Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection...Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection of appropriate embedding window size and principal components makes this method cumbersome and inefficient.To improve the efficiency and accuracy of singular spectrum analysis,this paper proposes an adaptive singular spectrum analysis method by combining spectrum analysis with a new trace matrix.The running time and correlation analysis indicate that the proposed method can adaptively set the embedding window size to extract the time-varying periodic signals from GNSS time series,and the extraction efficiency of a single time series is six times that of singular spectrum analysis.The method is also accurate and more suitable for time-varying periodic signal analysis of global GNSS sites.展开更多
With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk manageme...With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.展开更多
Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep lear...Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.展开更多
Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same g...Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.展开更多
Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in t...Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.展开更多
Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal depende...Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.展开更多
In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciat...In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.展开更多
Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically ...Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically relies on expert input and necessitates substantial manual involvement.This manual effort spans model development,feature engineering,hyper-parameter tuning,and the intricate construction of time series models.The complexity of these tasks renders complete automation unfeasible,as they inherently demand human intervention at multiple junctures.To surmount these challenges,this article proposes leveraging Long Short-Term Memory,which is the variant of Recurrent Neural Networks,harnessing memory cells and gating mechanisms to facilitate long-term time series prediction.However,forecasting accuracy by particular neural network and traditional models can degrade significantly,when addressing long-term time-series tasks.Therefore,our research demonstrates that this innovative approach outperforms the traditional Autoregressive Integrated Moving Average(ARIMA)method in forecasting long-term univariate time series.ARIMA is a high-quality and competitive model in time series prediction,and yet it requires significant preprocessing efforts.Using multiple accuracy metrics,we have evaluated both ARIMA and proposed method on the simulated time-series data and real data in both short and long term.Furthermore,our findings indicate its superiority over alternative network architectures,including Fully Connected Neural Networks,Convolutional Neural Networks,and Nonpooling Convolutional Neural Networks.Our AutoML approach enables non-professional to attain highly accurate and effective time series forecasting,and can be widely applied to various domains,particularly in business and finance.展开更多
In this paper,we describe and analyze two datasets entitled“Homogenised monthly and daily temperature and precipitation time series in China during 1960–2021”and“Homogenised monthly and daily temperature and preci...In this paper,we describe and analyze two datasets entitled“Homogenised monthly and daily temperature and precipitation time series in China during 1960–2021”and“Homogenised monthly and daily temperature and precipitation time series in Greece during 1960–2010”.These datasets provide the homogenised monthly and daily mean(TG),minimum(TN),and maximum(TX)temperature and precipitation(RR)records since 1960 at 366 stations in China and 56stations in Greece.The datasets are available at the Science Data Bank repository and can be downloaded from https://doi.org/10.57760/sciencedb.01731 and https://doi.org/10.57760/sciencedb.01720.For China,the regional mean annual TG,TX,TN,and RR series during 1960–2021 showed significant warming or increasing trends of 0.27℃(10 yr)^(-1),0.22℃(10 yr)^(-1),0.35℃(10 yr)^(-1),and 6.81 mm(10 yr)-1,respectively.Most of the seasonal series revealed trends significant at the 0.05level,except for the spring,summer,and autumn RR series.For Greece,there were increasing trends of 0.09℃(10 yr)-1,0.08℃(10 yr)^(-1),and 0.11℃(10 yr)^(-1)for the annual TG,TX,and TN series,respectively,while a decreasing trend of–23.35 mm(10 yr)^(-1)was present for RR.The seasonal trends showed a significant warming rate for summer,but no significant changes were noted for spring(except for TN),autumn,and winter.For RR,only the winter time series displayed a statistically significant and robust trend[–15.82 mm(10 yr)^(-1)].The final homogenised temperature and precipitation time series for both China and Greece provide a better representation of the large-scale pattern of climate change over the past decades and provide a quality information source for climatological analyses.展开更多
Transient deformation,such as post-seismic slip,slow slip and pre-seismic slip events,is a limited lowfrequency deformation that can last for hours to months,in contrast to a sudden slip on a fault caused by earthquak...Transient deformation,such as post-seismic slip,slow slip and pre-seismic slip events,is a limited lowfrequency deformation that can last for hours to months,in contrast to a sudden slip on a fault caused by earthquakes.Continuous Global Positioning System(CGPS),one of the most common geodetic techniques for continuously monitoring crustal deformation,is capable of capturing transient deformation signals.A critical point in characterizing transient deformation signals is the development of extracting and deciphering transient deformation signals from a huge and messy data set of position time series.Principal Component Analysis(PCA),one of the data-driven methods,has been employed to derive transient deformation signals from position time series combing with Kalman filtering.Independent Component Analysis(ICA)performs well in recovering and separating the sources of observed data,however,it is rarely used in extracting transient deformation signals.We aim to decompose the transient deformation signals from the daily GPS observation deployed in Akutan Island from 2007 to 2015 with the ICA method and obtain the spatiotemporal responses to the source signals of transient deformation.Our results indicate that ICA method can also characterize effectively transient deformation signals spatially and temporally.Additionally,the independent relationship between sources obtained by ICA allows for flexibility in linearly combining different sources.展开更多
