Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fa...Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.展开更多
Accurate mapping and timely monitoring of urban redevelopment are pivotal for urban studies and decisionmakers to foster sustainable urban development.Traditional mapping methods heavily depend on field surveys and su...Accurate mapping and timely monitoring of urban redevelopment are pivotal for urban studies and decisionmakers to foster sustainable urban development.Traditional mapping methods heavily depend on field surveys and subjective questionnaires,yielding less objective,reliable,and timely data.Recent advancements in Geographic Information Systems(GIS)and remote-sensing technologies have improved the identification and mapping of urban redevelopment through quantitative analysis using satellite-based observations.Nonetheless,challenges persist,particularly concerning accuracy and significant temporal delays.This study introduces a novel approach to modeling urban redevelopment,leveraging machine learning algorithms and remote-sensing data.This methodology can facilitate the accurate and timely identification of urban redevelopment activities.The study’s machine learning model can analyze time-series remote-sensing data to identify spatio-temporal and spectral patterns related to urban redevelopment.The model is thoroughly evaluated,and the results indicate that it can accurately capture the time-series patterns of urban redevelopment.This research’s findings are useful for evaluating urban demographic and economic changes,informing policymaking and urban planning,and contributing to sustainable urban development.The model can also serve as a foundation for future research on early-stage urban redevelopment detection and evaluation of the causes and impacts of urban redevelopment.展开更多
The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random mis...The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.展开更多
为了提高无人机遥感对冬小麦叶面积指数(leaf area index,LAI)反演模型的精度与泛化能力,该研究利用无人机搭载多光谱相机获取不同氮素处理和不同复种方式的冬小麦生长实测数据,结合PROSAIL辐射传输模型生成包含机理信息的模拟数据,基...为了提高无人机遥感对冬小麦叶面积指数(leaf area index,LAI)反演模型的精度与泛化能力,该研究利用无人机搭载多光谱相机获取不同氮素处理和不同复种方式的冬小麦生长实测数据,结合PROSAIL辐射传输模型生成包含机理信息的模拟数据,基于不同组合方式建立了5种LAI反演混合数据集,结合多种机器学习方法,以期构建经验与机理相结合的LAI高精度反演模型。由于LAI反演受近红外波段(near infrared,NIR)反射率影响大,该研究筛选7种与NIR波段相关的植被指数提取冬小麦光谱特征,构建与混合数据集LAI的相关系数矩阵,进一步探究不同光谱特征对冬小麦LAI的影响程度。在此基础上,采用具有代表性和普适性的4种机器学习方法,即贝叶斯岭回归模型、线性回归模型、弹性网络模型和支持向量回归模型,构建不同冬小麦LAI反演模型,用以评估基于半经验半机理数据反演冬小麦LAI的可行性,进一步探索其对不同氮素水平和复种方式的冬小麦长势评估能力。结果表明:1)筛选的与NIR波段相关的植被指数与冬小麦LAI之间存在较强的相关性,其中归一化差异植被指数、增强植被指数、归一化差异红边指数、比值植被指数、红边叶绿素植被指数、土壤调节植被指数与LAI呈正相关,结构不敏感色素植被指数与LAI呈负相关;2)辐射传输模型中体现了冬小麦LAI影响太阳光线传播的机理,结果表明,与实测数据混合建立的模型,具有较强的鲁棒性和泛化能力。相比于其他3种模型,支持向量回归模型在各种数据组合下均取得了较好的LAI预测性能,在C1、C2、C3、C4这4种训练-测试组合的训练集中R^(2)依次为0.86、0.87、0.88、0.91,RMSE依次为0.47、0.45、0.45、0.41;在测试集的R^(2)依次为0.85、0.19、0.89、0.87,RMSE依次为0.45、1.31、0.49、0.50;3)使用支持向量机生成试验区LAI反演图,对4种氮素水平和2种复种方式的冬小麦长势评估,结果表明,适当的施加氮素处理能提高冬小麦LAI值,麦-豆复种方式下的冬小麦LAI值普遍高于麦-玉复种的LAI值。该研究为冬小麦LAI的反演提供了一种有效的方法,并为高效评估冬小麦长势研究提供了参考。展开更多
株高和叶面积指数(Leaf Area Index,LAI)反映着作物的生长发育状况。为了探究基于无人机可见光遥感提取冬小麦株高的可靠性,以及利用株高和可见光植被指数估算LAI的精度,本文获取了拔节期、抽穗期、灌浆期的无人机影像,提取了冬小麦株...株高和叶面积指数(Leaf Area Index,LAI)反映着作物的生长发育状况。为了探究基于无人机可见光遥感提取冬小麦株高的可靠性,以及利用株高和可见光植被指数估算LAI的精度,本文获取了拔节期、抽穗期、灌浆期的无人机影像,提取了冬小麦株高与可见光植被指数,使用逐步回归、偏最小二乘、随机森林、人工神经网络四种方法建立LAI估测模型,并对株高提取及LAI估测情况进行精度评价。结果显示:(1)株高提取值Hc与实测值Hd高度拟合(R^(2)=0.894,RMSE=6.695,NRMSE=9.63%),株高提取效果好;(2)与仅用可见光植被指数相比,基于株高与可见光植被指数构建的LAI估测模型精度更高,且随机森林为最优建模方法,当其决策树个数为50时模型估测效果最好(R^(2)=0.809,RMSE=0.497,NRMSE=13.85%,RPD=2.336)。利用无人机可见光遥感方法,高效、准确、无损地实现冬小麦株高及LAI提取估测可行性较高,该研究结果可为农情遥感监测提供参考。展开更多
BACKGROUND The literature has discussed the relationship between environmental factors and depressive disorders;however,the results are inconsistent in different studies and regions,as are the interaction effects betw...BACKGROUND The literature has discussed the relationship between environmental factors and depressive disorders;however,the results are inconsistent in different studies and regions,as are the interaction effects between environmental factors.We hypo-thesized that meteorological factors and ambient air pollution individually affect and interact to affect depressive disorder morbidity.AIM To investigate the effects of meteorological factors and air pollution on depressive disorders,including their lagged effects and interactions.METHODS The samples were obtained from a class 3 hospital in Harbin,China.Daily hos-pital admission data for depressive disorders from January 1,2015 to December 31,2022 