication,and detected topic-level escalation signals in the observed monitoring window.The framework may support earlier identification of policy implementation issues,but its outputs should be interpreted as decision support signals rather than as substitutes for formal policy evaluation.
基金supported by the key laboratory fund of Hubei province (Grant No. 2015KLA0,DZ-2016-01-H )graduate research innovation Project of NCIAE (No. YKY2016-08 )the science and technology research projects of Hebei province (Grant No. ZD 2016 106 )
摘要Despite of the small amount in the atmosphere,ozone is one of the most critical atmospheric component as it protects human beings and any other life on the earth from the sun's high frequency ultraviolet radiation. In recent decades,the global ozone depletion caused by human activities is w ell know n and produces an " ozone hole",the most direct consequence of w hich is the increase in ultraviolet radiation,w hich w ill affect human survival,climatic environment,ecological environment and other important adverse impacts. Due to the implementation of the M ontreal protocol and other agreement,the total amount of ozone depleting substance in the atmosphere has been prominent reduced,w hich w ill lead to a new round of regional climate change.Therefore,predicting the changes of the total ozone in the future w ill have an important guiding significance for predicting the future climate change and making reasonable measures to deal w ith the climate change. In this paper,based on the ozone data of 1979 to 2016 in the southern hemisphere and ARIM A model algorithm,using time series analysis,w e obtain prediction effect of ARIM A model is good by Ljung-Box Q-test and R^2,and the model can be used to predict the future ozone change. With the help of SPSS softw are,the future trend of the total ozone can be predicted in the future 50 years. Based on the above experiment results,the global ozone change in the future 50 years can be forecasted,namely the atmospheric ozone layer w ill return to its 1980's standard by the middle of this century at the global scale.
基金Supported by the National Natural Science Foundation of China(No.81102680)China Postdoctoral Science Foundation(No.20100470524)
摘要Objective: To re-analyze the data published in order to explore plausible biological pathways that can be used to explain the anti-aging effect of curcumin. Methods: Microarray data generated from other study aiming to investigate effect of curcumin on extending lifespan of Drosophila melanogaster were further used for pathway prediction analysis. The differentially expressed genes were identified by using GeneSpdng GX with a criterion of 3.0-fold change. Two Cytoscape plugins including BisoGenet and molecular complex detection (MCODE) were used to establish the protein-protein interaction (PPI) network based upon differential genes in order to detect highly connected regions. The function annotation clustering tool of Database for Annotation, Visualization and Integrated Discovery (DAVID) was used for pathway analysis. Results: A total of 87 genes expressed differentially in D. melanogaster treated with curcumin were identified, among which 50 were up-regulated significantly and 37 were remarkably down-regulated in D. melanogaster treated with curcumin. Based upon these differential genes, PPI network was constructed with 1,082 nodes and 2,412 edges. Five highly connected regions in PPI networks were detected by MCODE algorithm, suggesting anti-aging effect of curcumin may be underlined through five different pathways including Notch signaling pathway, basal transcription factors, cell cycle regulation, ribosome, Wnt signaling pathway, and p53 pathway. Conclusion: Genes and their associated pathways in D. rnelanogaster treated with anti-aging agent curcumin were identified using PPI network and MCODE algorithm, suggesting that curnumin may be developed as an alternative therapeutic medicine for treating aging-associated diseases.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2021R1A6A1A10044950)。
摘要Achieving optimal mechanical performance in high-pressure die-cast(HPDC)Mg-based alloys through experimental methods is both costly and time-intensive due to significant variations in composition.This study leverages machine learning(ML)techniques to accelerate the development of high-performance Mg-based alloys.Data on alloy composition and mechanical properties were collected from literature sources,focusing on HPDC Mg-based alloys.Six ML models—extra trees,CatBoost,k-nearest neighbors,random forest,gradient boosting,and decision tree—were trained to predict mechanical behavior.Cat Boost yielded the highest prediction accuracy with R2 scores of 0.95 for ultimate tensile strength(UTS)and 0.92 for yield strength(YS).Further validation using published datasets reaffirmed its reliability,demonstrating R2 values of 0.956(UTS)and 0.936(YS),MAE of 1%and 2.8%,and RMSE of 1%and 3.5%,respectively.Among these,the CatBoost model demonstrated the highest predictive accuracy,outperforming other ML techniques across multiple optimization metrics.