Rising sea level is of great significance to coastal societies;predicting sea level extent in coastal regions is critical.When carrying out predictions,the subsequences obtained using decomposition methods may exhibit...Rising sea level is of great significance to coastal societies;predicting sea level extent in coastal regions is critical.When carrying out predictions,the subsequences obtained using decomposition methods may exhibit a certain regularity and therefore can provide multidimensional information that can be used to improve prediction models.Traditional decomposition methods such as seasonal and trend decomposition using Loess(STL)focus mostly on the fluctuating trend of time series and ignore its impact on prediction.Methods in the signal decomposition domain,such as variational mode decomposition(VMD),have no physical significance.In response to the above problems,a new decomposition method for sea level anomaly time series prediction(DMSLAP)is proposed.With this method,the trend term in a time series can be isolated and the effects of abnormal sea level change behaviors can be attenuated.We decompose multiperiod characteristics using this method while maintaining the smoothness of the analyzed series.Satellite altimetry data from 1993 to 2020 are used in experiments conducted in the study area.The results are then compared with predictions obtained using existing decomposition methods such as the STL and VMD methods and time varying filtering based on empirical mode decomposition(TVF-EMD).The performance of DMSLAP combined with a prediction method resulted in optimal sea level anomaly(SLA)predictions,with a minimum root mean square error(RMSE)of 1.40 cm and a maximum determination coefficient(R^(2))of 0.93 during 2020.The DMSLAP method was more accurate when predicting 1-year data and 3-year data.The TVF-EMD and DMSLAP methods had comparable accuracies,and the periodic term decomposed by the DMSLAP method was more in line with the actual law than that derived using the TVF-EMD method.Thus,DMSLAP can decompose SLA time series better than existing methods and is an effective tool for obtaining short-term SLA prediction.展开更多
This study focuses on analyzing the time series of DORIS beacon stations and plate motion of the Eurasian plate by applying Singular Spectrum Analysis(SSA)and Fast Fourier Transform(FFT).First,the rend terms and perio...This study focuses on analyzing the time series of DORIS beacon stations and plate motion of the Eurasian plate by applying Singular Spectrum Analysis(SSA)and Fast Fourier Transform(FFT).First,the rend terms and periodic signals are accurately separated by SSA,then,the periodic seasonal signals are detected using SSA,and finally,the main components of the time series are reconstructed successfully.The test results show that the nonlinear trends and seasonal signals of DORIS stations are detected successfully.The periods of the seasonal signals detected are year,half-year,and 59 days,etc.The contribution rates and slopes in E,N,and U directions of the trend items of each beacon station after reconstruction are obtained by least-square fitting.The velocities of these stations are compared with those provided by the GEODVEL2010 model,and it is found that they are in good agreement except the DIOB,MANB,and PDMB stations.Based on the DORIS coordinate time series,the velocity field on the Eurasian plate is constructed,and the test shows that the Eurasian plate moves eastward as a whole with an average velocity of 24.19±0.11 mm/y in the horizontal direction,and the average velocity of it is1.74±0.07 mm/y in the vertical direction.展开更多
Updating eucalyptus carbon stock data in a timely manner is essential for better understanding and quantifying its effects on ecological and hydrological processes.At present,there are no suitable methods to accuratel...Updating eucalyptus carbon stock data in a timely manner is essential for better understanding and quantifying its effects on ecological and hydrological processes.At present,there are no suitable methods to accurately estimate the eucalyptus carbon stock in a large area.This research aimed to explore the transferability of the eucalyptus carbon stock estimation model at temporal and spatial scales and assess modeling performance through the strategy of combining sample plots,airborne LiDAR and Landsat time series data in subtropical regions of China.Specifically,eucalyptus carbon stock estimates in typical sites were obtained by applying the developed models with the combination of airborne LiDAR and field measurement data;the eucalyptus plantation ages were estimated using the random localization segmentation approach from Landsat time series data;and regional models were developed by linking LiDAR-derived eucalyptus carbon stock and vegetation age(e.g.,months or years).To examine the models’robustness,the developed models at the regional scale were transferred to estimate carbon stocks at the spatial and temporal scales,and the modeling results were evaluated using validation samples accordingly.The results showed that carbon stock can be successfully estimated using the age-based models(both age variables in months and years as predictor variables),but the month-based models produced better estimates with a root mean square error(RMSE)of 6.51 t⋅ha1 for Yunxiao County,Fujian Province,and 6.33 t⋅ha1 for Gaofeng Forest Farm,Guangxi Zhuang Autonomous Region.Particularly,the month-based models were superior for estimating the carbon stocks of young eucalyptus plantations of less than two years.The model transferability analyses showed that the month-based models had higher transferability than the year-based models at the temporal scale,indicating their possibility for analysis of carbon stock change.However,both the month-based and year-based models expressed relatively poor transferability at a spatial scale.This study provides new insights for cost-effective monitoring of carbon stock change in intensively managed plantation forests.展开更多