were obtained.Meteorological and air pollution data were also collected during the same period.Generalized additive models with quasi-Poisson regre-ssion were used for time-series modeling to measure the non-linear and delayed effects of environmental factors.We further incorporated each pair of environ-mental factors into a bivariate response surface model to examine the interaction effects on hospital admissions for depressive disorders.RESULTS Data for 2922 d were included in the study,with no missing values.The total number of depressive admissions was 83905.Medium to high correlations existed between environmental factors.Air temperature(AT)and wind speed(WS)significantly affected the number of admissions for depression.An extremely low temperature(-29.0℃)at lag 0 caused a 53%[relative risk(RR)=1.53,95%confidence interval(CI):1.23-1.89]increase in daily hospital admissions relative to the median temperature.Extremely low WSs(0.4 m/s)at lag 7 increased the number of admissions by 58%(RR=1.58,95%CI:1.07-2.31).In contrast,atmospheric pressure and relative humidity had smaller effects.Among the six air pollutants considered in the time-series model,nitrogen dioxide(NO_(2))was the only pollutant that showed significant effects over non-cumulative,cumulative,immediate,and lagged conditions.The cumulative effect of NO_(2) at lag 7 was 0.47%(RR=1.0047,95%CI:1.0024-1.0071).Interaction effects were found between AT and the five air pollutants,atmospheric temperature and the four air pollutants,WS and sulfur dioxide.CONCLUSION Meteorological factors and the air pollutant NO_(2) affect daily hospital admissions for depressive disorders,and interactions exist between meteorological factors and ambient air pollution.展开更多
By employing the unique phenological feature of winter wheat extracted from peak before winter (PBW) and the advantages of moderate resolution imaging spectroradiometer (MODIS) data with high temporal resolution a...By employing the unique phenological feature of winter wheat extracted from peak before winter (PBW) and the advantages of moderate resolution imaging spectroradiometer (MODIS) data with high temporal resolution and intermediate spatial resolution, a remote sensing-based model for mapping winter wheat on the North China Plain was built through integration with Landsat images and land-use data. First, a phenological window, PBW was drawn from time-series MODIS data. Next, feature extraction was performed for the PBW to reduce feature dimension and enhance its information. Finally, a regression model was built to model the relationship of the phenological feature and the sample data. The amount of information of the PBW was evaluated and compared with that of the main peak (MP). The relative precision of the mapping reached up to 92% in comparison to the Landsat sample data, and ranged between 87 and 96% in comparison to the statistical data. These results were sufficient to satisfy the accuracy requirements for winter wheat mapping at a large scale. Moreover, the proposed method has the ability to obtain the distribution information for winter wheat in an earlier period than previous studies. This study could throw light on the monitoring of winter wheat in China by using unique phenological feature of winter wheat.展开更多
Multivariate time-series forecasting(MTSF)plays an important role in diverse real-world applications.To achieve better accuracy in MTSF,time-series patterns in each variable and interrelationship patterns between vari...Multivariate time-series forecasting(MTSF)plays an important role in diverse real-world applications.To achieve better accuracy in MTSF,time-series patterns in each variable and interrelationship patterns between variables should be considered together.Recently,graph neural networks(GNNs)has gained much attention as they can learn both patterns using a graph.For accurate forecasting through GNN,a well-defined graph is required.However,existing GNNs have limitations in reflecting the spectral similarity and time delay between nodes,and consider all nodes with the same weight when constructing graph.In this paper,we propose a novel graph construction method that solves aforementioned limitations.We first calculate the Fourier transform-based spectral similarity and then update this similarity to reflect the time delay.Then,we weight each node according to the number of edge connections to get the final graph and utilize it to train the GNN model.Through experiments on various datasets,we demonstrated that the proposed method enhanced the performance of GNN-based MTSF models,and the proposed forecasting model achieve of up to 18.1%predictive performance improvement over the state-of-the-art model.展开更多
