The methods to determine time delays and embedding dimensions in the phase space delay reconstruction of multivariate chaotic time series are proposed. Three nonlinear prediction methods of multivariate chaotic tim...The methods to determine time delays and embedding dimensions in the phase space delay reconstruction of multivariate chaotic time series are proposed. Three nonlinear prediction methods of multivariate chaotic time series including local mean prediction, local linear prediction and BP neural networks prediction are considered. The simulation results obtained by the Lorenz system show that no matter what nonlinear prediction method is used, the prediction error of multivariate chaotic time series is much smaller than the prediction error of univariate time series, even if half of the data of univariate time series are used in multivariate time series. The results also verify that methods to determine the time delays and the embedding dimensions are correct from the view of minimizing the prediction error.展开更多
The zero coprime system equivalence is one of important research in the theory of multidimensional system equivalence,and is closely related to zero coprime equivalence of multivariate polynomial matrices.We first dis...The zero coprime system equivalence is one of important research in the theory of multidimensional system equivalence,and is closely related to zero coprime equivalence of multivariate polynomial matrices.We first discuss the relation between zero coprime equivalence and unimodular equivalence for polynomial matrices.Then,we investigate the zero coprime equivalence problem for several classes of polynomial matrices,some novel findings and criteria on reducing these matrices to their Smith normal forms are obtained.Finally,an example is provided to illustrate the main results.展开更多
Often many variables have to be analyzed for their importance in terms of significant contribution and predictability in medical research. One of the possible analytical tools may be the Multiple Linear Regression Ana...Often many variables have to be analyzed for their importance in terms of significant contribution and predictability in medical research. One of the possible analytical tools may be the Multiple Linear Regression Analysis. However, research papers usually report both univariate and multivariate regression analyses of the data. The biostatistician sometimes faces practical difficulties while selecting the independent variables for logical inclusion in the multivariate analysis. The selection criteria for inclusion of a variable in the multivariate regression is that the variable at the univariate level should have a regression coefficient with p 〈 0.20. However, there is a chance that an independent variable with p 〉 0.20 at univariate regression may become significant in the multivariate regression analysis and vice versa, provided the above criteria is not strictly adhered to. We undertook both univariate and multivariate linear regression analyses on data from two multi-centric clinical trials. We recommend that there is no need to restrict the p value of 〈= 0.20. Because of high speed computer and availability of statistical software, the desired results could be achieved by considering all relevant independent variables in multivariate regression analysis.展开更多
Mortality time series display time-varying volatility. The utility of statistical estimators from the financial time-series paradigm, which account for this characteristic, has not been addressed for high-frequency mo...Mortality time series display time-varying volatility. The utility of statistical estimators from the financial time-series paradigm, which account for this characteristic, has not been addressed for high-frequency mortality series. Using daily mean-mortality series of an exemplar intensive care unit (ICU) from the Australian and New Zealand Intensive Care Society adult patient database, joint estimation of a mean and conditional variance (volatility) model for a stationary series was undertaken via univariate autoregressive moving average (ARMA, lags (p, q)), GARCH (Generalised Autoregressive Conditional Heteroscedasticity, lags (p, q)). The temporal dynamics of the conditional variance and correlations of multiple provider series, from rural/ regional, metropolitan, tertiary and private ICUs, were estimated utilising multivariate GARCH models. For the stationary first differenced series, an asymmetric power GARCH model (lags (1, 1)) with t distribution (degrees-of- freedom, 11.6) and ARMA (7,0) for the mean-model, was the best-fitting. The four multivariate component series demonstrated varying trend mortality decline and persistent autocorrelation. Within each MGARCH series no model specification dominated. The conditional correlations were surprisingly low (<0.1) between tertiary series and substantial (0.4 - 0.6) between rural-regional and private series. The conditional-variances of both the univariate and multivariate series demonstrated a slow rate of time decline from periods of early volatility and volatility spikes.展开更多
In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.A...In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.展开更多