Currently,the extraction of coseismic offset signals primarily relies on earthquake catalog data to determine the occurrence time of earthquakes.This is followed by the process of differencing the average GPS coordina...Currently,the extraction of coseismic offset signals primarily relies on earthquake catalog data to determine the occurrence time of earthquakes.This is followed by the process of differencing the average GPS coordinate time series data,with a time interval of 3 to 5 days before and after the earthquake.In the face of the huge amount of GPS coordinate time series data today,the conventional approach of relying on earthquake catalog data to assist in obtaining coseismic offset signals has become increasingly burdensome.To address this problem,we propose a new method for automatically detecting coseismic offset signals in GPS coordinate time series without an extra earthquake catalog for reference.Firstly,we pre-process the GPS coordinate time series data for filtering out stations with significant observations missing and detecting and removing outliers.Secondly,we eliminate other signals and errors in the GPS coordinate time series,such as trend and seasonal signals,leaving the coseismic offset signals as the primary signal.The resulting coordinate time series is then modeled using the first-order difference and data stacking method.The modeling method enables automatic detection of the coseismic offset signals in the GPS coordinate time series.The aforementioned method is applied to automatically detect coseismic offset signals using simulated data and the Searles Valley GPS data in California,USA.The results demonstrate the efficacy of our proposed method,successfully detecting coseismic offsets from vast amounts of GPS coordinate time series data.展开更多
BACKGROUND Hepatitis B(HB)and hepatitis C(HC)place the largest burden in China,and a goal of eliminating them as a major public health threat by 2030 has been set.Making more informed and accurate forecasts of their s...BACKGROUND Hepatitis B(HB)and hepatitis C(HC)place the largest burden in China,and a goal of eliminating them as a major public health threat by 2030 has been set.Making more informed and accurate forecasts of their spread is essential for developing effective strategies,heightening the requirement for early warning to deal with such a major public health threat.AIM To monitor HB and HC epidemics by the design of a paradigmatic seasonal autoregressive fractionally integrated moving average(SARFIMA)for projections into 2030,and to compare the effectiveness with the seasonal autoregressive integrated moving average(SARIMA).METHODS Monthly HB and HC incidence cases in China were obtained from January 2004 to June 2023.Descriptive analysis and the Hodrick-Prescott method were employed to identify trends and seasonality.Two periods(from January 2004 to June 2022 and from January 2004 to December 2015,respectively)were used as the training sets to develop both models,while the remaining periods served as the test sets to evaluate the forecasting accuracy.RESULTS There were incidents of 23400874 HB cases and 3590867 HC cases from January 2004 to June 2023.Overall,HB remained steady[average annual percentage change(AAPC)=0.44,95%confidence interval(95%CI):-0.94-1.84]while HC was increasing(AAPC=8.91,95%CI:6.98-10.88),and both had a peak in March and a trough in February.In the 12-step-ahead HB forecast,the mean absolute deviation(15211.94),root mean square error(18762.94),mean absolute percentage error(0.17),mean error rate(0.15),and root mean square percentage error(0.25)under the best SARFIMA(3,0,0)(0,0.449,2)12 were smaller than those under the best SARIMA(3,0,0)(0,1,2)12(16867.71,20775.12,0.19,0.17,and 0.27,respectively).Similar results were also observed for the 90-step-ahead HB,12-step-ahead HC,and 90-step-ahead HC forecasts.The predicted HB incidents totaled 9865400(95%CI:7508093-12222709)cases and HC totaled 1659485(95%CI:856681-2462290)cases during 2023-2030.CONCLUSION Under current interventions,China faces enormous challenges to eliminate HB and HC epidemics by 2030,and effective strategies must be reinforced.The integration of SARFIMA into public health for the management of HB and HC epidemics can potentially result in more informed and efficient interventions,surpassing the capabilities of SARIMA.展开更多
Time series classification(TSC)has attracted a lot of attention for time series data mining tasks and has been applied in various fields.With the success of deep learning(DL)in computer vision recognition,people are s...Time series classification(TSC)has attracted a lot of attention for time series data mining tasks and has been applied in various fields.With the success of deep learning(DL)in computer vision recognition,people are starting to use deep learning to tackle TSC tasks.Quantum neural networks(QNN)have recently demonstrated their superiority over traditional machine learning in methods such as image processing and natural language processing,but research using quantum neural networks to handle TSC tasks has not received enough attention.Therefore,we proposed a learning framework based on multiple imaging and hybrid QNN(MIHQNN)for TSC tasks.We investigate the possibility of converting 1D time series to 2D images and classifying the converted images using hybrid QNN.We explored the differences between MIHQNN based on single time series imaging and MIHQNN based on the fusion of multiple time series imaging.Four quantum circuits were also selected and designed to study the impact of quantum circuits on TSC tasks.We tested our method on several standard datasets and achieved significant results compared to several current TSC methods,demonstrating the effectiveness of MIHQNN.This research highlights the potential of applying quantum computing to TSC and provides the theoretical and experimental background for future research.展开更多
Time series forecasting and analysis are widely used in many fields and application scenarios.Time series historical data reflects the change pattern and trend,which can serve the application and decision in each appl...Time series forecasting and analysis are widely used in many fields and application scenarios.Time series historical data reflects the change pattern and trend,which can serve the application and decision in each application scenario to a certain extent.In this paper,we select the time series prediction problem in the atmospheric environment scenario to start the application research.In terms of data support,we obtain the data of nearly 3500 vehicles in some cities in China fromRunwoda Research Institute,focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou,Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them.This paper proposes a P-gLSTNet model,and uses Autoregressive Integrated Moving Average model(ARIMA),long and short-term memory(LSTM),and Prophet to predict and compare the emissions in the future period.The experiments are validated on four public data sets and one self-collected data set,and the mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE)are selected as the evaluationmetrics.The experimental results show that the proposed P-gLSTNet fusion model predicts less error,outperforms the backbone method,and is more suitable for the prediction of time-series data in this scenario.展开更多