In the past two decades,because of the significant increase in the availability of differential interferometry from synthetic aperture radar and GPS data,spaceborne geodesy has been widely employed to determine the co...In the past two decades,because of the significant increase in the availability of differential interferometry from synthetic aperture radar and GPS data,spaceborne geodesy has been widely employed to determine the co-seismic displacement field of earthquakes.On April 18,2021,a moderate earthquake(Mw 5.8)occurred east of Bandar Ganaveh,southern Iran,followed by intensive seismic activity and aftershocks of various magnitudes.We use two-pass D-InSAR and Small Baseline Inversion techniques via the LiCSBAS suite to study the coseismic displacement and monitor the four-month post-seismic deformation of the Bandar Ganaveh earthquake,as well as constrain the fault geometry of the co-seismic faulting mechanism during the seismic sequence.Analyses show that the co-and postseismic deformation are distributed in relatively shallow depths along with an NW-SE striking and NE dipping complex reverse/thrust fault branches of the Zagros Mountain Front Fault,complying with the main trend of the Zagros structures.The average cumulative displacements were obtained from-137.5 to+113.3 mm/yr in the SW and NE blocks of the Mountain Front Fault,respectively.The received maximum uplift amount is approximately consistent with the overall orogen-normal shortening component of the Arabian-Eurasian convergence in the Zagros region.No surface ruptures were associated with the seismic source;therefore,we propose a shallow blind thrust/reverse fault(depth~10 km)connected to the deeper basal decollement fault within a complex tectonic zone,emphasizing the thin-skinned tectonics.展开更多
The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist...The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist and education-centric localities.In the upcoming arrival of electric kickboard vehicles,deploying a customer rental service is essential.Due to its freefloating nature,the shared electric kickboard is a common and practical means of transportation.Relocation plans for shared electric kickboards are required to increase the quality of service,and forecasting demand for their use in a specific region is crucial.Predicting demand accurately with small data is troublesome.Extensive data is necessary for training machine learning algorithms for effective prediction.Data generation is a method for expanding the amount of data that will be further accessible for training.In this work,we proposed a model that takes time-series customers’electric kickboard demand data as input,pre-processes it,and generates synthetic data according to the original data distribution using generative adversarial networks(GAN).The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data.We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results.We modified The Wasserstein GAN-gradient penalty(GP)with the RMSprop optimizer and then employed Spectral Normalization(SN)to improve training stability and faster convergence.Finally,we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction.We used various evaluation criteria and visual representations to compare our proposed model’s performance.Synthetic data generated by our suggested GAN model is also evaluated.The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem,and it also converges faster than previous GAN models for synthetic data creation.The presented model’s performance is compared to existing ensemble and baseline models.The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error(MAPE)of 4.476 and increase prediction accuracy.展开更多
【目的】研究融合无人机遥感影像多光谱信息和纹理特征估算马铃薯Solanum tuberosum叶面积指数(Leaf area index,LAI)方法,提高马铃薯LAI反演精度。【方法】利用大疆P4M无人机采集2021年2-4月南方冬种马铃薯幼苗期、现蕾期、块茎膨大期...【目的】研究融合无人机遥感影像多光谱信息和纹理特征估算马铃薯Solanum tuberosum叶面积指数(Leaf area index,LAI)方法,提高马铃薯LAI反演精度。【方法】利用大疆P4M无人机采集2021年2-4月南方冬种马铃薯幼苗期、现蕾期、块茎膨大期多光谱影像,用LAI-2000冠层分析仪实测LAI数据。提取影像光谱、纹理等信息,分析植被指数、纹理特征与LAI的相关性,基于R^(2)_(adj)的全子集分析优选特征变量。采用主成分分析,融合光谱和纹理特征,用PCA-MLR(Principal component analysis-multiple linear regression)模型估算马铃薯LAI。【结果】从幼苗期到块茎膨大期,PCA-MLR估算模型优于T-MLR(Texture multiple linear regression)和VIMLR(Vegetation index multiple linear regression)模型,R2分别为0.73、0.59和0.66。【结论】本研究提出一种估算马铃薯LAI的PCA-MLR方法,为马铃薯的长势监测和田间管理提供数据支持。展开更多