基金Supported by the National Key Technological Equipment Plan of China (ZZ02030301)Longtan Hydropower Development Corpora-tion Limited of China Datang Corporation
摘要Anti-collision equipments system is developed to solve the collision problems of dam construction equipments, and in the system the determination of equipments' space state is important. A uniform moving equation of equipments is established based on the analysis prediction theory and the movements states of equipments. Method of least square was employed to deal with discrete data of equipments' space position. Fitting equation matched with the movement equation was presented to do data fitting, and a relevant algorithm was given. Applying the fitting equation, current and future space state of equipments can be accurately predicted. Finally, a case is given and results show that numerical values of data were steady and their precision was high. In LongTan dam construction of the equipments antiollision system, applying this method to forecast the equipments' space states and practical running of the system indicate that this method can improve the precision of position, obtain the better forecasting effect and increase the robustness of the system.
摘要In this paper, the j, υ corrected formulae of the amplitudes and the phases of 58 astronomical constituents are given, and the models for the analysis and prediction of 169 constituents are presented. The new Cartwright's calculated results of the tidal potential are used, and the quadratic analysis is made. It has been proved by a number of trials that the harmonic constants of constituents are more stable and the accuracy of the predicted result reliable.
基金The National Natural Science Foundation of China(No.51478114,51778136)the Transportation Science and Technology Program of Liaoning Province(No.201532)
摘要In order to study the variation o f the asphalt pavement water film thickness influenced by multi-factors,anew method for predicting water film thickness was developed by the combination o f the artificial neural network(ANN)a d two-dimensional shallow water equations based on hydrodynamic theory.Multi-factors included the rainfall intensity,pavement width,cross slope,longitudinal slope a d pavement roughness coefficient.The two-dimensional hydrodynamic method was validated by a natural rainfall event.Based on the design scheme o f Shen-Sha expressway engineering project,the limited training data obtained by the two-dimensional hydrodynamic simulation model was used to predict water film thickness.Furthermore,the distribution of the water film thickness influenced by multi-factors on the pavement was analyzed.The accuracy o f the ANN model was verified by the18sets o f data with a precision o f0.991.The simulation results indicate that the water film thickness increases from the median strip to the edge o f the pavement.The water film thickness variation is obviously influenced by rainfall intensity.Under the condition that the pavement width is20m and t e rainfall intensity is3m m/h,t e water film thickness is below10mm in the fast lane and20mm in t e lateral lane.Athough there is fluctuation due to the amount oftraining data,compared with the calculation on the basis o f the existing criterion and theory,t e ANN model exhibits a better performance for depicting the macroscopic distribution of the asphalt pavement water film.
摘要The capability of accurately predicting mineralogical brittleness index (BI) from basic suites of well logs is desirable as it provides a useful indicator of the fracability of tight formations.Measuring mineralogical components in rocks is expensive and time consuming.However,the basic well log curves are not well correlated with BI so correlation-based,machine-learning methods are not able to derive highly accurate BI predictions using such data.A correlation-free,optimized data-matching algorithm is configured to predict BI on a supervised basis from well log and core data available from two published wells in the Lower Barnett Shale Formation (Texas).This transparent open box (TOB) algorithm matches data records by calculating the sum of squared errors between their variables and selecting the best matches as those with the minimum squared errors.It then applies optimizers to adjust weights applied to individual variable errors to minimize the root mean square error (RMSE)between calculated and predicted (BI).The prediction accuracy achieved by TOB using just five well logs (Gr,ρb,Ns,Rs,Dt) to predict BI is dependent on the density of data records sampled.At a sampling density of about one sample per 0.5 ft BI is predicted with RMSE~0.056 and R2~0.790.At a sampling density of about one sample per0.1 ft BI is predicted with RMSE~0.008 and R2~0.995.Adding a stratigraphic height index as an additional (sixth)input variable method improves BI prediction accuracy to RMSE~0.003 and R2~0.999 for the two wells with only 1 record in 10,000 yielding a BI prediction error of>±0.1.The model has the potential to be applied in an unsupervised basis to predict BI from basic well log data in surrounding wells lacking mineralogical measurements but with similar lithofacies and burial histories.The method could also be extended to predict elastic rock properties in and seismic attributes from wells and seismic data to improve the precision of brittleness index and fracability mapping spatially.