An improved fuzzy time series algorithmbased on clustering is designed in this paper.The algorithm is successfully applied to short-term load forecasting in the distribution stations.Firstly,the K-means clustering met...An improved fuzzy time series algorithmbased on clustering is designed in this paper.The algorithm is successfully applied to short-term load forecasting in the distribution stations.Firstly,the K-means clustering method is used to cluster the data,and the midpoint of two adjacent clustering centers is taken as the dividing point of domain division.On this basis,the data is fuzzed to form a fuzzy time series.Secondly,a high-order fuzzy relation with multiple antecedents is established according to the main measurement indexes of power load,which is used to predict the short-term trend change of load in the distribution stations.Matlab/Simulink simulation results show that the load forecasting errors of the typical fuzzy time series on the time scale of one day and one week are[−50,20]and[−50,30],while the load forecasting errors of the improved fuzzy time series on the time scale of one day and one week are[−20,15]and[−20,25].It shows that the fuzzy time series algorithm improved by clustering improves the prediction accuracy and can effectively predict the short-term load trend of distribution stations.展开更多
Some reconstruction-based anomaly detection models in multivariate time series have brought impressive performance advancements but suffer from weak generalization ability and a lack of anomaly identification.These li...Some reconstruction-based anomaly detection models in multivariate time series have brought impressive performance advancements but suffer from weak generalization ability and a lack of anomaly identification.These limitations can result in the misjudgment of models,leading to a degradation in overall detection performance.This paper proposes a novel transformer-like anomaly detection model adopting a contrastive learning module and a memory block(CLME)to overcome the above limitations.The contrastive learning module tailored for time series data can learn the contextual relationships to generate temporal fine-grained representations.The memory block can record normal patterns of these representations through the utilization of attention-based addressing and reintegration mechanisms.These two modules together effectively alleviate the problem of generalization.Furthermore,this paper introduces a fusion anomaly detection strategy that comprehensively takes into account the residual and feature spaces.Such a strategy can enlarge the discrepancies between normal and abnormal data,which is more conducive to anomaly identification.The proposed CLME model not only efficiently enhances the generalization performance but also improves the ability of anomaly detection.To validate the efficacy of the proposed approach,extensive experiments are conducted on well-established benchmark datasets,including SWaT,PSM,WADI,and MSL.The results demonstrate outstanding performance,with F1 scores of 90.58%,94.83%,91.58%,and 91.75%,respectively.These findings affirm the superiority of the CLME model over existing stateof-the-art anomaly detection methodologies in terms of its ability to detect anomalies within complex datasets accurately.展开更多
At present,the interpretation of regional economic development(RED)has changed from a simple evaluation of economic growth to a focus on economic growth and the optimization of economic structure,the improvement of ec...At present,the interpretation of regional economic development(RED)has changed from a simple evaluation of economic growth to a focus on economic growth and the optimization of economic structure,the improvement of economic relations,and the change of institutional innovation.This article uses the RED trend as the research object and constructs the RED index to conduct the theoretical analysis.Then this paper uses the attention mechanism based on digital twins and the time series network model to verify the actual data.Finally,the regional economy is predicted according to the theoretical model.The specific research work mainly includes the following aspects:1)This paper introduced the development status of research on time series networks and economic forecasting at home and abroad.2)This paper introduces the basic principles and structures of long and short-term memory(LSTM)and convolutional neural network(CNN),constructs an improved CNN-LSTM model combined with the attention mechanism,and then constructs a regional economic prediction index system.3)The best parameters of the model are selected through experiments,and the trained model is used for simulation experiment prediction.The results show that the CNN-LSTM model based on the attentionmechanism proposed in this paper has high accuracy in predicting regional economies.展开更多
基金supported by the National Natural Science Foundation of China(Grants:42204006,42274053,42030105,and 41504031)the Open Research Fund Program of the Key Laboratory of Geospace Environment and Geodesy,Ministry of Education,China(Grants:20-01-03 and 21-01-04)。
文摘Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection of appropriate embedding window size and principal components makes this method cumbersome and inefficient.To improve the efficiency and accuracy of singular spectrum analysis,this paper proposes an adaptive singular spectrum analysis method by combining spectrum analysis with a new trace matrix.The running time and correlation analysis indicate that the proposed method can adaptively set the embedding window size to extract the time-varying periodic signals from GNSS time series,and the extraction efficiency of a single time series is six times that of singular spectrum analysis.The method is also accurate and more suitable for time-varying periodic signal analysis of global GNSS sites.
基金the National Natural Science Foundation of China(U2033213)the Fundamental Research Funds for the Central Universities(FZ2021ZZ01,FZ2022ZX50).
文摘With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.