To investigate the association between temperature and daily mortality in Shanghai from June 1, 2000 to December 31, 2001. Methods Time-series approach was used to estimate the effect of temperature on daily tota...To investigate the association between temperature and daily mortality in Shanghai from June 1, 2000 to December 31, 2001. Methods Time-series approach was used to estimate the effect of temperature on daily total and cause-specific mortality. We fitted generalized additive Poisson regression using non-parametric smooth functions to control for long-term time trend, season and other variables. We also controlled for day of the week. Results A gently sloping V-like relationship between total mortality and temperature was found, with an optimum temperature (e.g. temperature with lowest mortality risk) value of 26.7癈 in Shanghai. For temperatures above the optimum value, total mortality increased by 0.73% for each degree Celsius increase; while for temperature below the optimum value, total mortality decreased by 1.21% for each degree Celsius increase. Conclusions Our findings indicate that temperature has an effect on daily mortality in Shanghai, and the time-series approach is a useful tool for studying the temperature-mortality association.展开更多
In the past 30 years,the small baseline subset(SBAS)InSAR time-series technique has emerged as an essential tool for measuring slow surface displacement and estimating geophysical parameters.Because of its ability to ...In the past 30 years,the small baseline subset(SBAS)InSAR time-series technique has emerged as an essential tool for measuring slow surface displacement and estimating geophysical parameters.Because of its ability to monitor large-scale deformation with millimeter accuracy,the SBAS method has been widely used in various geodetic fields,such as ground subsidence,landslides,and seismic activity.The obtained long-term time-series cumulative deformation is vital for studying the deformation mecha-nism.This article reviews the algorithms,applications,and challenges of the SBAS method.First,we recall the fundamental principle and analyze the shortcomings of the traditional SBAS algorithm,which provides a basic framework for the following improved time series methods.Second,we classify the current improved SBAS techniques from different perspectives:solving the ill-posed equation,increasing the density of high-coherence points,improving the accuracy of monitoring deformation and measuring the multi-dimensional deformation.Third,we summarize the application of the SBAS method in monitoring ground subsidence,permafrost degradation,glacier movement,volcanic activity,landslides,and seismic activity.Finally,we discuss the difficulties faced by the SBAS method and explore its future development direction.展开更多
Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algor...Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.展开更多
A time-series similarity measurement method based on wavelet and matrix transform was proposed,and its anti-noise ability,sensitivity and accuracy were discussed. The time-series sequences were compressed into wavelet...A time-series similarity measurement method based on wavelet and matrix transform was proposed,and its anti-noise ability,sensitivity and accuracy were discussed. The time-series sequences were compressed into wavelet subspace,and sample feature vector and orthogonal basics of sample time-series sequences were obtained by K-L transform. Then the inner product transform was carried out to project analyzed time-series sequence into orthogonal basics to gain analyzed feature vectors. The similarity was calculated between sample feature vector and analyzed feature vector by the Euclid distance. Taking fault wave of power electronic devices for example,the experimental results show that the proposed method has low dimension of feature vector,the anti-noise ability of proposed method is 30 times as large as that of plain wavelet method,the sensitivity of proposed method is 1/3 as large as that of plain wavelet method,and the accuracy of proposed method is higher than that of the wavelet singular value decomposition method. The proposed method can be applied in similarity matching and indexing for lager time series databases.展开更多
基金supported by the National Natural Science Foundation of China(62073140,62073141)the Shanghai Rising-Star Program(21QA1401800).
文摘Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.