BACKGROUND Orthodontic treatment can easily cause local soft tissue reactions in the oral cavity of patients under mechanical stress,leading to oral mucosal ulcers and affecting their quality of life.At present,only l...BACKGROUND Orthodontic treatment can easily cause local soft tissue reactions in the oral cavity of patients under mechanical stress,leading to oral mucosal ulcers and affecting their quality of life.At present,only limited literature has explored the factors leading to oral ulcers in orthodontic treatment,and these research results are still controversial.AIM To investigate the current status and related factors of oral mucosal ulcers during orthodontic treatment,aiming to provide a valuable reference for preventing this disease in clinical practice.METHODS A total of 587 patients who underwent orthodontic treatment at the Peking University School of Stomatology and Hospital of Stomatology between 2020 and 2022 were selected and allocated to an observation or control group according to the incidence of oral mucosal ulcers during orthodontic therapy.A questionnaire survey was constructed to collect patient data,including basic information,lifestyle and eating habits,treatment details,mental factors,and trace element levels,and a comparative analysis of this data was performed between the two groups.RESULTS A logistic regression model with oral ulcers as the dependent variable was established.The regression results showed that age(≥60 years:odds ratio[OR]:6.820;95%confidence interval[CI]:2.226–20.893),smoking history(smoking:OR:4.434;95%CI:2.527–7.782),toothbrush hardness(hard:OR:2.804;95%CI:1.746–4.505),dietary temperature(hot diet:OR:1.399;95%CI:1.220–1.722),treatment course(>1 year:OR:3.830;95%CI:2.203–6.659),and tooth brushing frequency(>1 time per day:OR:0.228;95%CI:0.138–0.377)were independent factors for oral mucosal ulcers(P<0.05).Furthermore,Zn level(OR:0.945;95%CI:0.927–0.964)was a protective factor against oral ulcers,while the SAS(OR:1.284;95%CI:1.197–1.378)and SDS(OR:1.322;95%CI:1.231–1.419)scores were risk factors.CONCLUSION Age≥60 years,smoking history,hard toothbrush,hot diet,treatment course for>1 year,tooth brushing frequency of≤1 time per day,and mental anxiety are independent risk factors for oral mucosal ulcers.Therefore,these factors should receive clinical attention and be incorporated into the development and optimization of preventive strategies for reducing oral ulcer incidence.展开更多
Moistube irrigation is a new micro-irrigation technology.Accurately estimating its wetting pattern dimensions presents a challenge.Therefore,it is necessary to develop models for efficient assessment of the wetting tr...Moistube irrigation is a new micro-irrigation technology.Accurately estimating its wetting pattern dimensions presents a challenge.Therefore,it is necessary to develop models for efficient assessment of the wetting transport pattern in order to design a cost-effective moistube irrigation system.To achieve this goal,this study developed a multivariate nonlinear regression model and compared it with a dimensional model.HYDRUS-2D was used to perform numerical simulations of 56 irrigation scenarios with different factors.The experiments showed that the shape of the wetting soil body approximated a cylinder and was mainly affected by soil texture,pressure head,and matric potential.A multivariate nonlinear model using a power function relationship between wetting size and irrigation time was developed,with a determination coefficient greater than 0.99.The model was validated for cases with six soil texture types,with mean average absolute errors of 0.43-0.90 cm,root mean square errors of 0.51-0.95 cm,and mean deviation percentage values of 3.23%-6.27%.The multivariate nonlinear regression model outperformed the dimensional model.It can therefore provide a scientific foundation for the development of moistube irrigation systems.展开更多
Stress urinary incontinence(SUI)is a symptom of uncontrolled urine outflow that affects millions of women worldwide[1].SUI is a significant healthcare issue that affects the quality of life of women across numerous do...Stress urinary incontinence(SUI)is a symptom of uncontrolled urine outflow that affects millions of women worldwide[1].SUI is a significant healthcare issue that affects the quality of life of women across numerous domains,including social activities,physical health,mental well-being,employment,and sexual life.展开更多
Forecasting river flow is crucial for optimal planning,management,and sustainability using freshwater resources.Many machine learning(ML)approaches have been enhanced to improve streamflow prediction.Hybrid techniques...Forecasting river flow is crucial for optimal planning,management,and sustainability using freshwater resources.Many machine learning(ML)approaches have been enhanced to improve streamflow prediction.Hybrid techniques have been viewed as a viable method for enhancing the accuracy of univariate streamflow estimation when compared to standalone approaches.Current researchers have also emphasised using hybrid models to improve forecast accuracy.Accordingly,this paper conducts an updated literature review of applications of hybrid models in estimating streamflow over the last five years,summarising data preprocessing,univariate machine learning modelling strategy,advantages and disadvantages of standalone ML techniques,hybrid models,and performance metrics.This study focuses on two types of hybrid models:parameter optimisation-based hybrid models(OBH)and hybridisation of parameter optimisation-based and preprocessing-based hybridmodels(HOPH).Overall,this research supports the idea thatmeta-heuristic approaches precisely improveML techniques.It’s also one of the first efforts to comprehensively examine the efficiency of various meta-heuristic approaches(classified into four primary classes)hybridised with ML techniques.This study revealed that previous research applied swarm,evolutionary,physics,and hybrid metaheuristics with 77%,61%,12%,and 12%,respectively.Finally,there is still room for improving OBH and HOPH models by examining different data pre-processing techniques and metaheuristic algorithms.展开更多