基金supported by the Hainan Provincial Natural Science Foundation of China[2018CXTD333,617048]National Natural Science Foundation of China[61762033,61702539]+3 种基金Hainan University Doctor Start Fund Project[kyqd1328]Hainan University Youth Fund Project[qnjj1444]Ministry of Education Humanities and Social Sciences Research Program Fund Project[19YJA710010]the Opening Project of Shanghai Trusted Industrial Control Platform.
摘要New coronavirus disease(COVID-19)has constituted a global pandemic and has spread to most countries and regions in the world.Through understanding the development trend of confirmed cases in a region,the government can control the pandemic by using the corresponding policies.However,the common traditional mathematical differential equations and population prediction models have limitations for time series population prediction,and even have large estimation errors.To address this issue,we propose an improved method for predicting confirmed cases based on LSTM(Long-Short Term Memory)neural network.This work compares the deviation between the experimental results of the improved LSTM prediction model and the digital prediction models(such as Logistic and Hill equations)with the real data as reference.Furthermore,this work uses the goodness of fitting to evaluate the fitting effect of the improvement.Experiments show that the proposed approach has a smaller prediction deviation and a better fitting effect.Compared with the previous forecasting methods,the contributions of our proposed improvement methods are mainly in the following aspects:1)we have fully considered the spatiotemporal characteristics of the data,rather than single standardized data.2)the improved parameter settings and evaluation indicators are more accurate for fitting and forecasting.3)we consider the impact of the epidemic stage and conduct reasonable data processing for different stage.
基金The study is supported by the Guangxi Key Laboratory of Marine Environmental Science,Guangxi Academy of Sciences(No.GXKLHY21-04)the Special Funds for Fun-damental Scientific Research Operation of Central Universities(No.202113011)+2 种基金the Shandong Provincial Social Science Planning Research Youth Project(No.21DSHJ2)NSFC-Shandong Joint Fund(No.U1706215)the Tian-jin Philosophy and Social Science Planning Project of China(No.TJKS20XSX-015).
摘要The channel back-siltation problem has been restricting the development of channels,and its monitoring is limited by funds and natural conditions.Moreover,predicting the channel back-siltation situation in a timely and accurate manner is difficult.Hence,a numerical simulation of the back-siltation problem in the sea area near the channel is of great significance to the maintenance of a channel.In this study,the back siltation of a deep-water channel in the Lanshan Port area of the Port of Rizhao after dredging is predicted.This paper relies on the MIKE 21 software to establish the wave,tidal current,and sediment numerical models and uses measured data from two observation stations in the study area for verification.On this basis,taking one month as an example,the entire project channel was divided into five sections,and three observation points were set on each section.The results show that the area with offshore siltation is located in the northerly direction of the artificial anti-wave building.Siltation occurred on the northern seabed in the sea a little farther from the shore.Siltation occurred on the seabed surface far away from the shoreline,and with the increase in the distance from the shoreline,the amount of siltation in the south,center,and north became gradually closed,and the results can be used to guide actual engineering practices.This study will play a positive role in promoting the dredging project of Rizhao Lanshan Port.