文摘Accurate mapping and timely monitoring of urban redevelopment are pivotal for urban studies and decisionmakers to foster sustainable urban development.Traditional mapping methods heavily depend on field surveys and subjective questionnaires,yielding less objective,reliable,and timely data.Recent advancements in Geographic Information Systems(GIS)and remote-sensing technologies have improved the identification and mapping of urban redevelopment through quantitative analysis using satellite-based observations.Nonetheless,challenges persist,particularly concerning accuracy and significant temporal delays.This study introduces a novel approach to modeling urban redevelopment,leveraging machine learning algorithms and remote-sensing data.This methodology can facilitate the accurate and timely identification of urban redevelopment activities.The study’s machine learning model can analyze time-series remote-sensing data to identify spatio-temporal and spectral patterns related to urban redevelopment.The model is thoroughly evaluated,and the results indicate that it can accurately capture the time-series patterns of urban redevelopment.This research’s findings are useful for evaluating urban demographic and economic changes,informing policymaking and urban planning,and contributing to sustainable urban development.The model can also serve as a foundation for future research on early-stage urban redevelopment detection and evaluation of the causes and impacts of urban redevelopment.
基金supported by Graduate Funded Project(No.JY2022A017).
文摘The frequent missing values in radar-derived time-series tracks of aerial targets(RTT-AT)lead to significant challenges in subsequent data-driven tasks.However,the majority of imputation research focuses on random missing(RM)that differs significantly from common missing patterns of RTT-AT.The method for solving the RM may experience performance degradation or failure when applied to RTT-AT imputation.Conventional autoregressive deep learning methods are prone to error accumulation and long-term dependency loss.In this paper,a non-autoregressive imputation model that addresses the issue of missing value imputation for two common missing patterns in RTT-AT is proposed.Our model consists of two probabilistic sparse diagonal masking self-attention(PSDMSA)units and a weight fusion unit.It learns missing values by combining the representations outputted by the two units,aiming to minimize the difference between the missing values and their actual values.The PSDMSA units effectively capture temporal dependencies and attribute correlations between time steps,improving imputation quality.The weight fusion unit automatically updates the weights of the output representations from the two units to obtain a more accurate final representation.The experimental results indicate that,despite varying missing rates in the two missing patterns,our model consistently outperforms other methods in imputation performance and exhibits a low frequency of deviations in estimates for specific missing entries.Compared to the state-of-the-art autoregressive deep learning imputation model Bidirectional Recurrent Imputation for Time Series(BRITS),our proposed model reduces mean absolute error(MAE)by 31%~50%.Additionally,the model attains a training speed that is 4 to 8 times faster when compared to both BRITS and a standard Transformer model when trained on the same dataset.Finally,the findings from the ablation experiments demonstrate that the PSDMSA,the weight fusion unit,cascade network design,and imputation loss enhance imputation performance and confirm the efficacy of our design.