Population growth and expanding urbanization have caused persistent shortages and contamination of groundwater resources in Mali,Africa.The increase in groundwater salinity makes it more difficult for residents to obt...Population growth and expanding urbanization have caused persistent shortages and contamination of groundwater resources in Mali,Africa.The increase in groundwater salinity makes it more difficult for residents to obtain drinking water,it is necessary to clarify the causes and control factors of groundwater mineralization in Gao region,northern Mali.Based on the analysis of the hydrochemical composition of groundwater in 24 boreholes,Piper and Sch?eller diagrams,principal component analysis(PCA)and hierarchical cluster analysis(HCA)are used to carry out multivariate statistical analysis on the main ions.The results show that the groundwater samples are weakly alkaline,with pH values ranging from 5.83 to 8.40,and the average values of boreholes are 7.50,respectively.The average electrical conductivity(EC)value is 354.4(μS/cm),and the extreme value is between 124.0 and 1247(μS/cm).Water is usually mineralized and presents nine types of water phase.The three principal components explain 84.42%of the total variance for 13 parameters.The factor F1(58.85%),the factor F2(16.88%)and the factor F3(8.69%)present for the majority of the total data set.In addition,multivariate statistical analysis confirmed the genetic relationship among aquifers and identified three main clusters.Clustering related to groundwater mineralization(F1),clustering related to oxide reduction and iron enrichment(F2),and clustering of groundwater pollution caused by nitrate and magnesium(F3).We found that agriculture,weathering activities and dissolution of geological materials promote the mineralization of groundwater.Groundwater quality in the Gao region is becoming less and less potable because of increasing salinity.展开更多
This study investigates the factors that impact farmers'adoption of risk management strategies(RMS)in Pakistan during times of uncertainty.The study examines farmers'adoption of RMS using both multinomial prob...This study investigates the factors that impact farmers'adoption of risk management strategies(RMS)in Pakistan during times of uncertainty.The study examines farmers'adoption of RMS using both multinomial probit(MNP)and multivariate probit(MVP).Data were collected from 382 farmers sampled from four districts in KhyberPakhtunkhwa(KP)province of Pakistan via a multistage sampling technique.This study utilizes the MNP model,considering the assumption of Independence of Irrelevant Alternatives(IIA)and incorporating correlated error terms.The objective is to understand farmers'behavior in risky situations and determine if there is heterogeneity.Results are compared with the MVP model to assess robustness and gain deeper understanding of farmers'decisionmaking processes.The research findings reveal that our results are robust,and farmers behave homogeneously in various RMS scenarios.Farmers adopt RMS individually or in combination to mitigate the adverse effects of natural calamities on their livelihood.The risk-averse farmers,who perceive weather-related risks as a threat,access credits and information,and have farms close to a river are more likely to adopt RMS,irrespective of the format of the strategies available.Moreover,the predicted probabilities and correlation of the RMS and RM categories have strengthened our model estimation.These findings provide insights into the behavior of farmers in adopting RMS which are helpful for policymakers and stakeholders in developing strategies to mitigate the impacts of natural calamities on farmers.展开更多
Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoenc...Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data,while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors.To mine the spatio-temporal information from multivariate time series signals,this paper proposes an attention graph stacked autoencoder for EMA anomaly detection.Firstly,attention graph con-volution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions.Secondly,stacked autoencoder is applied to mine spatial information from those new aggregated temporal features.Finally,based on the bench-mark reconstruction loss of normal training data,different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data.In comparison with tra-ditional stacked autoencoder,the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.展开更多
In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)da...In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.展开更多
The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries an...The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.展开更多
Covalent organic frameworks(COFs)have attracted attention as photocatalysts,however,low electron transfer and reactive oxygen species(ROS)generation still hinder their photocatalytic application.In this work,we constr...Covalent organic frameworks(COFs)have attracted attention as photocatalysts,however,low electron transfer and reactive oxygen species(ROS)generation still hinder their photocatalytic application.In this work,we construct multivariate donor-acceptor(D-A)heterojunctions in the covalent organic frameworks by synchronously introducing electron-withdrawing and donating substituents.Importantly,the optoelectronic characteristics and visible-light photocatalytic performance were improved with the increase of the electron donor carbon chains in multivariate D-A COFs.Combining in‐situ characterization with theoretical calculations,the charge carrier separation and transfer efficiency,•O_(2)–generation and conversion,and the energy barrier of the rate determination steps related to the formation of*OH and*OOH,can be well regulated by the multivariate D-A COFs.More importantly,the ortho-carbon atom of the Br and OCH_(3) group-linked benzene rings and the imine bond(–C=N–)in COF-Br@OCH_(3) were activated to produce the key*OH and*OOH intermediates for effectively reducing the energy barrier of H2O oxidation and O_(2) reduction.This work provides valuable insights into the precise design and synthesis of COFs-based catalysts and the regulation of electron transfer and ROS generation by modulating the electron-withdrawing and donating substituents for highly efficient visible-light photocatalytic degradation of refractory organic pollutants.展开更多