基金National Natural Science Foundation of China,No.41071057National Natural Science Foundation of China,No.41001388 Key Research Institute of Humanities and Social Sciences under the Ministry of Education,No.2009JJD770025
摘要The paper presents the prediction of total energy production and consumption in all provinces and autonomous regions as well as determination of the variation of gravity center of the energy production, consumption and total discharge of industrial waste water, gas and residue of China via the energy and environmental quality data from 1978 to 2009 in China by use of GM(1,1) model and gravity center model, based on which the paper also analyzes the dynamic variation in regional difference in energy production, consumption and environmental quality and their relationship. The results are shown as follows. 1) The gravity center of energy production is gradually moving southwestward and the entire movement track approxi-mates to linear variation, indicating that the difference of energy production between the east and west, south and north is narrowing to a certain extent, with the difference between the east and the west narrowing faster than that between the south and the north. 2) The gravity center of energy consumption is moving southwestward with perceptible fluctuation, of which the gravity center position from 2000 to 2005 was relatively stable, with slight annual position variation, indicating that the growth rates of all provinces and autonomous regions are basically the same. 3) The gravity center of the total discharge of industrial waste water, gas and residue is characterized by fluctuation in longitude and latitude to a certain degree. But, it shows a southwestward trend on the whole. 4) There are common ground and discrepancy in the variation track of the gravity center of the energy production consumption of China, and the comparative analysis of the gravity center of them and that of total discharge of industrial waste water, gas and residue shows that the environmental quality level is closely associated with the energy production and consumption (especially the energy consumption), indicating that the environment cost in economy of energy is higher in China.
基金supported by a grant (12-TI-C04) from Advanced Water Management Research Program funded by Ministry of Land, Infrastructure and Transport of Korean government
摘要Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen(T-N) impact on the effluent water quality. The objective of this study is to establish two machine learning models-artificial neural networks(ANNs) and support vector machines(SVMs), in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination(R^2), Nash-Sutcliff efficiency(NSE), relative efficiency criteria(d rel). Additionally, Latin-Hypercube one-factor-at-a-time(LH-OAT) and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage.However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.
基金Supported by the Health Commission of Hubei Province Scientific Research Project,No. WJ2019M016
摘要BACKGROUND An accurate identification of individuals at ultra-high risk(UHR)based on psychometric tools to prospectively identify psychosis as early as possible is required for indicated preventive intervention.The diagnostic comparability of several psychometric tools,including the comprehensive assessment of at risk mental state(CAARMS),the structured interview for psychosis-risk syndrome(SIPS)and the bonn scale for the assessment of basic symptoms(BSABS),is unknown.AIM To address the psychometric comparability of CAARMS,SIPS and BSABS for subjects who are close relatives of patients with schizophrenia.METHODS In total,189 participants aged 18-58 years who were lineal relative by blood and collateral relatives by blood up to the third degree of kinship of patients with schizophrenia were interviewed in the period of May 2017 to January 2019.Relatives of the participants diagnosed schizophrenia were excluded.All the participants were assessed for a UHR state by three psychometric tools(CAARMS,SIPS and BSABS).The psychometric diagnosis results included at risk of psychosis(UHR+),not at risk of psychosis(UHR-)and psychosis.Demographic and clinical characteristics were also measured.The inter-rater agreement was assessed for evaluation of the coherence of the three scales.Transition rates for UHR+subjects to psychosis within 2 years were also recorded.RESULTS The overall agreement percentages were 93.12%,92.06%and 93.65%of CAARMS and SIPS,SIPS and BSABS and CAARMS and BSABS,respectively.The overall agreement percentage of the relative functional impairment of the three groups(UHR+,not at risk of psychosis and psychosis)were 89.24%,86.36%and 88.12%,respectively.The inter-rater reliability of the CAARMS,SIPS and BSABS total score was 0.90,0.89 and 0.85.The inter-rater reliability was very good to excellent for all the subscales of these three instruments.For CAARMS,SIPS and BSABS,the kappa coefficient about UHR criteria agreement was 0.87,0.84 and 0.82,respectively(P<0.001).The transition rates of UHR+to psychosis within 2 years were 16.7%(CAARMS),10.0%(SIPS)and 17.7%(BSABS).CONCLUSION There is good diagnostic agreement between the CAARMS,SIPS and BSABS towards identification of UHR participants who are close relatives of patients with schizophrenia.