基金funded by the Natural Science Foundation of Fujian Province,China (Grant No.2022J05291)Xiamen Scientific Research Funding for Overseas Chinese Scholars.
文摘Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.
基金funded by the Fujian Province Science and Technology Plan,China(Grant Number 2019H0017).
文摘Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.
基金supported by the National Key Research and Development Program of China(No.2018YFB2101300)the National Natural Science Foundation of China(Grant No.61871186)the Dean’s Fund of Engineering Research Center of Software/Hardware Co-Design Technology and Application,Ministry of Education(East China Normal University).
文摘Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.
基金This research was financially supported by the Ministry of Trade,Industry,and Energy(MOTIE),Korea,under the“Project for Research and Development with Middle Markets Enterprises and DNA(Data,Network,AI)Universities”(AI-based Safety Assessment and Management System for Concrete Structures)(ReferenceNumber P0024559)supervised by theKorea Institute for Advancement of Technology(KIAT).
文摘Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.
基金supported in part by the Gansu Province Higher Education Institutions Industrial Support Program:Security Situational Awareness with Artificial Intelligence and Blockchain Technology.Project Number(2020C-29).
文摘In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.
文摘Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically relies on expert input and necessitates substantial manual involvement.This manual effort spans model development,feature engineering,hyper-parameter tuning,and the intricate construction of time series models.The complexity of these tasks renders complete automation unfeasible,as they inherently demand human intervention at multiple junctures.To surmount these challenges,this article proposes leveraging Long Short-Term Memory,which is the variant of Recurrent Neural Networks,harnessing memory cells and gating mechanisms to facilitate long-term time series prediction.However,forecasting accuracy by particular neural network and traditional models can degrade significantly,when addressing long-term time-series tasks.Therefore,our research demonstrates that this innovative approach outperforms the traditional Autoregressive Integrated Moving Average(ARIMA)method in forecasting long-term univariate time series.ARIMA is a high-quality and competitive model in time series prediction,and yet it requires significant preprocessing efforts.Using multiple accuracy metrics,we have evaluated both ARIMA and proposed method on the simulated time-series data and real data in both short and long term.Furthermore,our findings indicate its superiority over alternative network architectures,including Fully Connected Neural Networks,Convolutional Neural Networks,and Nonpooling Convolutional Neural Networks.Our AutoML approach enables non-professional to attain highly accurate and effective time series forecasting,and can be widely applied to various domains,particularly in business and finance.
基金funded by the Hellenic and Chinese Governments,in the frame of the Greek-Chinese R&T Cooperation Programme project“Comparative study of extreme climate indices in China and Europe/Greece,based on homogenised daily observations—CLIMEX”(Contract T7ΔKI-00046)the National Key Technologies Research and Development Program“Comparative study of changing climate extremes between China and Europe/Greece based on homogenised daily observations”(Grant No.2017YFE0133600)。
文摘In this paper,we describe and analyze two datasets entitled“Homogenised monthly and daily temperature and precipitation time series in China during 1960–2021”and“Homogenised monthly and daily temperature and precipitation time series in Greece during 1960–2010”.These datasets provide the homogenised monthly and daily mean(TG),minimum(TN),and maximum(TX)temperature and precipitation(RR)records since 1960 at 366 stations in China and 56stations in Greece.The datasets are available at the Science Data Bank repository and can be downloaded from https://doi.org/10.57760/sciencedb.01731 and https://doi.org/10.57760/sciencedb.01720.For China,the regional mean annual TG,TX,TN,and RR series during 1960–2021 showed significant warming or increasing trends of 0.27℃(10 yr)^(-1),0.22℃(10 yr)^(-1),0.35℃(10 yr)^(-1),and 6.81 mm(10 yr)-1,respectively.Most of the seasonal series revealed trends significant at the 0.05level,except for the spring,summer,and autumn RR series.For Greece,there were increasing trends of 0.09℃(10 yr)-1,0.08℃(10 yr)^(-1),and 0.11℃(10 yr)^(-1)for the annual TG,TX,and TN series,respectively,while a decreasing trend of–23.35 mm(10 yr)^(-1)was present for RR.The seasonal trends showed a significant warming rate for summer,but no significant changes were noted for spring(except for TN),autumn,and winter.For RR,only the winter time series displayed a statistically significant and robust trend[–15.82 mm(10 yr)^(-1)].The final homogenised temperature and precipitation time series for both China and Greece provide a better representation of the large-scale pattern of climate change over the past decades and provide a quality information source for climatological analyses.
基金supported by the National Natural Science Foundation of China projects(U2139205,42072243)Natural Science Basic Research Program of Shaanxi(Program No.2023-JC-QN-0309)。
文摘Transient deformation,such as post-seismic slip,slow slip and pre-seismic slip events,is a limited lowfrequency deformation that can last for hours to months,in contrast to a sudden slip on a fault caused by earthquakes.Continuous Global Positioning System(CGPS),one of the most common geodetic techniques for continuously monitoring crustal deformation,is capable of capturing transient deformation signals.A critical point in characterizing transient deformation signals is the development of extracting and deciphering transient deformation signals from a huge and messy data set of position time series.Principal Component Analysis(PCA),one of the data-driven methods,has been employed to derive transient deformation signals from position time series combing with Kalman filtering.Independent Component Analysis(ICA)performs well in recovering and separating the sources of observed data,however,it is rarely used in extracting transient deformation signals.We aim to decompose the transient deformation signals from the daily GPS observation deployed in Akutan Island from 2007 to 2015 with the ICA method and obtain the spatiotemporal responses to the source signals of transient deformation.Our results indicate that ICA method can also characterize effectively transient deformation signals spatially and temporally.Additionally,the independent relationship between sources obtained by ICA allows for flexibility in linearly combining different sources.