Introduction:Alzheimer's disease(AD)is a progressive brain disorder that impairs cognitive functions,behavior,and memory.Early detection is crucial as it can slow down the progression of AD.However,early diagnosis...Introduction:Alzheimer's disease(AD)is a progressive brain disorder that impairs cognitive functions,behavior,and memory.Early detection is crucial as it can slow down the progression of AD.However,early diagnosis and monitoring of AD's advancement pose significant challenges due to the necessity for complex cognitive assessments and medical tests.Methods:This study introduces a data acquisition technique and a preprocessing pipeline,combined with multivariate long short-term memory(M-LSTM)and AdaBoost models.These models utilize biomarkers from cognitive assessments and neuroimaging scans to detect the progression of AD in patients,using The AD Prediction of Longitudinal Evolution challenge cohort from the Alzheimer's Disease Neuroimaging Initiative database.Results:The methodology proposed in this study significantly improved performance metrics.The testing accuracy reached 80%with the AdaBoost model,while the M-LSTM model achieved an accuracy of 82%.This represents a 20%increase in accuracy compared to a recent similar study.Discussion:The findings indicate that the multivariate model,specifically the M-LSTM,is more effective in identifying the progression of AD compared to the AdaBoost model and methodologies used in recent research.展开更多
[Objective] The plankton and macrobenthos samples in municipal polluted river were analyzed by different methods, so as to explore the method suitable for biological data analysis in heavy polluted area. [Method] Shan...[Objective] The plankton and macrobenthos samples in municipal polluted river were analyzed by different methods, so as to explore the method suitable for biological data analysis in heavy polluted area. [Method] Shannon-Wiener diversity index, cluster analysis of multivariate statistical analysis and MDS （Non-matric Multi- dimentional Scaling）analysis were used to analyze biological data of phytoplankton, zooplankton and Zoobenthos collected from the representative municipal polluted river in Pearl River Delta. The sediment samples were also collected to determine. Pb, Cd, Hg, Cr, As, Cu, Ni, Zn, as well as CODe, and NH3-N of porewater. Hakanson potential ecological risk index method was used to evaluate the ecological risk. [Re- suit] Shannon-Wiener diversity index analysis results can not effectively reflect the difference of pollution status of various stations in heavy polluted area; despite the presence of some problems, multivariate analysis method is superior to the Shannon-Wiener diversity index method in biological monitoring of heavy polluted river in the city. [Conclusion] The paper provided theoretical basis for biological data analysis in heavy polluted area.展开更多
The analysis result of absolute degree of grey incidence for multivariate time series is often inconsistent with the qualitative analysis. To overcome this shortage, a multivariate absolute degree of grey incidence ba...The analysis result of absolute degree of grey incidence for multivariate time series is often inconsistent with the qualitative analysis. To overcome this shortage, a multivariate absolute degree of grey incidence based on distribution characteristics of points is proposed. Based on the geometric description of multivariate time se- ries, the neighborhood extrema are extracted in the different regions, and a characteristic point set is constructed. Then according to the distribution of the characteristic point set, a characteristic point sequence reflecting the ge- ometric features of multivariate time series is obtained. The incidence analysis between multivariate time series is transformed into the relational analysis between characteristic point sequences, and a grey incidence model is established. The model possesses the properties of translational invariance, transpose and rank transform invari- ance, and satisfies the grey incidence analysis axioms. Finally, two cases are studied and the results prove the ef- fectiveness of the model.展开更多
文摘The methods to determine time delays and embedding dimensions in the phase space delay reconstruction of multivariate chaotic time series are proposed. Three nonlinear prediction methods of multivariate chaotic time series including local mean prediction, local linear prediction and BP neural networks prediction are considered. The simulation results obtained by the Lorenz system show that no matter what nonlinear prediction method is used, the prediction error of multivariate chaotic time series is much smaller than the prediction error of univariate time series, even if half of the data of univariate time series are used in multivariate time series. The results also verify that methods to determine the time delays and the embedding dimensions are correct from the view of minimizing the prediction error.