文摘为了提高无人机遥感对冬小麦叶面积指数(leaf area index,LAI)反演模型的精度与泛化能力,该研究利用无人机搭载多光谱相机获取不同氮素处理和不同复种方式的冬小麦生长实测数据,结合PROSAIL辐射传输模型生成包含机理信息的模拟数据,基于不同组合方式建立了5种LAI反演混合数据集,结合多种机器学习方法,以期构建经验与机理相结合的LAI高精度反演模型。由于LAI反演受近红外波段(near infrared,NIR)反射率影响大,该研究筛选7种与NIR波段相关的植被指数提取冬小麦光谱特征,构建与混合数据集LAI的相关系数矩阵,进一步探究不同光谱特征对冬小麦LAI的影响程度。在此基础上,采用具有代表性和普适性的4种机器学习方法,即贝叶斯岭回归模型、线性回归模型、弹性网络模型和支持向量回归模型,构建不同冬小麦LAI反演模型,用以评估基于半经验半机理数据反演冬小麦LAI的可行性,进一步探索其对不同氮素水平和复种方式的冬小麦长势评估能力。结果表明:1)筛选的与NIR波段相关的植被指数与冬小麦LAI之间存在较强的相关性,其中归一化差异植被指数、增强植被指数、归一化差异红边指数、比值植被指数、红边叶绿素植被指数、土壤调节植被指数与LAI呈正相关,结构不敏感色素植被指数与LAI呈负相关;2)辐射传输模型中体现了冬小麦LAI影响太阳光线传播的机理,结果表明,与实测数据混合建立的模型,具有较强的鲁棒性和泛化能力。相比于其他3种模型,支持向量回归模型在各种数据组合下均取得了较好的LAI预测性能,在C1、C2、C3、C4这4种训练-测试组合的训练集中R^(2)依次为0.86、0.87、0.88、0.91,RMSE依次为0.47、0.45、0.45、0.41;在测试集的R^(2)依次为0.85、0.19、0.89、0.87,RMSE依次为0.45、1.31、0.49、0.50;3)使用支持向量机生成试验区LAI反演图,对4种氮素水平和2种复种方式的冬小麦长势评估,结果表明,适当的施加氮素处理能提高冬小麦LAI值,麦-豆复种方式下的冬小麦LAI值普遍高于麦-玉复种的LAI值。该研究为冬小麦LAI的反演提供了一种有效的方法,并为高效评估冬小麦长势研究提供了参考。
文摘株高和叶面积指数(Leaf Area Index,LAI)反映着作物的生长发育状况。为了探究基于无人机可见光遥感提取冬小麦株高的可靠性,以及利用株高和可见光植被指数估算LAI的精度,本文获取了拔节期、抽穗期、灌浆期的无人机影像,提取了冬小麦株高与可见光植被指数,使用逐步回归、偏最小二乘、随机森林、人工神经网络四种方法建立LAI估测模型,并对株高提取及LAI估测情况进行精度评价。结果显示:(1)株高提取值Hc与实测值Hd高度拟合(R^(2)=0.894,RMSE=6.695,NRMSE=9.63%),株高提取效果好;(2)与仅用可见光植被指数相比,基于株高与可见光植被指数构建的LAI估测模型精度更高,且随机森林为最优建模方法,当其决策树个数为50时模型估测效果最好(R^(2)=0.809,RMSE=0.497,NRMSE=13.85%,RPD=2.336)。利用无人机可见光遥感方法,高效、准确、无损地实现冬小麦株高及LAI提取估测可行性较高,该研究结果可为农情遥感监测提供参考。
基金This study was reviewed and approved by the Ethics Committee of The First Psychiatric Hospital of Harbin.
文摘BACKGROUND The literature has discussed the relationship between environmental factors and depressive disorders;however,the results are inconsistent in different studies and regions,as are the interaction effects between environmental factors.We hypo-thesized that meteorological factors and ambient air pollution individually affect and interact to affect depressive disorder morbidity.AIM To investigate the effects of meteorological factors and air pollution on depressive disorders,including their lagged effects and interactions.METHODS The samples were obtained from a class 3 hospital in Harbin,China.Daily hos-pital admission data for depressive disorders from January 1,2015 to December 31,2022 were obtained.Meteorological and air pollution data were also collected during the same period.Generalized additive models with quasi-Poisson regre-ssion were used for time-series modeling to measure the non-linear and delayed effects of environmental factors.We further incorporated each pair of environ-mental factors into a bivariate response surface model to examine the interaction effects on hospital admissions for depressive disorders.RESULTS Data for 2922 d were included in the study,with no missing values.The total number of depressive admissions was 83905.Medium to high correlations existed between environmental factors.Air temperature(AT)and wind speed(WS)significantly affected the number of admissions for depression.An extremely low temperature(-29.0℃)at lag 0 caused a 53%[relative risk(RR)=1.53,95%confidence interval(CI):1.23-1.89]increase in daily hospital admissions relative to the median temperature.Extremely low WSs(0.4 m/s)at lag 7 increased the number of admissions by 58%(RR=1.58,95%CI:1.07-2.31).In contrast,atmospheric pressure and relative humidity had smaller effects.Among the six air pollutants considered in the time-series model,nitrogen dioxide(NO_(2))was the only pollutant that showed significant effects over non-cumulative,cumulative,immediate,and lagged conditions.The cumulative effect of NO_(2) at lag 7 was 0.47%(RR=1.0047,95%CI:1.0024-1.0071).Interaction effects were found between AT and the five air pollutants,atmospheric temperature and the four air pollutants,WS and sulfur dioxide.CONCLUSION Meteorological factors and the air pollutant NO_(2) affect daily hospital admissions for depressive disorders,and interactions exist between meteorological factors and ambient air pollution.