基金Supported by the Fundamental Research Funds for the Central Universities (No.17CX02071)the National Natural Science Foundation of China (No.61571009)the Key R&D Program of Shandong Province (No.2018GHY115046)。
文摘Rising sea level is of great significance to coastal societies;predicting sea level extent in coastal regions is critical.When carrying out predictions,the subsequences obtained using decomposition methods may exhibit a certain regularity and therefore can provide multidimensional information that can be used to improve prediction models.Traditional decomposition methods such as seasonal and trend decomposition using Loess(STL)focus mostly on the fluctuating trend of time series and ignore its impact on prediction.Methods in the signal decomposition domain,such as variational mode decomposition(VMD),have no physical significance.In response to the above problems,a new decomposition method for sea level anomaly time series prediction(DMSLAP)is proposed.With this method,the trend term in a time series can be isolated and the effects of abnormal sea level change behaviors can be attenuated.We decompose multiperiod characteristics using this method while maintaining the smoothness of the analyzed series.Satellite altimetry data from 1993 to 2020 are used in experiments conducted in the study area.The results are then compared with predictions obtained using existing decomposition methods such as the STL and VMD methods and time varying filtering based on empirical mode decomposition(TVF-EMD).The performance of DMSLAP combined with a prediction method resulted in optimal sea level anomaly(SLA)predictions,with a minimum root mean square error(RMSE)of 1.40 cm and a maximum determination coefficient(R^(2))of 0.93 during 2020.The DMSLAP method was more accurate when predicting 1-year data and 3-year data.The TVF-EMD and DMSLAP methods had comparable accuracies,and the periodic term decomposed by the DMSLAP method was more in line with the actual law than that derived using the TVF-EMD method.Thus,DMSLAP can decompose SLA time series better than existing methods and is an effective tool for obtaining short-term SLA prediction.
基金supported by the National Natural Science Foundation of China(Grant No.41704015,41774001)the Shandong Natural Science Foundation of China(Grant No.ZR2017MD032,ZR2017MD003)+1 种基金a Project of Shandong Province Higher Education Science and Technology Program(Grant No.J17KA077)Talent introduction plan for Youth Innovation Team in universities of Shandong Province(innovation team of satellite positioning and navigation)。
文摘This study focuses on analyzing the time series of DORIS beacon stations and plate motion of the Eurasian plate by applying Singular Spectrum Analysis(SSA)and Fast Fourier Transform(FFT).First,the rend terms and periodic signals are accurately separated by SSA,then,the periodic seasonal signals are detected using SSA,and finally,the main components of the time series are reconstructed successfully.The test results show that the nonlinear trends and seasonal signals of DORIS stations are detected successfully.The periods of the seasonal signals detected are year,half-year,and 59 days,etc.The contribution rates and slopes in E,N,and U directions of the trend items of each beacon station after reconstruction are obtained by least-square fitting.The velocities of these stations are compared with those provided by the GEODVEL2010 model,and it is found that they are in good agreement except the DIOB,MANB,and PDMB stations.Based on the DORIS coordinate time series,the velocity field on the Eurasian plate is constructed,and the test shows that the Eurasian plate moves eastward as a whole with an average velocity of 24.19±0.11 mm/y in the horizontal direction,and the average velocity of it is1.74±0.07 mm/y in the vertical direction.
基金supported by the National Key R&D Program of China(Grant No.2021YFD2200400102)Fujian Provincial Science and Technology Department(Grant No.2021R1002008).
文摘Updating eucalyptus carbon stock data in a timely manner is essential for better understanding and quantifying its effects on ecological and hydrological processes.At present,there are no suitable methods to accurately estimate the eucalyptus carbon stock in a large area.This research aimed to explore the transferability of the eucalyptus carbon stock estimation model at temporal and spatial scales and assess modeling performance through the strategy of combining sample plots,airborne LiDAR and Landsat time series data in subtropical regions of China.Specifically,eucalyptus carbon stock estimates in typical sites were obtained by applying the developed models with the combination of airborne LiDAR and field measurement data;the eucalyptus plantation ages were estimated using the random localization segmentation approach from Landsat time series data;and regional models were developed by linking LiDAR-derived eucalyptus carbon stock and vegetation age(e.g.,months or years).To examine the models’robustness,the developed models at the regional scale were transferred to estimate carbon stocks at the spatial and temporal scales,and the modeling results were evaluated using validation samples accordingly.The results showed that carbon stock can be successfully estimated using the age-based models(both age variables in months and years as predictor variables),but the month-based models produced better estimates with a root mean square error(RMSE)of 6.51 t⋅ha1 for Yunxiao County,Fujian Province,and 6.33 t⋅ha1 for Gaofeng Forest Farm,Guangxi Zhuang Autonomous Region.Particularly,the month-based models were superior for estimating the carbon stocks of young eucalyptus plantations of less than two years.The model transferability analyses showed that the month-based models had higher transferability than the year-based models at the temporal scale,indicating their possibility for analysis of carbon stock change.However,both the month-based and year-based models expressed relatively poor transferability at a spatial scale.This study provides new insights for cost-effective monitoring of carbon stock change in intensively managed plantation forests.