基金Supported by the National Natural Science Foundation of China(12271154)the Natural Science Foundation of Hunan Province(2022JJ30234)the Postgraduate Scientific Research Innovation Project of Hunan Province(CX20231032)。
文摘The zero coprime system equivalence is one of important research in the theory of multidimensional system equivalence,and is closely related to zero coprime equivalence of multivariate polynomial matrices.We first discuss the relation between zero coprime equivalence and unimodular equivalence for polynomial matrices.Then,we investigate the zero coprime equivalence problem for several classes of polynomial matrices,some novel findings and criteria on reducing these matrices to their Smith normal forms are obtained.Finally,an example is provided to illustrate the main results.
文摘Often many variables have to be analyzed for their importance in terms of significant contribution and predictability in medical research. One of the possible analytical tools may be the Multiple Linear Regression Analysis. However, research papers usually report both univariate and multivariate regression analyses of the data. The biostatistician sometimes faces practical difficulties while selecting the independent variables for logical inclusion in the multivariate analysis. The selection criteria for inclusion of a variable in the multivariate regression is that the variable at the univariate level should have a regression coefficient with p 〈 0.20. However, there is a chance that an independent variable with p 〉 0.20 at univariate regression may become significant in the multivariate regression analysis and vice versa, provided the above criteria is not strictly adhered to. We undertook both univariate and multivariate linear regression analyses on data from two multi-centric clinical trials. We recommend that there is no need to restrict the p value of 〈= 0.20. Because of high speed computer and availability of statistical software, the desired results could be achieved by considering all relevant independent variables in multivariate regression analysis.
文摘Mortality time series display time-varying volatility. The utility of statistical estimators from the financial time-series paradigm, which account for this characteristic, has not been addressed for high-frequency mortality series. Using daily mean-mortality series of an exemplar intensive care unit (ICU) from the Australian and New Zealand Intensive Care Society adult patient database, joint estimation of a mean and conditional variance (volatility) model for a stationary series was undertaken via univariate autoregressive moving average (ARMA, lags (p, q)), GARCH (Generalised Autoregressive Conditional Heteroscedasticity, lags (p, q)). The temporal dynamics of the conditional variance and correlations of multiple provider series, from rural/ regional, metropolitan, tertiary and private ICUs, were estimated utilising multivariate GARCH models. For the stationary first differenced series, an asymmetric power GARCH model (lags (1, 1)) with t distribution (degrees-of- freedom, 11.6) and ARMA (7,0) for the mean-model, was the best-fitting. The four multivariate component series demonstrated varying trend mortality decline and persistent autocorrelation. Within each MGARCH series no model specification dominated. The conditional correlations were surprisingly low (<0.1) between tertiary series and substantial (0.4 - 0.6) between rural-regional and private series. The conditional-variances of both the univariate and multivariate series demonstrated a slow rate of time decline from periods of early volatility and volatility spikes.
基金This work is partly supported by the National Key Research and Development Program of China(Grant No.2020YFB1805403)the National Natural Science Foundation of China(Grant No.62032002)the 111 Project(Grant No.B21049).
文摘In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.
文摘BACKGROUND Orthodontic treatment can easily cause local soft tissue reactions in the oral cavity of patients under mechanical stress,leading to oral mucosal ulcers and affecting their quality of life.At present,only limited literature has explored the factors leading to oral ulcers in orthodontic treatment,and these research results are still controversial.AIM To investigate the current status and related factors of oral mucosal ulcers during orthodontic treatment,aiming to provide a valuable reference for preventing this disease in clinical practice.METHODS A total of 587 patients who underwent orthodontic treatment at the Peking University School of Stomatology and Hospital of Stomatology between 2020 and 2022 were selected and allocated to an observation or control group according to the incidence of oral mucosal ulcers during orthodontic therapy.A questionnaire survey was constructed to collect patient data,including basic information,lifestyle and eating habits,treatment details,mental factors,and trace element levels,and a comparative analysis of this data was performed between the two groups.RESULTS A logistic regression model with oral ulcers as the dependent variable was established.The regression results showed that age(≥60 years:odds ratio[OR]:6.820;95%confidence interval[CI]:2.226–20.893),smoking history(smoking:OR:4.434;95%CI:2.527–7.782),toothbrush hardness(hard:OR:2.804;95%CI:1.746–4.505),dietary temperature(hot diet:OR:1.399;95%CI:1.220–1.722),treatment course(>1 year:OR:3.830;95%CI:2.203–6.659),and tooth brushing frequency(>1 time per day:OR:0.228;95%CI:0.138–0.377)were independent factors for oral mucosal ulcers(P<0.05).Furthermore,Zn level(OR:0.945;95%CI:0.927–0.964)was a protective factor against oral ulcers,while the SAS(OR:1.284;95%CI:1.197–1.378)and SDS(OR:1.322;95%CI:1.231–1.419)scores were risk factors.CONCLUSION Age≥60 years,smoking history,hard toothbrush,hot diet,treatment course for>1 year,tooth brushing frequency of≤1 time per day,and mental anxiety are independent risk factors for oral mucosal ulcers.Therefore,these factors should receive clinical attention and be incorporated into the development and optimization of preventive strategies for reducing oral ulcer incidence.