基金supported by the open research fund of the Key Laboratory of Agri-informatics,Ministry of Agriculture and the fund of Outstanding Agricultural Researcher,Ministry of Agriculture,China
文摘By employing the unique phenological feature of winter wheat extracted from peak before winter (PBW) and the advantages of moderate resolution imaging spectroradiometer (MODIS) data with high temporal resolution and intermediate spatial resolution, a remote sensing-based model for mapping winter wheat on the North China Plain was built through integration with Landsat images and land-use data. First, a phenological window, PBW was drawn from time-series MODIS data. Next, feature extraction was performed for the PBW to reduce feature dimension and enhance its information. Finally, a regression model was built to model the relationship of the phenological feature and the sample data. The amount of information of the PBW was evaluated and compared with that of the main peak (MP). The relative precision of the mapping reached up to 92% in comparison to the Landsat sample data, and ranged between 87 and 96% in comparison to the statistical data. These results were sufficient to satisfy the accuracy requirements for winter wheat mapping at a large scale. Moreover, the proposed method has the ability to obtain the distribution information for winter wheat in an earlier period than previous studies. This study could throw light on the monitoring of winter wheat in China by using unique phenological feature of winter wheat.
基金supported by Energy Cloud R&D Program(grant number:2019M3F2A1073184)through the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT.
文摘Multivariate time-series forecasting(MTSF)plays an important role in diverse real-world applications.To achieve better accuracy in MTSF,time-series patterns in each variable and interrelationship patterns between variables should be considered together.Recently,graph neural networks(GNNs)has gained much attention as they can learn both patterns using a graph.For accurate forecasting through GNN,a well-defined graph is required.However,existing GNNs have limitations in reflecting the spectral similarity and time delay between nodes,and consider all nodes with the same weight when constructing graph.In this paper,we propose a novel graph construction method that solves aforementioned limitations.We first calculate the Fourier transform-based spectral similarity and then update this similarity to reflect the time delay.Then,we weight each node according to the number of edge connections to get the final graph and utilize it to train the GNN model.Through experiments on various datasets,we demonstrated that the proposed method enhanced the performance of GNN-based MTSF models,and the proposed forecasting model achieve of up to 18.1%predictive performance improvement over the state-of-the-art model.
文摘In the past two decades,because of the significant increase in the availability of differential interferometry from synthetic aperture radar and GPS data,spaceborne geodesy has been widely employed to determine the co-seismic displacement field of earthquakes.On April 18,2021,a moderate earthquake(Mw 5.8)occurred east of Bandar Ganaveh,southern Iran,followed by intensive seismic activity and aftershocks of various magnitudes.We use two-pass D-InSAR and Small Baseline Inversion techniques via the LiCSBAS suite to study the coseismic displacement and monitor the four-month post-seismic deformation of the Bandar Ganaveh earthquake,as well as constrain the fault geometry of the co-seismic faulting mechanism during the seismic sequence.Analyses show that the co-and postseismic deformation are distributed in relatively shallow depths along with an NW-SE striking and NE dipping complex reverse/thrust fault branches of the Zagros Mountain Front Fault,complying with the main trend of the Zagros structures.The average cumulative displacements were obtained from-137.5 to+113.3 mm/yr in the SW and NE blocks of the Mountain Front Fault,respectively.The received maximum uplift amount is approximately consistent with the overall orogen-normal shortening component of the Arabian-Eurasian convergence in the Zagros region.No surface ruptures were associated with the seismic source;therefore,we propose a shallow blind thrust/reverse fault(depth~10 km)connected to the deeper basal decollement fault within a complex tectonic zone,emphasizing the thin-skinned tectonics.
基金This work was supported by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0016977,The Establishment Project of Industry-University Fusion District).
文摘The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features.Electric kickboards are gradually growing in popularity in tourist and education-centric localities.In the upcoming arrival of electric kickboard vehicles,deploying a customer rental service is essential.Due to its freefloating nature,the shared electric kickboard is a common and practical means of transportation.Relocation plans for shared electric kickboards are required to increase the quality of service,and forecasting demand for their use in a specific region is crucial.Predicting demand accurately with small data is troublesome.Extensive data is necessary for training machine learning algorithms for effective prediction.Data generation is a method for expanding the amount of data that will be further accessible for training.In this work,we proposed a model that takes time-series customers’electric kickboard demand data as input,pre-processes it,and generates synthetic data according to the original data distribution using generative adversarial networks(GAN).The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data.We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results.We modified The Wasserstein GAN-gradient penalty(GP)with the RMSprop optimizer and then employed Spectral Normalization(SN)to improve training stability and faster convergence.Finally,we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction.We used various evaluation criteria and visual representations to compare our proposed model’s performance.Synthetic data generated by our suggested GAN model is also evaluated.The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem,and it also converges faster than previous GAN models for synthetic data creation.The presented model’s performance is compared to existing ensemble and baseline models.The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error(MAPE)of 4.476 and increase prediction accuracy.