基金supported by the National Natural Science Foundation of China(No.42104008,42204006,41904031)the Jiangxi Provincial Natural Science Foundation(20232BAB213075)+1 种基金the Key Laboratory for Digital Land and Resources of Jiangxi Province,East China University of Technology(DLLJ202016)Open Fund of Hubei Luojia Laboratory(No.230100020,230100019)。
文摘Currently,the extraction of coseismic offset signals primarily relies on earthquake catalog data to determine the occurrence time of earthquakes.This is followed by the process of differencing the average GPS coordinate time series data,with a time interval of 3 to 5 days before and after the earthquake.In the face of the huge amount of GPS coordinate time series data today,the conventional approach of relying on earthquake catalog data to assist in obtaining coseismic offset signals has become increasingly burdensome.To address this problem,we propose a new method for automatically detecting coseismic offset signals in GPS coordinate time series without an extra earthquake catalog for reference.Firstly,we pre-process the GPS coordinate time series data for filtering out stations with significant observations missing and detecting and removing outliers.Secondly,we eliminate other signals and errors in the GPS coordinate time series,such as trend and seasonal signals,leaving the coseismic offset signals as the primary signal.The resulting coordinate time series is then modeled using the first-order difference and data stacking method.The modeling method enables automatic detection of the coseismic offset signals in the GPS coordinate time series.The aforementioned method is applied to automatically detect coseismic offset signals using simulated data and the Searles Valley GPS data in California,USA.The results demonstrate the efficacy of our proposed method,successfully detecting coseismic offsets from vast amounts of GPS coordinate time series data.
基金Supported by the Key Scientific Research Project of Universities in Henan Province,No.21A330004Natural Science Foundation in Henan Province,No.222300420265.
文摘BACKGROUND Hepatitis B(HB)and hepatitis C(HC)place the largest burden in China,and a goal of eliminating them as a major public health threat by 2030 has been set.Making more informed and accurate forecasts of their spread is essential for developing effective strategies,heightening the requirement for early warning to deal with such a major public health threat.AIM To monitor HB and HC epidemics by the design of a paradigmatic seasonal autoregressive fractionally integrated moving average(SARFIMA)for projections into 2030,and to compare the effectiveness with the seasonal autoregressive integrated moving average(SARIMA).METHODS Monthly HB and HC incidence cases in China were obtained from January 2004 to June 2023.Descriptive analysis and the Hodrick-Prescott method were employed to identify trends and seasonality.Two periods(from January 2004 to June 2022 and from January 2004 to December 2015,respectively)were used as the training sets to develop both models,while the remaining periods served as the test sets to evaluate the forecasting accuracy.RESULTS There were incidents of 23400874 HB cases and 3590867 HC cases from January 2004 to June 2023.Overall,HB remained steady[average annual percentage change(AAPC)=0.44,95%confidence interval(95%CI):-0.94-1.84]while HC was increasing(AAPC=8.91,95%CI:6.98-10.88),and both had a peak in March and a trough in February.In the 12-step-ahead HB forecast,the mean absolute deviation(15211.94),root mean square error(18762.94),mean absolute percentage error(0.17),mean error rate(0.15),and root mean square percentage error(0.25)under the best SARFIMA(3,0,0)(0,0.449,2)12 were smaller than those under the best SARIMA(3,0,0)(0,1,2)12(16867.71,20775.12,0.19,0.17,and 0.27,respectively).Similar results were also observed for the 90-step-ahead HB,12-step-ahead HC,and 90-step-ahead HC forecasts.The predicted HB incidents totaled 9865400(95%CI:7508093-12222709)cases and HC totaled 1659485(95%CI:856681-2462290)cases during 2023-2030.CONCLUSION Under current interventions,China faces enormous challenges to eliminate HB and HC epidemics by 2030,and effective strategies must be reinforced.The integration of SARFIMA into public health for the management of HB and HC epidemics can potentially result in more informed and efficient interventions,surpassing the capabilities of SARIMA.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.61772295 and 61572270)the PHD foundation of Chongqing Normal University (Grant No.19XLB003)Chongqing Technology Foresight and Institutional Innovation Project (Grant No.cstc2021jsyjyzysbAX0011)。
文摘Time series classification(TSC)has attracted a lot of attention for time series data mining tasks and has been applied in various fields.With the success of deep learning(DL)in computer vision recognition,people are starting to use deep learning to tackle TSC tasks.Quantum neural networks(QNN)have recently demonstrated their superiority over traditional machine learning in methods such as image processing and natural language processing,but research using quantum neural networks to handle TSC tasks has not received enough attention.Therefore,we proposed a learning framework based on multiple imaging and hybrid QNN(MIHQNN)for TSC tasks.We investigate the possibility of converting 1D time series to 2D images and classifying the converted images using hybrid QNN.We explored the differences between MIHQNN based on single time series imaging and MIHQNN based on the fusion of multiple time series imaging.Four quantum circuits were also selected and designed to study the impact of quantum circuits on TSC tasks.We tested our method on several standard datasets and achieved significant results compared to several current TSC methods,demonstrating the effectiveness of MIHQNN.This research highlights the potential of applying quantum computing to TSC and provides the theoretical and experimental background for future research.