基金supported by the National Natural Science Foundation of China(Grant No.51969013)the Natural Science Foundation of Gansu Province(Grant No.21JR7RA225).
文摘Moistube irrigation is a new micro-irrigation technology.Accurately estimating its wetting pattern dimensions presents a challenge.Therefore,it is necessary to develop models for efficient assessment of the wetting transport pattern in order to design a cost-effective moistube irrigation system.To achieve this goal,this study developed a multivariate nonlinear regression model and compared it with a dimensional model.HYDRUS-2D was used to perform numerical simulations of 56 irrigation scenarios with different factors.The experiments showed that the shape of the wetting soil body approximated a cylinder and was mainly affected by soil texture,pressure head,and matric potential.A multivariate nonlinear model using a power function relationship between wetting size and irrigation time was developed,with a determination coefficient greater than 0.99.The model was validated for cases with six soil texture types,with mean average absolute errors of 0.43-0.90 cm,root mean square errors of 0.51-0.95 cm,and mean deviation percentage values of 3.23%-6.27%.The multivariate nonlinear regression model outperformed the dimensional model.It can therefore provide a scientific foundation for the development of moistube irrigation systems.
文摘Stress urinary incontinence(SUI)is a symptom of uncontrolled urine outflow that affects millions of women worldwide[1].SUI is a significant healthcare issue that affects the quality of life of women across numerous domains,including social activities,physical health,mental well-being,employment,and sexual life.
基金This paper’s logical organisation and content quality have been enhanced,so the authors thank anonymous reviewers and journal editors for assistance.
文摘Forecasting river flow is crucial for optimal planning,management,and sustainability using freshwater resources.Many machine learning(ML)approaches have been enhanced to improve streamflow prediction.Hybrid techniques have been viewed as a viable method for enhancing the accuracy of univariate streamflow estimation when compared to standalone approaches.Current researchers have also emphasised using hybrid models to improve forecast accuracy.Accordingly,this paper conducts an updated literature review of applications of hybrid models in estimating streamflow over the last five years,summarising data preprocessing,univariate machine learning modelling strategy,advantages and disadvantages of standalone ML techniques,hybrid models,and performance metrics.This study focuses on two types of hybrid models:parameter optimisation-based hybrid models(OBH)and hybridisation of parameter optimisation-based and preprocessing-based hybridmodels(HOPH).Overall,this research supports the idea thatmeta-heuristic approaches precisely improveML techniques.It’s also one of the first efforts to comprehensively examine the efficiency of various meta-heuristic approaches(classified into four primary classes)hybridised with ML techniques.This study revealed that previous research applied swarm,evolutionary,physics,and hybrid metaheuristics with 77%,61%,12%,and 12%,respectively.Finally,there is still room for improving OBH and HOPH models by examining different data pre-processing techniques and metaheuristic algorithms.