文摘【目的】研究融合无人机遥感影像多光谱信息和纹理特征估算马铃薯Solanum tuberosum叶面积指数(Leaf area index,LAI)方法,提高马铃薯LAI反演精度。【方法】利用大疆P4M无人机采集2021年2-4月南方冬种马铃薯幼苗期、现蕾期、块茎膨大期多光谱影像,用LAI-2000冠层分析仪实测LAI数据。提取影像光谱、纹理等信息,分析植被指数、纹理特征与LAI的相关性,基于R^(2)_(adj)的全子集分析优选特征变量。采用主成分分析,融合光谱和纹理特征,用PCA-MLR(Principal component analysis-multiple linear regression)模型估算马铃薯LAI。【结果】从幼苗期到块茎膨大期,PCA-MLR估算模型优于T-MLR(Texture multiple linear regression)和VIMLR(Vegetation index multiple linear regression)模型,R2分别为0.73、0.59和0.66。【结论】本研究提出一种估算马铃薯LAI的PCA-MLR方法,为马铃薯的长势监测和田间管理提供数据支持。
文摘To investigate the association between temperature and daily mortality in Shanghai from June 1, 2000 to December 31, 2001. Methods Time-series approach was used to estimate the effect of temperature on daily total and cause-specific mortality. We fitted generalized additive Poisson regression using non-parametric smooth functions to control for long-term time trend, season and other variables. We also controlled for day of the week. Results A gently sloping V-like relationship between total mortality and temperature was found, with an optimum temperature (e.g. temperature with lowest mortality risk) value of 26.7癈 in Shanghai. For temperatures above the optimum value, total mortality increased by 0.73% for each degree Celsius increase; while for temperature below the optimum value, total mortality decreased by 1.21% for each degree Celsius increase. Conclusions Our findings indicate that temperature has an effect on daily mortality in Shanghai, and the time-series approach is a useful tool for studying the temperature-mortality association.
基金This work was funded by the National Key R&D Program of China(2019YFC1509205)the National Natural Science Foundation of China(Nos.42174023 and 41804015)+1 种基金the Postgraduate Scientific Research Innovation Project of Hunan Province(150110074)the Postgraduate Scientific Research Innovation Project of Central South University(212191010).
文摘In the past 30 years,the small baseline subset(SBAS)InSAR time-series technique has emerged as an essential tool for measuring slow surface displacement and estimating geophysical parameters.Because of its ability to monitor large-scale deformation with millimeter accuracy,the SBAS method has been widely used in various geodetic fields,such as ground subsidence,landslides,and seismic activity.The obtained long-term time-series cumulative deformation is vital for studying the deformation mecha-nism.This article reviews the algorithms,applications,and challenges of the SBAS method.First,we recall the fundamental principle and analyze the shortcomings of the traditional SBAS algorithm,which provides a basic framework for the following improved time series methods.Second,we classify the current improved SBAS techniques from different perspectives:solving the ill-posed equation,increasing the density of high-coherence points,improving the accuracy of monitoring deformation and measuring the multi-dimensional deformation.Third,we summarize the application of the SBAS method in monitoring ground subsidence,permafrost degradation,glacier movement,volcanic activity,landslides,and seismic activity.Finally,we discuss the difficulties faced by the SBAS method and explore its future development direction.
文摘Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.
基金Projects(60634020, 60904077, 60874069) supported by the National Natural Science Foundation of ChinaProject(JC200903180555A) supported by the Foundation Project of Shenzhen City Science and Technology Plan of China
文摘A time-series similarity measurement method based on wavelet and matrix transform was proposed,and its anti-noise ability,sensitivity and accuracy were discussed. The time-series sequences were compressed into wavelet subspace,and sample feature vector and orthogonal basics of sample time-series sequences were obtained by K-L transform. Then the inner product transform was carried out to project analyzed time-series sequence into orthogonal basics to gain analyzed feature vectors. The similarity was calculated between sample feature vector and analyzed feature vector by the Euclid distance. Taking fault wave of power electronic devices for example,the experimental results show that the proposed method has low dimension of feature vector,the anti-noise ability of proposed method is 30 times as large as that of plain wavelet method,the sensitivity of proposed method is 1/3 as large as that of plain wavelet method,and the accuracy of proposed method is higher than that of the wavelet singular value decomposition method. The proposed method can be applied in similarity matching and indexing for lager time series databases.