基金the Beijing Chaoyang District Collaborative Innovation Project(No.CYXT2013)the subject support of Beijing Municipal Science and Technology Key R&D Program-Capital Blue Sky Action Cultivation Project(Z19110900910000)+1 种基金“Research and Demonstration ofHigh Emission Vehicle Monitoring Equipment System Based on Sensor Integration Technology”(Z19110000911003)This work was supported by the Academic Research Projects of Beijing Union University(No.ZK80202103).
文摘Time series forecasting and analysis are widely used in many fields and application scenarios.Time series historical data reflects the change pattern and trend,which can serve the application and decision in each application scenario to a certain extent.In this paper,we select the time series prediction problem in the atmospheric environment scenario to start the application research.In terms of data support,we obtain the data of nearly 3500 vehicles in some cities in China fromRunwoda Research Institute,focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou,Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them.This paper proposes a P-gLSTNet model,and uses Autoregressive Integrated Moving Average model(ARIMA),long and short-term memory(LSTM),and Prophet to predict and compare the emissions in the future period.The experiments are validated on four public data sets and one self-collected data set,and the mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE)are selected as the evaluationmetrics.The experimental results show that the proposed P-gLSTNet fusion model predicts less error,outperforms the backbone method,and is more suitable for the prediction of time-series data in this scenario.
基金supported by the National Natural Science Foundation of China under Grant 51777193.
文摘An improved fuzzy time series algorithmbased on clustering is designed in this paper.The algorithm is successfully applied to short-term load forecasting in the distribution stations.Firstly,the K-means clustering method is used to cluster the data,and the midpoint of two adjacent clustering centers is taken as the dividing point of domain division.On this basis,the data is fuzzed to form a fuzzy time series.Secondly,a high-order fuzzy relation with multiple antecedents is established according to the main measurement indexes of power load,which is used to predict the short-term trend change of load in the distribution stations.Matlab/Simulink simulation results show that the load forecasting errors of the typical fuzzy time series on the time scale of one day and one week are[−50,20]and[−50,30],while the load forecasting errors of the improved fuzzy time series on the time scale of one day and one week are[−20,15]and[−20,25].It shows that the fuzzy time series algorithm improved by clustering improves the prediction accuracy and can effectively predict the short-term load trend of distribution stations.
基金support from the Major National Science and Technology Special Projects(2016ZX02301003-004-007)the Natural Science Foundation of Hebei Province(F2020202067)。
文摘Some reconstruction-based anomaly detection models in multivariate time series have brought impressive performance advancements but suffer from weak generalization ability and a lack of anomaly identification.These limitations can result in the misjudgment of models,leading to a degradation in overall detection performance.This paper proposes a novel transformer-like anomaly detection model adopting a contrastive learning module and a memory block(CLME)to overcome the above limitations.The contrastive learning module tailored for time series data can learn the contextual relationships to generate temporal fine-grained representations.The memory block can record normal patterns of these representations through the utilization of attention-based addressing and reintegration mechanisms.These two modules together effectively alleviate the problem of generalization.Furthermore,this paper introduces a fusion anomaly detection strategy that comprehensively takes into account the residual and feature spaces.Such a strategy can enlarge the discrepancies between normal and abnormal data,which is more conducive to anomaly identification.The proposed CLME model not only efficiently enhances the generalization performance but also improves the ability of anomaly detection.To validate the efficacy of the proposed approach,extensive experiments are conducted on well-established benchmark datasets,including SWaT,PSM,WADI,and MSL.The results demonstrate outstanding performance,with F1 scores of 90.58%,94.83%,91.58%,and 91.75%,respectively.These findings affirm the superiority of the CLME model over existing stateof-the-art anomaly detection methodologies in terms of its ability to detect anomalies within complex datasets accurately.
文摘At present,the interpretation of regional economic development(RED)has changed from a simple evaluation of economic growth to a focus on economic growth and the optimization of economic structure,the improvement of economic relations,and the change of institutional innovation.This article uses the RED trend as the research object and constructs the RED index to conduct the theoretical analysis.Then this paper uses the attention mechanism based on digital twins and the time series network model to verify the actual data.Finally,the regional economy is predicted according to the theoretical model.The specific research work mainly includes the following aspects:1)This paper introduced the development status of research on time series networks and economic forecasting at home and abroad.2)This paper introduces the basic principles and structures of long and short-term memory(LSTM)and convolutional neural network(CNN),constructs an improved CNN-LSTM model combined with the attention mechanism,and then constructs a regional economic prediction index system.3)The best parameters of the model are selected through experiments,and the trained model is used for simulation experiment prediction.The results show that the CNN-LSTM model based on the attentionmechanism proposed in this paper has high accuracy in predicting regional economies.