基金funded by the China's National Natural Science Foundation(No.41440027)。
文摘Population growth and expanding urbanization have caused persistent shortages and contamination of groundwater resources in Mali,Africa.The increase in groundwater salinity makes it more difficult for residents to obtain drinking water,it is necessary to clarify the causes and control factors of groundwater mineralization in Gao region,northern Mali.Based on the analysis of the hydrochemical composition of groundwater in 24 boreholes,Piper and Sch?eller diagrams,principal component analysis(PCA)and hierarchical cluster analysis(HCA)are used to carry out multivariate statistical analysis on the main ions.The results show that the groundwater samples are weakly alkaline,with pH values ranging from 5.83 to 8.40,and the average values of boreholes are 7.50,respectively.The average electrical conductivity(EC)value is 354.4(μS/cm),and the extreme value is between 124.0 and 1247(μS/cm).Water is usually mineralized and presents nine types of water phase.The three principal components explain 84.42%of the total variance for 13 parameters.The factor F1(58.85%),the factor F2(16.88%)and the factor F3(8.69%)present for the majority of the total data set.In addition,multivariate statistical analysis confirmed the genetic relationship among aquifers and identified three main clusters.Clustering related to groundwater mineralization(F1),clustering related to oxide reduction and iron enrichment(F2),and clustering of groundwater pollution caused by nitrate and magnesium(F3).We found that agriculture,weathering activities and dissolution of geological materials promote the mineralization of groundwater.Groundwater quality in the Gao region is becoming less and less potable because of increasing salinity.
文摘This study investigates the factors that impact farmers'adoption of risk management strategies(RMS)in Pakistan during times of uncertainty.The study examines farmers'adoption of RMS using both multinomial probit(MNP)and multivariate probit(MVP).Data were collected from 382 farmers sampled from four districts in KhyberPakhtunkhwa(KP)province of Pakistan via a multistage sampling technique.This study utilizes the MNP model,considering the assumption of Independence of Irrelevant Alternatives(IIA)and incorporating correlated error terms.The objective is to understand farmers'behavior in risky situations and determine if there is heterogeneity.Results are compared with the MVP model to assess robustness and gain deeper understanding of farmers'decisionmaking processes.The research findings reveal that our results are robust,and farmers behave homogeneously in various RMS scenarios.Farmers adopt RMS individually or in combination to mitigate the adverse effects of natural calamities on their livelihood.The risk-averse farmers,who perceive weather-related risks as a threat,access credits and information,and have farms close to a river are more likely to adopt RMS,irrespective of the format of the strategies available.Moreover,the predicted probabilities and correlation of the RMS and RM categories have strengthened our model estimation.These findings provide insights into the behavior of farmers in adopting RMS which are helpful for policymakers and stakeholders in developing strategies to mitigate the impacts of natural calamities on farmers.
基金supported by the National Natural Science Foundation of China (No.52075349)the National Natural Science Foundation of China (No.62303335)+1 种基金the Postdoctoral Researcher Program of China (No.GZC20231779)the Natural Science Foundation of Sichuan Province (No.2022NSFSC1942).
文摘Health monitoring of electro-mechanical actuator(EMA)is critical to ensure the security of airplanes.It is difficult or even impossible to collect enough labeled failure or degradation data from actual EMA.The autoencoder based on reconstruction loss is a popular model that can carry out anomaly detection with only consideration of normal training data,while it fails to capture spatio-temporal information from multivariate time series signals of multiple monitoring sensors.To mine the spatio-temporal information from multivariate time series signals,this paper proposes an attention graph stacked autoencoder for EMA anomaly detection.Firstly,attention graph con-volution is introduced into autoencoder to convolve temporal information from neighbor features to current features based on different weight attentions.Secondly,stacked autoencoder is applied to mine spatial information from those new aggregated temporal features.Finally,based on the bench-mark reconstruction loss of normal training data,different health thresholds calculated by several statistic indicators can carry out anomaly detection for new testing data.In comparison with tra-ditional stacked autoencoder,the proposed model could obtain higher fault detection rate and lower false alarm rate in EMA anomaly detection experiment.
基金supported by the Culture,Sports,and Tourism R&D Program through the Korea Creative Content Agency grant funded by the Ministry of Culture,Sports,and Tourism in 2024(Project Name:Development of Distribution and Management Platform Technology and Human Resource Development for Blockchain-Based SW Copyright Protection,Project Number:RS-2023-00228867,Contribution Rate:100%)and also supported by the Soonchunhyang University Research Fund.
文摘In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.
基金supported by the China Scholarship Council and the CERNET Innovation Project under grant No.20170111.
文摘The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.