摘要The first thunderstorm weather appeared in southern Shenyang on May 2,2010 and did not bring about severe lightning disaster for Shenyang region,but forecast service had poor effect without forecasting thunderstorm weather accurately.In our paper,the reasons for missing report of this thunderstorm weather were analyzed,and analysis on thunderstorm potential was carried out by means of mesoscale analysis technique,providing technical index and vantage point for the prediction of thunderstorm potential.The results showed that the reasons for missing report of this weather process were as follows:surface temperature at prophase was constantly lower going against the development of convective weather;the interpreting and analyzing ability of numerical forecast product should be improved;the forecast result of T639 model was better than that of Japanese numerical forecast;the study and application of mesoscale analysis technique should be strengthened,and this service was formally developed after thunderstorm weather on June 1,2010.
基金provided by the National Natural Science Foundation of China–China(No.41274100)the Fundamental Research Fund for State Level Scientific Institutes(No.ZDJ2012-20)
摘要The prediction of the stress field of deep-buried tunnels is a fundamental problem for scientists and engineers.In this study,the authors put forward a systematic solution for this problem.Databases from the World Stress Map and the Crustal Stress of China,and previous research findings can offer prediction of stress orientations in an engineering area.At the same time,the Andersonian theory can be used to analyze the possible stress orientation of a region.With limited in-situ stress measurements,the Hock-Brown Criterion can be used to estimate the strength of rock mass in an area of interest by utilizing the geotechnical investigation data,and the modified Sheorey's model can subsequently be employed to predict the areas'stress profile,without stress data,by taking the existing in-situ stress measurements as input parameters.In this paper,a case study was used to demonstrate the application of this systematic solution.The planned Kohala hydropower plant is located on the western edge of Qinghai-Tibet Plateau.Three hydro-fracturing stress measurement campaigns indicated that the stress state of the area is SH-Sh〉Sv or SH〉Sv〉Sh.The measured orientation of Sn is NEE(N70.3°-89°E),and the regional orientation of SH from WSM is NE,which implies that the stress orientation of shallow crust may be affected by landforms.The modified Sheorey model was utilized to predict the stress profile along the water sewage tunnel for the plant.Prediction results show that the maximum and minimum horizontal principal stres-ses of the points with the greatest burial depth were up to 56.70 and 40.14 MPa,respectively,and the stresses of areas with a burial depth of greater than 500 m were higher.Based on the predicted stress data,large deformations of the rock mass surrounding water conveyance tunnels were analyzed.Results showed that the large deformations will occur when the burial depth exceeds 300 m.When the burial depth is beyond 800 m,serious squeezing deformations will occur in the surrounding rock masses,thus requiring more attention in the design and construction.Based on the application efficiency in this case study,this prediction method proposed in this paper functions accurately.
摘要An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and consistent state estimation performance of vision-based navigation systems. The methodology leverages an efficient EOG-based observability analysis and a motion primitive-based path sampling technique to realize the local observability prediction with a real-time performance. The observability conditions of potential motion trajectories are evaluated,and an informed motion direction is selected to ensure the observability efficiency for the state estimation system. The proposed approach is specialized to a representative optimizationbased monocular vision-based state estimation formulation and demonstrated through simulation and experiments to evaluate the ability of estimation degradation prediction and efficacy of motion direction suggestion.
摘要Along with the speedy development of the economic growth in China, the shortage of oil and gas becomes more and more serious. Based on summarizing some related research results, the prediction of China's oil demand and supply in the year 2010 and the year 2020 has been given in the paper. The oil supply and demand situation is discussed on three different levels. Accordingly, suggestions about the oil supply safety and the national economy safety strategies have been given.