文摘Covalent organic frameworks(COFs)have attracted attention as photocatalysts,however,low electron transfer and reactive oxygen species(ROS)generation still hinder their photocatalytic application.In this work,we construct multivariate donor-acceptor(D-A)heterojunctions in the covalent organic frameworks by synchronously introducing electron-withdrawing and donating substituents.Importantly,the optoelectronic characteristics and visible-light photocatalytic performance were improved with the increase of the electron donor carbon chains in multivariate D-A COFs.Combining in‐situ characterization with theoretical calculations,the charge carrier separation and transfer efficiency,•O_(2)–generation and conversion,and the energy barrier of the rate determination steps related to the formation of*OH and*OOH,can be well regulated by the multivariate D-A COFs.More importantly,the ortho-carbon atom of the Br and OCH_(3) group-linked benzene rings and the imine bond(–C=N–)in COF-Br@OCH_(3) were activated to produce the key*OH and*OOH intermediates for effectively reducing the energy barrier of H2O oxidation and O_(2) reduction.This work provides valuable insights into the precise design and synthesis of COFs-based catalysts and the regulation of electron transfer and ROS generation by modulating the electron-withdrawing and donating substituents for highly efficient visible-light photocatalytic degradation of refractory organic pollutants.
文摘Introduction:Alzheimer's disease(AD)is a progressive brain disorder that impairs cognitive functions,behavior,and memory.Early detection is crucial as it can slow down the progression of AD.However,early diagnosis and monitoring of AD's advancement pose significant challenges due to the necessity for complex cognitive assessments and medical tests.Methods:This study introduces a data acquisition technique and a preprocessing pipeline,combined with multivariate long short-term memory(M-LSTM)and AdaBoost models.These models utilize biomarkers from cognitive assessments and neuroimaging scans to detect the progression of AD in patients,using The AD Prediction of Longitudinal Evolution challenge cohort from the Alzheimer's Disease Neuroimaging Initiative database.Results:The methodology proposed in this study significantly improved performance metrics.The testing accuracy reached 80%with the AdaBoost model,while the M-LSTM model achieved an accuracy of 82%.This represents a 20%increase in accuracy compared to a recent similar study.Discussion:The findings indicate that the multivariate model,specifically the M-LSTM,is more effective in identifying the progression of AD compared to the AdaBoost model and methodologies used in recent research.
基金Supported by National Natural Science Foundation of China(41001341)Natural Science Foundation of Guangdong Province(9152800001000007)+1 种基金Open Fund ofState Key Laboratory of Subtropical Building Science(2011KB12)Basic Scientific Research Expenses Project of Central Universities(2012ZM0082)~~
文摘[Objective] The plankton and macrobenthos samples in municipal polluted river were analyzed by different methods, so as to explore the method suitable for biological data analysis in heavy polluted area. [Method] Shannon-Wiener diversity index, cluster analysis of multivariate statistical analysis and MDS （Non-matric Multi- dimentional Scaling）analysis were used to analyze biological data of phytoplankton, zooplankton and Zoobenthos collected from the representative municipal polluted river in Pearl River Delta. The sediment samples were also collected to determine. Pb, Cd, Hg, Cr, As, Cu, Ni, Zn, as well as CODe, and NH3-N of porewater. Hakanson potential ecological risk index method was used to evaluate the ecological risk. [Re- suit] Shannon-Wiener diversity index analysis results can not effectively reflect the difference of pollution status of various stations in heavy polluted area; despite the presence of some problems, multivariate analysis method is superior to the Shannon-Wiener diversity index method in biological monitoring of heavy polluted river in the city. [Conclusion] The paper provided theoretical basis for biological data analysis in heavy polluted area.
基金Supported by the National Natural Science Foundation of China(71101043,70901041,71171113)the Joint Research Project of National Natural Science Foundation of China and Royal Society of UK(71111130211)+4 种基金the Major Program of National Funds of Social Science of China(10ZD&014,11&ZD168)the Doctoral Fundof Ministry of Education of China(20093218120032,200802870020)the Qinglan Project for Excellent Youth Teacherin Jiangsu Province(China)Research Funding in Nanjing University of Aeronautics and Astronautics(NR2011002)the Central University Scientific Research Expenses of HoHai University(2011B09914,2010B11114)~~
文摘The analysis result of absolute degree of grey incidence for multivariate time series is often inconsistent with the qualitative analysis. To overcome this shortage, a multivariate absolute degree of grey incidence based on distribution characteristics of points is proposed. Based on the geometric description of multivariate time se- ries, the neighborhood extrema are extracted in the different regions, and a characteristic point set is constructed. Then according to the distribution of the characteristic point set, a characteristic point sequence reflecting the ge- ometric features of multivariate time series is obtained. The incidence analysis between multivariate time series is transformed into the relational analysis between characteristic point sequences, and a grey incidence model is established. The model possesses the properties of translational invariance, transpose and rank transform invari- ance, and satisfies the grey incidence analysis axioms. Finally, two cases are studied and the results prove the ef- fectiveness of the model.
